Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sheng-Tao Chen has a total of 8 co-authors. Here are the top co-authors by number of shared publications:

  • Shih-Sung Lin

    Department of Computer Science and Information Engineering, Chinese Culture University, Taipei 11114, Taiwan

    3 shared publications
  • Chien-Wu Lan

    Department of Electrical and Electronic Engineering, Chung Cheng Institute of Technology, National Defense University, Taoyuan, Taiwan

    2 shared publications
  • Chih-Hsien Hsia

    Department of Computer Science and Information Engineering, National Ilan University, Yilan 260007, Taiwan

    2 shared publications
  • Hao-Yen Hsu

    Department of Electrical and Electronic Engineering, Chung Cheng Institute of Technology, National Defense University No. 75, Shiyuan Rd., Daxi District, Taoyuan City 33551, Taiwan

    2 shared publications
  • Chien-Wu Lan

    Department of Electrical and Electronic Engineering, Chung Cheng Institute of Technology, National Defense University No. 75, Shiyuan Rd., Daxi District, Tauyuan City 33551, Taiwan

    1 shared publication
  • Kuang-Chun Li

    Natl Def Univ, Dept Elect & Elect Engn, Chung Cheng Inst Technol, 75 Shiyuan Rd, Tayuan 33551, Taiwan

    1 shared publication

Latest Publications

  • Multi-Emotion Features Extraction for Driver Distraction Detection

    by Sheng-Tao Chen, Chih-Hsien Hsia, Yo-Cheng He

    Two major factors contributing to human-induced traffic accidents are driver fatigue and distraction. To reduce the rate of occurrence of car accidents, some studies introduced systems that record biometric measurements, diver behavior, and driver’s physical features while driving. Data obtained from these systems are used to predict the driver concentration states. However, these attention-detection systems face challenges in terms of applicability and accuracy in detecting negatively impacting driving behaviors. Contactless physical feature extraction and integration of deep learning are effective and applicable methods in this context. Therefore, this study proposes a method based on multi-feature processing in conjunction with you only look once (YOLO)-based object detection to classify driver attention. Experiments and validation were conducted using the open-source Yawn detection dataset (YawDD) and National Tsing Hua University drowsy driver detection dataset (NTHU-DDD). The proposed method not only outperforms those of certain studies and achieved high efficiency in detecting multi-emotion features of drivers and assisting driver attention.


  • Open Access

    Improved Lightweight Convolutional Neural Network for Finger Vein Recognition System

    by Chih-Hsien Hsia, Liang-Ying Ke, Sheng-Tao Chen

    Computer vision (CV) technology and convolutional neural networks (CNNs) demonstrate superior feature extraction capabilities in the field of bioengineering. However, during the capturing process of finger-vein images, translation can cause a decline in the accuracy rate of the model, making it challenging to apply CNNs to real-time and highly accurate finger-vein recognition in various real-world environments. Moreover, despite CNNs’ high accuracy, CNNs require many parameters, and existing research has confirmed their lack of shift-invariant features. Based on these considerations, this study introduces an improved lightweight convolutional neural network (ILCNN) for finger vein recognition. The proposed model incorporates a diverse branch block (DBB), adaptive polyphase sampling (APS), and coordinate attention mechanism (CoAM) with the aim of improving the model’s performance in accurately identifying finger vein features. To evaluate the effectiveness of the model in finger vein recognition, we employed the finger-vein by university sains malaysia (FV-USM) and PLUSVein dorsal-palmar finger-vein (PLUSVein-FV3) public database for analysis and comparative evaluation with recent research methodologies. The experimental results indicate that the finger vein recognition model proposed in this study achieves an impressive recognition accuracy rate of 99.82% and 95.90% on the FV-USM and PLUSVein-FV3 public databases, respectively, while utilizing just 1.23 million parameters. Moreover, compared to the finger vein recognition approaches proposed in previous studies, the ILCNN introduced in this work demonstrated superior performance.


  • Open Access

    Design and Development of Portable LoRa-based Teleoperation Controller

    by Shih-Sung Lin, Chien-Wu Lan, Sheng-Tao Chen, Kuang-Chun Li


  • Open Access

    Data Analytics of a Wearable Device for Heat Stroke Detection

    by Shih-Sung Lin, Chien-Wu Lan, Hao-Yen Hsu, Sheng-Tao Chen

    When exercising in a high-temperature environment, heat stroke can cause great harm to the human body. However, runners may ignore important physiological warnings and are not usually aware that a heat stroke is occurring. To solve this problem, this study evaluates a runner’s risk of heat stroke injury by using a wearable heat stroke detection device (WHDD), which we developed previously. Furthermore, some filtering algorithms are designed to correct the physiological parameters acquired by the WHDD. To verify the effectiveness of the WHDD and investigate the features of these physiological parameters, several people were chosen to wear the WHDD while conducting the exercise experiment. The experimental results show that the WHDD can identify high-risk trends for heat stroke successfully from runner feedback of the uncomfortable statute and can effectively predict the occurrence of a heat stroke, thus ensuring safety.


  • Open Access

    Design and Development of a Wearable Device for Heat Stroke Detection

    by Sheng-Tao Chen, Shih-Sung Lin, Chien-Wu Lan, Hao-Yen Hsu

    Heat stroke can be potentially damaging for people while exercising in hot environments. To prevent this dangerous situation, we designed a wearable heat-stroke-detection device (WHDD) with early notification ability. First, we used several physical sensors, such as galvanic skin response (GSR), heart beat, and body temperature, to acquire medical data from exercising people. In addition, we designed risk evaluation functional components that were based on fuzzy theory to detect the features of heat stroke for users. If a dangerous situation is detected, then the device will activate the alert function to remind the user to respond adequately to avoid heat stroke.