Special Cases

28
2021.9
【2021 Application Example】 Fongyu Uses AI Knowledge-based Fish Farming to Effectively Increase Aquatic Production by 10%

Fisheries is an important industry in an island economy However, the fish farming industry has faced severe challenges in recent years, including climate change, labor shortage, and rising costs In particular, nearly 110,000 workers in agriculture will retire due to old age over the next 10 years For this reason, the need for aquaculture to move towards smart farming is becoming increasingly urgent Founded in 2014, Fongyu Corp Ltd has developed a unique eco-friendly farming model based on its own fish farming It uses AI knowledge-based fish farming to effectively increase aquatic product production by 10, and reduced labor cost by 15 The word "Fongyu" has a profound meaning "Fong" represents good mountains and "Yu" represents good water, and is the hope that companies will allow Taiwan to always have good mountains and good waterIt is also a homophone for "having a full figure," expressing the hope that products will give consumers a full and healthy body and mind The founder of the company, Liu Chien-Shen, has been through the difficult entrepreneurial journey of becoming an apprentice in fish farming, raising funds, renting fish farms, establishing a fish farming company, building a brand, and expanding sales Labor shortage and aging workers are hidden worries in the fish farming industry Currently, fish farms in Taiwan are still mainly traditional fish farms, and farming techniques are still passed down through word-of-mouth In addition, the labor shortage and average age of workers exceeding 60 years old has made it impossible to effectively stably improve productivity and yield This farming method makes it difficult to prevent and control diseases, and greatly increases the possibility of excessive use of drugs, environmental pollution, and water quality and ecological damage, creating a vicious cycle that lowers the quality of fish farming In addition, 651 of workers in Taiwan's fish farming industry are inadequately skilled With limited support from IoT sensors, traditional fish farmers still mainly rely on their own experience and knowledge for water quality management, feeding, and disease detection Fish farming management relies heavily on the ability of individual fishermen Once experienced workers retire, the industry will not only face the issue of succession, but also the difficult of stably supplying a certain amount of harvest that meets quality standards This may cause a dilemma for the entire industry from fish farming to sales In order to improve the pain point of inability to pass on experience in fish farming, and at the same time create a "digital" foundation for fish farming, the top priority must be to collect farming behavior data and develop AI services as an important starting point Fishery digital twin technology helps fishermen transition to smart farming With the assistance of the Institute for Information Technology III, Fongyu implemented the "fishery digital twin" technology to dynamically adjust the farming schedule In other words, the fish farming schedule is adjusted according to the species, habits, and variables of the fish The use of AI in fish farming not only effectively increase aquatic production by 10, but also reduced labor cost by 15 In terms of specific methods, we first digitalized the fish ponds, feed, and decision-making behavior for each species, such as sea bass and Taiwan tilapia, and recorded the seasonal temperature changes from releasing seedlings to harvesting, all of which were digitalized, gradually recording the experience and methods of experienced workers into a rich database Based on the recorded data, we analyzed the compound variables to find the best farming behavior and generate a dynamic farming schedule The records for each pool provide data on workers' experience However, fish farming behavior generally relies on rules of thumb Even experienced fish farmers cannot ensure that they will find the best solution Therefore, new methods are proposed to solve this issue That is, "to determine the best fish farming behavior by predicting the interaction with water quality and past data on feeding, and evaluating fish farming behavior based on water quality and fish farming," and provide fishermen with the most intuitive recommendations through daily schedules To continue optimizing the dynamic fish farming calendar on a rolling basis, iterations of the model will be developed through the three-step cycle 1 Input the current fish farming calendar into the model 2 The model predicts the future environment 3 Shortcomings of the fish farming calendar are corrected based on the future environment to obtain a new version of the fish farming calendar In the process, the experience of aquaculture experts is used to establish the causal relationship between fish farming behavior and the environment The establishment of a dynamic fish farming process and technology-based fish farming recommendation services provide a traceable and detailed fish farming process It is one of the few technologies that can digitalize fish farming Fishermen can quickly and easily record their daily behaviors to build knowledge without taking up too much time, but in the long run it can reduce labor cost by 15 and increase output and revenue by an average of 10 Smart fish farming has achieved outstanding results, reducing labor cost by 15 and increasing output by 10 At the same time, the fish farming calendar can also be extended to different aquatic species, such as white shrimp, milkfish, clams, and Taiwan tilapia, to produce fish farming schedules for ponds with different specifications, and the harvested aquatic species can be traced according to different specifications, establishing vertically integrated services for safe food products Fongyu's main products are divided into two categories One is aquaculture modules, including fry, feed, materials and probiotics, production planning and processes, and monitoring, which can be sold separately or exported as modules The high-quality aquatic products produced by Fongyu have repeatedly won awards Figure Fongyursquos official website The other category is high-quality aquatic products, including seabass fillets, seabass balls, oil-free seabass balls, seabass dumplings, and seabass soup The products have won various awards, including the top ten souvenirs in Pingtung in 2017, "Barramundi Fillet" won the 2017 Eatender of the Council of Agriculture COA, "Oil-Free Barramundi Fillet" won the 2018 Eatender Gold Food Award of the COA, and "Dumplings of Barramundi" and "Barramundi Broth" won the 2019 Eatender of the COA The consecutive awards represent that the "quality" of Fongyursquos aquatic products can be seen and eaten with peace of mind In addition, Fongyu has exclusive fingerlings that meet international needs, such as Pure seawater cultured tilapia fingerlings and seawater Taiwan tilapia fingerlings from selective breeding FY-01 are items that aquaculture companies in many countries are looking forward to The company also has aquaculture modules, disease monitoring tools, and feeding materials designed in accordance with the environment, in order to provide customers with more stable income

2021-09-28
【2021 Application Example】 AI Complements the Disruption of Traditional Industry Experience: Production Forecast Analysis in Plastic Recycling Process

As the number of veteran craftsmen in traditional industries diminishes In Taiwan, SMEs have always played a central role in Taiwan's industry, accompanying Taiwan through various 'economic miracles' periods But as time progresses, the old masters gradually became elderly craftsmen Coupled with the phenomenon of fewer children and changes in the overall industrial structure, fewer and fewer of the new generation are willing to enter traditional industries Now, it can be observed that the main combination on most SMEs' operational fields is formed by 'elder craftsmen' together with 'foreign workers' These experienced craftsmen, who act as living dictionaries of field experience, suffer from a lack of successors to continue the tradition, leading to a growing difficulty in sustaining on-site experience transfer in traditional industries The limits of traditional hands-on process optimization are in sight Located in Tainan Baoan Industrial District, 'Tangxian Company' was established in 1972, initially manufacturing high-quality weaving equipment It possesses the capability to manufacture machinery, and in recent years it has actively developed environmentally friendly plastic recycling equipment in response to international green energy, recycling, and environmental protection demands Ultimately, they have successfully developed low energy consumption, low waste, high purity, and high output recycling granulators with a sleek and efficient machine design supplemented by advanced intelligent control technology Tangxian Company's self-developed plastic recycling granulator equipment However, in the production process of plastic recycling, when faced with hundreds of material types and dozens of process temperatures, speed settings, what is faced is thousands of possible parameter combinations Previously, the adjustment of various production process conditions was reliant on the on-site staff the experience of the craftsmen Thus, during the transition of production of different incoming materials such as PET, PP, PE, a significant amount of raw materials would be wasted during the trial phase The professional information gap in traditional industries Tangxian Company recognizes the importance of data In the past, although process parameters were recorded, due to a lack of data capabilities at the time, it was primarily in paper form, manually written down by the operating staff, accumulating a large amount of paper data However, this also meant a lack of scientifically accurate and detailed information available for real-time reference and adjustment Process parameters logbook, records the state of about a dozen machines and production figures hourly In quality control as well, due to a lack of control over the quality of output and monitoring and feedback mechanisms for unit time production, it becomes difficult to predict the profit conditions of each batch Production management can only estimate and average cost and productivity changes over the process from the outcomes, without being able to objectively and timely restore the production conditions to reasonableness or make clearer adjustments when facing quality abnormalities Site reality left image shows recycled scraps right image shows pellet production Taiwanese manufacturers possess strong machinery manufacturing capabilities, and many modern machines now have data capabilities, recording real-time status and information via IoT But is the infrastructure of the factory's on-site and information systems ready yet When the Old Master Meets AI With government referral, Tangxian Company partnered with a Taiwanese data science company, working together to integrate AI services and optimize internal processes using AI They started with a medium-sized plastic recycling production line within the factory as a trial field After establishing a successful benchmark, this model was expanded to larger plastic recycling machinery within the factory to continue verification and application Initially, both parties converted the past handwritten paper data into digital format using OCR supplemented by manual correction Tangxian Company also worked with the supplier of the human-machine interface of the machinery to integrate the control panel and parameter data into the factory's database, allowing real-time monitoring of machine status and eliminating the complexities and potential errors of manual transcription Panel of plastic recycling granulation machine, showing current process temperatures, speeds, and power usage Meanwhile, the Taiwanese data science company further modeled dozens of parameter data through AI, conducting scenario analysis to simulate various production possibilities under environmental parameters and material inputs, identifying key characteristic parameters and providing parameter adjustment recommendations to decrease costs during the trial phase Applying data analysis to traditional industry machinery processes After the old master receives the raw materials, they only need to enter the relevant material characteristic parameters, and the system automatically generates recommended process parameters After small adjustments by the old master, they proceed with the trial production of the material, effectively reducing the waste of materials, water, electricity, and manpower caused by incorrect attempts Moreover, Tangxian Company has proactively deployed the concept of 'production pedigree' in the plastic recycling process, allowing the batch's raw materials and process parameters to be accessed by scanning a QRCode Production and sales pedigree of plastic recycling pelletizing Taiwan's SMEs have strong machinery capabilities, just waiting for the 'east wind' of data From industrial revolutions 20 to 30, even 40, many Taiwanese SMEs face challenges in transitions not just in upgrading machinery, but after investing in modern equipment and generating data, they do not know how to utilize it effectively It is impractical for these manufacturers to develop a specialized data analysis department on their own meanwhile, Taiwan also has many innovative teams with strong software capabilities in AI and data analysis, possessing the technology but lacking the field and data Therefore, if the traditional industries of Taiwan could be fully integrated with the innovative teams in AI and data analysis, it would not only address the current challenges of manpower and experience transfer faced by traditional industries but also advance Taiwan's development and application of AI significantly「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

