Wei Cheng

ORCID: 0000-0002-0874-9927
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Wireless Communication Technologies
  • Indoor and Outdoor Localization Technologies
  • Energy Efficient Wireless Sensor Networks
  • Advanced MIMO Systems Optimization
  • Radar Systems and Signal Processing
  • Advanced SAR Imaging Techniques
  • Energy Harvesting in Wireless Networks
  • Quantum Computing Algorithms and Architecture
  • Mobile Ad Hoc Networks
  • Cooperative Communication and Network Coding
  • Optical Wireless Communication Technologies
  • Quantum Information and Cryptography
  • Target Tracking and Data Fusion in Sensor Networks
  • Wireless Communication Security Techniques
  • Quantum Mechanics and Applications
  • Opportunistic and Delay-Tolerant Networks
  • Rough Sets and Fuzzy Logic
  • Underwater Vehicles and Communication Systems
  • Advanced Algorithms and Applications
  • Speech and Audio Processing
  • Wireless Networks and Protocols
  • Caching and Content Delivery
  • RFID technology advancements
  • Advanced Wireless Communication Techniques
  • UAV Applications and Optimization

Northwestern Polytechnical University
2016-2025

Guangdong University of Technology
2024

Jilin University
2024

State Key Laboratory of Superhard Materials
2024

Chinese Academy of Medical Sciences Dermatology Hospital
2024

Chinese Academy of Medical Sciences & Peking Union Medical College
2024

Guizhou University
2024

Minnan University of Science and Technology
2023

ORCID
2021

Princeton University
2021

Click-through rate (CTR) prediction is a critical task in online advertising and marketing. For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks. First, they typically lack persuasive rationales to explain the outcomes of models. Unexplainable predictions recommendations may be difficult validate thus unreliable untrustworthy. In many applications, inappropriate suggestions even bring severe consequences. Second, approaches poor efficiency...

10.1145/3336191.3371785 article EN 2020-01-20

10.1016/j.ijar.2011.10.003 article EN publisher-specific-oa International Journal of Approximate Reasoning 2011-10-16

For the first time, a hybrid filter design approach based on combination of Integrated Passive Device (IPD) and acoustic technologies is proposed to satisfy new demands in 5G New Radio (NR) applications, where high frequency (above 3 GHz) wide bandwidth (up 900 MHz date) are defined by standards. The Band n77 used as an extreme example demonstrate capability achieve operating from 3.3 4.2 GHz, MHz, rejection 36 dB at 200 away, low insertion loss 2.5 dB.

10.1109/ultsym.2019.8925918 article EN 2017 IEEE International Ultrasonics Symposium (IUS) 2019-10-01

In this paper, we propose a downlink intelligent reflecting surface (IRS) aided non-orthogonal multiple access (NOMA) for millimeter-wave (mmWave) massive MIMO with lens antenna array, i.e., IRS-aided mmWave beamspace NOMA, where the single-antenna users without direct-link but connected to base station (BS) aid of IRS are grouped as one NOMA group. Considering power leakage problem in channel and per-antenna constraint, two multi-beam selection strategies BS-IRS link under models,...

10.1109/tvt.2021.3067938 article EN IEEE Transactions on Vehicular Technology 2021-03-23

For an indoor localization system based on visible light communication (VLC) by using received signal strength technique, signals used for estimating the distances between each target and reference nodes suffer from non-line-of-sight (NLoS) propagation, which could introduce large errors in their locations. Both line-of-sight (LoS) link NLoS are taken into account a noisy VLC channel, thus ambient noise sources of error. Ricean K factor is introduced to evaluate relation value quality...

10.1117/1.oe.58.5.056102 article EN cc-by Optical Engineering 2019-05-08

Frequency Diverse Array Multiple-Input Multiple-Output (FDA-MIMO) radar introduces range-dependent beamforming capabilities, enhancing its ability to differentiate true targets from main lobe jammers. However, this innovation also new challenges, particularly when errors disrupt the transceiver steering vectors, leading performance degradation in interference suppression. To end, a robust method tailored for FDA-MIMO systems is proposed address signal mismatches caused by range–angle errors,...

10.3390/rs17040577 article EN cc-by Remote Sensing 2025-02-08

Massive multi-input multi-output (MIMO) is envisioned as a key technology for the emerging fifth generation of communication networks (5G). However, considering energy consumption large number radio frequency (RF) chains, massive MIMO poses problem to efficiency (EE) requirement 5G. In this paper, we propose an energy-efficient power allocation method millimeter-wave (mmWave) beamspace non-orthogonal multiple access (NOMA) systems, where there may be users in each selected beam. First,...

10.1109/access.2019.2935495 article EN cc-by IEEE Access 2019-01-01

Link scheduling plays a key role in the network capacity and transmission delay. In this paper, we study problem of maximum link (MLS), aiming to characterize number links that can be successfully scheduled simultaneously under Rayleigh-fading multiuser interference. After analyzing minimum distance between successful existing GHW algorithm, propose DLS (Distance-based Scheduling) algorithm. Then, global interference is characterized bounded by introducing separation selected links, building...

