Special Cases

14
2021.10
【2021 Application Example】 Advancing to Smart Logistics 5.0: Hsinchu Logistics Delivers Medical Materials with Ultra-High Efficiency

After incorporating AI technology, traditional logistics companies have seen significant improvements in transportation efficiency and reductions in transportation costs, especially in the transfer of medical materials which involves timely service and rights of hospitals and patients The implementation of intelligent logistics can save medical material businesses the cost of constructing GDP warehouses and other expenses up to millions A major domestic logistics leader, Hsinchu Transport HCT, owns a fleet of 3,500 vehicles and a storage area of 60,000 square meters, providing customized logistics solutions including logistics, commerce, finance, information, distribution, storage, and processing The company handles up to 580,000 parcels per day, with a maximum capacity reaching 900,000 parcels, making the enhancement of transshipment efficiency crucial for HCT Medical materials transportation at hospitals need optimization of current operational processes and enhancements in systematization and intelligence Especially the transportation of hospital medical materials, which encounters various challenges Medical materials suppliers need to cater to varying customer product demands, temperature requirements, and delivery times through multiple logistics providers This highly depends on the experience and careful control of operations staff Whether it is the product shipment or actual logistics process, each step must be interconnected Any human errors can impact the service timing and rights of the hospitals and patients Thus, all concerned businesses, along with the government and hospitals, are working to optimize current operational processes and elevate the level of systematization, automation, and intelligence to minimize service errors and cost losses HCT's distribution process prior to AI implementation Currently, with the government's push for standardized platform operations on the demand side of hospitals, supply-side businesses collaborate through data coordination to improve the accuracy and efficiency of product shipments, enhancing operational quality and management benefits at the demand side At the same time, some businesses are also investing in the standardization and systematization of internal operational processes, thus enhancing operational efficiency and quality In the freight logistics sector, logistics companies' warehouse staff need to expend labor to control different logistics shipment operations If they often receive emergency task notifications for shipments to medical facilities, they usually depend on small regional logistics providers to provide customized delivery services Although this improves delivery times, it does not allow for integrated informational services The new GDP regulations for medical materials require suppliers to undergo GDP compliance certification Therefore, Hsinchu Transport, assisted by the Ministry of Economic Affairs' AI coaching program, not only extends existing logistics services compliant with GDP regulations but will also use data integration and optimized AI technologies to help medical material businesses streamline and improve their logistics operations Complex logistics issues are solved using the Simulated Annealing SA algorithm To meet the 'Good Distribution Practices for Medical Devices,' Hsinchu Transport is not only actively introducing new logistics vehicles but will also implement artificial intelligence-based mathematical optimization technologies to assist in intelligent scheduling at nationwide business points and transshipment stations They aim to optimize the routing of medical materials between business points or regions thereby enhancing efficiency in the distribution process Currently, during the transshipment process of medical materials at Hsinchu Transport, detachable tractor heads and containers are used Each business point and transshipment station differ in location design and staffing, impacting the throughput per unit of time Furthermore, daily cargo conditions size, destination vary, and due to these fluctuating and distinct demands, the deployment of tractor heads and containers changes accordingly Under these circumstances, Hsinchu Transport relies on past experiences to schedule departures at each satellite depot and adjusts daily according to the cargo needs Due to the reliance on empirical scheduling, it is often difficult to consider all variables and considerations, leaving room for improvement in the current departure schedules The cargo delivery planning inherently constitutes an NP-Hard problem, difficult to solve with traditional analytical methods Hsinchu Transport, in collaboration with Singular Infinity, utilizes the Simulated Annealing SA algorithm to find solutions The new logistic service introduced by Hsinchu Transport is 'GDP Container Shift Planning' This planning involves estimating future volumes of medical materials between stations and scheduling container truck shifts accordingly, ensuring timely and quality delivery of medical materials while maximizing operational benefits and reducing travel distances Hsinchu Transport introduces AI-optimized shift planning, constructing the most efficient route from its origin to destination Hsinchu Transport introduces 'Optimized Shift Planning' service, reducing transportation costs by 5 The introduction method involves using cloud software services Hsinchu Transport regularly inputs 'Interchange Item Tables' from station to station into the 'Optimized Shift Planning' service After setting the algorithm parameters, a GDP container shift schedule is generated At the same time, developing a Hsinchu Transport medical material scheduling system allows Hsinchu Transport's medical transport units to compile suitable schedules through the Interchange Item Tables Under the same level of service, it's estimated that this can reduce transportation costs by 5, saving medical material businesses millions in construction costs for GDP warehouses and distribution Due to its requirements for sanitation, temperature, and its fragility, the transportation and transshipment of medical materials should be minimized to reduce exposure and risk However, logistics efficiency and costs must still be considered AI designs the most efficient route for each cargo from its origin to destination, effectively completing daily transportation tasks In response to the future high development demand of industrial logistics, distribution and transshipment AI optimization will be a key issue Through this project, a dedicated project promotion organization will be established, staffed with AI technology, IT, and process domain talents After accumulating implementation experience, the application of AI will gradually expand, comprehensively optimizing and transforming Hsinchu Transport's operational system, and partnering with AIOT and various AI domain partners to accelerate and expand the achievement of benefits「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

