Runxin Li

Dr. Runxin Li


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 June 2024 in Digital Signal Processing
Verified
Journal Article
Closed access
ZSZhenhong Shang
Zhenhong Shang
CYChunhui Yu
Chunhui Yu
HHHua Huang
Hua Huang
RLRunxin Li
Runxin Li

16 April 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
RLRunxin Li
Runxin Li
GZGaozhi Zhou
Gaozhi Zhou
XLXiaowu Li
Xiaowu Li
LJLianyin Jia
Lianyin Jia
ZSZhenhong Shang
Zhenhong Shang

14 August 2024 in Neurocomputing
Verified
Journal Article
Closed access
GZGaozhi Zhou
Gaozhi Zhou
RLRunxin Li
Runxin Li
ZSZhenhong Shang
Zhenhong Shang
XLXiaowu Li
Xiaowu Li
LJLianyin Jia
Lianyin Jia

17 February 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
RLRunxin Li
Runxin Li
XYXiong Yang
Xiong Yang
XLXiaowu Li
Xiaowu Li
GSGuofeng Shu
Guofeng Shu
LJLianyin Jia
Lianyin Jia
ZSZhenhong Shang
Zhenhong Shang

21 January 2025 in The Astrophysical Journal Supplement Series
Verified
Journal Article
Open access
PDF file
ZSZhenhong Shang
Zhenhong Shang
PDPeng Du
Peng Du
ZQZhenping Qiang
Zhenping Qiang
RLRunxin Li
Runxin Li
Ground-based solar telescopes often encounter cloud interference during observations, leading to varying degrees of cloud cover in solar images. Existing cloud removal methods face several challenges, including incomplete cloud removal, insufficient restoration of solar features, and ineffectiveness against severe cloud cover. This paper proposes a novel deep learning-based approach for cloud removal and feature restoration in Hα full-disk solar images. First, to create a high-quality data set of cloud-covered images, we developed a method for detecting and classifying cloudiness in Hα full-disk solar images. This method correlates average intensity profiles in log-polar coordinates and utilizes the median pixel intensity in the images. Using this approach, we constructed a data set with three levels of cloudiness: mild, moderate, and severe, utilizing high-cadence Hα full-disk solar images from different sites within the Global Oscillation Network Group. Second, our cloud removal network employs an encoder–decoder structure, integrating the Res2Net module into the encoder to capture comprehensive solar image features. The decoder enhances the model's ability to extract semantic information about cloud-covered areas through a residual multiscale attention mechanism. Quantitative and qualitative experimental results demonstrate that the proposed method effectively removes complex cloud interference while preserving solar features, significantly improving the quality of observed data and outperforming existing solar image cloud removal methods. Additionally, the model serves as a valuable reference for removing clouds from other ground-based telescope data. The data and code are available on GitHub (https://github.com/dupeng24/full-disk-cloud-removal) under a CC0 1.0 License, and version 2.0 is archived in Zenodo (10.5281/zenodo.14184221).

1 February 2024 in Electronics
Verified
Journal Article
Open access
PDF file
XLXiaowu Li
Xiaowu Li
JXJunjie Xu
Junjie Xu
RLRunxin Li
Runxin Li
LJLianyin Jia
Lianyin Jia
Jinguo YouJinguo You
Jinguo You
LoRaWAN is an emerging Low-Power Wide-Area Network (LPWAN) technology, widely adopted in various Internet of Things (IoT) applications due to its long transmission range, low power consumption, and robust anti-interference capabilities. However, using the ALOHA medium access control (MAC) protocol in LoRaWAN significantly reduces the packet delivery rate, particularly in high-density networks where end devices (EDs) access the network randomly. It seriously affects the overall network performance. This paper introduces the Circular Region Grouped Bit-Slot CGBS-LoRa MAC protocol to address this challenge. The protocol takes a proactive approach by allocating transmission parameters for end devices, executing regional segmentation based on the distance between EDs and the gateway using different spreading factors. Concurrently, improving the ALOHA access method ensures the efficient communication of EDs in the region. Experimental results demonstrate that our proposed protocol markedly improves the scalability of LoRa networks and minimizes device collisions compared to three other MAC protocols. Even as the LoRaWAN network expands, the proposed protocol maintains a high packet delivery rate and low latency.