10.1109/twc.2020.2994998 article EN cc-by IEEE Transactions on Wireless Communications 2020-05-22

Joint transceiver beamforming is a fundamental and crucial research task in the field of signal processing. Despite extensive efforts made recent years, joint frequency diverse array (FDA)-based multiple-input multiple-output (MIMO) radar has received relatively less attention confronted with some tricky challenges, such as range–angle decoupling interaction between multiple performance metrics. In this paper, we initially derive generalized ambiguity function FDA-MIMO to explore intrinsic...

10.3390/rs16081364 article EN cc-by Remote Sensing 2024-04-12

10.1109/tnsm.2024.3395298 article EN IEEE Transactions on Network and Service Management 2024-04-30

The Internet of Things (IoT) and machine-to-machine (M2M) communication will play an important role in future communications, but there is currently no ultra-reliable low-latency wireless theory that guides its design. For highly mobile vehicle-to-vehicle (V2V) scenarios, asynchronous transmission should also be accepted. Therefore, it particularly urgent to study technology satisfies transmission. Universal Filter Multi-Carrier (UFMC) a new type filtering mechanism meets this character....

10.1109/access.2019.2923774 article EN cc-by IEEE Access 2019-01-01

10.1016/s0165-0114(02)00607-3 article EN Fuzzy Sets and Systems 2003-01-30

为了减少电子战平台的体积和电磁干扰,一种有效的途径就是实现雷达与通信的一体化。该文针对雷达通信一体化信号设计中存在的不兼容和互干扰问题,根据信号能量共享的原则,提出了基于频分准正交多载波Chirp信号的雷达通信一体化波形及其相应的系统实现方法。并采用宽带模糊函数对多载波一体化信号特性进行了详细分析,进一步研究了一体化信号的处理过程以及其系统性能。在均衡子载波准正交性和通信频谱效率下,通过理论分析和仿真结果表明在多载波频谱重叠率为20%的情况下,一体化信号能够满足雷达的常规探测,并且具有较低的误码特性。

10.3724/sp.j.1146.2012.00567 article ZH-CN cc-by JOURNAL OF ELECTRONICS INFORMATION TECHNOLOGY 2014-02-18

Point-of-interest (POI) recommendation is an emerging area of research on location-based social networks to analyze user behaviors and contextual check-in information. For this problem, existing approaches, with shallow or deep architectures, have two major drawbacks. First, for these the attributes individuals been largely ignored. Therefore, it would be hard, if not impossible, gather sufficient attribute features complete coverage possible motivation factors. Second, most models preserve...

10.1145/3459637.3481962 article EN 2021-10-26

Recently, the Transformer-based technique has emerged as a promising solution for modeling contextual information in Remote Sensing (RS) scenes and found widespread applications RS scene classification. However, how to make full use of intermediate features learned Transformers is crucial importance classification tasks. Therefore, this paper proposes Hierarchical Feature Fusion Transformer with Patch Dilating (HFFT-PD), which aims capture rich from hierarchical enhance performance...

10.1109/tgrs.2023.3331880 article EN IEEE Transactions on Geoscience and Remote Sensing 2023-01-01

In autonomous driving, Frequency-Modulated Continuous-Wave (FMCW) radar has gained widespread acceptance for target detection due to its resilience and dependability under diverse weather illumination circumstances. Although deep learning identification models have seen fast improvement, there is a lack of research on their susceptibility adversarial attacks. Various spoofing attack techniques been suggested sensors by deliberately sending certain signals through specialized devices. this...

10.3390/rs16163109 article EN cc-by Remote Sensing 2024-08-22

High peak-to-average power ratio (PAPR) leads to out-of-band and in-band distortion in the direct current-biased optical orthogonal frequency division multiplexing (DCO-OFDM) systems. In order effectively reduce PAPR with faster convergence lower complexity, this paper proposes a tone reservation based scheme, which is combination of signal-to-clipping noise (SCR) procedure least squares approximation (LSA) procedure. proposed transmitter DCO-OFDM indoor visible light communication (VLC)...

10.1364/oe.25.024630 article EN cc-by Optics Express 2017-09-27

Different from the conventional single-beam beamspace non-orthogonal multiple access (NOMA) scheme, where users only within same analog beam can be served by NOMA technique, in this article, we propose a multi-beam scheme for millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) with lens antenna array communication system. The proposed break constraint and perform transmission different beams. Then, design power allocation minimizing total consumption, which mainly includes...

10.1109/tvt.2020.3014090 article EN IEEE Transactions on Vehicular Technology 2020-08-04

The target tracking of nonlinear maneuvering radar in dense clutter environments is still an important but difficult problem to be solved effectively. Traditional solutions often rely on motion models and prior distributions. This paper presents a novel improved architecture Kalman filter based recursive neural network, which combines the sequence learning recurrent networks with precise prediction end-to-end manner. We employ three LSTM model equation, noise, measurement respectively, learn...

10.1155/2022/8280428 article EN cc-by Wireless Communications and Mobile Computing 2022-08-21
Coming Soon ...