2021-10-14
【2022 Application Example】 Even the United Nations is on board! Yoyo Data Application captures global business opportunities with agricultural data

Nearly 2,000 days in the fields have made Yoyo Data Application a top player in Taiwan’s agricultural data sector Their comprehensive grasp of crop yields, production periods, and prices has enabled them to collaborate with the United Nations The service area for agricultural land skyrocketed from 24 hectares to over 6,000 hectares in less than three years—a 250-fold increase For Wu Junxiao, founder and CEO of Yoyo Data Application, aligning with global environmental trends and becoming a data company at the intersection of climate technology and the green economy to serve the global market is his ultimate entrepreneurial goal Wu Junxiao, originally an engineer, joined the Industrial Technology Research Institute in 2010, where he honed his profound technical and data science analytic skills 'At that time, I was working in data analysis engineering, and almost all data-related materials would be directed to me Additionally, I worked on indoor cultivation boxes, planting vegetables and mushrooms, hence planting the seed of entrepreneurship by integrating agriculture with data analysis,' Wu recalls Since 2016, Wu Junxiao has been frequently visiting farms to 'embed' himself among farmers and agricultural researchers, chatting and sharing information systematically, which quickly established his agricultural know-how Solid data analysis capabilities have even convinced the United Nations In 2017, he left the Institute to start his own business and founded Yoyo Data Application in 2019 Today, many agricultural businesses are his clients, with service areas rapidly climbing from 24 hectares to over 6,000 hectares, expected to surpass 7,000 hectares in 2022 His clientele includes markets in Japan, Central America, and even entities under the United Nations like the World Farmers Organization, which utilizes the 'Yoyo Crop Algorithm System' supported by Yoyo Data How exactly does Yoyo Data Application manage to impress even UN agencies The 'Yoyo Crop Algorithm System' developed by Yoyo Data Application accurately predicts the production period, yield, and prices Firstly, due to Wu Junxiao's precise mastery over agricultural data, Yoyo Data Application's clients don't necessarily need sensors or other hardware devices 'Sensors are expensive and if you buy cheap devices, you just collect a lot of noise or flawed data, which is useless,' Wu explains He continues, 'Collecting data doesn't necessarily require sensors our data solutions can solve problems more directly and effectively' For instance, one of Yoyo Data Application's products, the Yoyo Money Report Agri-price Linebot, developed in collaboration with LINE in 2020, gathers data on origin, wholesale, and terminal prices spanning over 10 years, driven by Yoyo Data’s proprietary AI algorithms This enables the system to autonomously learn about agricultural product trading prices, using big data and AI to perform price prediction analysis, thereby helping buyers reduce transaction risks and expanding the data application to the entire agricultural supply chain Regarding banana prices, the accuracy of price predictions increased from the original 70 to 998 Wu Junxiao notes that both buyers and farmers are very sensitive to prices Now, through the Yoyo Money Report service, both buyers and farmers can precisely understand the fluctuations in agricultural product prices Yoyo Data can also provide customers with optimal decision-making advice based on predictive models for crop growth, yield, and price estimations Currently, price predictions cover 28 types of crops Precise estimates of production periods and price fluctuations allow Yoyo Data to provide differentiated services based on data analysis The 'Yoyo Crop Algorithm System' provided by Yoyo Data Application incorporates a 'Parameter Bank', usually collecting 200-300 parameters, not just straightforward data like temperature and humidity, but also data divided according to the physiological characteristics of the crops Through effective dynamic data algorithms, it can accurately calculate when crops will flower and when they can be harvested, what the yield will be, and so forth For instance, the prediction accuracy of the broccoli production period is 0-4 days, with the flowering period predicted this year to be precisely 0 days, perfectly matching the actual flowering time in the field In these dynamic calculations, a 7-day range is considered reasonable, and the average error value of Yoyo Data's predictions typically ranges from 2-4 days, with most crop production period accuracies above 80 Through effective dynamic data algorithms, over 120 global crops can have their production periods and yields accurately estimated Using these effective dynamic data algorithms can set estimates for production quantities, helping adjust at the production end Yoyo Data Application's clientele primarily includes exporters of fruit crops like pineapples, bananas, guavas, mangos, pomelos, sugar apples, Taiwan's agricultural production is highly homogenized, often leading to a rush to plant the same crops and resulting in price crashes Yoyo Data Application helps clients differentiate their offerings Thus, Wu Junxiao positions his company as a boutique digital consultant, carefully selecting clients for quality over quantity He notes that Taiwanese agricultural clients focus on how to improve yield rates, even categorizing yield rates by quality, aiming for high-quality, specialized export markets whereas international clients prioritize maximizing per-unit yields, showing different operational approaches in domestic and international markets In addition to agricultural fruit, Yoyo Data Application has also extended its services to the fisheries sector, including species like milkfish, sea bass, and white shrimp, all using the same system to establish various parameters related to the growth of fish and shrimp, such as when to feed and when to harvest, and the anticipated yield, timing, and prices Yoyo Data Application harnesses the power of data to create miracles in smart agriculture In response to the company's rapid development, Yoyo Data Application introduced venture capital funds in 2021 to expand its staff and promote its business Wu Junxiao states that in response to the global trend towards net zero carbon emissions by 2050, he plans to help clients plant carbon in the soil, effectively retaining carbon in the land while also connecting clients to carbon trading platforms, creating environmental business opportunities together Wu Junxiao says that from the start of his entrepreneurial journey, he positioned the company as a global entity, thus continuous international collaborations are planned As a data company serving a global clientele and focused on climate technology and the green economy, this represents Wu’s expectations for himself and his company's long-term goals Yoyo Data Application founder and CEO Wu Junxiao「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

