Vehicle Classification enables transportation authorities to automatically identify and classify vehicles according to their visual attributes. This technology finds widespread application in traffic management systems, toll collection, parking facilities, and security setups. FETCi leverages AI algorithms and machine learning methodologies to analyze video data collected through LiDAR technology. With an extensive database and repository, FETCi's AI AVC proficiently sorts vehicles into distinct categories, including cars, trucks, motorcycles, buses, and more. By integrating LiDAR technology with AI-powered image recognition, FETCi establishes a vehicle recognition system equipped with self-enhancement and deep learning capabilities.

As solar generation applications continue to evolve, ensuring stable equipment operation and maximizing generation efficiency have been a main concern for owners. The platform integrates AI-driven O&M technology with precise data analysis to provide comprehensive equipment monitoring, real-time anomaly detection, and intelligent maintenance recommendations. This reduces operational costs and significantly enhances overall power generation efficiency.

The Ministry of Economic Affairs, Department of Industrial Technology has commissioned the Industrial Technology Research Institute's Center for Smart Sensing and System Technology to develop a "Composite Long-Term Air Quality Sensor." This sensor is capable of simultaneously measuring particulate matter (PM2.5), ozone (O3), carbon monoxide (CO), volatile organic compounds (VOC), and other air quality monitoring parameters. The sensor utilizes optical detection methods to detect concentrations of suspended particulate matter (PM2.5) and ozone (O3) in the air. Innovative key technologies, including dual-channel micro-particle sieving, micro-particle signal feature recognition, LED dynamic light source stability, and multi-environmental factor compensation, are employed to enhance the sensor's lifespan and accuracy. Furthermore, semiconductor and micro-electromechanical (MEMS) technologies are utilized to create a micro-heating chip. This chip, combined with gas nano-sensing materials and a single-chip sensing control circuit, converts the detected gas sensing resistance changes into carbon monoxide concentration values for the detection of carbon monoxide (CO), total volatile organic compounds (TVOC), and other harmful and odorous gas concentrations.

The "Dosage Evaluation Method" applies AI technology to assess dosages for high-risk medications, using Vancomycin as an example. This method addresses limitations in clinical practice, where dosages are typically determined by physician experience or population pharmacokinetic parameters, which may not account for individual patient variability. Although several AI-based prediction models for dosage evaluation currently exist, most of these models directly suggest dosages, often without fully considering physician expertise. The innovation of this method lies in its approach to validating only the physician-selected dosage, providing reference feedback without influencing the physician’s final decision. This design not only respects the physician’s professional judgment but also enhances the safety of medication administration.

Nearly 90 towns and cities across Taiwan have witnessed the convenience of garbage collection services, which help build smart cities. Through a mobile app, citizens can check the location of garbage trucks and pickup points, ensuring that they never miss the garbage truck again.

CMS-WS Powerful digital signage server to give you maximum flexibility on the choice of media players! One for All, All with One With one CMS-WS, you can transform all your personal computers, notebooks, tablets, mobiles, etc., into digital signage players to strategically deploy customer touchpoints for different applications. Moreover, CMS-WS allows you to remotely manage up to 1000 devices through a simple and easy-to-use web interface. Small Budget, Big Result Compared to other cloud-based CMS software, you can spend less but benefit more from CMS-WS software. With CMS-WS powerful features, you can create a more personalized, more informative, and more memorable experience anytime, anywhere to maximize engagement with target audiences. CMS-WS is the most cost-effective solution for retail or small and medium-sized businesses to get big results from a small budget!

Billion Electric Group , in collaboration with Taiwanese partners, has successfully deployed 495 kWp of solar PV and 1,997 kWh of battery energy storage systems (BESS) in Palau, Tuvalu, and the Marshall Islands. These modular microgrids reduce reliance on imported fossil fuels, ensuring stable green energy supply for agriculture, aquaculture, and local communities. The project is expected to cut carbon emissions by 800 metric tons annually, with over 50% renewable energy self-sufficiency at aquaculture centers and demonstration farms. Meanwhile, livestock farms, offices, and dormitories now operate on 100% green energy, significantly lowering both energy costs and environmental impact. Billion Electric Group provides end-to-end energy solutions, from R&D and manufacturing to system integration and deployment. The project features MIT ( Made In Taiwan) renewable energy technologies, including Billion’s Fusio series BESS, Giga series PV inverters, and an AI-driven EMS (Energy Management System). The system enables real-time power optimization, bidirectional energy transmission, and cloud-based monitoring platform, significantly enhancing grid stability and energy efficiency.

