Yuqiang Heng

ORCID: 0000-0001-7075-9600
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Millimeter-Wave Propagation and Modeling
  • Advanced MIMO Systems Optimization
  • Microwave Engineering and Waveguides
  • Indoor and Outdoor Localization Technologies
  • Antenna Design and Analysis
  • Internet Traffic Analysis and Secure E-voting
  • Image and Video Quality Assessment
  • Video Coding and Compression Technologies
  • Energy Harvesting in Wireless Networks
  • Advanced Malware Detection Techniques
  • Fault Detection and Control Systems
  • Wireless Networks and Protocols
  • Antenna Design and Optimization
  • Mineral Processing and Grinding
  • Spectroscopy and Chemometric Analyses
  • Network Security and Intrusion Detection
  • Advanced Wireless Network Optimization
  • Scheduling and Optimization Algorithms
  • Radio Wave Propagation Studies
  • Telecommunications and Broadcasting Technologies

The University of Texas at Austin
2019-2024

Samsung (United States)
2023-2024

Research!America (United States)
2023

University of Malaya
2010

Future cellular networks will increasingly rely on the millimeter-wave bands to increase capacity. Migrating ever higher carrier frequencies require directional beamforming establish and maintain link. Intelligent beam management (BM) protocols be critical for establishing maintaining connections between base station user equipment in a dynamic channel. This article first provides brief overview of BM protocol Release 15 5G New Radio, then identifies six major challenges later releases that...

10.1109/mcom.001.2001184 article EN IEEE Communications Magazine 2021-07-01

Beam alignment – the process of finding an optimal directional beam pair is a challenging procedure crucial to millimeter wave (mmWave) communication systems. We propose novel method that learns site-specific probing codebook and uses measurements predict narrow beam. An end-to-end neural network (NN) architecture designed jointly learn predictor. The learned consists beams can capture particular characteristics propagation environment. proposed relies on sweeping codebook, does not require...

10.1109/twc.2022.3143121 article EN IEEE Transactions on Wireless Communications 2022-01-24

Beam alignment is a challenging and time-consuming process for millimeter wave (mmWave) systems, particularly as they trend towards higher carrier frequencies which require ever narrower beams. We propose beam method that assisted by machine learning (ML), where we train ML models to predict the optimal access point (AP) – or best few candidates user equipment (UE) given just its GPS coordinates, can be fed back UE estimated network using emerging localization techniques. evaluate with data...

10.1109/tccn.2021.3078147 article EN IEEE Transactions on Cognitive Communications and Networking 2021-05-07

Beam alignment is a challenging and time-consuming process for millimeter wave (mmWave) initial access (IA). We propose beam training method that assisted by machine learning (ML), where we train ML models to predict the optimal Access Point (AP) user equipment (UE) given its Global Positioning System (GPS) coordinates. After (possibly offline) phase during which exhaustive or hierarchical performed, our predicts few candidate APs beams knowing only location of UE. evaluate performance with...

10.1109/globecom38437.2019.9013296 article EN 2015 IEEE Global Communications Conference (GLOBECOM) 2019-12-01

Beam alignment is a critical bottleneck in millimeter wave communication. An ideal beam technique should achieve high beamforming gain with low latency, scale well to systems higher carrier frequencies, larger antenna arrays and multiple user equipment, not require hard-to-obtain context information. These qualities are collectively lacking existing methods. We depart from the conventional codebook-based (CB) approach where optimal chosen quantized codebooks instead propose grid-free method...

10.1109/twc.2023.3283475 article EN IEEE Transactions on Wireless Communications 2023-06-13

A high-quality network traffic dataset is essential to the development of accurate classification algorithms. In this work, we present a new labeled public with realistic mobile from wide range popular applications. An automated platform constructed generate and collect data specified applications in controlled environment. The contains over 21 million packets more than 29 hours application activity-level labels. We provide an example using machine learning (ML) models trained on proposed dataset.

