Wenbo Ding
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
Wenbo Ding has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
Fang Yang
Department of Electronic Engineering, Tsinghua University, Beijing, China
7 shared publicationsJian Song
7 shared publicationsChangyong Pan
Department of Electronic Engineering, Tsinghua University, Beijing, China
2 shared publications- Fang Yang
Department of Electronic Engineering, Tsinghua University, Beijing, China
2 shared publications - Haoyang Wang
Tsinghua University
2 shared publications - Jian Song
Tsinghua University
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12222-12231
Don't Just Classify, Compare: Evidence-Driven Multimodal Experts Framework for Fake News Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12222-12231
Open AccessDon't Just Classify, Compare: Evidence-Driven Multimodal Experts Framework for Fake News Detection
- Open Access
- 8 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 743-748
CaliFormer: Leveraging Unlabeled Measurements to Calibrate Sensors with Self-supervised Learning
Accurate calibration of low-cost sensors is critical for improving their potential in environmental monitoring. State-of-the-art (SOTA) methods based on supervised learning commonly calibrate sensor measurements with ground truth from the immediate past or future. However, these techniques rely heavily on labeled data which is challenging to obtain in real-world scenarios. Thus, this paper introduces CaliFormer, a novel representation learning model using self-supervised learning to extract time- and spatial-invariant knowledge from unlabeled measurements. Moreover, we propose pre-training enhancements and model architecture modifications to help train CaliFormer. We then fine-tune the calibration model with the learned representations, which is supervised by limited labeled data. Finally, we comprehensively evaluate our calibration model with a dataset collected by low-cost sensors. Results show that our model outperforms other SOTA calibration methods significantly.
- 8 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 743-748
Open AccessCaliFormer: Leveraging Unlabeled Measurements to Calibrate Sensors with Self-supervised Learning
Accurate calibration of low-cost sensors is critical for improving their potential in environmental monitoring. State-of-the-art (SOTA) methods based on supervised learning commonly calibrate sensor measurements with ground truth from the immediate past or future. However, these techniques rely heavily on labeled data which is challenging to obtain in real-world scenarios. Thus, this paper introduces CaliFormer, a novel representation learning model using self-supervised learning to extract time- and spatial-invariant knowledge from unlabeled measurements. Moreover, we propose pre-training enhancements and model architecture modifications to help train CaliFormer. We then fine-tune the calibration model with the learned representations, which is supervised by limited labeled data. Finally, we comprehensively evaluate our calibration model with a dataset collected by low-cost sensors. Results show that our model outperforms other SOTA calibration methods significantly.
- Open Access
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 306-307
Poster Abstract: TENG-enabled Self-powered Human-machine Interfaces for the Metaverse | Proceedings of the 22nd International Conference on Information Processing in Sensor Networks
Human-machine interface (HMI) of high degrees of freedom (DoF) is one of the most critical bases of the metaverse. The ideal HMI for the metaverse should be cheap, robust, customizable, and ergonomically friendly. In light of this, we propose a triboelectric nanogenerator (TENG)-based sensing system. We developed a low-cost, soft, light, and customizable TENG sensor to collect data from the human body. We then used an artificial neural network (ANN) to obtain the corresponding human motion from collected sensory data. The effectiveness of the proposed system is demonstrated with experiments of a working prototype.
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 306-307
Open AccessPoster Abstract: TENG-enabled Self-powered Human-machine Interfaces for the Metaverse | Proceedings of the 22nd International Conference on Information Processing in Sensor Networks
Human-machine interface (HMI) of high degrees of freedom (DoF) is one of the most critical bases of the metaverse. The ideal HMI for the metaverse should be cheap, robust, customizable, and ergonomically friendly. In light of this, we propose a triboelectric nanogenerator (TENG)-based sensing system. We developed a low-cost, soft, light, and customizable TENG sensor to collect data from the human body. We then used an artificial neural network (ANN) to obtain the corresponding human motion from collected sensory data. The effectiveness of the proposed system is demonstrated with experiments of a working prototype.
