Development of Cyber-physical system for Smart Farm： Digital management: Digital Data Collection System, AI Genetic Analysis Module, Big Data Module, and Virtual AI breeding Expert, Information Security Module. Genotyping and selection platform: Developing highly accurate genotyping and selection systems for screening dominant individuals. Optimization of breeding prediction system: Enhance breeding prediction systems through data analysis and prediction model to improve breeding efficiency and yield. Enhancing competitiveness: Enhance the competitiveness of Taiwan’s agriculture by improving breeding technologies and management practices of dominant individuals.

MIRDC’s continuously Rotating Wind Turbine UAV Inspection System can effectively inspect the working wind turbine without interference. It takes 5 minutes to complete the inspection of a single blade to effectively detect 4mm small cracks. The system will not lose power generation by turning off the wind turbine, further observes the actual movement status of running blade structure and pillars to grasp the defects beforehand.

The Track Safety Management System is primarily aimed at addressing safety concerns along the track. It provides real-time monitoring, statistics, and detection-triggered alerts for trackside environments including stations, level crossings, along the track, and slope areas. The goal of this management system is to establish early warning alerts and prevent accidents from causing damage. Through the intelligent AIOT recognition monitoring system, it detects and analyzes station pedestrian traffic, tracks pedestrians at level crossings, identifies passing vehicles and traffic flow, detects foreign objects at level crossings and activates alarms, monitors personnel lingering and debris along the track, conducts rockfall monitoring on slopes with a rain gauge, monitors the environmental conditions in equipment boxes, and oversees the operation status of level crossing equipment. The monitoring data and image information are transmitted to the management system platform for integrated management via fiber-optic networks, NBIOT, or mobile communication. Additionally, it provides central management personnel with real-time interpretation and remote control in case of anomalies.

Traffic approach warning system is the combination of smart detectors and LED warning signs. The intersection is divided into detection lanes and warning lanes. Smart detectors are installed on the detection lanes. When a vehicle enters the detection area, the signal is transmitted to activate the LED signs on the warning lane to warn drivers to slow down in advance.

Prof. Chia-Hsin Chen’s Team – An Innovative AI-Powered Tongue Vibration Training System This project develops an AI-driven tongue vibration training system for dysphagia and obstructive sleep apnea. It combines a safe, adjustable tongue device, AI motion tracking with real-time biofeedback, EEG-based cognitive monitoring, and AR-based gamified training to deliver personalized, engaging, and data-driven rehabilitation.

LIGHTSPEED is specialized in communication for 31 years up to 2025. All engineers has more than 20 years' experience in Modem, Router, 5G gateway, & LoRaWAN ChirpStack Gateway design. Product lines cover 5G,4G, 3G, WiFi 6,WiFi 7 router, Serial/IP gatway,, 4G/3G IP CAM, modem, 4G miniPCIe card, 802.11ah HaLow 4G gateway, LoRaWAN ChirpStack Gateway, WIFI 802.11n/g/b/ac/ax/be miniPCIe with USB interface, outdoor 5G +wifi router, tracker, 4G security guard/police video surveillance recorder and server, as well as cloud service. We also provide ODM/OEM service for special requirements, such as multi-SIM card failover system, multiple channel aggregation, cell tower tester..etc

In recent years, the number of motor vehicle noise cases has increased, and it has been a concern for people in Taiwan. In order to protect the living environment and eliminate improper vehicle modifications, the Ministry of Environment has used acoustic camera technology for law enforcement since 2021. The system contains several scientific instruments, including a license plate recognition function that helps authorities identify noisy vehicles. Technology also improves inspection efficiency and quality of noisy vehicles. Existing roadside inspections require onsite noise measurement. The stationary noise test takes at least 20 minutes for each vehicle. Law enforcement using acoustic camera technology can simultaneously record videos, take photos, identify vehicles and complete noise measurements, to increase efficiency by a factor of 200. It is no longer necessary to use a large amount of manpower to carry out checks and inspections, greatly reducing labor costs. The Acoustic Camera equipment equipment used in this exhibition is provided by OE Scientech Co., Ltd. They not only supply fixed or mobile sound-based photography equipment to Taipei City, Taichung City, Chiayi City, and Changhua County but also have extensive experience in assisting with technology enforcement operations.

Criminal and street violence cases will affect and cause panic to citizens. In order to diminish street violence cases, reducing the time to solve these cases, protecting citizens’ lives and properties, and allow citizens to live without fear, the Kaohsiung City Police Department (KCPD) built the “3D Street Violence Early Warning, AI Intelligence Collection and Integration Platform” (hereinafter called “the Platform”). The platform utilizes the Internet of Things (IoT) to combine AI image recognition and sound sensing technologies for cross-domain big data analyses. KCPD established cross-platform data interfacing and integration, mainly through “data integration” and “network analyses” to collect with the municipal government’s transportation bureaus and social bureaus; and import existing data from the KCPD data platforms. The Platform will, through web service API, (a) retrieve data built by information systems, (b) conduct big data analysis, aggregate applicable intelligence data and present it in the form of dynamic information, (c) Integrate all information and display it as maps and topologies, improve case handling efficiency. According to KCPD employees’ query, they can adjust factor weights and relationships. Analyze the results based on rational mathematical models and professional case-handling concepts, so that intelligence analysis goes beyond the limitations of platform developers and allows criminal police to maximize their capabilities.

-)Mainframe monitoring system, maximally supporting one million spots in real time. -)Smart loading balanbe for AOS -)Remote backup for AOS -)Adjudge amount of AOS as required, based on flexible structure. -)Central security management.

airaTrack is a comprehensive personnel tracking system that utilizes AI algorithms developed by our team to extract features from both the "face and figure." It generates unique biometric IDs with a recognition accuracy of up to 99%, all without the need for registering facial data, addressing privacy concerns. Capable of cross-camera searches and matching 10,000 faces per second, it significantly enhances the efficiency of traditional manual matching processes and increases search efficiency and accuracy by 97% enabling automatic path tracking of personnel in the field. The system also generates investigation reports for evidential preservation.

Delta's smart city solutions are based on three main axes: smart park management, smart light poles, and community security monitoring: smart park management uses a cross-system city information integration platform that handles a wide range of data transmission, aggregation, visualisation, and analysis to help achieve the goals of smart city governance. Intelligent light poles provide low-carbon lighting services in the parks, and at the same time serve as information collection and transmission nodes for the intelligent Internet of Things, while security surveillance protects people and assets in the parks and the city from infringement. Delta's smart city solutions help customers achieve a better smart city with both technology and humanity.

Prof. Ming-Yen Lin’s Team – A Prediction Model for Type 2 Diabetes Complications Our research group develops a decision-support prediction model for type 2 diabetes complications using data from over 163,000 Taiwanese patients. Integrating age, HbA1c, and other dynamic factors, the model estimates long-term risks of major complications and mortality, visualizes future trends, and supports personalized care planning to improve disease management and outcomes.