2021-01-21
【2021 Application Example】 HRT Technology Improves Production Efficiency by 20% Through AOI Detection of Defects in VCSEL Packaging

In 2017, the launch of the iPhone X made 3D sensor technology used in Face ID highly popular, which drove the development of VCSEL, a core component in the 3D sensor module In the detection of defects in incoming packaged VCSEL, the use of AI inference models can solve the industry's issue with low yield and improve reliability to 95 VCSEL technology currently can be used in many applications and various end consumer markets, including robots, mobile devices, surveillance, drones, and ARVR VCSELs are a good solution in applications that require high-speed modulation capabilities, such as cameras and biometrics VCSEL technology has a wide range ofnbsp applications, including in drones Pictured Zoyi Technology's Agricultural Drone VCSEL technology has a wide range of applications, AI technology assists in defect detection HRT Technology stated that the packaged VCSEL market is also facing strong price competition from competitors, and needs to further reduce costs and enhance product competitiveness One of the key problems is the replacement of glass lens with epoxy resin lens The production of traditional glass lenses has high yield, but the cost is higher than that of epoxy resin lenses Due to the cutting process of epoxy resin, the side wall of cutting lines can easily have rough edges, causing it to be oversized The release of stress caused by heat during the mounting process will directly cause the optical lens to break HRT Technology pointed out that the incoming inspection of VCSEL epoxy resin lenses is very important Under the constraints of packaging space, the space for fitting the package and optical lens is limited Moreover, the optical lenses will be confined to a metal frame If the dimensional tolerances are properly controlled, stress release due to heat during mounting can easily cause the optical lens to break, resulting in a yield loss of up to 10 in the VCSEL package reliability verification, resulting in an increase in production costs In order to solve the problems above, HRT Technology hopes to use AI to monitor the size and appearance defects of epoxy resin components in the VCSEL epoxy resin lens incoming stage, verifying whether their dimensions meet specifications, whether the cutting edges are smooth, and whether there are any defects in their appearance Since traditional incoming material inspection requires a rough visual inspection by humans to distinguish the quality The problem of image collection needs to be solved first to successfully collect image data Therefore, HRT Technology first developed an Automated Optical Inspection AOI device, which includes X, Y, Z three-axis motion, high-resolution cameras, and related control software to automatically record images After collecting the image data, opencv aligns the test image and a normal image to determine differences between the two images, and then pixel mapping is used to compare the pixel area to complete initial screening Manual labeling is carried out according to the image classification above, including samples that are normal, have defects in appearance, or have different shape characteristics, and then algorithm training and verification is carried out Residual neural network ResNet or other related algorithms are used for deep learning to identify the quality of lenses Implementation of AOI inspection improves production efficiency by 20 and above Comparing the differences before and after the implementation of AI image inspection, the incoming VCSEL lens inspection before implementation only involved manual inspection of the appearance The lens is packaged on the VCSEL package that has completed die bonding After passing the general light up test, the final reliability test high temperature reflow is performed Failed samples go into the rework process However, after the implementation of AOI inspection, it can screen defective lenses sooner and reduce the cost of subsequent materials input, it can also reduce the need for rework due to failure, improving yield to 95 and above in the reliability verification This is expected to help companies reduce production costs by 10 and increase production efficiency by 20 and above The difference before and after implementing AI image detection HRT Technology pointed out that this technology is an AI application developed based on tiny images It uses deep learning algorithms to identify defects in the images The trained network automatically classifies image data to predetermined categories Defect categories can be determined through reference images, so cumbersome programming is not required In the industrial machine vision environment, deep learning is mainly used for classification tasks in applications, such as inspection of industrial products or identification of parts In the future, with the development of IoT wearable devices and the trend of energy saving, the size of optoelectronic components will continue to shrink This technology can be applied to the detection of defects in the appearance of other tiny optoelectronic components in the future

2021-12-05
【2021 Application Example】 AI Analysis Cloud Service Platform for Remote Sensing Big Data Enables the Smooth Application of Satellite Remote Sensing Images

Although satellite remote sensing images can make all surface objects visible, it still requires a lot of time and manpower to be truly applied to the industry In order to effectively solve the problems that customers face in digesting huge amounts of image data and eliminate technical obstacles for cross-domain users to process satellite remote sensing images, ThinkTron has developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" as a new beginning for cross-domain AI applications for spatial information In recent years, in response to the impact of industrial globalization, Taiwan's agriculture has continued to transition towards technology-based and higher quality, improving the yield and quality of crops by solving problems, such as microclimate impacts and pest and disease control The demand of agriculture on images has expanded endlessly to accurately grasp the growing environment of crops In the early years when UAVs unmanned aerial vehicles were not yet popular, manual field surveys were the most basic but most labor-intensive work With the emergence of UAV drones, aerial photography operations might not be difficult, but the range that can be photographed is limited Furthermore, surveying expertise is required to accurately capture spatial information At this time, the use of satellite remote sensing data may break away from the past imagination of using image data Taiwan Space Agency TASA ODC data warehouse services In the past ten years, with the breakthrough of modern satellite remote sensing application technology, Digital Earth has become a new trend in global data collection Countries have developed data cube image storage technology, and the development of smart agriculture has become one of the largest image users Determining planting distribution is the first step in understanding crop yields Free satellite remote sensing images, powerful data warehousing support, and the team's robust image recognition technology are important supports for accelerating agricultural transformation Using satellite remote sensing image data can accelerate the development of smart agriculture However, in the past, it was difficult to extract large-area crop distribution through satellite remote sensing images, not to mention the cost If you wanted to use free information, you had to visit all websites of international space agencies, look through the wide variety of satellite specifications, and carefully evaluate the sensor specifications, image resolution, and revisit cycle After finding suitable images, you had to look at them one by one to filter the ones you need Next is downloading dozens of images that are often several hundreds of Megabytes MB each, which might exceed the capacity of your computer Also, after overcoming image access and preparing data, you must then start to confirm the downloaded image products and which bands you want, because the image you see is not just an image file jpg or png, but rather complex multi-spectral information, attribute fields and coordinate information It takes a lot of effort just to confirm the correct information Facing GIS software packages with complex functions is the start of another trouble The complex image pre-processing process and the inflexible machine learning package greatly reduce the efficiency of analyzing data After finally getting the results of crop identification, you might find that the best time for using map information may have already passed The above-mentioned complex and time-consuming satellite image processing problems are precisely the pain points of the market ThinkTron expanded from traditional machine learning to modern deep learning applications, and developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" under the GeoAI framework, breaking through the constraints of details in the spatial information for customers Differences between the process before and after introducing the AI analysis cloud service platform ThinkTron said that Taiwan's ODC Open Data Cube system has been completed and began providing services after years of efforts from the Taiwan Space Agency TASA, formally becoming aligned with international trends The powerful warehousing technology allows users to easily capture and use image data of a specific time and spatial range according to their needs The warehouse stores multiple satellite image resources from international space agencies, including the ESA's Sentinel-1 one image every 6 days, Sentinel-2 one image every 6 days, USGS's Landsat-7 one image every 16 days, Landsat-8 one image every 16 days, and the domestic Formosat-2 one image every day and Formosat-5 one image every 2 days ThinkTron develops satellite image recognition tools based on Python Breaking free from the limitations of GIS Geographic Information System software packages, ThinkTron integrated GDAL Geospatial Data Abstraction Library based on Python, and considered computing efficiency and parallel processing when developing all tools required for satellite image processing and image recognition modeling, including coordinate system and data format conversion, grid and vector data interaction, and data intra-difference and normalization All of the tools are designed with AI applications in mind, and some commonly used tools are packaged into an open source package under the name TronGisPy to benefit the technical community ThinkTron utilized the team's understanding of satellite remote sensing images and the collected tagged data crop distribution maps to preset the image recognition modeling process, the required training data specifications, and dataset definitions This is imported into the machine learning LightGBM or deep learning CNN framework that was completed in advance, and the entire training process to be performed in the Web GIS interface, providing users with partial flexibility to freely filter images, confirm spatial and temporal ranges, select models, and adjust hyperparameters In addition to the operation of training models, it also provides historical models to output identification results, and finally displays the identification results of crop distribution on the Web GIS map In fact, agriculture is not the only industry that needs satellite remote sensing applications AI applications of spatial information have also appeared in various fields as companies in different industries aim to enhance their global competitiveness For example, surveying and mapping companies that have a large amount of map data can use the AI analysis cloud service platform to store map data while also accelerating the efficiency of digital mapping Under the severe global climate change and the risk of strong earthquakes, there is a wide variety industrial insurance, agricultural insurance, financial insurance, or disaster insurance are all inseparable from spatial information The use of remote sensing image recognition to understand insurance targets has long been an international trend AI Analysis Cloud Service Architecture for Remote Sensing Big Data

2021-11-28

Records of

【導入案例】LEO國眾電腦AI行動視力智慧箱 定點視力檢測關懷行動不便長者
【2020 Application Example】 LEO National Computers AI Mobile Vision Smart Box - Fixed-Point Vision Testing for Mobility-Impaired Elders