- 15 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 5 (6) , 4550-4557
Intercommunity Detection Scheme for Social Internet of Things: Compressive Sensing Over Graphs Approach
As a cluster between Internet of Things (IoT) and mobile social networks (MSN), social IoT allows close interaction between humans and things. Many applications of IoT and MSN are based on the community structure to realize efficient services, and thus the detection of the community structure has become a key problem and attracted much academic attention. In this paper, a compressive sensing (CS) over graphs based inter-community detection scheme is proposed for the social IoT. By exploiting the probability of two nodes encountering each other, the encounter probability and the edge-clustering coefficient are utilized to define a novel metric for each connection and construct the measurement matrix. Then a CS based detection algorithm is proposed to detect the inter-community links. Moreover, the edge-clustering coefficient is exploited as the prior information to further improve accuracy and reduce complexity. Simulations show that the proposed detection scheme outperforms the conventional random walk based scheme in the social IoT.
- 15 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 5 (6) , 4550-4557
Intercommunity Detection Scheme for Social Internet of Things: Compressive Sensing Over Graphs Approach
As a cluster between Internet of Things (IoT) and mobile social networks (MSN), social IoT allows close interaction between humans and things. Many applications of IoT and MSN are based on the community structure to realize efficient services, and thus the detection of the community structure has become a key problem and attracted much academic attention. In this paper, a compressive sensing (CS) over graphs based inter-community detection scheme is proposed for the social IoT. By exploiting the probability of two nodes encountering each other, the encounter probability and the edge-clustering coefficient are utilized to define a novel metric for each connection and construct the measurement matrix. Then a CS based detection algorithm is proposed to detect the inter-community links. Moreover, the edge-clustering coefficient is exploited as the prior information to further improve accuracy and reduce complexity. Simulations show that the proposed detection scheme outperforms the conventional random walk based scheme in the social IoT.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Hierarchical Game Approach for Visible Light Communication and D2D Heterogeneous Network
The visible light communication (VLC) technology is able to provide indoor users with high quality of service and low cost. However, the performance of the VLC is limited in shaded or strong sun- light areas. In this paper, we combine the VLC network with Device-to-Device (D2D) technology. We consider that some mobile users accessible to the VLC network is able to relay the transmitted data to the nearby mobile users. We suppose all the mobile users as relays (MUaRs), cellular service provider (CSP) and VLC service provider (VLCSP) are autonomous individuals, and propose a hierarchical game to analyze the optimal strategies for each of them. In the game, the VLCSP determines the data transmission route and data packet size first. Based on the behaviors of the VLCSP, the CSP determines the prices of wireless licensed spectrum. According to the behaviors of the VLCSP, the CSP and the MUaRs in the neighborhood, all MUaRs determines their transmission data rates for optimal utility. Therefore, there is a graphical game among all MUaRs. When all MUaRs consider the corresponding reactions of other MUaRs in the neighborhood and achieve Nash Equilibrium, the Stackelberg Equilibriums can be achieved in the Stackelberg games between the VLCSP and the CSP, between the CSP and all MUaRs and between the VLCSP and all MUaRs. Simulation results show the correctness of the analysis and the VLC network with multi-hop D2D relay is able to bring high profits for the CSP.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Hierarchical Game Approach for Visible Light Communication and D2D Heterogeneous Network
The visible light communication (VLC) technology is able to provide indoor users with high quality of service and low cost. However, the performance of the VLC is limited in shaded or strong sun- light areas. In this paper, we combine the VLC network with Device-to-Device (D2D) technology. We consider that some mobile users accessible to the VLC network is able to relay the transmitted data to the nearby mobile users. We suppose all the mobile users as relays (MUaRs), cellular service provider (CSP) and VLC service provider (VLCSP) are autonomous individuals, and propose a hierarchical game to analyze the optimal strategies for each of them. In the game, the VLCSP determines the data transmission route and data packet size first. Based on the behaviors of the VLCSP, the CSP determines the prices of wireless licensed spectrum. According to the behaviors of the VLCSP, the CSP and the MUaRs in the neighborhood, all MUaRs determines their transmission data rates for optimal utility. Therefore, there is a graphical game among all MUaRs. When all MUaRs consider the corresponding reactions of other MUaRs in the neighborhood and achieve Nash Equilibrium, the Stackelberg Equilibriums can be achieved in the Stackelberg games between the VLCSP and the CSP, between the CSP and all MUaRs and between the VLCSP and all MUaRs. Simulation results show the correctness of the analysis and the VLC network with multi-hop D2D relay is able to bring high profits for the CSP.
