Chunyi Peng
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
Chunyi Peng has a total of 108 co-authors. Here are the top co-authors by number of shared publications:
- Guan-Hua Tu
Michigan State University, East Lansing, Michigan, USA
7 shared publications - Yanbing Liu
Department of Computer Science, Purdue University, West Lafayette, IN, USA
7 shared publications - Chi-Yu Li
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
6 shared publications - Songwu Lu
Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA
6 shared publications - Tian Xie
Utah State University, Logan, Utah, USA
6 shared publications - Min-Yue Chen
Michigan State University, East Lansing, Michigan, USA
5 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 115-121
D epth 4 vtol : Precise Depth Estimation for Vertical Take-off and Landing UAVs over Residential Houses
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 115-121
Open AccessD epth 4 vtol : Precise Depth Estimation for Vertical Take-off and Landing UAVs over Residential Houses
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 49-54
FollowMe: Automating Precise Image Annotation Across Various Environments
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 49-54
Open AccessFollowMe: Automating Precise Image Annotation Across Various Environments
- Open Access
- 31 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Co-Designing Agentic AI and Wireless/Edge Networks: A Vision for Self-Evolving, Trustworthy Network Intelligence
- 31 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessCo-Designing Agentic AI and Wireless/Edge Networks: A Vision for Self-Evolving, Trustworthy Network Intelligence
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 712-726
LoRaSeek: Boosting Denoising Ability in Neural-enhanced LoRa Decoder via Hierarchical Feature Extraction
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 712-726
Open AccessLoRaSeek: Boosting Denoising Ability in Neural-enhanced LoRa Decoder via Hierarchical Feature Extraction
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 941-956
5G in the Sky: Uplink Throughput Measurement, Analysis, and Enhancement
In this work, we present an in-depth study to measure, analyze and enhance aerial performance (here, uplink throughput) for drones flying in the low sky over two operational 5G networks in the US (AT&T and T-Mobile). Different from prior aerial 5G measurement studies, we have made three new endeavors. First, through extensive experiments in the low sky (below 120 m), we not only characterize aerial performance observed over operational 5G networks, but also quantitively assess performance potentials not observed but missed in the sky. We have several new findings that have not been reported before: higher 5G performance potentials are realized in the sky than on the ground (say, faster data speed in the sky); But surprisingly, more performance potentials are also missed in the sky (namely, 5G could have been even much faster but such potentials are not fully utilized in the sky). Second, we delve into root causes behind missed performance potentials and find that current 5G cell selection should take the blame despite the impacts of radio resource allocation in the underlying physical layer. Cell selection is designed for terrestrial scenarios and misses good 5G cells under aerial radio channel conditions. Third, we thus devise a data-driven solution called 5GAir++ to patch cell selection in practice. 5GAir++ is promising to pursue more 5G performance potentials in the low sky. We have validated its effectiveness over real-world traces with two applications of bulky file upload and video live streaming. Datasets and codes are released.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 941-956
5G in the Sky: Uplink Throughput Measurement, Analysis, and Enhancement
In this work, we present an in-depth study to measure, analyze and enhance aerial performance (here, uplink throughput) for drones flying in the low sky over two operational 5G networks in the US (AT&T and T-Mobile). Different from prior aerial 5G measurement studies, we have made three new endeavors. First, through extensive experiments in the low sky (below 120 m), we not only characterize aerial performance observed over operational 5G networks, but also quantitively assess performance potentials not observed but missed in the sky. We have several new findings that have not been reported before: higher 5G performance potentials are realized in the sky than on the ground (say, faster data speed in the sky); But surprisingly, more performance potentials are also missed in the sky (namely, 5G could have been even much faster but such potentials are not fully utilized in the sky). Second, we delve into root causes behind missed performance potentials and find that current 5G cell selection should take the blame despite the impacts of radio resource allocation in the underlying physical layer. Cell selection is designed for terrestrial scenarios and misses good 5G cells under aerial radio channel conditions. Third, we thus devise a data-driven solution called 5GAir++ to patch cell selection in practice. 5GAir++ is promising to pursue more 5G performance potentials in the low sky. We have validated its effectiveness over real-world traces with two applications of bulky file upload and video live streaming. Datasets and codes are released.
- Open Access
- 28 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 592-609
An In-Depth Look into 5G ON-OFF Loops in the Wild
- 28 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 592-609
Open AccessAn In-Depth Look into 5G ON-OFF Loops in the Wild
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 611-612
Poster: SiHear (Sign-to-Hear): Empowering Seemless Sign-Speech Interactions over Smart Glasses
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 611-612
Open AccessPoster: SiHear (Sign-to-Hear): Empowering Seemless Sign-Speech Interactions over Smart Glasses
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 693-698
δ-ATP: Towards Fast and Reliable Aerial Traffic Patrol
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 693-698
Open Accessδ-ATP: Towards Fast and Reliable Aerial Traffic Patrol
- Open Access
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1605-1607
D-AirPatrol: A Dual-Layer Architecture for Traffic Patrol From the Sky
In this poster, we present our efforts to enhance air patrol for monitoring traffic and violations from the sky. Through a new dual-layer architecture to decouple the foreground and background of aerial views, our solution D-AirPatrol holds promise to make air patrol more accurate and reliable.
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1605-1607
Open AccessD-AirPatrol: A Dual-Layer Architecture for Traffic Patrol From the Sky
In this poster, we present our efforts to enhance air patrol for monitoring traffic and violations from the sky. Through a new dual-layer architecture to decouple the foreground and background of aerial views, our solution D-AirPatrol holds promise to make air patrol more accurate and reliable.