Artificial Intelligence

Autonomous vehicle test at a limited field or even on the public road has its limitations. Simulation is essential to increase the test coverage. Taiwan Semiconductor Research Institute(TSRI) develop an autonomous vehicle test system based on CarMaker, which is a simulation tool from IPG Automotive. 13 testing scenarios and 6 testing routes corresponding to the physical test at Shalun testing field are built and included in this autonomous vehicle test system. An AEB(Autonomous Emergency Braking) function will be demonstrated to show how this autonomous vehicle test system works.

This theme is designed to implement the robot＇s appearancepractical functions. Apply PSPNet to detect the walkable planeYolo to detect obstacles, so that the robot has the autonomous obstacle avoidance function, informing more information about the environmental obstacles around the visually impaired,apply CNN to locate indoor position with self-built indoor database.

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.

This project designs a biomedical theranostic chip for neural disorders. It can not only function as an implantable device for treating the Parkinson＇s disease, depression, dementia, but also monitor physiological signals in wearable devices. For the development of medical device, the NeuLive system based on the microchip can accelerate the pre-clinical data collectionverification.

”AI2 Robot City” is a game-based learning kit for primary and secondary school students, which combines AI image-recognition teaching tool of MIT App Inventor and the computational thinking board game named as "Robot City." Through this learning kit, users will learn to make smart cars, create image-recognition models, write and perform mobile application. Users will learn to write a program to recognize the personal cards in the board game, and furthermore to control the smart cars with blue-tooth and compete in the computational thinking board game.

This product is a novel risk assessment tool for carotid artery stenosis and stroke. This is a revolutionary healthcare technology using motion analysis and quantification to extract information from pulses for risk assessments. The entire process is completed by taking a short video clip aimed at the neck with only one simple click on any mobile devices or our apparatus, anywhere, anytime. In less than five minutes, the user receives an evaluation report indicating low to high stroke risk. Our product accuracy stands higher than 90% when compared to the clinical outcome. The future indications of this product can be extended to arrhythmia, venous fistula obstruction, etc. This product has the great potential to achieve our dream of “personalized mobile hospital” in the future world.

This system provides multiple functions for digital slides, allowing users to complete all tasks without switching between different software systems. The functions include, Project management, Image management, Annotation, Zoon In / Zoom Out view, Navigation view, Category shortcuts, Authority management,Annotation overview.

The sweet pepper cultivationplant protection robot developed includes three parts: the intelligent image identificationpositioning system of sweet pepper diseasesinsect pests is composed of YOLO4 deep learning modelimage 3D vision integration. It can perform disease detectionspatial positioning,guide the robotic arm spraying device to accurately spray the diseased. The automatic walking system can use GPS to plan the movement path of the plant protection robot in the field, search for plants infected with pestsdiseases,perform the tasks of pest control.

　　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.

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 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.

(1) Ｇel-type solid electrolytes and All solid-state electrolytes for Lithium Ion Battery (LIBs) (2) Fabrication of dye-sensitized solar cells by printing process and its applications on Internet-of-Things (IoT) - MOST 2019 Award (3) Silicon-carbon coating anode materials for LIBs: SiLican startup company growth and global business layout (4) Power enhanced Intermediate Temperature Solid State Fuel Cell (SOFC) (5) Worldwide highest conversion efficiency (19.4%) perovskite solar cells (6) Industrial linking and Product design : LevioPole and Smart motorcycle suitcase

This study explores the energy-saving efficiency of a complex water-cooled chiller system composed of multiple chillers, cooling towerswater pumps connected by circulation pipelines. The deep learning modeling method driven by big data provides optimized parameters of the water-cooled chiller system to reduce the power consumption of the chiller system. Experiments show that this technology can increase the power saving efficiency of AU Optronics Longtan L5B factory by 2.42. This method has been implemented in many factories of AUO.

iTech has developed an Innovative Wireless Positioning&Tracking System. iShield can simultaneously detect drones & operators. iPosition tracks thousands of targets indoor. iFollow is an auto-following function for smart droids.

An IOT sensor was presented to detect human motionvital signs with Wi-Fi signals. It mainly combines MIMO beamforming, injection-locking radarmachine learning techniques to recognizetrack physicalphysiological activities for health status monitoring. As a proof of concept for pandemic prevention, the presented sensor aims to inspect whether someone is exhibiting signssymptoms of COVID-19 infection within the Wi-Fi coverage area, such as fatigue, cough, shortness of breathirregular heart rhythm,even to detect sudden death.

"AI is applied to assist data cleaningcross-database authority control of namesinstitutions in the bibliographic materials such as patents, papersresearch projects. The evolution analysis of industrial technology development is based on the AIbigdata output of technology development in terms of global industries. Next, the focus narrows down to local view, in order to compare each countryinstitute’s technology development path. By using the technology gap model, the strengthsshortcomings of each countryinstitute comparing to the global mainstream development can be implied."

In this study, the embedded LiDARAI recognition of smart headlight for autonomous driving is demonstrated. At driving process, the vehicle can provide artificial intelligence to identify the type, distancespeed of the object to be measured based on the fusion data of the LiDAR point cloudoptical image of the environment,then feedback to the headlight control system. Finally, this smart headlight would perform the suitable lighting mode during the daynightfit the automotive lamp safety regulationsstandards (ECE R112SAE J3069).