2022-03-14
【2020 Application Example】 "AI Color Recognition and Cost Optimization Control System" automatically recognizes colors, breaks through the traditional color grading model, significantly reduces costs, and improves yield!

Mixing new colors relies on the experience of master craftsmen The so-called "computer color matching" in the paint industry is simply the selection of "existing colors" for mixing, but there is actually no way to mix paint for a ldquonew colorrdquo and it all relies on the experience of master craftsmen Hence, it is necessary to start from scratch when a new color is encountered, which consumes a lot of manpower and time Moreover, due to the different color mixing habits of each master craftsman, the cost can be significantly different despite producing the same result The trilogy when paint factories face the crises of transformation I Lack of color mixing standards Generally, when traditional paint factories produce new colors, they will use a "spectrophotometer" to measure the LAB value of the sample color, and then the paint mixer will mix the paint of that color based on past experience After color mixing is completed, the instrument will be used to test the LAB value and C and H wavelength This process does not have a complete system and database records, and there are not standards for color mixing II Production costs are difficult to control Paint factories produce many pigments with different materials and functions, and the cost of paint will vary depending on the "color masterbatch material" used Even if the color number of the masterpiece is the same, the cost will be different if the ratio of the color masterbatch is different Paint mixers do not have a set of color mixing standards when mixing paint, making it difficult to control production costs III The color grading process is lengthy and personnel training is difficult As instruments cannot replace manual color mixing, the training of a paint mixer requires years of experience in paint mixing, familiarity with chromatology, as well as basic understanding of hue, saturation, and brightness If there is no basic reference color values when mixing paint, the paint mixer must spend a lot of time repeatedly mixing colors, resulting in a loss from time cost Developing an "AI Color Recognition and Cost Optimization Control System" The paint factory engaged in industry-academia collaboration with the Department of Computer Science amp Information Engineering of Chaoyang University of Technology through CDIT Information Co Ltd, and utilized the university's AI research capabilities to jointly develop the "AI Color Identification and Cost Optimization Control System" It established a database of "paint color numbers" and "color masterbatch material cost," and analyzes the optimal color mixing and optimal cost formula through data mining methods The paint mixer can refer to the formula analyzed by the system for color mixing, and then input the formula into the system after paint mixing is completed The formula is fed back to the basic database and an "artificial neural network model" is used by the system for deep learning, establishing a color grading standardization system for cost control and data collection, so as to solve the current difficulties faced by paint factories In the early stages of system development, CDIT planned the system requirements of the paint factory, established the system architecture and system database, and then worked with Chaoyang University of Technology on the implementation of model functions for the application of data mining and artificial neural network After the system is completed, CDIT will assist the paint factory in system testing and correction The system will be introduced after correction and testing are completed, and training on system use will be provided to ensure the correct use of the system System Screen Differences before and after using the system Expand new markets for the paint industry to see the paint industry thrive The "AI Color Recognition and Cost Optimization Control System" collects the color mixing formulas of paint mixers, establishes a paint color masterbatch formula database, and records the cost of each color number The system's deep learning function is then used with a spectrophotometer to analyze the optimal color mixing formula for each data entry, so that the paint factory can control the cost of paint mixing The optimal color mixing formula recommended by the system increases the speed of paint mixing and increases output value Future benefits include The improvement in product yield reduces customer complaints and improves customer satisfaction The breakthrough in the traditional color mixing model improves corporate image Improves the efficiency of paint mixing, and allows the remaining time to be invested in training to enhance the professional capabilities of personnel It will also allow the joint expansion of new markets with the paint industry and learning of new application technologies, and promote them to other paint companies, enhancing the industry's overall competitiveness to see the paint industry thrive

