Hao Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hao Wang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Liangyin Chen
Sichuan University
6 shared publications - Shijia Liu
College of Computer Science, Sichuan University, Chengdu, China
3 shared publications - Dasha Hu
College of Computer Science, Sichuan University 3 , Chengdu 610065
2 shared publications - Yanru Chen
College of Computer Science, Sichuan University, Chengdu, China
2 shared publications - Yuming Jiang
Key Laboratory of Digital Protection for Unearthed Medical Literature and Cultural Relics, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China
2 shared publications - Bin Xing
Chongqing Innovation Center of Industrial Big-Data Co., Ltd., Chongqing 400707, China
1 shared publication
Latest Publications
- 28 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 329
DRLVCM: Vehicle-cargo matching via deep reinforcement learning
- 28 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 329
DRLVCM: Vehicle-cargo matching via deep reinforcement learning
- 3 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 5083-5096
Generalizing Wireless Cross-Multiple-Factor Gesture Recognition to Unseen Domains
Cross-domain wireless sensing has always been challenging due to the sensitivity of wireless signals to various environmental factors, which we refer to as subdomains. However, current efforts are limited to cross-one-subdomain tasks requiring target domain data for model training or multiple receivers for data collection. Taking common gesture recognition as an application example, we attempt to demonstrate the feasibility of cross-multiple-subdomain wireless sensing in the more challenging domain generalization (DG) setting. It is possible to extract domain-invariant features from one or several source domain(s), thereby avoiding the need for multiple receivers or target domain data. We also propose an intelligent wireless data augmentation technique based on subdomain-guided perturbations, named WiSGP. Specifically, the independent domain model generates perturbations in the direction of the largest subdomain variations. Then, these subdomain-guided perturbations augment the gesture model's input to enable better domain-invariant feature extraction, even when various subdomains interact. Similarly, gesture-guided perturbations augment the domain model's input, resulting in more accurate subdomain-guided perturbations and minimal gesture label changes. Extensive experiments have been conducted on three datasets collected from various NICs. In terms of room, location, orientation, and user subdomains, WiSGP exhibits excellent accuracy, generalizability, and portability for both cross-one-subdomain and cross-multiple-subdomain tasks.
- 3 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 5083-5096
Generalizing Wireless Cross-Multiple-Factor Gesture Recognition to Unseen Domains
Cross-domain wireless sensing has always been challenging due to the sensitivity of wireless signals to various environmental factors, which we refer to as subdomains. However, current efforts are limited to cross-one-subdomain tasks requiring target domain data for model training or multiple receivers for data collection. Taking common gesture recognition as an application example, we attempt to demonstrate the feasibility of cross-multiple-subdomain wireless sensing in the more challenging domain generalization (DG) setting. It is possible to extract domain-invariant features from one or several source domain(s), thereby avoiding the need for multiple receivers or target domain data. We also propose an intelligent wireless data augmentation technique based on subdomain-guided perturbations, named WiSGP. Specifically, the independent domain model generates perturbations in the direction of the largest subdomain variations. Then, these subdomain-guided perturbations augment the gesture model's input to enable better domain-invariant feature extraction, even when various subdomains interact. Similarly, gesture-guided perturbations augment the domain model's input, resulting in more accurate subdomain-guided perturbations and minimal gesture label changes. Extensive experiments have been conducted on three datasets collected from various NICs. In terms of room, location, orientation, and user subdomains, WiSGP exhibits excellent accuracy, generalizability, and portability for both cross-one-subdomain and cross-multiple-subdomain tasks.
