Yi-Ting Shen

Yi-Ting Shen

Auto-generated profile, based on publicly available information

Yi-Ting Shen

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

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
27 July 2023 in IEEE Access
Verified
Journal Article
Open access
YSYi-Ting Shen
Yi-Ting Shen
YLYaesop Lee
Yaesop Lee
HKHeesung Kwon
Heesung Kwon
DCDamon M. Conover
Damon M. Conover
SBShuvra S. Bhattacharyya
Shuvra S. Bhattacharyya
FSFrank Skirlo
Frank Skirlo
Learning to detect objects, such as humans, in imagery captured by an unmanned aerial vehicle (UAV) usually suffers from tremendous variations caused by the UAV’s position towards the objects. In addition, existing UAV-based benchmark datasets do not provide adequate dataset metadata, which is essential for precise model diagnosis and learning features invariant to those variations. In this paper, we introduce Archangel , the first UAV-based object detection dataset composed of real and synthetic subsets captured with similar imagining conditions and UAV position and object pose metadata. A series of experiments are carefully designed with a state-of-the-art object detector to demonstrate the benefits of leveraging the metadata during model evaluation. Moreover, several crucial insights involving both real and synthetic data during model optimization are presented. In the end, we discuss the advantages, limitations, and future directions regarding Archangel to highlight its distinct value for the broader machine learning community.

25 November 2024 in IEEE Access
Verified
Journal Article
Open access
CWChiao-Yi Wang
Chiao-Yi Wang
GPGuru Nandhan Appiya Dilipkumar Peethambari
Guru Nandhan Appiya Dilipkumar Peethambari
YSYi-Ting Shen
Yi-Ting Shen
WCWei-Yu Chen
Wei-Yu Chen
SKSandip Sharan Senthil Kumar
Sandip Sharan Senthil Kumar
Yang TaoYang Tao
Yang Tao
Shellfish aquaculture significantly contributes to the coastal economy of the United States. However, the current primary and most productive harvesting method for on-bottom shellfish farming—dredging with tow dredges —is highly inefficient, as farmers typically tow the dredges blindly and randomly in their fields. To enhance efficiency, we propose ShellCollect , a smart precision shellfish harvesting framework that generates harvesting paths based on underwater oyster distributions. We formulate this problem as data collection path planning and solve it by a Variable Neighborhood Search (VNS) based approach with a novel simplification scheme called merge-and-filtering . Additionally, we introduce ShellMapSim , a dedicated simulator for designing and evaluating harvesting path-planning methods. Through simulations in ShellMapSim, we demonstrate the effectiveness of our method across diverse oyster distributions. Moreover, we conducted field tests to validate the viability of our ShellCollect framework for real-world applications. To the best of our knowledge, this work is the first to address smart precision harvesting in shellfish.

6 June 2025 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
CWChiao-Yi Wang
Chiao-Yi Wang
FSFaranguisse Kakhi Sadrieh
Faranguisse Kakhi Sadrieh
YSYi-Ting Shen
Yi-Ting Shen
GOGiovanni Oppizzi
Giovanni Oppizzi
LZLi-Qun Zhang
Li-Qun Zhang
Yang TaoYang Tao
Yang Tao
Falls are a leading cause of injury among older adults, with research indicating that they often fall due to certain individual biomechanical factors. Therefore, real-time individual fall risk assessment is essential for designing more effective fall prevention programs and developing advanced home-based training solutions. However, existing methods for fall risk assessment either raise privacy concerns due to sensors installed in the environment or require multiple wearable devices, limiting their practicality for home-based applications and long-term monitoring. In this paper, we introduce EgoFall, a real-time privacy-preserving fall risk assessment system. EgoFall utilizes a chest-mounted commercial tracking camera and a carefully designed data pre-processing pipeline to acquire the ego-body motion data of the subject. The data is then fed to a lightweight CNN-Transformer model for fall risk assessment. To evaluate the proposed method, we establish the EgoWalk dataset, which includes four walking patterns: normal, anterior-posterior instability, medial-lateral instability, and combined instability. Experimental results show that EgoFall achieves an accuracy exceeding 95% on the EgoWalk dataset, outperforming baseline methods while maintaining low computational complexity. Additionally, a series of ablation studies explore the impact of fine-tuning data and error analysis, further highlighting EgoFall’s practicality in real-world applications.