- 1 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Compressive sensing based time-frequency joint non-orthogonal multiple access
Non-Orthogonal Multiple Access (NOMA) has been considered to be one of the promising key technologies for future wireless communications and broadcasting return channels due to its high spectral efficiency under massive connectivity. The major challenge of NOMA is to realize interference cancellation and detect the optimal transmitted signals among multiple users. The message passing algorithm (MPA) based multi-user detection (MUD) has been developed to approximate optimal signals from multiple users. However, the conventional MPA always suppose that the user-activity is exactly known at the receiver, which is impractical in real systems. Thus, precise user-activity detection is significant in realizing MPA based NOMA system. In this paper, we propose a compressive sensing based time-frequency joint NOMA scheme in the uplink grant-free low density signature orthogonal frequency division multiplexing (LDS-OFDM) systems, where the priori information obtained from the time-domain m-sequence and the frequency-domain training sequence are utilized for user-activity detection under the framework of CS, while the MPA is performed for the successive user-data detection. The proposed method has a superior performance and less complexity compared to the conventional MPA detector in numerical stimulation.
- 1 June 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Compressive sensing based time-frequency joint non-orthogonal multiple access
Non-Orthogonal Multiple Access (NOMA) has been considered to be one of the promising key technologies for future wireless communications and broadcasting return channels due to its high spectral efficiency under massive connectivity. The major challenge of NOMA is to realize interference cancellation and detect the optimal transmitted signals among multiple users. The message passing algorithm (MPA) based multi-user detection (MUD) has been developed to approximate optimal signals from multiple users. However, the conventional MPA always suppose that the user-activity is exactly known at the receiver, which is impractical in real systems. Thus, precise user-activity detection is significant in realizing MPA based NOMA system. In this paper, we propose a compressive sensing based time-frequency joint NOMA scheme in the uplink grant-free low density signature orthogonal frequency division multiplexing (LDS-OFDM) systems, where the priori information obtained from the time-domain m-sequence and the frequency-domain training sequence are utilized for user-activity detection under the framework of CS, while the MPA is performed for the successive user-data detection. The proposed method has a superior performance and less complexity compared to the conventional MPA detector in numerical stimulation.
- 1 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
NBI cancellation for smart grid communications: A block sparse Bayesian learning perspective
A block sparse Bayesian learning (BSBL) based approach of narrowband interference (NBI) cancellation for cyclic prefixed orthogonal frequency division multiplexing based smart grid communications is proposed in this paper. The BSBL theory is firstly introduced to recover the practical block sparse NBI with a frequency offset compared with the sub-carriers. The block sparse representation of the NBI is constituted through the proposed temporal differential measuring approach. A BSBL based method, estimated partitioned BSBL, is proposed for NBI recovery. The intra-block correlation is firstly considered to facilitate the recovery of block sparse NBI. Reported simulation results demonstrate that the proposed methods are effective and significantly outperform conventional counterparts.
- 1 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
NBI cancellation for smart grid communications: A block sparse Bayesian learning perspective
A block sparse Bayesian learning (BSBL) based approach of narrowband interference (NBI) cancellation for cyclic prefixed orthogonal frequency division multiplexing based smart grid communications is proposed in this paper. The BSBL theory is firstly introduced to recover the practical block sparse NBI with a frequency offset compared with the sub-carriers. The block sparse representation of the NBI is constituted through the proposed temporal differential measuring approach. A BSBL based method, estimated partitioned BSBL, is proposed for NBI recovery. The intra-block correlation is firstly considered to facilitate the recovery of block sparse NBI. Reported simulation results demonstrate that the proposed methods are effective and significantly outperform conventional counterparts.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Study of Training Sequence Design for Channel Estimation Based on Compressive Sensing
Nowadays, orthogonal frequency division multiplexing(OFDM) plays a more and more important role in mobile communications where the training sequence (TS) is usually adopted for synchronization and channel estimation. However, to achieve a channel estimation scheme which has both high accuracy and high spectral efficiency is still challenging due to the high communication capacity demand of the future 5G wireless cellular network. In this paper, by applying the compressive sensing (CS) theory into the channel estimation process with time domain TS, we turn our concentration to the maximum coherence of two different columns of the measurement matrix which determines the reconstruction accuracy. To minimize the coherence of the measurement matrix, we first propose a TS in the form of inverse discrete Fourier transform (IDFT) with cyclic structure based on CS, and then, a genetic algorithm is proposed to further lower the coherence with low complexity. Simulation results show that by using the proposed optimized TS, the system can achieve better channel estimation performance than the conventional TSs obtained by either selected PN sequence or brute force searching sequence in both recovery probability and mean square error, which might be suitable to the physical layer technology in the future 5G communications.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Study of Training Sequence Design for Channel Estimation Based on Compressive Sensing
