Bing Zhou
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
Bing Zhou has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Xianyu Zuo
Henan University, Kaifeng, China
3 shared publications - Jiaguo Li
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
2 shared publications - Minghu Fan
School of Computer and Information Engineering, Henan University, Kaifeng, China
2 shared publications - Xinxin Yang
School of Computer and Information Engineering, Henan University, Kaifeng, Henan, China
2 shared publications - Yang Liu
Henan University
2 shared publications - Baojun Qiao
Henan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475000, China
1 shared publication
Latest Publications
- Open Access
- 20 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 677-682
Prediction-Aware Dynamic Scheduling Strategy for Long-Tail Remote Sensing Tasks in Heterogeneous Clusters
To address the challenges of computational power fragmentation and long-tail blocking encountered during the operational processing of remote sensing big data in heterogeneous clusters, this paper proposes a multi-dimensional dynamic scheduling strategy based on execution time prediction awareness. A Directed Acyclic Graph (DAG) is introduced to achieve fine-grained decoupling of complex remote sensing production workflows. Combined with advanced network storage protocols, a cross-layer zero-copy data architecture is constructed to fundamentally eliminate I/O congestion in concurrent environments. In response to the extreme right-skewed long-tail distribution of remote sensing atomic task execution times, a two-stage ensemble learning model, XLHP (XGBoost & LightGBM Hybrid Predictor), is proposed. This model utilizes XGBoost for high-dimensional monitoring feature refinement and integrates the Log1p transformation with LightGBM's Leaf-wise growth mechanism, achieving accurate microsecond-level prediction for both high-residual, long-duration tasks and massive short-duration tasks. Ultimately, the temporal prior knowledge is incorporated into a multi-objective combinatorial optimization model for heterogeneous clusters, formulating the PABF (Prediction-Aware Best Fit) scheduling algorithm, which features multi-stage funnel capacity pre-checking and dual-mode adaptive weighting. Experimental results demonstrate that, compared with traditional static heuristic scheduling, the proposed strategy leverages a dynamic backfilling mechanism for short tasks to reduce the maximum completion time (Makespan) by 42.2%, while maintaining the core resource utilization of the cluster at a stable, high-level equilibrium range of 80% to 95%.
- 20 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 677-682
Open AccessPrediction-Aware Dynamic Scheduling Strategy for Long-Tail Remote Sensing Tasks in Heterogeneous Clusters
To address the challenges of computational power fragmentation and long-tail blocking encountered during the operational processing of remote sensing big data in heterogeneous clusters, this paper proposes a multi-dimensional dynamic scheduling strategy based on execution time prediction awareness. A Directed Acyclic Graph (DAG) is introduced to achieve fine-grained decoupling of complex remote sensing production workflows. Combined with advanced network storage protocols, a cross-layer zero-copy data architecture is constructed to fundamentally eliminate I/O congestion in concurrent environments. In response to the extreme right-skewed long-tail distribution of remote sensing atomic task execution times, a two-stage ensemble learning model, XLHP (XGBoost & LightGBM Hybrid Predictor), is proposed. This model utilizes XGBoost for high-dimensional monitoring feature refinement and integrates the Log1p transformation with LightGBM's Leaf-wise growth mechanism, achieving accurate microsecond-level prediction for both high-residual, long-duration tasks and massive short-duration tasks. Ultimately, the temporal prior knowledge is incorporated into a multi-objective combinatorial optimization model for heterogeneous clusters, formulating the PABF (Prediction-Aware Best Fit) scheduling algorithm, which features multi-stage funnel capacity pre-checking and dual-mode adaptive weighting. Experimental results demonstrate that, compared with traditional static heuristic scheduling, the proposed strategy leverages a dynamic backfilling mechanism for short tasks to reduce the maximum completion time (Makespan) by 42.2%, while maintaining the core resource utilization of the cluster at a stable, high-level equilibrium range of 80% to 95%.
- Open Access
- 20 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 117-123
Dynamic Weighted Task Scheduling Method Based on Multi-Dimensional Load
- 20 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 117-123
Open AccessDynamic Weighted Task Scheduling Method Based on Multi-Dimensional Load
- Open Access
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 315-322
Parallel Computing Method of Commonly Used Interpolation Algorithms for Remote Sensing Images
Parallel computing is a common method to accelerate remote sensing image processing. The paper briefly describes six commonly used interpolation functions and studies three commonly used parallel computing methods of the corresponding nine interpolation algorithms in remote sensing image processing. Firstly, two kinds of general parallel interpolation algorithms (for CPU and GPU respectively) were designed. Then, in two typical application scenarios (data-intensive and computing-intensive), four computing methods (one serial method and three parallel methods) of these interpolation algorithms were tested. Finally, the acceleration effects of all parallel algorithms were compared and analyzed. On the whole, the acceleration effect of parallel interpolation algorithm is better in computer-intensive scenario. In CPU-oriented methods, the speedup of all parallel interpolation algorithms mainly depends on the number of physical cores of CPU, while in GPU-oriented methods, a speedup is greatly affected by the computation complexity of an algorithm and the application scenario. GPU has a better acceleration effect on the interpolation algorithms with bigger computation complexity, and has more advantages in the computing-intensive scenarios. In most cases, GPU-based interpolation is ideal for efficient interpolation.
