Integrating deep learning, 3D information analysis, hyperspectral analysis, computer vision analysiscombined the multi-source images to develop fruit quality monitoring techniques, including: planting area monitoring, position monitoring, yield monitoring, harvesting time prediction, fruit maturity measurement, fruit quality testing, to achieve the goal of enhancing industrial value.

In agriculture, the team has developed a “Chinese Medicinal Functional Compound Prediction A.I. System” that can predict compounds production during cultivation period. Moreover, in application, we have implemented a smart agricultural platform-AgriTalk to link the “Functional Compound Prediction System”“Smart Fertilization System” to provide a comprehensive management in farm production.

This study built an automatic insect pest image identification system based on tiny Yolov3 deep learning model. By optimizing the tiny Yolov3 detection model, images of insect pests on scanned sticky paper can be automatically identified. The system achieves a testing accuracy of 0.93, 0.90 for whitefliesthrips respectively.

The technology aims to develop an AI-based integrated system for emotional detections (anger, sadness, happiness,neutral)multimodal physiological signals (ECG, EEG,PPG),apply to patients with cardiovascular disease. Patients monitor their emotionalphysical statusadminister bio-neuro-feedback to improve their well-being, track disease progression,prevent adverse prognosis.

Our team construct an AIoT smart aquaculture management system. The management system mainly consists of: (1) Image Behavior MonitoringAnalysis Subsystem (2) Smart Feeding Subsystem (3) IOT Subsystem including underwater sensors, ROV,Drone (4) Cloud Subsystem (5) Big Data Analysis Subsystem.

We develope ZnO:Li as lead-free piezoelectric materialssuccessfully develop lead-free piezoelectric MEMS accelerometers through MEMS process technology. Since the input signal of the SAR ADC is voltage, Therefore, the charge generated by the accelerometer must be converted into a voltage signalthen transfer to the digital code from the SAR ADC.

This work presents a low powersecure IoT communication scheme. A physical unclonable function (PUF) based mutual authentication scheme in conjunction with a trusted third party (TTP),the low power transceiver with secure wake-up mechanism are integrated for networkhardware security thereby enabling to extend the battery lifetimeensuring reliability for the IoT systems.

Based on the optical fluorescence of the plant, the technology distinguishes the difference of the main protein infected by virus from the normal ones with the feature light. The main difference of this technology is to omit the complicatedbiochemical-material- consumption procedures. With the establishment of big data, the artificial intelligence algorithm identifies whether the implant is.

The technology is an integrated solution incorporating the retrievable personality for multimodal emotion sensing for spoken services. This framework provides a real-world flexibility that enables the estimation of the target speaker emotion states without manual personalization.

STT-MRAM: scaling down (submicron scale) along with issues of magnetic propertyintegration with semiconductor processing. SOT-MRAM: fundamental understanding on mechanism, integration with STT-MRAMCMOS for readout. VCMA-MRAM: understand the mechanism behind the observable VCMA phenomenon, integration with other RAMs for write/read.

The Al-based web diagnostic system provides an online assessment tool for diagnosing schizophrenia. The Explainable Deep Neural Network classifier is deployed to analyze gray matterwhite matter to derive diagnostic classification of schizophrenia. The structural brain abnormalities associated with schizophrenia is visualized on the AI-based web diagnostic system at individual level.

The computer-aided nodule detection system in CT image consists of the search sliding window, YOLOv2 architecture, 3-D CapsNet, skip connection,post-processing. First, the CT image is divided into numerous VOIs by sliding window. Second, a 3-D CapsNet based on YOLOv2 architectureskip connection is applied to the VOIs for classifying VOIs as nodulenot. Finally, the non-maximum suppression algorithm is performed to decide the final detection result.

Our technique is a liver tumor detection method using machine learning which is the most popular AI technique in these years. the high-magnification image provides more details, but the view is smaller in contrast, a low-magnification image has the larger view but less details. Thus, our method combines the two magnificationsyields more accurate tumor detection results.

Ted-ICU AI Platform: (1)Provide a single view of patients＇ EMRsvital signs (2)Support remote ICU monitoring (3)Online labeling tool & Expandable AI algorithms repository (4)Disease-specific prediction models (5)Standardized EMR templates

The core technology includes lightweight UAV, heterogeneous sensor integration, obstacle avoidance, group flight automatic flight control, RTK precision positioning systemfruit tree 3D stereo modeling technology. The UAV can be used for 3D scanningspectral information collection. The information can use for fruit tree growth monitoring, nutrient analysis,fruit quality monitoring.