Nowadays, orthogonal frequency division multiplexing(OFDM) plays a more and more important role in mobile communications where the training sequence (TS) is usually adopted for synchronization and channel estimation. However, to achieve a channel estimation scheme which has both high accuracy and high spectral efficiency is still challenging due to the high communication capacity demand of the future 5G wireless cellular network. In this paper, by applying the compressive sensing (CS) theory into the channel estimation process with time domain TS, we turn our concentration to the maximum coherence of two different columns of the measurement matrix which determines the reconstruction accuracy. To minimize the coherence of the measurement matrix, we first propose a TS in the form of inverse discrete Fourier transform (IDFT) with cyclic structure based on CS, and then, a genetic algorithm is proposed to further lower the coherence with low complexity. Simulation results show that by using the proposed optimized TS, the system can achieve better channel estimation performance than the conventional TSs obtained by either selected PN sequence or brute force searching sequence in both recovery probability and mean square error, which might be suitable to the physical layer technology in the future 5G communications.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Structured Compressed Sensing Based NBI Recovery for MIMO WLAN Systems
Narrowband interference (NBI) is a major concern that constrains the performance and development of wireless local area network (WLAN) systems. Compressed sensing (CS) is a new and powerful signal processing technique that is applied to solve this problem in this paper. In the framework of structured CS (SCS), we investigated the multiple input multiple output (MIMO) WLAN system, and proposed a novel NBI recovery method based on spatial multiple differential measuring (SMDM). At each receive antenna, a differential measurement vector is acquired from the repeated training sequences in the IEEE 802.11 preamble. Then multiple measurement vectors from each receive antenna are utilized for NBI recovery using the proposed SCS greedy algorithm, i.e. structured sparsity adaptive matching pursuit (S-SAMP). Simulation results indicate that the proposed scheme outperforms conventional ones over the MIMO wireless channel.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Structured Compressed Sensing Based NBI Recovery for MIMO WLAN Systems
Narrowband interference (NBI) is a major concern that constrains the performance and development of wireless local area network (WLAN) systems. Compressed sensing (CS) is a new and powerful signal processing technique that is applied to solve this problem in this paper. In the framework of structured CS (SCS), we investigated the multiple input multiple output (MIMO) WLAN system, and proposed a novel NBI recovery method based on spatial multiple differential measuring (SMDM). At each receive antenna, a differential measurement vector is acquired from the repeated training sequences in the IEEE 802.11 preamble. Then multiple measurement vectors from each receive antenna are utilized for NBI recovery using the proposed SCS greedy algorithm, i.e. structured sparsity adaptive matching pursuit (S-SAMP). Simulation results indicate that the proposed scheme outperforms conventional ones over the MIMO wireless channel.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21647038,p. 2375-2380
Structured compressive sensing based narrowband interference mitigation for vehicular communications
In this paper, a novel narrowband interference (NBI) cancellation scheme based on structured compressive sensing (SCS) for dependable vehicular communications systems is proposed. The temporal joint correlation of the repeated training sequences in the preamble are exploited by SCS-based differential measuring (SCS-DM) to acquire the joint measurements matrix of the NBI. Using the proposed structured sparsity adaptive matching pursuit (S-SAMP) algorithm, the sparse high-dimensional NBI signal can be accurately recovered and cancelled out at the receiver. Simulation results validate that the proposed SCS-DM approach outperforms conventional CS-based and non-CS-based NBI mitigation schemes under wireless vehicular channels.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21647038,p. 2375-2380
Structured compressive sensing based narrowband interference mitigation for vehicular communications
In this paper, a novel narrowband interference (NBI) cancellation scheme based on structured compressive sensing (SCS) for dependable vehicular communications systems is proposed. The temporal joint correlation of the repeated training sequences in the preamble are exploited by SCS-based differential measuring (SCS-DM) to acquire the joint measurements matrix of the NBI. Using the proposed structured sparsity adaptive matching pursuit (S-SAMP) algorithm, the sparse high-dimensional NBI signal can be accurately recovered and cancelled out at the receiver. Simulation results validate that the proposed SCS-DM approach outperforms conventional CS-based and non-CS-based NBI mitigation schemes under wireless vehicular channels.