Yu-Hsuan Liu

ORCID: 0009-0003-7384-8029
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Photonic and Optical Devices
  • Advanced Fluorescence Microscopy Techniques
  • Semiconductor materials and devices
  • Advanced Fiber Laser Technologies
  • Semiconductor Lasers and Optical Devices
  • Phonocardiography and Auscultation Techniques
  • Video Surveillance and Tracking Methods
  • Advanced optical system design
  • ECG Monitoring and Analysis
  • Advanced Optical Sensing Technologies
  • Advanced Neural Network Applications
  • Semiconductor Quantum Structures and Devices
  • Image Enhancement Techniques
  • Music and Audio Processing

National Tsing Hua University
2017-2024

Feng Chia University
2023

National Chung Hsing University
2022

InnoLux (Taiwan)
2017

To exploit an image-based in-cabin monitoring system for driving behavior and in-vehicle occupants detections to improve safety, in this paper, by installing a fisheye-lens camera at the in-car roof center using RGB-format images as inputs, YOLO-based deep learning models, including YOLOv3-tiny, YOLOv3-tiny-3I, YOLO-fastest, YOLO-fastest-xl, YOLO-fastest-three scales, are studied be candidate detectors. The proposed design can detect normal distracted cases back seat passengers pet dogs....

10.1109/icce53296.2022.9730235 article EN 2023 IEEE International Conference on Consumer Electronics (ICCE) 2022-01-07

The healthcare industry has made significant progress in the diagnosis of heart conditions due to use intelligent detection systems such as electrocardiograms, cardiac ultrasounds, and abnormal sound diagnostics that artificial intelligence (AI) technology, convolutional neural networks (CNNs). Over past few decades, methods for automated segmentation classification sounds have been widely studied. In many cases, both experimental clinical data require electrocardiography (ECG)-labeled...

10.3390/bioengineering10111237 article EN cc-by Bioengineering 2023-10-24

For present-day optical communication systems, the commonly used normal-incidence photodetectors suffer from tradeoff between bandwidth and quantum efficiency. Such a is especially adverse for long wavelength systems operating at higher data rates. example, maximum responsivity commercially available 25 Gbps photodetector 1310 nm limited to less than 0.8 A/W. In this work, we design demonstrate high-speed, backside-incidence, critically-coupled Ge on SOI while maintaining high Our device...

10.1117/12.2251694 article EN Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2017-02-16

We present a novel photon-acid diffusion method to integrate polymer microlenses (MLs) on four-channel, high-speed photo-receiver consisting of normal-incidence germanium (Ge) p-i-n photodiodes (PDs) fabricated 200 mm Si substrate. For 29 µm diameter PD capped with 54 ML, its dark current, responsivity, 3 dB bandwidth (BW), and effective aperture size at -3 V bias 850 nm wavelength are measured be 138 nA, 0.6 A/W, 21.4 GHz, µm, respectively. The enlarged significantly decouples the tradeoff...

10.3390/s24134221 article EN cc-by Sensors 2024-06-29
Coming Soon ...