Wentao Ai

Wentao Ai

Auto-generated profile, based on publicly available information

Wentao Ai

School of Information Science and Engineering, Shandong University, Qingdao, China

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
19 December 2023 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
JLJianjun Li
Jianjun Li
Hongji XuHongji Xu
Hongji Xu
JZJiaqi Zeng
Jiaqi Zeng
WAWentao Ai
Wentao Ai
SLShijie Li
Shijie Li
XLXinya Li
Xinya Li
Over the past few years, radar-based human activity recognition (HAR) has emerged as a prominent research area. The typical approach involves converting radar data into image data, such as micro-Doppler images, and then feeding them into networks for activity classification. However, relying solely on a single type of feature may restrict the ability of the networks to recognize activities accurately. To address this limitation and make the most of spatiotemporal features in the data, a dual-stream spatial and temporal feature fusion (DSTFF) network that leverages attention mechanism is proposed, which comprises a temporal feature extraction patial feature extraction stream (SFES) network. Additionally, a coordinates-based spatial attention mechanism (CSAM) is introduced to enhance the accuracy and efficiency of extracting deep spatial features. It focuses on the key spatial information from both horizontal and vertical directions of the feature map, which means range and velocity information in reality, respectively. Furthermore, it effectively connects the information across each channel. Meanwhile, a radar HAR (RadHAR) dataset based on two-dimensional (2D) and three-dimensional (3D) data is created by using a millimeter-wave radar. The evaluation experiments of the CSAM and the DSTFF network are carried out on the public dataset collected by the University of Glasgow (UOG) and the RadHAR dataset, respectively. The experimental results show that the CSAM exhibits strong generalization ability, and the DSTFF network presents effectiveness and superiority with the accuracy of 97.10%, which is higher than those of the classical and state-of-the-art networks.

5 November 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XLXinya Li
Xinya Li
Hongji XuHongji Xu
Hongji Xu
YWYang Wang
Yang Wang
JZJiaqi Zeng
Jiaqi Zeng
YLYiran Li
Yiran Li
YDYupeng Duan
Yupeng Duan
As the Internet of Things (IoT) technology advances, human activity recognition (HAR) using IoT devices, including wearable sensors has become prevalent in various applications. Nevertheless, many sensor-based HAR methods still struggle to balance recognition accuracy with network complexity. Meanwhile, most existing sensor-based HAR networks fail to achieve an effective fusion of multidimensional features. To address the above issues, a hierarchical multiscale time-frequency and channel feature adaptive fusion (HMTF-CFAF) network is put forward. The HMTF-CFAF efficiently extracts unique multiscale time-frequency and channel features in sensor data using hierarchical connectivity. Furthermore, it incorporates a feature fusion mechanism to integrate and exchange multiscale and multidimensional features, providing more comprehensive and richer features. To evaluate the HMTF-CFAF network, we utilize three datasets: 1) the University of California Irvine HAR (UCI-HAR); 2) physical activity monitoring for aging people (PAMAP2); and 3) self-collected household behavior (HB) dataset. The HMTF-CFAF network achieves the accuracies of 97.66%, 98.75%, and 98.80% on the above three datasets, respectively, demonstrating its excellent performance.

11 November 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
WAWentao Ai
Wentao Ai
Hongji XuHongji Xu
Hongji Xu
JLJianjun Li
Jianjun Li
XLXiaoman Li
Xiaoman Li
XLXinya Li
Xinya Li
YYYonghui Yu
Yonghui Yu
Due to the flourishing of Internet of Things (IoT) technology, radar-based human activity recognition (HAR) technology has made significant progress and has become an indispensable research area. Many radar systems use multiple feature maps and handle them directly in image format. However, the generation of multiple forms of feature maps requires heavy computational resources, which makes it impractical for real-world applications. Additionally, many networks fail to fully extract temporal information from the time-Doppler (TD) map during the feature extraction. Therefore, a time-weighted network based on strip pooling (TWN-SP) using the TD map is proposed in this article. The TWN-SP consists of two time-weighted modules based on fire (TWMs-F) and a feature fusion module based on temporal and channel attention (FFM-TCA). Due to the application of depthwise separable convolution (DSC) and placing the feature fusion step at the forefront, the proposed network has fewer parameters. Moreover, a radar dataset named RadSet is constructed, containing TD maps of six daily activities. To validate the performance of the TWN-SP, a ten-fold cross-validation (CV) on the public dataset named Radar848 and a leave-one-subject-out (LOSO) CV on the RadSet dataset are carried out, respectively. To further validate the generalization performance of TWN-SP, a comparative analysis was conducted on another public dataset, Ci4R. The TWN-SP achieves an accuracy of 99.28% on the RadSet dataset. Experimental results indicate that the TWN-SP surpasses the current leading networks in both performance and complexity.

4 July 2025 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
ZXZhikai Xu
Zhikai Xu
Hongji XuHongji Xu
Hongji Xu
WAWentao Ai
Wentao Ai
YYYonghui Yu
Yonghui Yu
YDYupeng Duan
Yupeng Duan
PTPeiquan Tian
Peiquan Tian
Developing efficient and robust millimeter-wave (mmWave) radar human activity recognition (HAR) networks for real-world applications presents significant challenges. Key difficulties include managing network complexity and maintaining stable performance across datasets with substantial variations in scale or imbalanced class distributions. Additionally, many current networks fail to fully leverage the latent information contained in micro-Doppler (MD) signatures. To address these issues, this article proposes the masked concatenation with gated convolution and linear unit (MC-GCLU) network, which aims to improve the accuracy and robustness of radar-based HAR. The MC-GCLU network utilizes MD signatures as input. The network consists of the masked concatenation (MC) module and the gated convolution and linear unit (GCLU) module, which features the pyramid structure. This design achieves computational efficiency, requiring only 0.06 G floating-point operations (FLOPs). Through comparative experiments on the public datasets IMG848, Ci4R, and the self-constructed RadarMD dataset, the MC-GCLU network achieved accuracies of 96.33%, 82.93%, and 97.40%, respectively. To further assess the effectiveness of the individual modules within the MC-GCLU network, ablation experiments are conducted, and hyperparameters, including the mask rate and batch size, are optimized. The experimental results showcase that the MC-GCLU network achieves competitive performance without pretraining, exhibiting strong generalization capabilities and demonstrating a favorable balance between accuracy and efficiency.