AI-enabled Service Assurance Platform for 5G Vertical Application

We use DRL to train the models for personalized laddervisual learning based on Scaffolding Learning theory. It could improve the quality of our AI Go services. The services are running on an online AI-assisted board games learning platform for teaching, learningplaying Go. It will be the largest AI Go service with one billion annual AI service count.

The invention relates to a thermoplastic thin 2D mesh fabric composite structure, which particularly can be used as a medical protectorin connection with sporting activities with impact resistance, light weighthigh air permeability,has a reshapeable orthopedic support,fixed support bandages for limbs/joints. The thermoplastic thin 2D mesh fabric composite structure mainly includes a breathable mesh fabrica high molecular polymer coated on the breathable mesh fabric that can be reshapedreused when exposed to heat.

Surface-enhanced Raman spectroscopy (SERS) is a useful analytical technique for detecting extremely small amounts of molecules. Herein, we designed a paper-based quasi-three-dimensional SERS substrate (P-SERS) that can provide potential to improve Raman analyses for food safety, pesticide poisoning, precision medicine, drug abuseDNA/RNA testing. The sensitive, low-cost, flexibledisposable SERS substrate could be easily fabricated by physical deposition of gold nanoparticles array onto a filter paper. In this case, we are able to create non-continuous Au islands on the fiber surfaces, where the gaps between AuNPs can dramatically generate the high electric field to enhance Raman signal of target molecules.

This research project aims to establish an intelligent agricultural cultivation support system, by integrating unmanned aerial vehicle (UAV) surveillanceartificial intelligent (AI) analytical techniques.

This technology uses the ultrasonic non-destructive test technology to detect Li-ion battery packs which are commonly used in EVs. After the detection is completed, the ultrasonic signals are input into the AI diagnostic & evaluation model to obtain the status of each pouch cell in the battery pack.

In response to the global COVID-19 pandemic, Prof. Jinn-Moon Yang, the director of the Department of Biological Science & Technology at the National Yang Ming Chiao Tung University (NYCU),also leading an AI project as a principal investigator within MOST Joint Research Center for AI TechnologyAll Vista Healthcare (AINTU), created an intercollegiateinterdisciplinary smart dynamic system-based biologicalmedicine development team.

This project develops a high-performance end-to-end reinforcement learning training platform for autonomous miniature car racing. With this platform, our team won the championship of Amazon DeepRacer, a world autonomous racing competition. In addition, by combining various reinforcement learning algorithms and frameworks, our self-developed autonomous racing platform can operate at a much higher speed, surpassing the performance of Amazon DeepRacer.

National Cheng Kung University’s AI medical technology research results are gaining international recognition. Professor Akira Ishibashi of Hokkaido University, who specializes in the R&D of air purification systems for home sleep environments, has shown great interest in the smart sleep assessmentresearch conducted by Prof. Sheng-Fu Liang, Director of the NCKU Institute of Medical Informatics. The two parties signed a memorandum of cooperation at NCKU. Past cooperation on “T-CUSP” serves as a foundation for further research on sleep sensingimprovement with the goal of constructing a comprehensive sleep enhancement program.

PANCREASaver contains a “Pancreas Cancer (PC) automatic segmentation model” (image segmentation) and a “Pancreas Cancer (PC) analysis AI model” (image classification) that can read the DICOM format of postcontrast CT images directly for the automatic analysis process. After conducting prep-processing with image processing algorithms, C2FNAS is employed to illustrate the tumor position prior to the diagnosis conducted by CNN. The results can be provided to the physician for diagnostic reference so as to reduce early omissions and increase the detection rate of pancreatic cancer.

The application of voice assistants is becoming more and more popular, however, due to the inefficiency of artificial intelligence-based technology, current products are mostly built by using rules-based methods. Therefore, in this project, we would like to propose some corresponding solutions for different components of the dialogue system to improve the data efficiency and work efficiency of each component.

With the maturity of deep learning technology, reading comprehension model (given an article and a question, the AI model automatically finds the answer to the question from the article) has become a key element in natural language applications. Such as knowledge extraction and knowledge graph construction can be solved through reading comprehension model. In this project, we investigate the employment of the reading comprehension model to build an agricultural knowledge graph from Taiwan agricultural literatures. One challenge, however, is that existing reading comprehension models are not tailored for agricultural literature and therefore cannot be used directly. In this project, we leverage the question generation technology as a mechanism for agricultural data augmentation, and then train the literature reading comprehension model in the agricultural field.