In order to develop an AI model that can accuratelycompletely segment coronary arteries, our team, the TW-CVAI, has established a training dataset composed of strictly verified annotations of coronary lumen boundaries in coronary CT angiography (CCTA). We designed a deep learning model, two-channel 3D-UNet, with a priori prerequisite (vesselness prior) to facilitate identification of vascular structures. The final model, the TaiCAD-Net, greatly shortens the CCTA interpretation time from 6 hours to 10 minutes, with the overall segmentation accuracy of 86 by Dice similarity coefficient.

Migraine patients account for about 640 million people (15) in the world,about 1.75 million (9.1) in Taiwan. Our team had developed a wearable brain-computer interface system with the newly developed graphene dry electrodeadaptive noise subspace reconstruction technology. This system combined the physiological indicators before migraine attacksuses AI technology to build an intelligent migraine early warning system,combined BrainSTIM electrical stimulation technology to assist migraine patients.

This technique employs AIbig data analytics to precisely forecast cooling load demandestimate efficiency of different chiller combinations. Time-of-Use Pricingoptimal chiller load interval are also considered for practical needs. Decision supports of optimal chiller configuration are provided to enhance energy conservation.

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.

With the rapid growth of the aging population, the safety of the hospitalized elderly has become an important issue. Therefore, our team propose an innovative bed-exit alarm system using multiple sensors for bed-exit detection. With data fusion, IoTAI technologies, the system can achieve early detectionsignificantly reduce false alarms. In addition, it can realize real-time video streami

By integration of professions including phytopathology, pesticides analysis, aquaticlivestock management, microbial fermentation, epidemiology,artificial intelligence, our interdisciplinary team jointly have developed microbial products for multi-industry applications including crop health care, circular agriculture, livestockaquaculture. The intelligent monitoring modelsmanagement technology for evaluating the efficacy of microbial products are implemented to provide key time pointdecision support for microbial products application,in turns to enhance the application efficacy. The developed microbial agentstechnology would greatly reduce the use of chemical pesticidesantibioticsenhance agricultural output valuemarket competitiveness.

We develop an image-based sim-to-real transfer technique for deep reinforcement learning. First, we train a teacher model to move along a near optimal path. We then use this model to teach a student model the correct actions along with randomization. The technique bridges the sim-to-real gap, improving the driving speedrobustness of the simulator-trained student model in the real world.

Based on deep learning camera/radar object detectiontracking technology, the proposed road side unit (RSU) system has achieved over 95 vehicle detection accuracy within 100m detection range in the processing performance of 10fps under nVidia Jetson Xavier platform. Compared to the 32-beam lidar based RSU, the proposed RSU achieves 97 reduction of sensor cost that exhibits high competitiveness in deployment cost. The proposed RSU system has been verified in fieldswe are now cooperating with an industry partner to deploy the RSU system in both TainanTao-Yuan cities.

This technique employs AIbig data analytics to precisely forecast cooling load demandestimates the efficiency of different chiller combinations. Time-of-Use Pricingoptimal chiller load-interval are also considered for practical needs. Decision supports of optimal chiller configuration is provided to enhance energy conservation. Moreover, using real data feedbackmodel health examination, the model can do self-calibrationmake evolution, continuously learn from the experts,provide decision supports in good quality.

The developed Unmanned autonomous underwater vehicles (AUV) included 3-D modeling technology, wireless power transfer between sub-system in AUV, GPS underwater locate system, low complexity frequency domain on ocean floor analyze with AI network, underwater objects detection network, image dehaze network on groundunder water, underwater color correction network, underwater objects classification network, underwater optical characteristic algorithmLED color compensation system.

This successful technology is the digital interventions on depression patients based on (1) heart rate variability bio-feedbacks (HRVBs) measured by a novel flexible sensor patch attached on patient’s wrist(2) an APP. An innovative flexible low-power PPG patch has been designed which is capable of providing weeks of high-quality PPG signals which are essential towards accurate estimation of HRV for favorable efficacy of designed digital interventions. Also, An AI model correlating the HRVsand PHQ-9/HDRS scores of depression patients will be built based on collected data.

Artificial intelligence 3D sensing image processing system based on array sensing Lidar aims to construct 3D image with high-quality immersion for AR/VR. The developed 3D scene recording system is based on the color camerahigh-accuracy chaotic LiDAR. The chaotic Lidar with APD arrayTOF sensors supports millimeter-accuracyinterference-avoiding capability within 100 meter in both indooroutdoor environments. High-performance embedded CNN processor supports high-throughput, high energy-efficient,low DRAM bandwidth computations for various image AI applications.

This technique uses multimodal nonlinear optical microscopy with the image contrast of second harmonic generation (SHG)coherent anti-Stokes Raman scattering (CARS). By analyzing the nonlinear signals on images, it can be used to characterizequantify the structural variation in the collagen scaffolds processed with different crosslinking methods. The correlation between signalsmechanical properties can then be derived. Additionally, comparative analysis of these two signals can be used to monitor the structural (triple-helix) change of collagen molecules during the crosslinking processes.