- Open Access
Intelligent Reflecting Surface-Assisted Physical Layer Key Generation with Deep Learning in MIMO Systems
Physical layer secret key generation (PLKG) is a promising technology for establishing effective secret keys. Current works for PLKG mostly study key generation schemes in ideal communication environments with little or even no signal interference. In terms of this issue, exploiting the reconfigurable intelligent reflecting surface (IRS) to assist PLKG has caused an increasing interest. Most IRS-assisted PLKG schemes focus on the single-input-single-output (SISO), which is limited in future communications with multi-input-multi-output (MIMO). However, MIMO could bring a serious overhead of channel reciprocity extraction. To fill the gap, this paper proposes a novel low-overhead IRS-assisted PLKG scheme with deep learning in the MIMO communications environments. We first combine the direct channel and the reflecting channel established by the IRS to construct the channel response function, and we propose a theoretically optimal interaction matrix to approach the optimal achievable rate. Then we design a channel reciprocity-learning neural network with an IRS introduced (IRS-CRNet), which is exploited to extract the channel reciprocity in time division duplexing (TDD) systems. Moreover, a PLKG scheme based on the IRS-CRNet is proposed. Final simulation results verify the performance of the PLKG scheme based on the IRS-CRNet in terms of key generation rate, key error rate and randomness.
Open AccessIntelligent Reflecting Surface-Assisted Physical Layer Key Generation with Deep Learning in MIMO Systems
Physical layer secret key generation (PLKG) is a promising technology for establishing effective secret keys. Current works for PLKG mostly study key generation schemes in ideal communication environments with little or even no signal interference. In terms of this issue, exploiting the reconfigurable intelligent reflecting surface (IRS) to assist PLKG has caused an increasing interest. Most IRS-assisted PLKG schemes focus on the single-input-single-output (SISO), which is limited in future communications with multi-input-multi-output (MIMO). However, MIMO could bring a serious overhead of channel reciprocity extraction. To fill the gap, this paper proposes a novel low-overhead IRS-assisted PLKG scheme with deep learning in the MIMO communications environments. We first combine the direct channel and the reflecting channel established by the IRS to construct the channel response function, and we propose a theoretically optimal interaction matrix to approach the optimal achievable rate. Then we design a channel reciprocity-learning neural network with an IRS introduced (IRS-CRNet), which is exploited to extract the channel reciprocity in time division duplexing (TDD) systems. Moreover, a PLKG scheme based on the IRS-CRNet is proposed. Final simulation results verify the performance of the PLKG scheme based on the IRS-CRNet in terms of key generation rate, key error rate and randomness.
- Open Access
Semi-Supervised Instance-Segmentation Model for Feature Transfer Based on Category Attention
In the task of image instance segmentation, semi-supervised instance segmentation algorithms have received constant research attention over recent years. Among these algorithms, algorithms based on transfer learning are better than algorithms based on pseudo-label generation in terms of segmentation performance, but they can not make full use of the relevant characteristics of source tasks. To improve the accuracy of these algorithms, this work proposes a semi-supervised instance segmentation model AFT-Mask (attention-based feature transfer Mask R-CNN) based on category attention. The AFT-Mask model takes the result of object-classification prediction as “attention” to improve the performance of the feature-transfer module. In detail, we designed a migration-optimization module for connecting feature migration and classification prediction to enhance segmentation-prediction accuracy. To verify the validity of the AFT-Mask model, experiments were conducted on two types of datasets. Experimental results show that the AFT-Mask model can achieve effective knowledge transfer and improve the performance of the benchmark model on semi-supervised instance segmentation.
Open AccessSemi-Supervised Instance-Segmentation Model for Feature Transfer Based on Category Attention
In the task of image instance segmentation, semi-supervised instance segmentation algorithms have received constant research attention over recent years. Among these algorithms, algorithms based on transfer learning are better than algorithms based on pseudo-label generation in terms of segmentation performance, but they can not make full use of the relevant characteristics of source tasks. To improve the accuracy of these algorithms, this work proposes a semi-supervised instance segmentation model AFT-Mask (attention-based feature transfer Mask R-CNN) based on category attention. The AFT-Mask model takes the result of object-classification prediction as “attention” to improve the performance of the feature-transfer module. In detail, we designed a migration-optimization module for connecting feature migration and classification prediction to enhance segmentation-prediction accuracy. To verify the validity of the AFT-Mask model, experiments were conducted on two types of datasets. Experimental results show that the AFT-Mask model can achieve effective knowledge transfer and improve the performance of the benchmark model on semi-supervised instance segmentation.
