Zechen Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zechen Li has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Kun Wang
School of Computer Science, Nanjing Audit University, Nanjing, China
3 shared publications - Lei Zhang
School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, China
3 shared publications - Aiguo Song
Southeast University
2 shared publications - Guangjie Chen
School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, China
2 shared publications Qifan Sun
School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, China
2 shared publicationsHao Wu
School of Information Science and Engineering, Yunnan University, Kunming, China
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47603-47620
Unsupervised Sensor-Based Human Activity Recognition via Contrastive Learning of Representation
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47603-47620
Unsupervised Sensor-Based Human Activity Recognition via Contrastive Learning of Representation
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (15) , 1
TSA-Former: Linear Transformer with Taylor Series Attention for Sensor-Based Human Activity Recognition
Transformer models have demonstrated superior capability in capturing long-range temporal dependencies crucial for Sensor-Based Human Activity Recognition (HAR). However, the quadratic computational complexity inherent to the Softmax-Attention mechanism significantly impedes their deployment on resource-constrained wearable devices and real-time streaming tasks. To address this, we propose a novel Linear Transformer with Taylor Series Attention specifically tailored for the HAR domain, named TSA-Former. It leverages the first-order Taylor expansion to approximate the Softmax-Attention and utilizes the norm-preserving mapping to approximate the high-order non-linear information, resulting in a linear computational complexity. In addition, TSA-Former integrates a multi-branch architecture featuring multi-scale patch embedding, which enables the model to dynamically capture multi-scale temporal features while minimizing overhead. Experimental results across four public HAR benchmarks, namely UniMiB-SHAR, UCI-HAR, WISDM, and OPPORTUNITY, demonstrate that TSA-Former achieves state-of-the-art (SOTA) accuracy and efficiency, outperforming conventional Transformers and existing linear-attention models. Deployment experiments conducted on the Raspberry Pi 5 platform further validate the model’s superior low-latency and minimal power consumption profile, confirming its robust suitability for real-world embedded HAR applications. Code will be released.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (15) , 1
TSA-Former: Linear Transformer with Taylor Series Attention for Sensor-Based Human Activity Recognition
Transformer models have demonstrated superior capability in capturing long-range temporal dependencies crucial for Sensor-Based Human Activity Recognition (HAR). However, the quadratic computational complexity inherent to the Softmax-Attention mechanism significantly impedes their deployment on resource-constrained wearable devices and real-time streaming tasks. To address this, we propose a novel Linear Transformer with Taylor Series Attention specifically tailored for the HAR domain, named TSA-Former. It leverages the first-order Taylor expansion to approximate the Softmax-Attention and utilizes the norm-preserving mapping to approximate the high-order non-linear information, resulting in a linear computational complexity. In addition, TSA-Former integrates a multi-branch architecture featuring multi-scale patch embedding, which enables the model to dynamically capture multi-scale temporal features while minimizing overhead. Experimental results across four public HAR benchmarks, namely UniMiB-SHAR, UCI-HAR, WISDM, and OPPORTUNITY, demonstrate that TSA-Former achieves state-of-the-art (SOTA) accuracy and efficiency, outperforming conventional Transformers and existing linear-attention models. Deployment experiments conducted on the Raspberry Pi 5 platform further validate the model’s superior low-latency and minimal power consumption profile, confirming its robust suitability for real-world embedded HAR applications. Code will be released.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (7) , 14923-14939
Beyond 1 × 1 Convolutions: A Dynamic Select-and-Fuse Channel Sampling Strategy for On-Device Human Activity Recognition
The proliferation of low-cost, portable sensors has made wearable human activity recognition (HAR) a cornerstone for real-time health monitoring and behavior analysis. However, deploying accurate yet lightweight deep learning models on resource-constrained wearable devices poses a significant challenge for on-device activity recognition. While channel pruning is a common solution to accelerate deep convolutional neural networks (CNNs), existing works often require specialized implementations or pretrained models, which potentially degrade performance by simply removing an entire channel, limiting their ability to handle complex multimodal sensor inputs. Moreover, lightweight CNN design, particularly the heavy use of $1\times 1$ convolution layers for channel squeezing, remains inefficient for sensor-based HAR, which consumes resources without expanding the receptive field due to their pointwise nature. To address these issues, we propose a novel dynamic channel sampling module, select-and-fuse (SaF), specifically designed for sensor-based HAR. SaF divides channels into subsets and performs a dynamic, input-dependent selection from them, with the picking decision being made per time step based on the input sensor signal activations, allowing for fine-grained feature adaptation to multimodal sensor signals. While integrated into compact backbones, SaF significantly reduces model size and inference latency while maintaining high accuracy. Extensive evaluations on public UCI-HAR, OPPORTUNITY, WISDM, and UniMiB-SHAR benchmarks confirm a favorable performance–cost tradeoff. Crucially, we measure actual inference latency on a Raspberry Pi, proving its practicality for resource-constrained HAR applications. The code will be released.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (7) , 14923-14939
Beyond 1 × 1 Convolutions: A Dynamic Select-and-Fuse Channel Sampling Strategy for On-Device Human Activity Recognition
The proliferation of low-cost, portable sensors has made wearable human activity recognition (HAR) a cornerstone for real-time health monitoring and behavior analysis. However, deploying accurate yet lightweight deep learning models on resource-constrained wearable devices poses a significant challenge for on-device activity recognition. While channel pruning is a common solution to accelerate deep convolutional neural networks (CNNs), existing works often require specialized implementations or pretrained models, which potentially degrade performance by simply removing an entire channel, limiting their ability to handle complex multimodal sensor inputs. Moreover, lightweight CNN design, particularly the heavy use of $1\times 1$ convolution layers for channel squeezing, remains inefficient for sensor-based HAR, which consumes resources without expanding the receptive field due to their pointwise nature. To address these issues, we propose a novel dynamic channel sampling module, select-and-fuse (SaF), specifically designed for sensor-based HAR. SaF divides channels into subsets and performs a dynamic, input-dependent selection from them, with the picking decision being made per time step based on the input sensor signal activations, allowing for fine-grained feature adaptation to multimodal sensor signals. While integrated into compact backbones, SaF significantly reduces model size and inference latency while maintaining high accuracy. Extensive evaluations on public UCI-HAR, OPPORTUNITY, WISDM, and UniMiB-SHAR benchmarks confirm a favorable performance–cost tradeoff. Crucially, we measure actual inference latency on a Raspberry Pi, proving its practicality for resource-constrained HAR applications. The code will be released.