Junsheng Mu

ORCID: 0000-0002-5352-8314
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Cognitive Radio Networks and Spectrum Sensing
  • Radar Systems and Signal Processing
  • Indoor and Outdoor Localization Technologies
  • Wireless Signal Modulation Classification
  • Distributed Sensor Networks and Detection Algorithms
  • PAPR reduction in OFDM
  • Telecommunications and Broadcasting Technologies
  • Privacy-Preserving Technologies in Data
  • Blind Source Separation Techniques
  • Advanced MIMO Systems Optimization
  • Sparse and Compressive Sensing Techniques
  • Speech and Audio Processing
  • UAV Applications and Optimization
  • Advanced Wireless Communication Technologies
  • Millimeter-Wave Propagation and Modeling
  • Energy Efficient Wireless Sensor Networks
  • EEG and Brain-Computer Interfaces
  • Advanced Adaptive Filtering Techniques
  • Advanced SAR Imaging Techniques
  • Wireless Communication Security Techniques
  • Blockchain Technology Applications and Security
  • Direction-of-Arrival Estimation Techniques
  • Satellite Communication Systems
  • Underwater Vehicles and Communication Systems
  • Face and Expression Recognition

Beijing University of Posts and Telecommunications
2016-2025

University of Southampton
2022

China Electronics Technology Group Corporation
2022

ORCID
2020

Shanghai Key Laboratory of Trustworthy Computing
2019

Sichuan Normal University
2013

Recent advances in wireless communication and solid-state circuits together with the enormous demands of sensing ability have given rise to a new enabling technology, integrated (radar) (ISAC). ISAC captures two main advantages over dedicated functionalities: integration gain efficiently utilize congested wireless/hardware resources, even more interesting, coordination balance dual-functional performance or/and perform mutual assistance. Triggered by ISAC, we are also witnessing paradigm...

10.1109/mnet.010.2100152 article EN IEEE Network 2021-09-01

Currently, sensing and communication are two indispensable functions in the UAV platform while these modules independent hardware. However, similarities between them seem a growing trend, such as hardware, channel characteristics, signal processing methods, etc. Integrated (ISAC) has been hot topic to alleviate issue of low spectrum efficiency pursuit hardware gain integration far possible. As vital for functions, is facing great potential development when meeting ISAC. If ISAC load replaces...

10.1109/mcom.008.2200510 article EN IEEE Communications Magazine 2023-01-02

Currently, developments in wireless sensing technologies have shown that signals can be employed to transmit information between communication devices and are also able realize passive target sensing. Wireless has diverse Internet-of-Things applications indoor human detection, such as device-free localization, activity recognition fall respiration gait recognition, user identification, so forth. Deep learning (DL), with the latest breakthroughs machine (ML) artificial intelligence (AI),...

10.1109/jiot.2020.3024234 article EN IEEE Internet of Things Journal 2020-09-16

Gesture recognition is the central enabler of human-computer interaction (HCI). In addition to semantic information contained in gestures, gesture-based user identification can effortlessly enhance HCI system security. Recently, Wi-Fi-integrated sensing and communication (ISAC) technology has shown great potential a field hitherto occupied by computer vision radar sensing. this work, leveraging Wi-Fi sensing, we propose called WiGesID that achieves joint gesture human (JGRHI). The basic idea...

10.1109/jsac.2022.3155526 article EN IEEE Journal on Selected Areas in Communications 2022-03-02

Accurate beam tracking in high-mobility vehicular networks has become a key issue for reliable communication link establishment. Recent work on integrated sensing and shown the superiority of sensing-assisted tracking. By estimating angular parameters vehicles based radar echoes, roadside unit (RSU) can perform so-called predictive beamforming to pair beams with high accuracy as well low latency. To further reduce estimation error due nonlinear measurements, this letter, we develop deep...

10.1109/lcomm.2021.3098748 article EN publisher-specific-oa IEEE Communications Letters 2021-07-21

Deep learning (DL) has been widely applied in automatic modulation classification (AMC), while the superb performance highly depends on high-quality datasets. Motivated by this, AMC under few-shot conditions is considered this letter, where a novel network architecture proposed, namely relation (AMCRN), and verified with baseline methods. Experimental results state that accuracy of proposed AMCRN exceeds 90% 10% to 50% improvements are obtained compared classical schemes...

10.1109/lcomm.2021.3135688 article EN IEEE Communications Letters 2021-12-14

To fulfill the requirements of future intelligent transportation system in 6G era, ultra-reliable and low-latency vehicular communications is great importance. In high-mobility scenarios, conventional orthogonal frequency division multiplexing (OFDM) modulation may fail to work due high Doppler spreads. Moreover, dynamic network topology imposes challenges on aligning beams multiple antenna systems. this context, article introduces a new time space (OTFS) sensing-assisted predictive...

10.1109/mwc.005.2200408 article EN IEEE Wireless Communications 2023-04-01

Nowadays, a possible approach to designing commercial-attractive sensing solution is integrating capability into widely deployed communication systems, e.g., the force coming fifth-generation (5G) new radio (NR), by slightly modifying standard. To this end, in paper, we firstly investigate possibility of re-using NR waveform for reviewing current frame structure. Then, self-ambiguity and cross-ambiguity functions are analyzed exploit performance limitations. Several synchronizations...

10.1109/icassp43922.2022.9746355 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022-04-27

The digital twin (DT), which effectively represents the actual real-world physical system or process, has reshaped classic manufacturing, construction, as well healthcare industry. As for realizing DT, both sensing and communication functionalities are demanded, fully builds connectivity between world world. We first conducted a survey on current situation of DT combined with sensing. Inspired from this development sensing, in paper, we attempt to study annd technologies layer reduce...