- 3 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 3077-3090
A Low-Calculation Contactless Continuous Authentication Based on Postural Transition
Currently, available contactless continuous authentication (CA) techniques depend on physiological biometrics to identify individuals at long intervals through complex feature extraction, resulting in poor accuracy, high computation costs, and security vacuums during lengthy intervals. To address these issues, we propose WiPT, a WiFi-based contactless CA system that utilizes contextual features and behavioral biometrics to optimize contactless CA technology. Specifically, we designed a low-computation two-step user state detection (TUSD) mechanism that continuously monitors user states in real-time. It locks the system when the registered user leaves and allows user authentication only when the departing user returns. Therefore, it eliminates pointless periodic re-authentication and results in considerably shorter monitoring intervals while significantly reducing computation. Subsequently, benefiting from contextual features, WiPT can identify individuals using more detectable behavioral biometrics. We built a one-class classification model based on the Convolutional Autoencoder to automatically extract rich representations of WiFi signals associated with postural transition movements, resulting in lower authentication delay, higher accuracy, and anti-interference. WiPT was implemented by the widely available 802.11n devices and has been extensively evaluated with typical sit-to-stand postural transitions. WiPT achieves an average accuracy of 96.63% in authentication and 99.78% in defense across 30 subjects with an authentication delay of 5.59 milliseconds and a monitoring interval of 2 seconds. They are 4.87% and 5.03% more accurate and dozens of times less time-consuming than existing WiFi-based CA solutions.
- 3 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 3077-3090
A Low-Calculation Contactless Continuous Authentication Based on Postural Transition
Currently, available contactless continuous authentication (CA) techniques depend on physiological biometrics to identify individuals at long intervals through complex feature extraction, resulting in poor accuracy, high computation costs, and security vacuums during lengthy intervals. To address these issues, we propose WiPT, a WiFi-based contactless CA system that utilizes contextual features and behavioral biometrics to optimize contactless CA technology. Specifically, we designed a low-computation two-step user state detection (TUSD) mechanism that continuously monitors user states in real-time. It locks the system when the registered user leaves and allows user authentication only when the departing user returns. Therefore, it eliminates pointless periodic re-authentication and results in considerably shorter monitoring intervals while significantly reducing computation. Subsequently, benefiting from contextual features, WiPT can identify individuals using more detectable behavioral biometrics. We built a one-class classification model based on the Convolutional Autoencoder to automatically extract rich representations of WiFi signals associated with postural transition movements, resulting in lower authentication delay, higher accuracy, and anti-interference. WiPT was implemented by the widely available 802.11n devices and has been extensively evaluated with typical sit-to-stand postural transitions. WiPT achieves an average accuracy of 96.63% in authentication and 99.78% in defense across 30 subjects with an authentication delay of 5.59 milliseconds and a monitoring interval of 2 seconds. They are 4.87% and 5.03% more accurate and dozens of times less time-consuming than existing WiFi-based CA solutions.
- Open Access
- 8 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 5855
ASAD: Adaptive Seasonality Anomaly Detection Algorithm under Intricate KPI Profiles
Anomaly detection is the foundation of intelligent operation and maintenance (O&M), and detection objects are evaluated by key performance indicators (KPIs). For almost all computer O&M systems, KPIs are usually the machine-level operating data. Moreover, these high-frequency KPIs show a non-Gaussian distribution and are hard to model, i.e., they are intricate KPI profiles. However, existing anomaly detection techniques are incapable of adapting to intricate KPI profiles. In order to enhance the performance under intricate KPI profiles, this study presents a seasonal adaptive KPI anomaly detection algorithm ASAD (Adaptive Seasonality Anomaly Detection). We also propose a new eBeats clustering algorithm and calendar-based correlation method to further reduce the detection time and error. Through experimental tests, our ASAD algorithm has the best overall performance compared to other KPI anomaly detection methods.