When it comes to vision testing, most people think of visiting an ophthalmologist, but this can be inconvenient for those living in rural areas or for older elders Mobile vision testing could easily solve this issue LEO National Computers has launched the 'AI Mobile Vision Smart Box', aiming to provide vision tests deep into rural and community areas to solve the medical disparity between urban and rural areas The 'AI Mobile Vision Smart Box' resolves urban-rural medical disparities Taiwan has officially entered an aging society According to health insurance data, the rate of cataract changes in individuals over 70 is as high as 90 In the 29 districts of New Taipei City, up to 13 districts lack ophthalmology clinics Some areas due to their remoteness and low population density have no doctors willing to provide services, highlighting the significant disparity in medical resources LEO National Computers, founded by Dr Jian Ming-Ren in 1985, aims to tackle the issue of insufficient medical staff by using AI technology, thus cooperating with the team from the Service System Technology Center of the Industrial Technology Research Institute Since 2014, the Industrial Technology Research Institute has been involved in the integration platform for fundus cameras, collecting millions of fundus photographs from teaching hospitals and clinics, from which they selected about several hundred thousand suitable data entries Professional ophthalmologists review, annotate, and grade each photo into one of four different disease condition levels, which are then fed into artificial intelligence for training Following this, new functionalities were gradually developed according to medical field needs, offering a fully automated self-service fundus photography service This case was facilitated by technology transfer coaching from the Industrial Technology Research Institute, with National Computers providing integrated service operation and customer service The Industrial Technology Research Institute was responsible for system integration and platform maintenance Additionally, the field service was provided by a university optical ophthalmology department offering testing locations and services, promoting to diabetes care networks, optometric centers, opticians, ophthalmology clinics, and community service points for fundus camera testing The 'AI Mobile Vision Smart Box' was also officially showcased at the AI HUB conference, aiming to enhance the provision of vision tests in rural and community areas in the future, addressing the issue of insufficient medical resources in rural areas The 'AI Mobile Vision Smart Box' integrates ophthalmic handheld instruments like slit lamps, tonometers, and fundus cameras with a mobile vision testing system into a single suitcase, capable of providing 2 to 5 vision tests 'AI Mobile Vision Smart Box' instantly uploads data The usage of the 'AI Mobile Vision Smart Box' is quite simple, with a built-in local area network allowing for the immediate uploading of scanned images and data The 'AI Mobile Vision Smart Box' combines ophthalmic handheld instruments such as slit lamps, tonometers, and fundus cameras with a mobile vision testing system into a single suitcase, offering 2 to 5 types of vision testing functions The design is patient-centered, providing identity verification, test data retrieval, an automatic retina comparison system, and medical record file management, especially enabling individual patient file management Additionally, with the built-in local wireless network and smart gateway, it facilitates the immediate upload of all testing data, including images and measurements Currently, the 'AI Mobile Vision Smart Box' has collaborated with major hospitals in Taipei and family medicine clinics in New Taipei City, with plans to expand further into rural areas 'AI Mobile Vision Smart Box' apart from being used in fixed locations such as medical institutions and health check centers, its portability allows optometrists or nurses to carry it to ordinary homes or rural areas to perform eye examinations, enhancing the convenience and mobility of medical staff, and allowing vision testing to move out of hospitals into communities Currently, the 'AI Mobile Vision Smart Box' is collaborating with major hospitals in Taipei and family medicine clinics in New Taipei City, hoping to bring eye examinations closer to mobility-impaired elders in rural and community areas, aiming to achieve early detection and treatment「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

「知識圖譜」打造衛教小天使,回答孕期遇到的大小問題
【2020 Solutions】 'Knowledge Graphs' create health education angels, answering all questions faced during pregnancy

Artificial Intelligence AI is evolving rapidly Traditional scripted response smart customer services are no longer sufficient Emerging from this is the use of Knowledge Graphs in smart assistants Through knowledge graphs, these smart assistants can provide exhaustive, tailored customer service, helping consumers efficiently and effortlessly find their desired products The most common AI applications in daily life are smart customer services or smart assistants For smart customer services, the aim is mainly to address customer inquiries, but they often face the issue of providing too generic and rigid responses, lacking flexibility Utilizing knowledge graphs to establish smart assistants To develop a smooth-questioning smart assistant, it's crucial to optimize technologies such as natural language processing, semantic analysis engines, multi-turn dialogues, context awareness, emotion recognition, and personalization Supported by the Economic Ministry's Technology Department, the Institute for Information Industry’s Service Innovation Research Institute has developed tools for domain knowledge construction and management These tools assist in transforming corporate websites, databases, and documents into corporate knowledge graphs using AI recognition models When used in smart customer service, if the customer query is vague, it can proactively ask follow-up questions based on the knowledge graph and provide precise answers through multiple dialogue rounds, saving on professional labor costs and response time, and delivering better consumer service experiences Chen Bing-Yi, head of the Institute, points out that simple smart assistants operate by connecting to fixed APIs and responding based on predefined data formats, which is straightforward for queries like tracking shipments through Line or Facebook Messenger However, for more flexible customer issues such as cancer insurance clauses, credit card application terms, or legal advice, more complex technologies are required Technically, AI must convert unstructured data from documents, websites, or even social media into patterns that computers can understand, ie, establishing corporate knowledge graphs In simple terms, knowledge graphs are primarily built by extracting all significant texts and marking the relationships between them, automatically creating relational graphs among all individuals, events, and objects For example, the computer can extract and determine the relation between Nantou and Oolong Tea as 'Origin' from social data, and link 50 Lan's products to Oolong Tea as 'Product' Once a consumer wishes to know 'Where does 50 Lan’s Oolong tea come from', the system can infer using the knowledge graph and provide 'Nantou' as the response, making customer service smarter and more professional Additionally, smart assistants no longer passively receive queries they can actively notify and remind consumers, for instance, notifying pregnant women of important prenatal tests they need to undergo through Line and Facebook Messenger, ensuring no tests are missed and enhancing safety The smart assistants developed by the Institute are being progressively applied across retail, finance, and medical sectors including applications such as querying credit card benefits, product specifications, and medical education advice, with several companies already having successfully implemented these practices Plans are in place to integrate external social data or open up knowledge graphs for future development, continuing to collaborate with partners to advance the application of knowledge graphs in various new forms of AI services Applications of Knowledge Graphs Health Education Angel Chatbot New mothers often face a multitude of questions during pregnancy, such as morning sickness, diet, fetal health, and prenatal check-up considerations, affecting their sleep, personal health, and potentially impacting fetal health The Service Innovation Research Institute, in collaboration with Hua Xin Health Technology, uses AI technology to process health education manuals from the Ministry of Health and Welfare and community discussion articles This initiative aims to build a Health Education Angel using natural language processing and knowledge graph technologies specifically for addressing various issues encountered during pregnancy The institute and Hua Xin Health Technology have collaborated to develop the Health Education Angel chatbot to answer various questions during pregnancy If there are questions related to prenatal examinations, they can be inquired through 'Prenatal Examination ABC', where the system will provide information about whether certain prenatal tests are chargeable and the diseases they can screen for If there are concerns regarding dietary and health status during pregnancy, 'Pregnancy Encyclopedia' can be utilized By posing questions in natural language, the system will offer the most relevant expert answers Additionally, information about valuable pregnancy resources and welfare assistance is available for pregnant mothers to consult The Health Education Angel can pose questions in natural language, and the system will provide the most relevant expert responses「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

OMO數位服務流程設計 描述消費者輪廓達到精準行銷
【2020 Solutions】 OMO Digital Service Process Design: Profiling Consumers for Targeted Marketing

OMO Digital Service Process Design Service analyzes digital footprints to capture consumer profiles Currently in Taiwan, retailers are primarily divided into four major categories convenience stores, wholesale stores, supermarkets, and department stores Among these, department stores, which are the largest in scale, despite their long history, face the challenge of weak digital capabilities Even today, they continue to use traditional methods such as physical DMs, sales events, and anniversary celebrations to communicate with consumers In today’s environment of intense price competition and rising labor costs, coupled with their lack of a price advantage, it is unrealistic to expect consumers to remain loyal These issues also reflect in their gradually diminishing sales force The III Service Innovation team believes that 'OMO Digital Service Process Design Service' may be a viable solution to help department store sectors transform「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】雲象科技AI數位病理解決方案 提升醫療品質 減輕醫師負擔
【2020 Solutions】 AetherAI's Digital Pathology AI Solutions Enhance Healthcare Quality and Reduce Physician Workload

In the medical imaging AI industry, an increasing number of startups are emerging, among which AetherAI has recently attracted attention At last year's MICCAI, an international medical imaging conference, AetherAI's digital pathology AI defeated Stanford University's team, aiming to utilize artificial intelligence to achieve precision medicine and alleviate the burden of time-consuming tasks on physicians Providing digital pathology solutions to meet artificial intelligence application needs Led by Dr Zhao-Yuan Yeh, AetherAI, though only a few years old, includes members skilled in both healthcare and technology, possessing strong interdisciplinary integration capabilities They excel in medical research, data science, software development, systems engineering, and medical knowledge and information technology, committed to offering solutions for digital transformation in pathology and AI-assisted diagnostics With digital pathology becoming a milestone in the development of whole-slide imaging technology, AetherAI has introduced the aetherSlide system solution Besides developing digital slide management and viewing systems, it also integrates image annotation, deep neural network inference, and training functionalities, thereby fulfilling the needs for AI module applications and development Although AetherAI has been formed only a few years ago, it has recently gained significant attention in the medical imaging AI industry Just recently, Dr Zhao-Yuan Yeh, Co-founder and CEO, was awarded as one of Taiwan's Top 100 MVP Managers Photo credit AetherAI's Facebook page A key feature of the digital pathology system is the customizable digital slide status bar, which can sort cases by priority, urgency, etc, thus providing clear visibility and facilitating time management The interface is also user-friendly, offering hotkeys combinations, one-click slide assembly, along with tools such as rulers, magnifiers, and seamless rotations that enhance consultation or discussion efficiency Regarding AI services, it offers applications like cancer detection and quantification, immunostaining quantification, and blood cell classification counting Cooperation between AI and physicians minimizes repetitive work, and the system supports extensive training annotation features with various selection modes, multi-category tagging, and freehand drawing Annotations integrate seamlessly into deep learning training, structured format output, and AI training data generation in everyday processes Last year, AetherAI developed an AI medical imaging development platform aetherAI, notable for its diagnostic automation, providing an end-to-end digital pathology AI development process Photo credit AetherAI's Facebook page It is worth mentioning that the digital pathology system supports robust management functions, especially capable of being integrated according to the hospital department's work assignment process, and even with existing hospital information systems, this saves man-power, enhances administrative efficiency through digitization In terms of file formats, it supports multiple brands of slide scanner types and whole-slide image formats like svs, ndpi, scn, mrxs, bif, tif Additionally, to reduce the burden of long-term storage in medical facilities, AetherAI's infrastructure supports significant expansion capabilities, offering scalable options based on user needs, and supporting local and data center options for long-term storage solutions AetherAI's digital pathology system boasts strong management features and supports various brands of slide scanners, enhancing workflow efficiency through digital operations AetherAI Digital Pathology AI Applications Reduce Doctor's Burden and Enhance Productivity and Consistency At the recent AI HUB conference, AetherAI demonstrated its AI medical imaging development platform launched last year aetherAI, its main feature being diagnostic automation This allows departments within hospitals to integrate various types of DICOM files and medical knowledge, boasting a highly scalable AI model capability, and providing an end-to-end digital pathology AI development workflow Currently, it offers digital pathology AI modules including automated bone marrow smear classification, nasopharyngeal carcinoma recognition, and glomerulus detection applications, involving nearly ten different types of datasets So, what are the tangible benefits for doctors Simply put, with a prior scan using AI, cancers can be confirmed without the lengthy manual review previously typical in bone marrow exams, thus greatly shortening repetitive tasks for doctors and enhancing efficiency in complex diagnoses Currently, aetherAI has reached recognition levels comparable to a pathology doctor's visual assessment standards, achieving an identification rate as high as 97 for nasopharyngeal cancer AetherAI's AI medical imaging development platform aetherAI can significantly reduce repetitive tasks for doctors, leading to more efficient and effective high-complexity diagnoses Currently, AetherAI's partners and customers mainly include large medical centers, with the University of Pittsburgh Medical Center leading internationally In Taiwan, includes major medical institutions such as Taipei National University Hospital, Taipei Veterans General Hospital, Chang Gung Hospital, Cathay General Hospital, Tri-Service General Hospital, Chung Shan Medical University Hospital, Taipei Medical University Hospital, among others, aiming to use artificial intelligence for precise medical applications, enabling deep learning in clinical practice to reduce the workload for doctors and elevate the consistency of medical quality AetherAI official website「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】專注各種量化分析技巧 木刻思挑戰深不可測的問題
【2020 Solutions】 Focusing on Various Quantitative Analysis Techniques to Tackle Profound Challenges!