10.1109/jsac.2023.3314826 article EN IEEE Journal on Selected Areas in Communications 2023-09-19

Recently, integrated sensing and communication (ISAC) has been a hot topic to alleviate the issue of low spectrum efficiency, pursuit hardware gain integration as far possible. However, coexistence functions triggers mutual interference therein, seriously affecting their respective performance. To solve this problem, model are built respectively in paper, considering between signals signals. Then, ratio total transmitting data rate power consumption is regarded optimization objection paper...

10.1109/tgcn.2023.3234404 article EN IEEE Transactions on Green Communications and Networking 2023-01-06

Federated learning (FL) enables collaborative training of machine models across distributed medical data sources without compromising privacy. However, applying FL to image analysis presents challenges like high communication overhead and heterogeneity. This paper proposes novel techniques using explainable artificial intelligence (XAI) for efficient, accurate, trustworthy analysis. A heterogeneity-aware causal approach selectively sparsifies model weights based on their contributions,...

10.1109/jbhi.2024.3375894 article EN IEEE Journal of Biomedical and Health Informatics 2024-03-18

We propose a novel palm vein recognition scheme based on an adaptive 2D Gabor filter. Three key steps were studied in this scheme: region of interest (ROI) extraction, filtering, and template matching. First, the image extraction step, authors used index finger both sides valley to locate square area, then iteratively expanded area box maximise ROI. Second, feature parameter selection was proposed for optimising Third, matching author presented algorithm referred as minimum normalised...

10.1049/iet-bmt.2016.0085 article EN IET Biometrics 2016-12-14

The integration of unmanned aerial vehicles (UAVs) in future communication networks has received great attention, and it plays an essential role many applications, such as military reconnaissance, fire monitoring, etc. In this paper, we consider a UAV-aided video transmission system based on mobile edge computing (MEC). Considering the short latency requirements, UAV acts MEC server to transcode videos relay forward transcoded ground base station. Subject constraints discrete variables...

10.1109/tgcn.2024.3352173 article EN IEEE Transactions on Green Communications and Networking 2024-01-10

Integrated sensing and communication (ISAC) enables numerous innovative wireless applications. Communication-centric design is a practical choice for the construction of sixth generation (6G) ISAC networks. Continuous-wave-based systems, with orthogonal frequency-division multiplexing (OFDM) being representative example, suffer from self-interference (SI) problem, hence are less suitable long-range sensing. On other hand, pulse-based half-duplex systems free SI, but also favourable...

10.48550/arxiv.2502.08996 preprint EN arXiv (Cornell University) 2025-02-13

Spectrum sensing with single primary user (PU) has attracted the attention of researchers due to its influence on scarce radio spectrum. Yet, co-existence multiple PUs within region is considered rarely. In this letter, spectrum users over fading channel investigated based subspace filtering in same frequency band. The corresponding closed-form solution false alarm and detection probabilities given together simulation verifications.

10.1109/lcomm.2017.2741938 article EN IEEE Communications Letters 2017-08-23

Recent advances in wireless communication and solid-state circuits together with the enormous demands of sensing ability have given rise to a new enabling technology, integrated communications (ISAC). The ISAC captures two main advantages over dedicated functionalities: 1) Integration gain efficiently utilize congested resources, even, 2) Coordination balance dual-functional performance or/and perform mutual assistance. Meanwhile, triggered by ISAC, we are also witnessing paradigm shift...

10.48550/arxiv.2104.11457 preprint EN other-oa arXiv (Cornell University) 2021-01-01

Along with the commercialization of evolved multimedia broadcast multicast services (eMBMS), number mobile broadcasting users is growing notably. Previous works reveal that accuracy channel estimation will significantly impact quality services. Motivated by this fact, we apply machine learning (ML) to fifth-generation Radio Access Network (5G RAN) slicing in paper for and prediction status scenarios. More specifically, a cascaded convolutional neural network (CNN)-long short term memory...

10.1109/tbc.2021.3122353 article EN IEEE Transactions on Broadcasting 2021-10-28

Integrated sensing and communication (ISAC) has received increasing attention as a potential technology to alleviate spectrum shortage. This paper studies the power-saving problem based on power assignment subcarrier allocation in ISAC. Specifically, we propose joint design method jointly optimize transmit allocated services respectively. To ensure quality of service (SS) (CS), minimum total required by system is obtained optimizing subcarriers transmission power. Since formulated nonconvex,...

10.1109/wcnc55385.2023.10118989 article EN 2022 IEEE Wireless Communications and Networking Conference (WCNC) 2023-03-01

Coordinated multipoint transmission is applied to multi-cell millimeter wave (mmWave) non-orthogonal multiple access (NOMA) networks in downlink this letter. Multiple cooperative base stations (BSs) jointly transmit same signal a cell-edge user as far user. And each BS individually serves near at the beamwidth with NOMA. Subsequently, outage probability, sum rate and energy efficiency are derived. Further, simulation results provided verify correctness of analytical derivation demonstrate...

10.1109/lcomm.2020.3029572 article EN IEEE Communications Letters 2020-10-08

With the continuous evolution of emerging technologies such as mobile network, machine learning (ML), 5G, etc., digital twins (DT) bursts out great potential by its capacity data analysis, tracking, prediction, etc, building a bridge between physical and information world. Meanwhile, network is moving towards data-driven paradigm, issue privacy security seem to be bottleneck. As result, federated (FL) are deeply converging. However, time-varying parameters FL-empowered huge continue increase...

10.1109/jsac.2023.3310082 article EN IEEE Journal on Selected Areas in Communications 2023-08-30
Coming Soon ...