10.1109/lnet.2021.3098455 article EN publisher-specific-oa IEEE Networking Letters 2021-08-10

Beam alignment - the process of finding an optimal directional beam pair is a challenging procedure crucial to millimeter wave (mmWave) communication systems. In this work, we propose method that learns site-specific probing codebook and uses measurements predict narrow beam. A novel neural network (NN) architecture designed jointly learn predictor in end-to-end fashion. The learned consists beams can capture particular characteristics propagation environment. proposed relies on sweeping...

10.1109/globecom46510.2021.9685512 article EN 2015 IEEE Global Communications Conference (GLOBECOM) 2021-12-01

Beam alignment - finding optimal analog beam-forming (BF) weights is a critical bottleneck for millimeter wave (mmWave) systems. Existing beam approaches typically assume that devices adopt codebooks of beams with uniform coverage, from which good pair selected after an exhaustive search or sweeping few candidate beams. In this work, we propose method grid-less the synthesized continuous set instead being chosen quantized codebook, and one-shot near-optimal BF are directly predicted without...

10.1109/globecom48099.2022.10001720 article EN GLOBECOM 2022 - 2022 IEEE Global Communications Conference 2022-12-04

Providing a high quality video streaming experience in mobile data network via the ubiquitous HTTP Adaptive Streaming (HAS) protocol is challenging. This largely because HAS traffic arrives as regular Internet Protocol (IP) packets, indistinguishable from those of other services. paper presents real-time network-based Machine Learning (ML) classifiers incurring low overhead and capable (a) detecting service type different flows including HAS, (b)detecting player status for users with flows....

10.1109/access.2019.2933273 article EN cc-by IEEE Access 2019-01-01

Beam alignment (BA) in modern millimeter wave standards such as 5G NR and WiGig (802.11ay) is based on exhaustive and/or hierarchical beam searches over pre-defined codebooks of wide narrow beams. This approach slow bandwidth/power-intensive, a considerable hindrance to the deployment bands. A new needed we move towards 6G. BA promising use case for deep learning (DL) 6G air interface, offering possibility automated custom tuning procedure each cell its unique propagation environment user...

10.48550/arxiv.2403.16186 preprint EN arXiv (Cornell University) 2024-03-24

Beam alignment (BA) in modern millimeter wave standards, such as 5G NR and WiGig (802.11ay), is based on exhaustive and/or hier-archical beam searches over pre-defined code-books of wide narrow beams. This approach slow bandwidth/power-intensive, a considerable hindrance to the deployment bands. A new needed we move toward 6G. BA promising use case for deep learning (DL) 6G air interface, offering possibility automated custom tuning procedure each cell its unique propagation environment user...

10.1109/mcom.001.2300451 article EN IEEE Communications Magazine 2024-08-01

A mobile device - or user equipment (UE) using 5G can be configured to operate with large bandwidths and a number of MIMO layers enable high-throughput applications. This, however, comes at the cost high power consumption. variety applications run UE widely varying throughput requirements. For low requirement, over-configuration results in unnecessary We propose classify traffic UE, then configure accordingly meet requirement current application without Specifically, we (i) use machine...

10.1109/access.2023.3338158 article EN cc-by-nc-nd IEEE Access 2023-01-01

Beam alignment is a critical bottleneck in millimeter wave (mmWave) communication. An ideal beam technique should achieve high beamforming (BF) gain with low latency, scale well to systems higher carrier frequencies, larger antenna arrays and multiple user equipments (UEs), not require hard-to-obtain context information (CI). These qualities are collectively lacking existing methods. We depart from the conventional codebook-based (CB) approach where optimal chosen quantized codebooks instead...

10.48550/arxiv.2209.08198 preprint EN cc-by arXiv (Cornell University) 2022-01-01

Beam alignment - the process of finding an optimal directional beam pair is a challenging procedure crucial to millimeter wave (mmWave) communication systems. We propose novel method that learns site-specific probing codebook and uses measurements predict narrow beam. An end-to-end neural network (NN) architecture designed jointly learn predictor. The learned consists beams can capture particular characteristics propagation environment. proposed relies on sweeping codebook, does not require...

10.48550/arxiv.2107.13121 preprint EN cc-by arXiv (Cornell University) 2021-01-01
Coming Soon ...