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 315-322
Open AccessParallel Computing Method of Commonly Used Interpolation Algorithms for Remote Sensing Images
Parallel computing is a common method to accelerate remote sensing image processing. The paper briefly describes six commonly used interpolation functions and studies three commonly used parallel computing methods of the corresponding nine interpolation algorithms in remote sensing image processing. Firstly, two kinds of general parallel interpolation algorithms (for CPU and GPU respectively) were designed. Then, in two typical application scenarios (data-intensive and computing-intensive), four computing methods (one serial method and three parallel methods) of these interpolation algorithms were tested. Finally, the acceleration effects of all parallel algorithms were compared and analyzed. On the whole, the acceleration effect of parallel interpolation algorithm is better in computer-intensive scenario. In CPU-oriented methods, the speedup of all parallel interpolation algorithms mainly depends on the number of physical cores of CPU, while in GPU-oriented methods, a speedup is greatly affected by the computation complexity of an algorithm and the application scenario. GPU has a better acceleration effect on the interpolation algorithms with bigger computation complexity, and has more advantages in the computing-intensive scenarios. In most cases, GPU-based interpolation is ideal for efficient interpolation.
- Open Access
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1) , 8683226
Vehicle Detection in Remote Sensing Image Based on Machine Vision
Target detection in remote sensing images is very challenging research. Followed by the recent development of deep learning, the target detection algorithm has obtained large and fast growth. However, in the application of remote sensing images, due to the small target, wide range, small texture, and complex background, the existing target detection methods cannot achieve people’s hope. In this paper, a target detection algorithm named IR‐PANet for remote sensing images of an automobile is proposed. In the backbone network CSPDarknet53, SPP is used to strengthen the learning content. Then, IR‐PANet is used as the neck network. After the upper sampling, depthwise separable convolution is used to greatly avoid the lack of small target feature information in the convolution of the shallow network and increase the semantic information in the high‐level network. Finally, Gamma correction is used to preprocess the image before image training, which effectively reduces the interference of shadow and other factors on training. The experiment proves that the method has a better effect on small targets obscured by shadows and under the color similar to the background of the picture, and the accuracy is significantly improved based on the original algorithm.
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1) , 8683226
Open AccessVehicle Detection in Remote Sensing Image Based on Machine Vision
Target detection in remote sensing images is very challenging research. Followed by the recent development of deep learning, the target detection algorithm has obtained large and fast growth. However, in the application of remote sensing images, due to the small target, wide range, small texture, and complex background, the existing target detection methods cannot achieve people’s hope. In this paper, a target detection algorithm named IR‐PANet for remote sensing images of an automobile is proposed. In the backbone network CSPDarknet53, SPP is used to strengthen the learning content. Then, IR‐PANet is used as the neck network. After the upper sampling, depthwise separable convolution is used to greatly avoid the lack of small target feature information in the convolution of the shallow network and increase the semantic information in the high‐level network. Finally, Gamma correction is used to preprocess the image before image training, which effectively reduces the interference of shadow and other factors on training. The experiment proves that the method has a better effect on small targets obscured by shadows and under the color similar to the background of the picture, and the accuracy is significantly improved based on the original algorithm.
- 1 July 2020
- Published by Institute of Geographic Science and Natural Resources Research, Chinese Academy of Sciences in Journal of Resources and Ecology
- Vol. 11 (4) , 405-413
Analysis of the Causes of Cyanobacteria Bloom: A Review
Among water blooms, cyanobacteria bloom occurs over the widest range and is much more harmful than other blooms. Its occurrence in inland water bodies is affected by many factors, such as meteorology, hydrology, and human activities. Therefore, the study of the causes of cyanobacterial bloom has become a major focus of scholars. The China Knowledge Network Journal Database contains 143 papers from China and abroad from the years 2004 to 2019 that are relevant to the study of cyanobacteria bloom. We begin by analyzing keywords in these studies and creating a keyword distribution map which indicates the factors related to the blooms. Based on parameters such as the frequency of words appearing in the text, the full text of each of the 143 papers is analyzed to form a word cloud created by a program written in Python language. After irrelevant terms are eliminated, the word cloud map can reveal potential factors that were not identified by keywords alone. After completing this macro analysis, we examined approximately 100 related papers from the China Knowledge Network Journal Database and Web of Science Database published from 2014 to 2019. Finally, we summarize the main reasons for the outbreak of water blooms. The factors causing blooms can be divided into natural factors and human factors. Among the natural factors are illumination, water temperature and nutrient salt conditions. The human factors are generally related to large-scale water conservancy projects. This paper analyzes and summarizes these factors, and provides a reference to aid in the prevention and treatment of algal blooms. The information in the paper has a certain practical significance for the protection of water environments.