The main purpose of this invention is to provide a training system with the surrounding photographing unit, the display unit,a force platform. The system can immediately capture the motion of the user from various angles,measure the force of the user from both legs, in order to provide the useful biofeedback information to coachesathletes.

　　Mobile Magnetic Survey System is composed of 20 precisesensitive magnetic detector arrays, which are used for measuring the 3D magnetic fields. With the LiDAR positioning systemattitude rotation, the magnetic vector field can analyze the magnetic field intensity at different positions. In addition, the visualized map can help users to evaluate the metal body locationdepth.

The technology is video-based blood pressure monitoring which will help people know the continuous BP status in real time. Also, the contactless measurement can make a daily health record. We have conducted clinical trials in hospitalsestablished a large database to optimize AI solution. The system joins the physicians＇ specialty to analyze the users＇ health status with AI,takes care of human life with technology.

　　This pressure-detection smart baseball obtains applied force, dynamicinertial features of pitcher during pitching. Through the connection between wireless moduleterminal, data will be transferredprovides vibration as a pitching signal. Also, precise adjustment is achievable through back-end analysiscustomized training formulation, which enhances pitching ability, optimizes training,improves pitcher＇s condition assessment.

Although there are few open-source core network projects, none of them are conformed to 3GPP Release 15 (R15). The free5GC is the first one in the world based on 3GPP R15. The ultimate goal of free5GC is to implement a full commercial, operational core network including Operation, AdministrationManagement (OAM), orchestrator,network slicing complied with 3GPP R15beyond.

The overall system first extracts embedded speaker identity features using a neural network model, then the deep neural network speech enhancement takes the augmented features as the input to generate the enhanced spectra. With the additional embedded features, the speech enhancement system can be guided to generate the optimal output corresponding to the speaker identity.

Low-power deep learning accelerator integrates neural network design / training, model compressionaccelerator design. It uses a small amount of computationmemory footprint to realize high performance on the edge device. The image semantic segmentation technology can reach 80 frames per second (resolution:1024*2048) to meet real-time requirements for autonomous driving.

The environmental information is very important to the human life, the proposed technologies of Environment Sensing Hub including: (1) Air sensing hub: temperature sensor, humidity sensor, pressure sensor, infrared sensor, noise sensor (microphone), PM 2.5 sensor (2) Water sensing hub: heavy metal ion sensor, spectrochip

Super fast terapixel server allows multiple users to viewanalyze gigapixelterapixel images with mobile devices, such as iPhones, iPads, Android mobiles,laptops at the same time. Users could annotateanalyze the data using built-in tools such as 3d effect, color deconvolution, color quantification, nuclei/object detection, lengtharea measurement,quantitative reporting system.

This technique combines more than one AI models to precisely predict current under noisy data from current sensoroptimizes speed rate based on this AI forecasting model. At the same time, it considers the practical requirementslimitations of workpiece surface roughness, tool machine current load, etc. This technique provides decision supports for optimizing parameters of CNC milling machine to keep high efficiencyenhance energy conservation.

1.Low-Power Processing-in-sensor CMOS Image Sensor 2.Implementation of Low-PowerLow-Latency Deep Learning Chip based on Neuromorphic Intelligence (collaborated with MOST 108-2622-8-007-009) 3.Development of Neuromorphic Chip based on The Fruit Fly VisualSpatial Sensory Systems 4.Hardware-Software Co-Design for Neuromorphic AI Chips

We developed our very own battery management system as well as improved the battery infrastructure, ensuring higher voltage as well as better safety we completely redesigned the suspension system, monitoring different dynamic performances via individual shock absorbers we also used the lighterstronger carbon fiber as the material for our wishbones.

Currently, the calculation program built into smart phones is not convenient for blind people. The invention patent allows the blind to view the touch screen as a large buttonconstruct a computer program using the finite state machine theory. The blind person can inputcomplete all four operations by continuously clicking the touch screen.

The red-leaf aglaonema were promoted growth of by water-retaining materials. For the growers, the technology can effectively shorten the duration of cultivationpromote the quality of potted flower. Therefore, the technology solves the problems of productionwill have practical application in the industry.

This technology used special process to enhance the functional ingredients, accelerate the processenhance the safety of black garlic. The bioactive test had confirmed the effect of improving gastrointestinal functionhepatoprotective effect. In the future, it is expected that this technologies will be applied to related industries.