AI Deep Compression Toolchain: To enhance the computing power and lower the power consumption of edge devices, this toolchain delivers a 120x AI model compression ratio from original floating-point inference models, compress into fixed-point and bit-accurate edge models with a smaller than 1% accuracy loss. We also provide an open-source image bank and fully automatic labeling tool, available for free application and use at https://www.aicreda.com/.

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.

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.

Quote:br / “It is worth giving up some things because of dream pursuing” Professor SHOU-DE, LIN  at the department of computer scienceInformation Engineering in National Taiwan University, Chief Machine Learning Scientist in Appier, said “An escape from comfort zone to seek new challenges makes my life become more colorful.”br /  br / Content:br /  br / Given qualified for being as the freshman of National Taiwan University College of Medicine, Professor Lin chose the department of electrical engineering in NTU as the first priority in Joint College Entrance Examination (JCEE). Though the undergraduate education  did not cultivate him the passion on the field of electrical engineering, Professor Lin said, however, he was still recommended for further study at the graduate institute of electronics engineering in NTU due to his talentsoutstanding academic performance.

This study proposes a 5G C-V2I (Cellular Vehicle-to-Infrastructure) enabled intelligent trajectory predictionwarning system, which can be implemented in a framework including RSUs (Road Side Units) with radar detection ability5G edge computing servers. This study exploits artificial intelligence to predict instant trajectories of vehicles at crossroads. The resulting augmented-awareness navigation information is then broadcasted to road users through 5G C-V2I with low latency. In practical applications, road users can obtain real-time dynamics of surrounding vehicles so that their level of safety can be effectively enhanced.

Multidisciplinary rounds (MDRs) are scheduled, patient-focused communication mechanisms among multidisciplinary providers in the intensive care unit (ICU). The surgical ICU team of National Cheng Kung University Hospital has developed and integrated i-Dashboard as a platform to facilitate MDRs. i-Dashboard is a custom-developed visualization dashboard that supports (1) key information retrieval and reorganization, (2) time-series data, and (3) display on large touchscreens during MDRs. The i-Dashboard increases the efficiency in data gathering and enhances communication accuracy and information exchange in MDRs.

The NeRF-based technique describes a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses.

By using the machine learning algorithms, this study developed a risk stratification model for predicting the occurrence of in-hospital cardiac arrest (IHCA) events in patients admitted from the emergency department with COVID-19 and pneumonia. The results showed that the model's performance is better than by using the National Early Warning Score (NEWS).

Our team develops an accurate PWV estimation algorithm that uses wrist PPG and ECG signals from wearable devices. A missing-feature imputation and ambiguous-feature resolution technique is developed and the availability of wrist PPG morphological features is raised from 60% to 99.1%. A weighted pulse decomposition approach is adopted and 5 component waves can be acquired to examine more detailed properties. The PWV is then estimated by XGBoost algorithm with the hierarchical regression model.

The Pericardium/Aorta Segmentation and Cardiovascular Risk Prediction AI Total Solution Model, HeaortaNet, is a deep learning model based on UNet and attention gate, and had been trained by >70,000 axial images with verified annotations of the pericardium and aorta. It shortens the time for data processing from 60 minutes, by manual segmentation of both pericardium and aorta, to 0.4 seconds. The segmentation accuracy is 94.8% for the pericardium, and 91.6% for the aorta. The applicability of HeaortaNet had been demonstrated by analyzing the non-contrast chest CT scans (>5,000 cases) deposited in the mega-image bank of National Health Insurance Databank.