- 1 July 2020
- Published by Institute of Geographic Science and Natural Resources Research, Chinese Academy of Sciences in Journal of Resources and Ecology
- Vol. 11 (4) , 405-413
Analysis of the Causes of Cyanobacteria Bloom: A Review
Among water blooms, cyanobacteria bloom occurs over the widest range and is much more harmful than other blooms. Its occurrence in inland water bodies is affected by many factors, such as meteorology, hydrology, and human activities. Therefore, the study of the causes of cyanobacterial bloom has become a major focus of scholars. The China Knowledge Network Journal Database contains 143 papers from China and abroad from the years 2004 to 2019 that are relevant to the study of cyanobacteria bloom. We begin by analyzing keywords in these studies and creating a keyword distribution map which indicates the factors related to the blooms. Based on parameters such as the frequency of words appearing in the text, the full text of each of the 143 papers is analyzed to form a word cloud created by a program written in Python language. After irrelevant terms are eliminated, the word cloud map can reveal potential factors that were not identified by keywords alone. After completing this macro analysis, we examined approximately 100 related papers from the China Knowledge Network Journal Database and Web of Science Database published from 2014 to 2019. Finally, we summarize the main reasons for the outbreak of water blooms. The factors causing blooms can be divided into natural factors and human factors. Among the natural factors are illumination, water temperature and nutrient salt conditions. The human factors are generally related to large-scale water conservancy projects. This paper analyzes and summarizes these factors, and provides a reference to aid in the prevention and treatment of algal blooms. The information in the paper has a certain practical significance for the protection of water environments.
- 24 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- Vol. 8 (3) , 50-62
Target Classification and Recognition for High-Resolution Remote Sensing Images: Using the Parallel Cross-Model Neural Cognitive Computing Algorithm
Target classification and recognition (TCR) are important information-extraction techniques for high-resolution remote sensing images (HRIs). However, because methods with high accuracy usually have higher time complexity, the massive remote sensing image has brought great difficulties for realtime application. In this article, we propose a hybrid, heterogeneous parallel processing algorithm to improve the efficiency TCR based on the Crossmodel Neural Cognitive Computing (CNCC) algorithm [parallel TCR based on MapReduce of hierarchical CNCC (PTCR-C)]. Parallel programming technologies used in this article include Open Multiprocessing (OpenMP), Compute Unified Device Architecture (CUDA), and the message passing interface (MPI). Experiments on public remote sensing image data sets show that the PTCR-C algorithm can effectively improve the efficiency of the original TCR algorithm. The PTCR-C algorithm has better augmented ability and provides the reference for further real-time TCR of remote sensing applications.
- 24 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- Vol. 8 (3) , 50-62
Target Classification and Recognition for High-Resolution Remote Sensing Images: Using the Parallel Cross-Model Neural Cognitive Computing Algorithm
Target classification and recognition (TCR) are important information-extraction techniques for high-resolution remote sensing images (HRIs). However, because methods with high accuracy usually have higher time complexity, the massive remote sensing image has brought great difficulties for realtime application. In this article, we propose a hybrid, heterogeneous parallel processing algorithm to improve the efficiency TCR based on the Crossmodel Neural Cognitive Computing (CNCC) algorithm [parallel TCR based on MapReduce of hierarchical CNCC (PTCR-C)]. Parallel programming technologies used in this article include Open Multiprocessing (OpenMP), Compute Unified Device Architecture (CUDA), and the message passing interface (MPI). Experiments on public remote sensing image data sets show that the PTCR-C algorithm can effectively improve the efficiency of the original TCR algorithm. The PTCR-C algorithm has better augmented ability and provides the reference for further real-time TCR of remote sensing applications.
- 31 January 2007
- Published by Elsevier in Neurocomputing
- Vol. 70 (4-6) , 809-818
A parallel hierarchical clustering algorithm for PCs cluster system
- 31 January 2007
- Published by Elsevier in Neurocomputing
- Vol. 70 (4-6) , 809-818
A parallel hierarchical clustering algorithm for PCs cluster system