In today's digital age, both individuals and companies face challenges in writing copy and designing layouts when managing a brand online What constitutes good design The online world often gives a mysterious impression, and the WoodThought team has been focusing on studying various data sources for years, hoping to find the answers they seek Focused on data analysis for exploring and solving problems WoodThought is a group of consultants specializing in data Big Data amp Deep Learning and solving the essence of problems The team utilizes various quantitative analysis techniques to challenge many of the profound issues found on the internet and strives to continually enhance the data analysis capabilities of both Taiwanese businesses and individuals The application of this technology is extensive, including personalized navigation and recommendation systems on news platforms, eCommerce personalization for navigation, search, and recommendations, or strategy development, design, and backtesting in financial transactions Moreover, WoodThought also offers data analysis courses like web scraping and data visualization in response to technological and current events, aiming to cooperate with both domestic and international enterprises to implement various data science solutions WoodThought is a group of consultants dedicated to data analysis, exploring and solving fundamental issues, utilizing various quantitative analysis techniques to challenge the many uncertainties of the internetImage Source) Taking the simplest web design as an example, WoodThought believes that with the advancement of personalized tracking technology and the combination of AB Testing experimental designs and testing techniques, professionals in all industries can now avoid relying on the so-called '20 years of marketing experience' Instead of using inefficient and unpredictable methods, making use of data analysis enables even intuitive observations to have a basis, thereby capturing the sentiments of online users Supported by adequate data evidence, incorrect decisions and directions can be corrected promptly before mistakes are made WoodThought showcased its proprietary 3D marking system at the recent AI HUB conference, which utilizes AI image recognition technology to help doctors quickly determine the condition of patients' lung nodules The AI model will automatically learn from the markings, providing recommendations for future markings by doctors, allowing for early discovery and immediate treatment, resolving past difficulties of 3D image marking and the challenge of obtaining marking data The team developed a 3D marking system using AI image recognition technology, significantly enhancing the efficiency of medical diagnosis The same AI data analysis technology, also applicable in the medical sector, was showcased by WoodThought at the recent AI HUB conference This includes their own 3D marking system with features like Auto-Learning and Pre-Labeling This system assists doctors in diagnosing lung nodules As doctors complete the diagnosis and marking, the AI model will learn from it and provide future marking suggestions, enabling early discovery and immediate treatment, thereby greatly resolving the difficulties of 3D imaging marking and issues of data accessibility WoodThought aims to solve various personalized service demands through data analysis techniques and calls for everyone to go beyond mere imagination, interact personally with different types of data, and dig out the answers behind the problems Over the past two years, core members of the WoodThought team have actively assisted and guided ordinary users on various e-commerce and media platforms to establish correct views through introducing relevant technologies and services This helps solve various personalized service demand issues and enhances the likelihood of matching products with customers WoodThought encourages everyone to leave behind imaginary notions, to engage with data, and to uncover the answers behind the problems, while also experiencing the problems behind the answers Given the rapid changes of the internet era, each rising wave brings different user needs and voices WoodThought aims to help everyone solve problems quickly and efficiently using various data analysis techniques「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】偲倢科技-被動元件高速AI瑕疵檢測平台 以機器取代肉眼提高產線效率
【2020 Solutions】 Spingence - High-speed AI defect detection platform for passive components improves production line efficiency by using machines to replace manual inspection

Inspection is an important part of maintaining quality in all factory production lines However, manual inspection is traditionally used to inspect the appearance of products for defects Visual inspection is not only prone to errors, but also requires high labor costs Spingence implemented AI technology into the inspection system and developed a high-speed AI defect inspection system for passive components, hoping to greatly improve the speed and efficiency of the inspection process Focusing on automation software development to improve production line inspection efficiency Spingence focuses on software design, development and sales It has a comprehensive and easy-to-understand automation development platform It uses the automation graphical platform LabVIEW and high-end software to provide evaluation planning for automation projects, including robotic arms, machine vision, and motion control equipment, in hopes of changing the existing automation software model through various implementation cases and experience It provides a production line inspection platform that can be quickly introduced and is easy to use, which helps major companies improve the automation process of their production line Spingence focuses on software design, development and sales, provides a production line inspection platform that can be quickly introduced, and assists major companies in improving the production line automation process Source of image Spingence At the recent AI HUB conference, Spingence displayed its high-speed AI defect inspection system for passive components As the name implies, the inspection system introduces AI technology to make the entire production line more efficient The reason for developing the equipment is because most factories used to use manual inspection of the appearance of products for defects, but long hours of manual inspection will result in a decline in work quality In addition, as more components become smaller and production speeds increase, it will become unbearable to the human eye This is why we hope to use the power of technology and use high-resolution cameras and high-performance imaging software to make inspection work of the entire process more efficient Rapid recognition and self-learning meet the high-speed inspection requirements of production lines The high-speed AI defect detection system for passive components can easily complete automatic process editing and arrangement based on different hardware configurations, and also provides optimized models Its speed can reach 1,200 pieces per minute with missed detection rate below 50ppm More importantly is the flexibility of configuration, in which different edge devices can be selected according to customersrsquo cost and speed requirements Of course, there is no problem in mixing them Taking the defect detection demonstrated on site as an example, the integrity of glue dispensed on the white platform is detected If traditional AOI algorithm is used, the surface of the glue may reflect light due to ambient light, leading to many misjudgments However, if the automatic learning characteristics of AI neural network are used, then it will be able to stably differentiate between reflection and defects from incomplete dispensing The high-speed AI defect detection system for passive components can easily complete automatic process editing and arrangement according to different hardware configurations Highly flexible configurations can be built according to customers' cost and speed requirements To build a network model with high accuracy, it not only requires long-term training, but also optimizes parameters for different products Spingence has highly optimized the algorithm in embedded devices, allowing the high-speed AI defect detection system for passive components to inspect thousands of objects in just one minute, meeting the high-speed detection requirements of production lines Image recognition has become the most important application of AI, especially in defect detection on production lines AI has fast recognition and self-learning functions, which can more significantly improve overall implementation benefits The software platform and technology of Spingence have been certified by many partners, and the introduction of automation into factories has become a trend in recent years Due to the differences in the design of each production line, automation must be highly customized work As more resources are invested in the future, Spingence also hopes that this automation software platform will provide customers with more diverse solutions and help companies easily move towards Industry 40 Spingence's official website

【解決方案】即時推薦對的商品 太米讓你的顧客轉換與回流自動增加
【2020 Solutions】 Instantly Recommend the Right Products: Taimi Increases Your Customer Conversion and Retention Automatically

Have you ever had an experience where, while randomly browsing online stores, it seems like the website can read your mind, constantly recommending products you want to buy Recommending the right product to the right customer at the right time For example, when you see a piece of clothing you like, similar items or accessories that could match it immediately appear below, and before you know it your shopping cart gets fuller and fuller The reason the webpage understands you so well is primarily due to the implementation of an AI engine that can automatically analyze customer preferences and recommend the right product at the right moment, invisibly increasing the consumer's purchasing intent and stabilizing the platform's customer base This is the expertise of Taimi Rosettaai Taimi Rosettaai provides software services to e-commerce platforms aimed at increasing conversion rates and customer retention rates, by analyzing consumer preferences through various AI engines and recommending personalized products online and offline Taimi Rosettaai is an internet company specialized in creating one-stop customer conversion and retention services for e-commerce, analyzing consumer behavior through various AI engines, and recommending personalized products both online and offline Referring to the previous mention of online shopping, throughout the entire shopping journey, clever integration of different AI engines on various situational pages—home page, product page, category page, shopping cart, checkout page—these designed APIs tailored to consumer needs and shopping contexts further deepen the analysis of consumer preferences Through accurate sales forecasting, it elevates the consumer experience and conversion rates Throughout the entire shopping journey, Taimi Rosettaai is capable of installing different AI engines on various pages, instantly recommending the right products in the right context, thereby invisibly enhancing consumer's purchasing intentions Different AI engines analyze different situations to create consumer return flow and increase lift-to-cart rates For instance, if a consumer lingers on a page buying a coat, not only similar styles get recommended below, but there may also appear clothing or accessories that complement that coat, such as undergarments, pants, belts, bags, etc The system will also consider the consumer's past shopping habits and recommend items they might be interested in For instance, if the consumer has previously purchased a DSLR camera, the page might suggest camera bags, cleansing kits, etc, relevant products Through AI technology, cross-analyzing merchandise information with customer preferences achieves personalized promotions Besides targeting the e-commerce market, Taimi Rosettaai also actively expands overseas, collaborating with major domestic and international accelerators in recent years, and hopes to apply its capabilities in different industries to seek more collaboration opportunities Taimi Rosettaai offers a variety of instantly usable API modules and basic situational combinations, allowing users to choose according to the characteristics of their website, without the need for large investments in building an AI infrastructure This enables clear understanding of customer preferences, significant reduction in marketing costs, and even inventory forecasting, thus effectively increasing e-commerce revenue Besides focusing on the e-commerce market, Taimi Rosettaai is also actively expanding overseas, having been selected by well-known domestic and international accelerators such as AppWorks, Founder Institute, Orange Fab, Zerothai, etc, over the past two years It also hopes to apply its capabilities to different industries in the future, seeking more collaborative opportunities Taimi Rosettaai official website「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】公廁如何靠IoT及雲端科技變乾淨、解決7成客訴,並且提昇120倍效率
【2019 Application Example】 How can public restrooms rely on IoT and cloud technology to become cleaner, solve 70% of customer complaints, and increase efficiency by 120 times?

