Shengkai Chen

Traversal-guided vertex index reordering for high-capacity reversible data hiding in encrypted meshes

Yuan‐Yu Tsai, Shengkai Chen, Jie Yang, Ching-Ta Lu et autres

tw (code pays fourni par la source)

Doping Engineering of p-GaN Gate HEMTs on Si

J WANG, Kai-Chieh Chen, Shengkai Chen, Po-Chun Yeh et autres

This work reports the investigation of p-GaN gate HEMTs with different gate-stack structures to evaluate the effects of Mg profile on their DC characteristics. The device with a dual-layer p-GaN and an undoped GaN interlayer exhibited an on-resistance of 2.5 Ω•mm, a …

tw (code pays fourni par la source)

An Intelligent AI glasses System with Multi-Agent Architecture for Real-Time Voice Processing and Task Execution

Shengkai Chen, Jyh-Horng Wu, Ching-Yao Lin, Yen-Ting Lin

This paper presents an AI glasses system that integrates real-time voice processing, artificial intelligence(AI) agents, and cross-network streaming capabilities. The system employs dual-agent architecture where Agent 01 handles Automatic Speech Recognition (ASR) and Agent 02 manages AI processing through local Large Language …

An Intelligent AI glasses System with Multi-Agent Architecture for Real-Time Voice Processing and Task Execution

Shengkai Chen, Jyh-Horng Wu, Ching-Yao Lin, Yen-Ting Lin

This paper presents an AI glasses system that integrates real-time voice processing, artificial intelligence(AI) agents, and cross-network streaming capabilities. The system employs dual-agent architecture where Agent 01 handles Automatic Speech Recognition (ASR) and Agent 02 manages AI processing through local Large Language …

Machine-Learning-Empowered Propagation Measurement and Modeling for an Amphitheater

Soo Yong Lim, C. K. Ong, Jay Sern Chow, K. L. Lee et autres

This paper presents a machine learning (ML) approach to modeling radio signal strength in an open-air amphitheater environment. Towards this end, we have first collected field measurement data from an amphitheater located on the Malaysia Campus of the University of Nottingham at …

my, tw (code pays fourni par la source)

Microdroplets Catalyze C( sp 2 )–H Nitration Reactions

Shengkai Chen, Ziying Qi, Ke Dong, Xiaofang Su et autres

Microdroplet chemistry is reforming organic synthesis in a green and sustainable manner in recent years because of the unique catalytic and redox environment at the gas–liquid interface. Nitration, an important way of introducing nitro groups, traditionally requires the use of nitric acid …

cn (code pays fourni par la source)

Efficient Grasp Detection via Knowledge Distillation: A Lightweight Generative Grasping Convolutional Neural Network Framework

Shengkai Chen, Jie-Yu Chao, Po-Lien Wu, Jr-Yu Chang et autres

Despite the effectiveness of deep neural networks in robotic grasp detection, deploying them on resource-constrained platforms remains challenging due to high computational demands. This study proposed a knowledge distillation-based approach to compress the Generative Grasping Convolutional Neural Network (GGCNN), enabling efficient real-time …

tw (code pays fourni par la source)

SimCast: Enhancing Precipitation Nowcasting with Short-to-Long Term Knowledge Distillation

Yifang Yin, Shengkai Chen, Yiyao Li, Lu Wang et autres

Precipitation nowcasting predicts future radar sequences based on current observations, which is a highly challenging task driven by the inherent complexity of the Earth system. Accurate nowcasting is of utmost importance for addressing various societal needs, including disaster management, agriculture, transportation, and …

Supercritical nitrogen-enhanced interface control for high-frequency T-gate GaN HEMTs fabricated on 8-inch CMOS-compatible wafer

Po-Tsung Tu, Hsin‐Chu Chen, Sheng‐Yao Chou, Shengkai Chen et autres

tw (code pays fourni par la source)

Incorporating Multi-Scale Module Kernel for Disease-Gene Identification in Biological Networks

Ju Xiang, Shengkai Chen, Xiangmao Meng, Ruiqing Zheng et autres

Abstract Biomedical data mining plays a crucial role in studying diseases, with disease-gene identification being one of the most prominent areas of research in this field. Many biomolecular networks are known to have multi-scale module structures, which may be helpful for studying …

cn, sg (code pays fourni par la source)

Inverse Kinematics Neural Network Models for Improving Inference Efficiency and Memory Usage

Shengkai Chen, Yi‐Ling Tsai, Chun‐Chih Chang, Yan-Chen Chen et autres

As the demand for inverse kinematics (IK) applications in embedded systems grows, developing efficient and accurate IK neural network models for resource-constrained devices remains a critical challenge. In this study, we propose two improved versions of the original IKNet: Improved IKNet and …

tw (code pays fourni par la source)

SimCast: Enhancing Precipitation Nowcasting with Short-to-Long Term Knowledge Distillation

Yifang Yin, Shengkai Chen, Yiyao Li, Lu Wang et autres

Precipitation nowcasting predicts future radar sequences based on current observations, which is a highly challenging task driven by the inherent complexity of the Earth system. Accurate nowcasting is of utmost importance for addressing various societal needs, including disaster management, agriculture, transportation, and …

sg (code pays fourni par la source)