2020-08-11
【2020 Application Example】 Peeking into a Baozi to See How AI Reduces Scrap Rates by 50% and Boosts Production Efficiency by 60% for Frozen Foods

From production line to dining table, who oversees the hygiene management of what we eat In recent years, there has been a continuous stream of news reports concerning food safety, such as repackaging expired goods, and poisoning incidents at Hong Rui Zhen It's clear that people are increasingly concerned about the hygiene of their food However, due to various quality control methods in food processing, there are inherent risks The World Health Organization WHO has pointed out that unsafe food and water cause physical harm to 2 million people each year Hence, international markets demand that food processing companies must establish a traceability system for products This is why major domestic food processors also aim to set up a production traceability system to quickly trace back to problematic raw materials and initiate recall and destruction of problematic food Visible assurance, implementing production transparency A major domestic food manufacturer producing frozen food and instant meals has expanded its market presence to North America, New Zealand, Japan, etc They are also at the forefront in promoting food management domestically, having obtained certifications such as HACCP, ISO22000, ISO14001 Since food production is labor-intensive, it is prone to quality impacts caused by worker fatigue Additionally, the production lines often have unclear records of production quantities, processes, and timing This obscurity in traceability makes it difficult to track production information when defects occur, leading to food safety management gaps that result in the scrapping of entire batches To address this, the Production Development Center at National Sun Yat-sen University utilized its advisory resources to help the food manufacturer tackle food safety management challenges, planning the use of AI technology to collect production data and establish anti-fraud and traceability for food production Intelligent manufacturing boosts food safety Although the level of automation is not high in the processing of bakery products, the food plant in this case is keen to enhance the automation of its production lines and introduce smart manufacturing For businesses, a traceability system not only helps establish brand image and increase product and brand value, but also gives consumers peace of mind due to the transparency of production lines Therefore, the Production Development Center at National Sun Yat-sen University matched AI technology service providers, Hong Ge Technology, in the first phase to plan the introduction of data collection devices to link food work orders information, reducing human operational omissions and capturing real-time production information through dashboards to ensure the consistency of production stage information potentially affected by human factors Schematic for intelligent production line planning The second phase involves using deep learning during the dough fermentation stage to calculate size and volume, analyze the relationship between temperature, humidity, fermentation time, and product volume, and assess whether to introduce AOI foreign object detection after freezing as a second quality control step Schematic of AI-integrated quality control for finished products Food processing ID card, launching the AI-era of food safety tracing In Taiwan, the understanding and acceptance of production history by consumers is gradually improving From the supply of raw materials, processing, production, to distribution and sales, it is necessary to have complete control and provide transparent information Publicly disclosing the production history not only increases trust between enterprises and consumers, but also aligns Taiwan's food safety environment with international standards In 2020, the Production Development Center at National Sun Yat-sen University will assist enterprises with the adoption of advanced AI technology, documenting the entire data process from industry to dining table and supervising food production processes to successfully implement product tracing, prevention of adulteration, and the establishment of high standards for products, thus advancing food processing products to international standards「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