IoT smart restroom A revolution of clean, power-saving, and convenient new smart restrooms Six sensors are used to detect toilet paper, hand soap level, water leakage, odor, people flow, and toilet usage conditions, and combined with NBIoT transmission, cloud system, and LINE robot It greatly reduces customer complaints and improves the efficiency of replenishing consumables in restrooms Coupled with real-time notifications, it can prevent illegal smoking in restrooms and improve safety Users will no longer face the dilemma of wet, dirty, smelly restrooms, or toilet paper running out, greatly upgrading their experience What is your impression when you walk into a public restroom in a popular tourist area No hand soap No toilet paper Or even a dirty, smelly, and leaking restroom The IoT big data smart restroom solution of the Institute for Information Technology III solves all inconveniences of restrooms all at once According to statistics of the Environmental Protection Administration EPA, Executive Yuan, there were more than 43,000 public restrooms registered and managed in Taiwan as of the end of September 2019, but the entire EPA only had over 34,000 people Cleaning and managing such a large number of sites is obviously not an easy task Coupled with the inevitable arrival of an aging society, the number and quality of personnel cleaning restrooms will inevitably encounter unprecedented bottlenecks The introduction of effective service processes and assistance of technologies has become a major issue that must be faced sooner or later The IoT smart restroom service solution demonstrated by the III at over 20 restrooms around Taiwan may provide a good direction for us to solve this problem Overwhelming number of customer complaints, four major problems, and three solutions of the III In 2016, when the MRT Songshan Station, which is connected to the train station, was officially opened, the public restrooms that were already at full capacity resulted in serious customer complaints due to the overwhelming use Songshan Train Station, which originally had an average daily passenger volume of only 40,000, was already near a bottleneck in service capacity After the connected MRT Songshan Station was opened, the number of passengers increased to 70,000 The restrooms that were already near full capacity were completely unable to cope with the additional passenger volume after the MRT station was opened Cao Xueqin once wrote a classic line that touched people's hearts in the novel "A Dream of Red Mansions" "When a wall is about to collapse, everybody gives it a shove" may be able to describe this phenomenon The toilet paper and hand soap in each restroom was never replenished in time, the sinks were dirty, and the toilets could never be cleaned in time There was an overwhelming number of customer complaints about the restrooms as a result In addition, the public restrooms of Songshan Train Station are closer to the main passageways of passengers than the public toilets of MRT Songshan Station At this point Songshan Train Station had to face and solve this problem Since Songshan Train Station has worked with the III for a long period of time, it commissioned the III to help solve this troublesome problem Edison has a famous saying "If I find 10,000 ways something won't work, I haven't failed I am not discouraged, because every wrong attempt discarded is another step forward" The first thing that the III needs to do is conduct pain point analysis and think about the underlying problem After reviewing customer complaints and discussing and analyzing them with front-line cleaning service companies, the III found four problems and three solutions The four problems are Toilet paper and hand soap are not promptly replenished, sinks are damp, and the space has a foul smell The three solutions correspond to these four problems respectively 1 Delicacy management of consumables such as toilet paper and hand soap 2 Digitize the key performance indicators KPI in the service process, such as the dampness of the sink, or the odor concentration in the space 3 Use new Internet of Things IoT technology to implement the first two solutions, and assist big data and cloud technology in achieving efficient site cleaning management "Technology features and RampD process" The combination of six key sensors with IoT cloud motherboard and big data, thoroughly resolving 70 of customer complaints and increasing efficiency by 120 times I Delicacy management of consumables To achieve delicacy management of toilet paper and hand soap, the first step is to develop sensors to detect these two consumables Starting in 2017, the III began to design the first infrared toilet paper detection module The module mainly uses the physical characteristics of toilet paper usage habits for detection Under normal use, toilet paper is placed on an iron drum holder, and its thickness slowly becomes thinner as it is used This module requires the combination of a position sensitive detector PSD , infrared emitting diode IRED, and signal processing circuit SPC to effectively determine the length of toilet paper with accuracy reaching one decimal place When the detection module was first developed, there were no designs that could be referenced, so sensor selection, circuit board designing and planning, sensor programming, and even the light-cured 3D printed casing design were all completed in the III However, despite overcoming all the difficulties in designing and producing the toilet paper sensor, there was no way to foresee that fixing the sensor in place would be the most difficult problem The III team shared with us ldquoAt first, we used hot melt adhesive to fix it in place, but cleaning personnel needed to open and close it every time they replenished toilet paper The sensor fell due to too much vibration and not being firmly fixed in place The worst situation was in the women's restroom When a female passenger was using the toilet, the sensor was not properly fixed in place and fell Donrsquot you think this sensor looks like a pinhole camera If something like this suddenly falls on the ground in the women's toilet, how bad do you think it will be laughs Fortunately, our superiors supported us, and we continued to develop the technology until we were able to successfully fix the sensor firmly in place Otherwise, this project would have been aborted a long time ago" After the toilet paper detection module was launched, an inspection of toilet paper usage that once took cleaning personnel 15-20 minutes to complete now only takes 10 seconds by opening the app This greatly improved efficiency by 120 times Now that the consumption of toilet paper has been solved, the next problem is detection when hand soap is at a low level Unlike toilet paper, the amount refilled each time for hand soap isn't always the same Because the design philosophy was to use the lowest cost and most stable components to complete this function to facilitate future scaling, a common Hall sensor was chosen It was mounted on the exterior of the soap dispenser to achieve the detection of low soap levels The principle is actually very simple Once the liquid level is lower than a certain percentage, the Hall effect sensor can sense the change in voltage from electromagnetic induction of the liquid level The sensor sends a signal to the back-end cloud server, and then the server then sends a message to cleaning personnel the same as the toilet paper sensor II Digitization of key performance indicators KPIs in service processes If the sink is wet, water will often seep onto the floor In addition, the bottom of passengersrsquoshoes will inevitably carry dust, so the floor will become dirty when they step on the wet floor Visually, this will give people a sense that the ldquorestroom is dirty" However, it is impossible to have cleaning personnel on duty in the restroom at all times, so a special sensor is needed to detect this situation The III uses the resistance characteristics of thin film resistors When there is liquid on the surface of the thin film resistor, it will lower the overall resistance value and further change related values of the analog signal output In this way, moisture can be detected by simply laying thin film resistors on surfaces that often become wet For example, next to the windowsill or on the sink However, since sensors are relatively expensive and scratches will damage the performance of the sensors, this moisture detection sensor is only used in specific public restrooms Apart from looking dirty, if a foul smell comes from a public restroom, people will think it is dirty even if it looks bright and clean However, odor detection is not that easy to solve At first, we searched all kinds of sensors in Taiwan and overseas to find this "electronic nose" We eventually found a suitable MEMS chip in the product line of a major Japanese manufacturer that specializes in the production of gas sensors The III started from breadboard testing, circuit design drawings, to outsourced chip production, taking nearly six months to complete the design of the sensor Furthermore, in the process of developing smart nbsprestrooms, we also received requests to develop other modules, such as people flow detection and usage detection During the development process, we found that users may accidentally close the door of some accessible toilets after use and forget to turn off the lights, so it seems as if the toilet has been occupied all day long However, people who really need to the toilets are blocked outside the door of accessible toilets that are actually vacant This problem was relatively simple The engineer found a ready-made people flow sensor module and installed it under the sink, and the problem was easily solved In addition, environmental protection and carbon reduction requirements are hard to meet for some remote public restrooms, such as Tri-Mountain Lishan National Scenic Area Due to the remote location, responsible personnel must turn on the lights every day at work and turn off the lights when they get off work Sometimes not many tourists use the public restroom all day long, but all the lights and equipment are still on all day long, which is a waste of electricity Generally, commercially available sensors are very dull and will turn off the power as soon as the set time of 30 seconds to 10 minutes is up Such a sensor may be adequate at home when only one person uses the toilet However, in a restroom that can easily reach 60 ping or above, several detectors will be needed to work together to ensure whether there are still users in the restroom This is another problem without a commercially available solution The III had no choice but to integrate multiple sensors and develop algorithms on the MCU to solve this problem III The introduction of new IoT, cloud, big data, and 5G NBIoT technologies On the path of innovation, there are always difficulties waiting for engineers to overcome In the process of solving problems as they come, we also refined the solution step by step, making it cheaper, more reliable, and more convenient After the sensors described above were completed, the system gradually generated new problems for the III to solve For example, the barrier of user habits, power consumption issues, cost issues, etc The app was changed to a LINE group robot to become more aligned with user habits When the public restroom of about 60 ping at Songshan Train Station was completed for the first time in 2017, MCU and WIFI communication were used to monitor and transmit data to the server around the clock After the system determines an abnormality, it uses the mobile app developed by the III to notify cleaning personnel This design seems to be impregnable at first glance However, the average age of on-site cleaning personnel is over 50 years old, no one used the dedicated app, and front-line personnel often deleted the program within a few days of use There is a whole set of sensors monitoring, but no cleaning personnel actually use it User habits are often the biggest obstacle to the introduction of new technologies After conducting user interviews we found that the cleaning personnel of every public restroom have a LINE group The III team mentioned "Knowing that they cleaning personnel have a LINE group makes things easier At first, we cautiously asked the cleaning personnel if they would invite a robot "new colleague" to help inspect toilet paper and determine abnormalities in the restrooms At the beginning, the cleaning ladies were a little skeptical When they discovered that this robot "new colleague" was very useful, they fell in love with it" Due to cost, environmental protection, and convenience issues, WIFI was upgraded to NBIoT communication protocol WIFI is fast and has wide bandwidth A restroom has a men's room and women's room, which requires two separate systems for monitoring, and each system needs an independent 4G network to connect to the cloud system Therefore, the construction and communication costs are relatively high, and the power consumption is also relatively high At this point, readers may have questions Public restrooms are all set up in public spaces Is there no public WIFI network available The III team gave us a very in-depth answer "Actually, almost every public space has a WIFI network that can be used However, sharing WIFI with other people is prone to interference, and IoT devices are simple and lack security control mechanisms If you use public WIFI, there is a certain degree of security risk Therefore, in our solution, we still designed a closed WIFI communication system to solve the communication problem In addition, since a WIFI base station can only support 20-30 nodes, a women's room with 18 toilets requires a separate systems Coupled with the fact that it is separated by a concrete wall, the signal will be very weak and even affect the stability of the signal Therefore, a public restroom installing two systems is mainly due to stability considerations rather than cost considerations" In densely populated areas, using WIFI to transmit data to the server is not too troublesome However, when smart restroom systems are beginning to be applied to restrooms in remote areas, such as Lishan, Guguan, Shitoushan and other public restrooms of national park visitor centers, maintaining network connection is indeed a difficult problem Fortunately, new generation mobile communication networks of 5G includes narrow-band Internet of Things NBIoT specially designed for the Internet of Things The III is the first in Taiwan to develop Taiwan's first NBIoT MCU control system designed for smart restrooms using the NBIoT chipset of a domestic chip manufacturer In addition to the significant cost reduction, this system is also very energy efficient, requiring only 16 of the power of the original WIFI system The most important thing is that compared to traditional WIFI, which requires a relatively stable 4G signal connection, this system has wider coverage and allows communication deep in the mountains and out in the wild This allows wider coverage of smart restrooms in the future without being limited by network signals IV "Effect Analysis and Future Outlook" IoT smart toilet A revolution of clean, power-saving, and convenient new smart toilets As the complete set of sensors, cloud system, NBIoT, and LINE robot are gradually launched, the benefits are clear In the case of public restrooms at Songshan Train Station, from being overwhelmed at first to greatly reducing the number of customer complaints by 70, the time required to inspect toilet paper use was shortened from the original 15-20 minutes to only 10 seconds Once an abnormal situation occurs, it has gone from being undetected to the prompt notifications today Interestingly and unexpectedly, this entire system also brings the added benefits of safety and thorough enforcement of tobacco hazards prevention laws When a toilet is occupied for more than 40 minutes, a warning will be sent to the cleaning personnel group Hence, when a user occupies a toilet for too long, cleaning personnel will knock on the door This greatly improves safety In addition, odor detectors are also very sensitive to the smell of smoke Since smoking is prohibited in national parks, tourists sometimes sneak into public restrooms in remote areas to smoke In public restrooms of national parks, once the odor detector detects the smell of smoke, it will play a voice message about the Tobacco Hazard Prevention Act to let tourists clearly know that smoking in public restrooms will result in a fine of NT2,000 to NT10,000 Since the installation of odor detectors, the number of users smoking secretly in public restrooms has significantly decreased The "smart public restrooms" at Songshan Train Station won the "Golden Way Award" from the Ministry of Transportation and Communications for overcoming various difficulties, which made it famous From a constant stream of customer complaints to model public restrooms that the public sector has enthusiastically visited, the additional workload on the case officer from handling group visits is actually a luxury to be worrying about Future Outlook The system has proven its stability and cost effectiveness during the three years of RampD and field experiments, and has now been successfully transferred to domestic system integration companies The III also hopes that this system can be expanded in the future, and the technology can even be transferred to Europe and the United States In addition, on the basis of stable and reliable data flow and communication connections, the introduction of big data for analysis may make the deployment of manpower more delicate, and the problem of uneven work distribution can be expected to be fundamentally corrected Facing the arrival of an aging society, NBIoT communication systems, combined with various IoT sensors, may be able to bring us a healthier and safer living environment Some repetitive tasks that traditionally relied heavily on manpower can also use technology to greatly improve efficiency