ALOVAS Platform: ALOVAS acts as an A.I. Pathology Platform which provides high resolution pathology image viewer. Even Giga-pixel-level original images can be viewed online in real time. ALOVAS platform can be used not only on computer, but also on iPad. Users can upload images on the platform and select AI models for automated detection, and browse the detection results on the platform. ALOVAS also provides commonly used annotation tools, including hand-drawing, dots, rectangles, etc., which can be used to mark areas of interest. Embedded with the ALOVAS platform also provided several detection algorithms. We hope ALOVAS can assist physicians in rapid diagnosis, in related pathological research, and reduce the workload of pathologists in the future.

Intelligent Portable Neurofeedback Training System: Highlights of our product: 1. High accurate EEG value (with rigorous hardware and software design and verification) 2. real-time feedback by computer screen or APP 3. can be used at home (easy to ware, easy to use)

The technology optimizes the antigen protein expression system, so that the structural protein Erns of classical swine fever virus (CSFV) converts insoluble proteins into soluble proteins during the production process. The breakthrough of this technology allows the antigen protein to be applied to the development of an immune attachment screening platform, as a specialized differential diagnostic reagents can distinguish between virus-infected and vaccinated pigs, which can be applied to the monitoring system of virus transmission range and vaccination

This research team develops unmanned 3D intelligent marine aquaculture technology, using omni AIoT aquaculture technology, especially strengthening the integration of gyroplane, ROV, unmanned ship and central control room, and using long-distance intelligent control to make employees shift from traditional field work to base and central control room. Due to the huge cross domain system of omni AIoT, it modularizes it, At the same time, edge computing technology is developed to facilitate commercial promotion.

Reliability of Cu-to-Cu direct bonging: In order to realize the reliability of Cu-to-Cu direct bonding interconnects, we adopted nanotwinned Cu (nt-Cu) electroplating process to fabricate nt-Cu microbump for Cu-to-Cu direct bonding. Figure (a) is the photo of chip after bonding. Underfill (UF) dispensing was used to protect Cu microbumps. The cross-section SEM image of Cu microbump is shown in figure (b). Some chips underwent the reliability tests, including temperature cycling test (TCT) and electromigration (EM) test. To further study the failure mechanism, finite element analysis (FEA) was done to know the stress and current distribution during reliability test. This research could provide fundamental understanding for Cu-Cu joints with organic dielectric hybrid bonding.

This project proposes a learning from demonstration (LfD) system that allows robots to be not only taught by human via demonstration but also adjusted by themselves.

Constructing a functional connectomeits computational model is a crucial step toward understanding the mechanisms of brain functions. To achieve this goal, we developed two correlated technologies: (1) An all-optical physiology (AOP) that is capable of millisecond volumetric imagingaccurate stimulation in living animal brains. This system allows us to establish functional connectomeneural coding with a single-cell resolution. (2) A cellular-level spiking neural circuit simulation system that is capable of tuning itself based on the input data from the AOP system. We have demonstrated our technologies in the Drosophila late visual systemwill apply them in the brains of larger species such as mice. Our technologies will greatly enhance knowledge of brain operation.

The Strategic Cooperation beyond Borders Signing Ceremony was jointly signed by MOST AI Biomedical Research Center Director Sheng-Fu Liang, NCKU Computer Science & Computer Engineering Dept. Chair Yeim-Kuan Chang, Prof. Fu-Chiang Tsui,Associate Professor at University of Pennsylvania’s Perelman School of Medicine & Childrens Hospital of PhiladelphiaTzyy-Ping Jung, Co-Director of Swartz Center for Computational Neuroscience at UC San Diego.

“MeDA OXR: Real-time Hazard Recognition System,” which can automatically screen and interpret the medical images in real-time, is designed for emergency rooms to assist physicians in diagnosis, reducing medical risks, and improving overall efficiency. Combining portable X-Ray and AI algorithms, the system performs real-time and accurate preliminary screening and diagnoses of diseases, such as pneumothorax, pneumonia, and tuberculosis. It can also locate the nasogastric tube, endotracheal tube, and central venous catheter, while misplacement of that is sent to the physicians when detected.