In 2020, commercial 5G network has come into our lives. Taiwan’s fixed network, Taiwan Mobile Co., Ltd and Taiwan Win TV Media CO., Ltd. launched a 5G smart sports application at the Xinzhuang Baseball Stadium. We use the 5G network to provide the characteristics of Enhanced Mobile Broadband, Massive Machine Type Communications, and Ultra-reliable and Low Latency Communications, and together with local partners in Taiwan to generate a 5G smart application solution ecosystem. This project focuses on the interactive management of fans, and uses many innovative technologies for demonstration, including the key video uses MEC and 5G, integrates 3D modeling animation and collects live light and shadow, provides dynamic and static image playback, high-quality real-time 4K panoramic photography, providing live stream of sports events, AR virtual opening display, giving fans a different visual experience, highly immersive virtual baseball games bring real-life experience, 3D Holographic projection technology is used to interact with virtual player images for pitching and playing games. Finally, it is also matched with the stadium's 3D depth technology and dynamic people counting analytics technology to provide security control requirements for the stadium. The player’s training platform uses sports technology to detect player swing speed, elevation angle, or distance is provided to the coach for immediate adjustment and improvement.

In response to the implementation of Taiwan's carbon fee and the ESG-driven carbon reduction requirements of enterprises, we offer customized carbon management services. ESL establishes "Carbon Accounts" based on client-specific requirements, utilizing automated systems to collect and analyze carbon emission data via an integrated platform. This service provides optimization opportunities, balances the economic advantages of carbon management, and maximizes the value of corporate sustainability and green transformation initiatives.

TextileGPT is an AI platform specifically designed for the textile industry, combining TNet's historical expertise and professional knowledge to accelerate product launches, reduce development costs, and strengthen knowledge transfer. Built on the TNet knowledge base, it provides intelligent dialogue capabilities enriched with industry-specific knowledge to address various challenges. The platform supports processing multiple data formats, including PDF, PPT, DOC, XLS, and web content, and features a user-friendly interface for quick adoption. TextileGPT aims to tackle issues like talent gaps and difficulties in knowledge inheritance, driving innovation and efficiency to enhance competitiveness, making it a key enabler for the textile industry's future development.

1) Automatic Notification System 1. Consolidate the IOT info from various sensors, as well as history of user behaviors 2. Big Data Analytics & AI-enabled recommendation engine: Send delivery notice or abnormal alert 3. Push mobile APP message to User and Operator 2) Electronic Ordering System (Customized) 1. Planed delivery schedule service, user confirmed the delivery time, system automatically plans routing and deliveryman 2. Delivery schedule: Push individual mobile APP message to each deliveryman 3) Cylinder Management System (Customized) 1. Cylinder barcode APP scanning, Deliveryman scan the barcode and upload to cloud system 2. Automatic notification mechanism for expired cylinder 3. Data Analytics & Statistical Report 4) Safety Reporting System 1. LPG safety sensors: Including gas detector, Solenoid Valve, pressure switch and UVIR Flame Detector 2. IOT-BOX showoff Solenoid Valve and reporting 3. Push mobile APP message to User and Operator for emergency response 5) Cloud ERP System (Customized) 1. Modular management system: Accounting, Administrative, Financial, Procurement, Human Resource, inventory, Customer Service and sales management 2. Data collection, Analytics & Statistical Report

Our AI server features several advanced patented functionalities: • Ensure the Privacy of Local Data: Patented trusted computing protection mechanisms ensure data security and privacy. • Protect Local AI Models from Theft: Prevents locally deployed AI models from being stolen, safeguarding corporate intellectual property. • Specialized LLM Compression Technology: Efficiently processes large AI models, enhancing performance and reducing resource requirements. Enables the use of NVIDIA A-series GPUs in place of H-series GPUs, significantly reducing hardware costs. • Reduce Enterprise Deployment Costs and Energy Consumption: For example, when training a 13B model, GPU requirements can be reduced from 7 H100 GPUs to 2 A6000 GPUs, significantly lowering costs and energy consumption. Our solution not only ensures the security and privacy of corporate data and AI models but also reduces the costs and energy consumption associated with AI deployment, making it an ideal choice for enterprise users.