【解決方案】海量數位工程 智能羽球拍讓訓練變得更好玩
【2019 Solutions】 Massive Digital Engineering: Smart Badminton Rackets Make Training More Fun!

For many professional team trainers, recording players' training conditions in the past often required manual effort However, by mounting sensors on sports equipment and combining them with corresponding AI devices, it's now possible to easily record training data Massive Digital Engineering has launched the napa smart badminton racket, digitizing the often abstract actions in sports, which assists athletes in finding the right training direction Introduction to Massive Digital Engineering Established in 2000, Massive Digital Engineering focuses on data analysis and mining in areas such as ERP, Industry 40, and financial big data It services manufacturing industries like chemicals, sports equipment, and automotive components, as well as various retail and distribution sectors by offering system development, customization, installation, and integration, helping companies enhance operational efficiency The company excels in cloud big data, using publicly traded financial databanks to design up to 92 financial assessment standards, which serve as benchmarks for businesses to improve their corporate structures Additionally, in response to Industry 40 and smart manufacturing trends, Massive Digital Engineering continues to develop innovative intelligent technologies aiming to boost production efficiency while reducing costs and pollution The napa smart badminton racket handle embeds high-performance sensors that automatically transmit the collected data for AI-driven analysis to an app Massive Digital Engineering showcased the napa smart badminton racket at the AI HUB Conference Recently at the AI HUB Conference, Massive Digital Engineering unveiled the extensively developed napa smart badminton racket, digitizing complex and hard-to-measure sports movements applicable in various competitive sports This tool helps coaches in training and assists athletes in finding the right direction For leisure and entertainment, the napa smart badminton racket can transform traditional courts into smart courts, complete with real-time data display boards on both sides of the court This not only displays scores during matches but also enables players to instantly access various swing data, vastly enhancing the fun and interactive aspect of the game With years of experience in data analysis and mining, one may wonder why Massive Digital Engineering ventured into the sports domain It turns out that there is a backstory involving long-term subcontracting work for the well-known sports brand WILSON, combined with the good reputation of its own Napa badminton rackets and familiarity with badminton-related products Hence, starting from the basic physical product of the racket, years of AI research were integrated into the development of the napa smart badminton racket project The sensors on the racket record all swinging actions including speed, posture, energy use, and striking force, and even 3D swing trajectories can be reviewed via the app But how does the napa smart badminton racket work Here's the principle sensors embedded in the racket handle automatically collect data, which, through AI algorithms, is linked to cloud big data When connected to a smartphone, various sports records can be viewed via an app The racket's sensors document every swing—its speed, energy consumption, posture, and power—and even 3D trajectories If used with a smart wristband on the same hand, it can also monitor heart rate and blood pressure, then through various big data applications, provide personalized scientific sports recommendations For instance, some players may swing too broadly with enough power but incorrect direction, or they may exert too much force during a swing but lack strength during impact These common training issues can be effectively addressed and improved through the napa smart badminton system Besides the napa smart badminton racket, the napa intelligent system can also be applied to baseball By installing sensors in the bat handle, swings can be recorded in real-time Smart sports application scenarios The primary target audience for napa smart badminton includes players and coaches, and it is also suitable for individuals who want to train independently Beyond badminton, the napa intelligent system can be applied to other sports like baseball The underlying principle is similar, hiding sensors in the bat handle to instantly record swing trajectories, enabling hitters to more precisely determine the impact position and power point Additionally, integrating more professional training, such as weightlifting—where Hsu Shu-ching won two Olympic gold medals—has gained more national attention Traditional training predominantly uses verbal instructions, such as directing athletes to apply a certain amount of force backward or forward, but these descriptions are abstract Integrating the napa intelligent system into weightlifting, for instance embedding miniature sensors in silicone gloves, would allow precise tracking of movement trajectories through app data, making adjustments more accurate with systematic data Massive Digital Engineering is actively collaborating with various badminton venues, aiming to upgrade traditional courts to smart courts using the napa smart badminton racket Massive Digital Engineering has recently started collaborating with various badminton venues to upgrade traditional courts to smart courts using the napa smart badminton racket They also continue promoting through sports communities, sports digitalization, experiential marketing, and other diverse applications to revolutionize the current sports industry「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】艾歐資訊「AU照護辨識服務系統」 提升醫療完善率瞄準150億商機
【2019 Solutions】 Aurora Information 'AU Care Recognition Service System' Aiming at a 15 Billion Business Opportunity by Enhancing Medical Completion Rates

As the population ages, home care has become a universal issue In the face of low medical staff ratios, whether in hospitals or external care facilities, medical personnel face the challenge of insufficient manpower Aurora Information has introduced the 'AU Care Recognition Service System', aiming to enhance medical completion rates through AI and 3D imaging technology Aurora Information introduces the 'AU Care Recognition Service System' using non-contact 3D imaging technology to instantly detect patient movements and physiological data from beds, significantly enhancing medical completion rates The 'AU Care Recognition Service System' incorporates Time-of-Flight ToF and mmWave Radar sensing technologies, coupled with point cloud and mmWave deep learning analysis AI algorithms, significantly strengthening computer vision and image processing capabilities Preserving Personal Privacy While Precisely Monitoring Patient Admission Status Aurora Information recently showcased the 'AU Care Recognition Service System' at the AI HUB conference With the use of Time-of-Flight ToF, mmWave Radar, and other sensing technologies, along with point cloud and mmWave deep learning analysis of AI algorithms, it greatly enhances computer vision and image processing capabilities Additionally, unlike traditional cameras that raise personal privacy concerns, this system uses non-contact 3D imaging technology for tracking bed exits and physiological data, providing instant notifications to users The system offers long-range, multi-target, high accuracy, continuity, and persistence advantages, all while maintaining patient privacy and precisely monitoring various admission statuses Through 3D imaging technology, when detecting potential danger actions like falls or tremors on the screen, it can immediately alert designated personnel or medical stations within 3 seconds, lowering the chances of sudden patient deaths The 'AU Care Recognition Service System' also measures heart rate, respiration, and other physiological data, using AI algorithms to predict the likelihood of sudden death 3D Imaging Technology for Immediate Reflection of Patient Emergency Situations How does it work in practice Suppose a patient falls out of bed when unattended, traditionally, they could only passively wait for help However, with the 'AU Care Recognition Service System' using 3D imaging technology to detect actions such as falls or tremors, it can immediately notify designated personnel or medical stations within 3 seconds, reducing the chances of sudden death by 20 it also measures heart rate, breathing, and other physiological data, using AI algorithms to assess the risk of sudden death, potentially reducing the death rate by over 40 Moreover, the system can simultaneously assess multiple patients, infants, and the elderly, enhancing timely care efficiency by more than 20, thereby significantly lightening the burden on medical staff Through the smart monitoring interface, medical personnel can clearly see real-time conditions in hospital wards or stairways, with intuitive icons helping them grasp the situation immediately Amidst the global challenges of aging and chronic diseases leading to high medical care costs, the 'AU Care Recognition Service System' effectively addresses the pain point of insufficient medical care According to the medical data released by the Ministry of Health and Welfare last year, if the 'AU Care Recognition Service System' were to be standardized, the market size for Taiwan's medical care institutions alone would be as high as 15 billion NTD Currently, Aurora Information is actively cooperating with the government, universities, and nonprofit organizations, hoping to contribute to medical care「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

這是一張圖片。 This is a picture.
【2019 Solutions】 Do products need 'AI Face Recognition' to qualify? The era of smart imaging has arrived, spearheaded by Juou Technology's interdisciplinary developments.