This technology uses a customized high-resolution saltwater proof video camera that operates underwater for months on end without maintenance. The captured images are pre-processed to adjust the brightnessmaximize the sharpness, after which the images are input into a region-based convolutional neural networks (R-CNN) for trainingidentification. This technology is currently able to reliable identify shrimp in these imagesto distinguish between the shrimp’s headtail in order to conclude whether the image shows a complete shrimp.

The technology combines specific visual recognition and electrochemical quantitative detection in a single portable device, providing instant and convenient copper ion detection. The sensing sensitivity has reached the standards of Taiwan and the United States for heavy metal detection for food, human body, and environments. In use, this portable and user-friendly interface device not only makes it simple to report back to the EPA database for water quality analysis, but also it can be utilized for real-time detection from youngsters to the elderly.

div style="text-align: justify"Taiwan was once the shrimp capital of the world. Though just a small island, the technology, abundance,reputation was globally known. Over time, the changes in water qualitythe environment led to lessless shrimp. AI may be the innovative solution needed to revive the industry./div

The world is moving towards a more aged society, with Asia being at the most rapid pace. Since 2018, Taiwan has also officially
become an Aged Society. It is estimated that by 2026 it will become a Super-Aged Society. As aging is inevitable, it is important to pay attention to health maintenance and upkeep.

Based on deep learning camera/radar object detection and tracking 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 fields and we are now cooperating with an industry partner to deploy the RSU system in both Tainan and Tao-Yuan cities.

div style="text-align: justify"Constructing a functional connectomeits computational model is a crucial step toward understanding the mechanisms of brain functions. To achieve this goal, we developed two correlated technologies: (1) An all- optical physiology (AOP) that is capable of millisecond volumetric imagingaccurate stimulation in living animal brains. This system allows us to establish functional connectomeneural coding with a single-cell resolution. (2) A cellular-level spiking neural circuit simulation system that is capable of tuning itself based on the input data from the AOP system. We have demonstrated our technologies in the Drosophila late visual systemwill apply them in the brains of larger species such as mice. We expect that our technologies will be able to greatly enhance our knowledge of the brain operation principles. Our 3D all-optical physiology (AOP) platform incorporates single-photon point stimulationtwo-photon high-speed volumetric recordings (Optics Letters 2019, "Editors pick"). We have demonstrated its effectiveness in studying the anterior visual pathway of fruit flies (iScience2019). In comparison, contemporary high-speed AOP platforms are limited to single-depthdiscrete multi-plane recordings that are not suitable for studying functional connections. Our high-resolution computational model is constructed based on the combination of static connectomeAOP data,is much more realistic than the existing models. Our work aids establishing in-vivo 3D functional connectomescomputational models of the brains, thus provides insight into the mechanisms of brain functions./div

Tool wear and health condition monitoring during the processing: The tool wear monitoring technology developed by our researching team is specifically designed to analyze whether the tool is broken, collapsed, etc., and to estimate the remaining useful life(RUL) of the tool according to the working conditions of mass processing. By acquiring the vibration signal data with three-axis accelerometers installed on the machine tool, this technology could determine whether the current tool cutting vibration has exceeded the safety range by plotting a control chart. Once it exceeds the safe range, the current tool processing state will be assumed as abnormal. It gives users a reference to replace the broken tools immediately to prevent continuing processing, which causes vast loss such as poor quality of workpieces. In addition, this technology allows users to build models for distinct working conditions to predict the RUL of tools. It could allow users to evaluate the current health condition of tools and schedule the time to change the tool.

Taiwan is rapidly entering the era of "aging"simultaneously having "less children". Last year, it officially became a "senior society." How do we cope with the constant aging of those around us? What medicalcare needs will be faced? How will the younger generation juggle long-term care for the aging, along with lifework?

PCA-BM includes two models: “Automatic BMs Segmentation AI Model” and " Distant Brain Failure Prediction Model". The former one uses C2FNAS (coarse to fine network architecture search) to detect the location, size, and the number of brain metastases. The latter uses radiomics to extract numerous radiographic features and employs machine learning methods such as XGBoost to establish a prognostic model of brain metastases. PCA-BM provides more precision treatment decisions for patients and improves personalized and accurate overall stereotactic radiosurgery planning.

With our autonomous UAV systems, we can effectively reduce many high-risk and high-cost inspections which require high manpower, such as inspections of dams, river, coastline patrols, etc.. Operators only need to setup and launch the system to allow the UAV to complete the designated tasks independently.