Wei-Lun Hsu

Wei-Lun Hsu

Auto-generated profile, based on publicly available information

Wei-Lun Hsu

University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA,20742

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 August 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
WHWei-Lun Hsu
Wei-Lun Hsu
JLJin Xian Liu
Jin Xian Liu
CYChia-Cheng Yang
Chia-Cheng Yang
JenqShiou LeuJenqShiou Leu
JenqShiou Leu
Fall detection has become a popular research field in recent years due to the fact that falls can cause serious injuries. Most existing fall detection systems rely on wearable devices or image recognition technology. However, these approaches possess limitations. For instance, most people take off wearable devices during showers, while cameras with image recognition raise privacy concerns. To overcome these challenges, this study proposes a novel approach using 60 GHz radar to develop a fall detection system. We collected raw data from the frequency-modulated continuous wave (FMCW) radar in three bathrooms and two other indoor fields. Then, we derived features by generating Range-Doppler images and proposing a new Doppler image preprocessing method, Long-Time Interval Range-Doppler Histogram, each histogram represents the cumulative speed information of the Doppler images. Specifically, each histogram is composed of 30 Doppler images per second, capturing the overall speed distribution over a longtime interval. In addition, we proposed two deep learning models, a trigger model, and a fall detection model, for the fall detection system. The trigger model employs convolutional neural networks (CNNs) to identify Range-Doppler images with significant speed and distance variations and is optimized to run on devices with limited central processing unit (CPU) resources. The fall detection model utilizes a bidirectional long short-term memory-based deep learning model to make the final decision. Over 700 records were collected during the experiment, and the fall detection system achieved an accuracy rate of nearly 96%, with recall and precision rates exceeding 90%.

19 August 2023
Verified
Conference Paper
Closed access
WHWei-Lun Hsu
Wei-Lun Hsu
CHChien-Jui Huang
Chien-Jui Huang
YCYou-Cheng Chen
You-Cheng Chen
SLShih-Cheng Lin
Shih-Cheng Lin
SCSheng-Fuh Chang
Sheng-Fuh Chang
To investigate the deployment methodology of reconfigurable intelligent surface (RIS) in an indoor scenario, a technique of incorporating the RIS into a ray-tracing simulation is studied. In this work, the effects of deploying RIS in an indoor environment are thoroughly considered by skillfully embedding the simulated radiation field pattern of RIS in the raytracing simulator. Depending on the demanded power density distribution in the target environment, the RISs can be configured by adjusting the electrical characteristics and setups such as incident angles, beamwidths, types of transmitting antennas, and so on. With this approach, the realistic impact of the 1-bit RIS unit cell are included. The capabilities/effectiveness of utilizing RISs for enhancing the communication channel can be evaluated. Specifically, the results facilitate the determination of deployment locations and parameters of RISs, thereby brining about the effective usage of RISs in actual indoor environment.

12 November 2023
Verified
Conference Paper
Closed access
YZYang Zhang
Yang Zhang
WHWei-Lun Hsu
Wei-Lun Hsu
PGPradip Gatkine
Pradip Gatkine
SVSylvain Veilleux
Sylvain Veilleux
MDMario Dagenais
Mario Dagenais
Arrayed waveguide gratings with spiral reusable delay lines (SRDL-AWG) are demonstrated as high resolving power, high throughput, and highly compact integrated photonics spectrometers. SRDL-AWG with a throughput of 22% and a resolving power of 102,920 is experimentally demonstrated.