Pengxin Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pengxin Ren has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Lishuai Xie
Jiangsu Key Laboratory of Advanced Structural Materials and Application Technology, Nanjing Institute of Technology, Nanjing 211167, China
1 shared publication - Pei He
School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
1 shared publication - Xiaodong Wang
Ningbo Institute of Northwestern Polytechnical University, Ningbo 315103, China
1 shared publication - Yangming Guo
Northwestern Polytechnical University, Xi'an, China
1 shared publication - Yuyan Wang
College of Computer and Information Science, Guangdong University of Technology, Guangzhou 510006, China
1 shared publication
Latest Publications
- Open Access
AWARE-Net: A Lightweight Joint Optimization Framework for Robust Sensor-Based Human Activity Recognition
Sensor-based human activity recognition (SHAR) serves as a core research direction in pervasive computing, mobile health, and related fields. Although existing deep learning methods have achieved promising progress in SHAR tasks, most optimize from a single dimension only. They struggle to simultaneously balance recognition accuracy, noise robustness, adaptation to class imbalance, and lightweight deployment requirements, leading to performance bottlenecks in real-world scenarios. To address these challenges, this paper proposes a lightweight joint optimization framework named AWARE-Net. Leveraging the lightweight TS-ResNet as a backbone encoder, the framework integrates spatiotemporal dynamic convolution feature encoding with a global loss function that fuses class-balanced loss, contrastive learning auxiliary loss, and temporal smooth regularization to achieve multi-objective joint optimization. Extensive experiments on three widely used SHAR benchmark datasets, namely OPPORTUNITY, PAMAP2, and USC-HAD, demonstrate that the proposed AWARE-Net achieves competitive performance compared with representative state-of-the-art HAR methods.
Open AccessAWARE-Net: A Lightweight Joint Optimization Framework for Robust Sensor-Based Human Activity Recognition
Sensor-based human activity recognition (SHAR) serves as a core research direction in pervasive computing, mobile health, and related fields. Although existing deep learning methods have achieved promising progress in SHAR tasks, most optimize from a single dimension only. They struggle to simultaneously balance recognition accuracy, noise robustness, adaptation to class imbalance, and lightweight deployment requirements, leading to performance bottlenecks in real-world scenarios. To address these challenges, this paper proposes a lightweight joint optimization framework named AWARE-Net. Leveraging the lightweight TS-ResNet as a backbone encoder, the framework integrates spatiotemporal dynamic convolution feature encoding with a global loss function that fuses class-balanced loss, contrastive learning auxiliary loss, and temporal smooth regularization to achieve multi-objective joint optimization. Extensive experiments on three widely used SHAR benchmark datasets, namely OPPORTUNITY, PAMAP2, and USC-HAD, demonstrate that the proposed AWARE-Net achieves competitive performance compared with representative state-of-the-art HAR methods.