AI information technology can be utilized in very distinct industrial fieldsUnmanned factories, automated production lines, and robotic arms, etc To accelerate production lines to achieve economies of scale and simultaneously reduce costs, major production lines look forward to continuously optimizing in various aspects to reduce errors and increase yield rateIn the production line, quality control testing is a critical step that significantly impacts product quality Taiwan's Juou Technology Corporation stands out in its research and development efforts, not only addressing the management of Taiwan's resources and urban-rural development issues but also in its performance through innovative cross-disciplinary integrationWithin Juou's GEO IOT plan, two parts of the cross-disciplinary technology project are implementedPart oneWithin the AOI technology area, there is active investment in the technical development of big data, artificial intelligence, and data science It also involves the development of a high-speed, high-precision optical imaging inspection system in the production line quality management This technology utilizes machine vision with high focus and sensing to capture the surface images of products and automatically assess whether the products meet the quality standardsThis non-contact inspection tool not only speeds up the inspection process and identifies product defects but also automatically discriminates flawed products It is also applicable for the inspection of semi-finished products in the production line In enterprises that are major producers in Taiwan or those with a focus on quality, this optical combined with image processing system is necessaryPart twoBlood tests, crowd recognition, access control in danger areas construction sites, IVS, AIR vehicle controlBiometric recognition technology utilizes the characteristics of organisms for identification, including iris, retinal, and body shape recognition It also enables the monitoring of people flow within a specific space to quickly capture more information about crowd movements Beyond handling crowd recognition, Juou Technology also employs recognition technologies for control and monitoring of hazardous areas such as construction sites and production lines For instance, in spatial detection technology—if a construction worker forgets to wear a safety helmet or safety suit, the detection equipment will notify them upon entry to the site, thus reducing risks caused by human oversightCommitted to the innovation of the brand and the integration between sectors, it is believed that through digital technology and multi-disciplinary integration, the sustainable and innovative development of Taiwan will be driven「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】切斯特SchoolBot機器人 為親師間打造最佳溝通平台
【2019 Solutions】 Chester SchoolBot Robot - Creating the Optimal Communication Platform for Parents and Teachers

For parents with young children, discussing matters with school teachers via the instant messaging app LINE is a good method Although LINE groups are convenient, if there are too many people talking at once, it can make what should be simple communication inefficient Starting from the service of campus smart vending machines, solving the pain points in parent-teacher communication In order to facilitate better communication between parents and schools, Chester International Co, Ltd and Zhonghua Lin Co, Ltd have collaborated to launch the SchoolBot service In fact, last year when Chester deployed the iMvending smart vending machine service at Taipei's Xingan Elementary School, they observed many communication pain points between parents and teachers This influenced the development of SchoolBot Utilizing the popular instant messaging app LINE as its platform, SchoolBot is essentially a robotic assistant for schools, incorporating LINE Bot and AI auto-response technology, and offering a pioneering one-on-one communication method that eliminates the clutter of traditional LINE groups SchoolBot incorporates LINE Bot and AI automatic response techniques, along with a pioneering one-on-one communication method in Taiwan, ensuring avoidance of the chaotic situation common in traditional LINE groups Automatic categorization makes it user-friendly, and privacy is secured Thanks to the adoption of AI technology, SchoolBot offers more applications than expected, providing a user-friendly and intuitive operation experience, as if chatting with a real person Whether helping children take leaves, sending messages to specific teachers, the system emphasizes categorization, allowing schools to identify and send messages to the appropriate recipients For parents, aside from basic inquiries, SchoolBot also supports categorization by child's student ID Upon the first use, when parents input their child's student ID, the system automatically categorizes it into the corresponding class, eliminating the need for manual selection and ensuring privacy security Whether helping children take leaves or sending messages to specific teachers, SchoolBot provides a smooth and intuitive operation experience, similar to chatting with a real person Additionally, SchoolBot caters to the common discussion scenarios faced by teachers and parents, integrating a practical online survey service This not only saves time and streamlines work processes for teachers but also supports the modern trend of going paperless Notably, the SchoolBot system automatically 'levels up' at the start of a new academic year, automatically advancing students to the next grade level, addressing the manual update problem that similar services face Chester has already collaborated with Xingan Elementary School, and hopes to expand the service into various community-based scenarios, creating a more convenient communication platform Besides schools, SchoolBot is also suitable for various scenarios like daycare centers, tutoring centers, and parent associations Chester has already partnered with Taipei's Xingan Elementary School and plans to continue expanding SchoolBot to other places, aiming to build a more convenient communication bridge for community-based scenarios「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】訊連科技FaceMe 不光性別年齡就連情緒也能完整偵測
【2019 Solutions】 CyberLink FaceMe: Not Only Gender and Age, but Emotions Can Also Be Fully Detected

AI facial recognition has become an extremely popular topic in recent years and has been widely applied across various fields CyberLink's FaceMe facial recognition engine utilizes deep neural network learning algorithms, enabling comprehensive detection of not only gender and age but emotions as well CyberLink recently showcased the FaceMe facial recognition engine at the AI HUB conference, highlighting its capability to accurately pinpoint up to 106 facial feature points using deep neural network algorithms CyberLink presented the FaceMe facial recognition engine at the AI HUB conference CyberLink has devoted years to developing AI facial recognition and facial attribute technology, recently demonstrating the FaceMe facial recognition engine at the AI HUB conference Its standout feature is its precise localization of up to 106 facial feature points using deep neural network algorithms This makes it easier for developers to build dynamic 3D facial models and features a high accuracy recognition rate of 995 and a very low error rate, along with a software development kit SDK that enables system integrators and solution developers to incorporate high precision facial recognition technology into various products and services as needed The FaceMe facial recognition engine boasts a 995 accuracy rate How powerful is the FaceMe facial recognition engine It can detect not just basic attributes like gender and age, but also abstract ones like emotions At the recent AI HUB conference, CyberLink demonstrated this technology, showing that at the bustling venue, the FaceMe engine rapidly recognizes facial attributes such as age, gender, skin color, and head movements as soon as someone enters the camera's range and can even calculate emotional indices like surprise, happiness, anger, and sadness from slight facial changes The FaceMe facial recognition engine can detect subtle facial changes and calculate emotional indices such as surprise, happiness, anger, and sadness Applications of FaceMe facial recognition technology How can the FaceMe facial recognition technology be applied Imagine a scenario where police are tracking a criminal By focusing the search in a busy train station lobby using the FaceMe engine, every face can be detected and quickly matched with facial databases based on detected features, while also monitoring fluctuations in emotional indices to deduce potential suspects The FaceMe facial recognition engine provides various anti-spoofing mechanisms that can target the built-in camera lenses of mainstream mobile devices to prevent circumvention of access control systems using photos or videos of faces It's worth noting that the FaceMe AI facial recognition engine is compatible with mainstream platforms such as iOS, Linux, Windows, and Android It is suitable for a full range of devices from fully-equipped workstations to small, low-power devices Offering high precision and real-time advantages, the engine is suitable for scenarios like smart retail, smart finance, smart security, public safety, smart home, and more, making its potential applications in AIoT promising「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【解決方案】創博科技-智慧自助結帳系統 未來買東西好方便
【2019 Solutions】 NexCOBOT - Smart Self-Checkout System Makes Future Shopping Convenient

Imagine a future where all shops have no clerks, fully replaced by smart devices Simply placing items on the table and letting the intelligent self-checkout system handle the rest makes shopping convenient and easy This scenario is not far-fetched, as unmanned store projects have already emerged in Taiwan, such as the recent multi-million investment by FamilyMart to create their second tech-concept store Through human-machine collaboration and the latest technology, they aim to alleviate clerical work, and NexCOBOT hopes to bring this concept into unmanned stores to simplify the checkout process for consumers NexCOBOT introduces a smart self-checkout system, aiming to incorporate this technology into unmanned stores, simplifying the checkout experience for consumers Dedicated to smart retail solutions to enhance consumer technology experience NexCOBOT, a subsidiary of NEXCOM, specializes in the independent development of six-axis robots and smart retail solutions With the rise of the Internet of Things, the line between physical and virtual commerce has blurred NexCOBOT identifies three foundational elements of IoT commerce smart retail, smart logistics, and cloud-based real-time management systems Continually, NexCOBOT commits to smart retail solutions, addressing major pain points for business owners while considering enhanced technological experiences for consumers, hoping to pioneer unprecedented innovative applications When it's time to check out, simply place the items on the table, and a scanner will identify the products and display both the items and prices on the screen How does NexCOBOT's smart self-checkout system work When checking out, place the shopping cart's items on the table An overhead scanner performs image recognition, then the screen displays the types of products and the amounts Payment can then be made using cards, smartphones, or other payment devices It can even integrate with facial recognition systems, allowing customers to pay through face scanning, which saves the time previously spent scanning barcodes and queuing Additionally, the store can utilize backend analyses to track customer data and popular products Due to the need for precise image scanning, a detailed product database must be established beforehand The store can also analyze customer data and popular items through backend analytics Establishing a product database to gain control of product information Precise image scanning requires that all items have a previously established database Scanning could include detailed 3D images of merchandise like cookie boxes or drink cans The more detailed the database, the faster the checkout process and the more effective the backend analytics However, because of limited space on counters, scanning large volumes of merchandise could be problematic Initially, items easily recognizable like those in bakeries might be prioritized Additionally, NexCOBOT offers modular solutions such as smart shelves, smart self-order systems, smart self-checkouts, smart marketing dashboards, etc, all customizable as per the client's requirements Integration with existing systems such as Point of Sale POS, Enterprise Resource Planning ERP, Customer Relationship Management CRM, and Digital Signage is also feasible Besides using payment devices, it can even integrate with facial recognition systems, allowing customers to pay through facial scanning, eliminating the need for manual barcode scanning「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【導入案例】智慧農漁業數位分身:一個高效率、永續經營的農漁業升級解決方案。養殖漁業如何靠著稱為「數位分身」的AI 技術達成三倍產量
【2019 Application Example】 Smart agriculture and fisheries digital twin: A highly efficient and sustainable agriculture and fisheries upgrade solution. How did the AI technology called "digital twin" triple the output of aquaculture?