- 8 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (12) , 5855
Open AccessASAD: Adaptive Seasonality Anomaly Detection Algorithm under Intricate KPI Profiles
Anomaly detection is the foundation of intelligent operation and maintenance (O&M), and detection objects are evaluated by key performance indicators (KPIs). For almost all computer O&M systems, KPIs are usually the machine-level operating data. Moreover, these high-frequency KPIs show a non-Gaussian distribution and are hard to model, i.e., they are intricate KPI profiles. However, existing anomaly detection techniques are incapable of adapting to intricate KPI profiles. In order to enhance the performance under intricate KPI profiles, this study presents a seasonal adaptive KPI anomaly detection algorithm ASAD (Adaptive Seasonality Anomaly Detection). We also propose a new eBeats clustering algorithm and calendar-based correlation method to further reduce the detection time and error. Through experimental tests, our ASAD algorithm has the best overall performance compared to other KPI anomaly detection methods.
- 1 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 129-133
Resource Allocation Mechanism with the Base Station Assistance in New Radio-Vehicle
The radio resource selection in vehicular-to-vehicular (V2V) communication is essential because the vehicle has to select the appropriate resource block to send the information under the broadcast scenario. When buildings obscure the V2V link, it will bring the problem of the hidden station, which means the transmitters may use the same radio resource as the hidden station, affecting the correct reception ratio of the data packet. To solve this problem, we propose the base station-assisted information acquisition mechanism and two steps exclusion of occupied resources mechanism to improve the resource allocation performance. The simulation results show that the success rate of V2V communication can be improved by using our base station assistance mechanism.
- 1 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 129-133
Resource Allocation Mechanism with the Base Station Assistance in New Radio-Vehicle
The radio resource selection in vehicular-to-vehicular (V2V) communication is essential because the vehicle has to select the appropriate resource block to send the information under the broadcast scenario. When buildings obscure the V2V link, it will bring the problem of the hidden station, which means the transmitters may use the same radio resource as the hidden station, affecting the correct reception ratio of the data packet. To solve this problem, we propose the base station-assisted information acquisition mechanism and two steps exclusion of occupied resources mechanism to improve the resource allocation performance. The simulation results show that the success rate of V2V communication can be improved by using our base station assistance mechanism.
- Open Access
- 11 January 2017
- Published by Wiley in Journal of Sensors
- Vol. 2017, 1-8
Trajectory-Based Hierarchical Adaptive Forwarding in Vehicular Ad Hoc Networks
This paper proposes a Trajectory-Based Hierarchical Adaptive Forwarding (THAF) scheme, tailored and optimized for the efficient multihop vehicle-to-vehicle (v2v) data delivery in vehicular ad hoc networks. We utilize the trajectories of vehicles provided by GPS-based navigation systems to predict forward delay and access area in a privacy-preserving manner. Different from existing trajectory-based forwarding schemes, we establish a hierarchical VANET topology to optimize forwarding path and adopt adaptive diffusion strategy to forward data in light-traffic situations. Through theoretical analysis and extensive simulation, it is shown that our design performs better than the existing schemes.
- 11 January 2017
- Published by Wiley in Journal of Sensors
- Vol. 2017, 1-8
Open AccessTrajectory-Based Hierarchical Adaptive Forwarding in Vehicular Ad Hoc Networks
This paper proposes a Trajectory-Based Hierarchical Adaptive Forwarding (THAF) scheme, tailored and optimized for the efficient multihop vehicle-to-vehicle (v2v) data delivery in vehicular ad hoc networks. We utilize the trajectories of vehicles provided by GPS-based navigation systems to predict forward delay and access area in a privacy-preserving manner. Different from existing trajectory-based forwarding schemes, we establish a hierarchical VANET topology to optimize forwarding path and adopt adaptive diffusion strategy to forward data in light-traffic situations. Through theoretical analysis and extensive simulation, it is shown that our design performs better than the existing schemes.