2020-03-12

Records of Application Example

【導入案例】AI建構最佳塗裝模型,降低電磁鋼片廢材檢驗成本,每年可省200萬
【2020 Application Example】 AI constructs the best coating model to reduce the inspection cost of scrap electrical steel sheets, saving NT$2 million per year

Surface treatment applications face rising costs and talent gaps The development of metal surface treatment technology affects the quality of aerospace, automobile, machinery, home appliance, communications, and fastener products sold domestically and exported At the same time, it plays a pivotal role in domestic smart machinery, national defense, and circular economy in the " 52 Industrial Innovation Plan" According to 2018 survey statistics, the output value of the metal surface treatment industry reached NT1515 billion, an increase of 36 compared to 2017 However, metal surface treatment is a labor-intensive, energy-consuming, and pollution-intensive industry It has long suffered from a shortage of professional and technical talent, and the tightening of environmental regulations has caused processing costs to continue to rise As a result, the industry is facing a crisis of survival and a crisis of competition from international high-value supply chains Manual quality control faces market challenges, while the coating process has found new opportunities Overseas markets currently account for 70 of the revenue of a domestic steel plate coating plant It expanded into the automotive steel, diverse supply chain, and various special steel product markets in 2016 It is imperative to improve the quality of surface treatment through innovative technologies, in order to seize international markets In the continuous steel plate coating process, the price difference between finished steel plate products and defective products is about 10 times Manual inspection is used in the current stage During the production process, 10 m needs to be cut from each steel coil and becomes fixed inspection waste, incurring a significant amount of cost for waste materials, and also delaying production At the same time, the instability in manual inspection quality also makes production quality unstable The Southern Taiwan Industry Promotion Center STIPC utilized the guidance capabilities it accumulated over a decade in Southern Taiwan, and matched the steel plate coating plantrsquos pain point with an AI optical measurement technology service provider This reduced the cost of consumables used in steel plate inspection, and reduce errors caused by fatigue during manual inspection Stabilizing steel plate coating quality with optical measurement technology In order to control the quality of the coating process, image recognition must be used to identify product yield General measurement technology requires contact to detect the thickness of coating Therefore, the STIPC match the plant with an AI optical measurement technology service provider to assist in the development of a non-contact optical measuring instrument, record coating data, and then compare the data to obtain the best process parameters Illustration of 3D non-contact measuring instrument testing Presentation of measuring instrument data Rapid scanning through AOI achieves non-contact measurement It can quickly scan the profile and overall dimensions of the object being measured without directly making contact with the product or damaging the surface of the steel plate It can immediately control coating thickness and quality of steel plates without increasing cost We hope to calculate data of the process environment and design the product abnormality warning range, so that it can be used to make the process smarter In the future, this solution will further detect surface defects and color differences of finished steel plates to reduce the proportion of discarded material, solve the problem of the gap in professional and technical talent, and improve product yields Schematic diagram of non-contact measuring instrument Establish an AI coating model to create world-class steel plate supply standards With the guidance of the STIPC in 2020, the steel plate coating plant accelerated the application of advanced process technology and established quantified indicators of surface treatment process quality standards, which will help domestic surface treatment companies produce high-quality electrical steel sheets, and is expected to increase the product price by 2 In addition, it can also assist companies in the industry obtain heat treatment certifications for high-value aerospace, electric vehicle, fastener, and aerospace products, increasing the industryrsquos added value through innovative thinking, and continuing to lead the metal industry forward

【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」

【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

【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:67, 8 pages