Relying on nine types of sensors to detect water quality, while monitoring the growth of the farmed species and fishermen's behavioral decisions, the artificial intelligence AI solution "Smart Agriculture and Fisheries Digital Twin" can significantly increase production by 300 The ldquoHappy Harvestrdquo - style high-tech integrated solution allows novices to get started quickly It significantly reduces the reliance of agriculture and fisheries on experience, and makes it more appealing for young people to return to their hometowns to work in agriculture and fisheries There was a time when Facebook games were just starting to become popular, and everyone could be called a farmer due to the popular game ldquoHappy Harvestrdquo Office workers took out their mobile phones one by one during their lunch breaks and started living the life of a happy farmer life on their mobile phones Some people were naughty, secretly went on Facebook during work hours to steal the harvest from their colleagues The game was so therapeutic that some people actually went into the fields to become farmers during the holidays If I said that "Happy Harvest" really exists, would you believe me THE "Digital Twin" -"Smart Greenhouse" and "Smart Farm" solutions developed by the Innovative DigiTech-Enabled Applications amp Service Institute IDEAS Institute for Information Technology III are "Happy Harvest" and "Happy Fish Dream Aquarium" in real life Here, nine sensors based on IoT will continuously monitor the "facility factors" of the cropaquaculture growth environment, such as water quality, and upload them to the cloud through the control box The AI robot in the cloud will continue to simulate a digital twin in the system, receiving "facility factors" such as water temperature and dissolved oxygen, and continuously collecting "growth factors" for the growth status of cropsfarmed species A simulated "digital twin" of the fisherman is created in the cloud system, and the AI robot will also calculate appropriate "behavioral decisions" based on the successful strategies of past fishermen When the oxygen content is low and the water temperature exceeds the standard, AI will suggest you to make behavioral decisions, such as turning on the water wheel, turning on the aerator, or using medication Fishermen use their own experience or knowledge to decide whether to follow the suggestion Afterwards, the system will compare the results of the decision, and fishermen can also judge based on the results whether the decision made by a real person is better than the behavioral decision made by the ldquodigital twinrdquoIn addition, the digital twin AI of smart agriculture operates in the background around the clock, silently recording and analyzing the corresponding "behavioral decisions" of fishermen in response to various "facility factors" and "growth factors" in smart farms Decision-making", slowly establishing the best solution model for the farming strategies Slowly, AI silently learns these "tacit knowledge" from fishermen like a little apprentice at their side, so that this knowledge will not be lost when the fishermen retireMoreover, this technology can not only be used to "farm fish," but also "farm vegetables" These optimized farming models can become a precious database Even novices who have just entered the industry can skip the process of exploration and directly become a master The greatest challenges currently faced are insufficient manpower, aging population, loss of experience, and high cost of new technologies Taiwan is famous for its agricultural technologies and farming technologies However, small farmers generally have a shortage of manpower and aging workers Digital transformation is imperative The cost of new technologies is too high for 80 of small farmers and fishermen Since there are too many uncertainties in environmental factors, such as climate change, and water quality changes, they are all highly dependent on experience Therefore, the most severe challenge comes from farmers and fishermen retiring before young farmers and fishermen can take over, and many years of experience are lost because they cannot be passed on Smart agriculture and fisheries digital twin allow continuous optimization without downtime "Digital twin" is an emerging technology that combines AI and HI craftsman wisdom, and was rated by Gartner as one of the top ten key technologies for the future for three consecutive years The Department of Industrial Technology, Ministry of Economic Affairs began to engage in RampD of digital twin in 2016 It believes that in addition to automation efficiency, industries also need to digitally preserve experience and skills to develop optimal human-machine collaboration technologies through AI and HI interactive learning In the field of aquaculture, the "digital twin" of AIoT Artificial Internet of Things for "fishery and electricity symbiosis fish farms" digitalizes the tacit knowledge of fishermen Using the analysis of "facility factors" constructed from different types of water quality data and ldquogrowth factorsrdquo such as fish and shrimp images and disease symptom images, as well as the "behavioral decisions" of fishermen, to train AI can produce optimized models for water quality management, aquatic product growth management, and aquatic disease managementThe "digital twin" of AIoT for "fishery and electricity symbiosis fish farms" digitalizes the tacit knowledge of fishermen These AI management models are combined to create a smart farming solution with high survival rate and high feed conversion rate The entire farming process has digital monitoring data and quality that can be analyzed Traceability can reach the initial stage of farming, greatly improving the quality, value, and output of aquatic products Despite promising prospects, there are still many challenges The III IDEAS first become involved in ldquodigital twinrdquo due to a forward-looking technology project supported by the Department of Industrial Technology, Ministry of Economic Affairs in 2018 At that time, the Department of Industrial Technology believed that in addition to automation efficiency, industries also need to digitally preserve experience and skills to develop optimal human-machine collaboration technologies through AI and HI interactive learning Taiwan Agricultural Research Institute, Council of Agriculture, Executive Yuan subsequently supported the application of "digital twin" in smart agriculture "The application of digital twin technology in agriculture helps small farmers digitally accumulate experience, and improves their agricultural skills through the interaction of group experience and AI, resolving the greatest challenge of intelligent agriculturerdquo Intelligent agriculture digital twin technology is expected to increase production efficiency by 30 after commercialization and is quite promising Team leader Qiu Jingming "The behavioral decisions made by powerful fishermen are three times better than those of ordinary fishermen in terms of results" nbsp Digital Twin Aqua-Solution After working with technology-based aquaculture companies and gaining support from an industry project of the Industrial Development Bureau, Ministry of Economic Affairs, III IDEAS applied digital twin technology in the field of "smart fish farms" The field application team responsible for aquaculture pointed out ldquoIn fish farms, fishermen often make different behavioral decisions when facing various environmental changes The behavioral decisions made by experienced fishermen are three times better than ordinary fishermen in terms of results For example, the survival rate of white shrimps is generally about 10, but some fishermen can achieve a yield of up to 30 This reduced production costs and tripled profitsDigital twin technology can pass on the tacit knowledge of these experts and ultimately upgrade the entire industry" The "digital twin" is composed of 9 sensors, fish images, and fishermen's behavioral decisions 9 sensors, constantly monitoring "facility factors" such as water quality IDEAS uses nine sensors to monitor water quality, nbspincluding dissolved oxygen, water temperature, pH, salinity, turbidity, ammonia nitrogen, nitrate, chlorophyll a, and ORP Oxidation-Reduction Potential, in order to obtain the environmental data of various farms These factors are also known as ldquofacility factorsrdquo In addition, fishermen will regularly take fish and shrimp out of the pond, or use submersible cameras to take pictures of farmed species underwater This is used to determine the current size of the farmed species and its growth condition, which is also called "growth factor" "Facility factors," "growth factors" plus "behavioral decisions" made by fishermen in different situations can create a "digital twin" in the cloud server Source of diagram Taiwan Salt Green Energy Co, Ltd commissioned Sanyi Design Consultants Co, Ltd to designnbsp With these two factors plus "behavioral decisions" made by fishermen in different situations, a "digital twin" can be created in the cloud server In this game-like "digital twin," we can simulate as much as we want to find the best "behavioral decision" under different "facility factors" and obtain the optimal "growth factorrdquo To put it in a way that is easier to understand, readers can try to imagine that we have a game called "Happy Fish Farm" The environmental parameters of the fish farm are all recorded from actual situations We also record the behavioral decisions made by each "Happy Fish Farm" player under different environmental parameters and the final results When the number of recorded data sets is sufficient, a digital twin of the fish farm can be obtained from machine learning, and then real-time data is simulated to obtain optimal combinations This simulated world is the "digital twin" of "Happy Fish Farm" How is the issue of sensors easily being damaged resolved However, there will always be challenges in the RampD process For example, underwater sensors such as water temperature and dissolved oxygen sensors are often damaged due to algae growth Underwater cameras that record the size of fish are often blurred and unrecognizable due to sediment or algae pollution on the bottom of the pond There are two solutions for overcoming the issue with sensor damage One is to regularly scoop water out from the pond and pass it through the sensor for detection The other is to make the sensor into a box and put it into the pond every day to detect the water quality As for the growth condition of fish and shrimp, fishermen only need to fish them out of the pond every day to take pictures and measure them Low cost and effective Team leader Chiu said "We are currently developing a 9-in-1 water quality detection box After successful integration, we can prepare for mass production and start commercial operation by selling the box plus a monthly connection fee" Team leader Chiu of IDEAS of the III said "The issue with sensor damage is the cost Even though it provides great benefits, it would be meaningless if fishermen are not willing to use it due to high cost We are currently developing a 9-in-1 water quality detection box After successful integration, we can prepare for mass production and start commercial operation by selling the box plus a monthly connection fee We are now very close to completing the integration, and welcome companies to discuss cooperationrdquo Difficulties in recording fishermenrsquos behavioral decisions Another challenge comes from fishermen Some fishermen will consciously record the water quality and environmental indicators they observe every day, and record their own operating strategies and results However, not every fisherman will do this This is why it is necessary to use GAN generative adversarial network technology, which is very important in AI GAN will generate possible strategies of fishermen based on past data, ie, it "guesses" the fishermen's decisions to supplement the behavioral decisions that the fishermen do not input If it is completed by fishermen afterwards, it will not affect the training data set After the award-winning technology is put into mass production, 300 production efficiency will no longer be out of reach Current applications of "digital twin" technology worldwide are mostly in aerospace and manufacturing Taiwan and the Netherlands are the first to engage in the RampD of digital twin in intelligent agriculture Therefore,the "Intelligent Agriculture Digital Twin" winning the US RampD 100 Awards is proof of Taiwanrsquos technological leadership We are currently completing the integrated water quality monitoring box and total solution, and the product is expected to increase production efficiency by 300 In the future, "digital twin" technology will not only be used in agriculture and fisheries, but can also be extended to industries that originally relied on "tacit knowledge", such as tea making, fisheries, etc Due to the digitization of the entire process, quality no longer relies on experience and the weather This can upgrade farmers' technology for "AI monitoring" and "precision production" In addition to improving the productivity of traditional agriculture and fisheries, it also has a good chance of achieving sustainable operations, upgrading the entire industry, and making it more appealing for young people to return to their hometowns to work in agriculture and fisheries Reference materials A key piece of the puzzle of smart manufacturing Innovative sensing technology that accelerates the realization of "digital twin" - Digital era

rows
Rows:330, 22 pages