Yunke Xiong
Research Subjects
Yunke Xiong has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Qun Hou
Jianghan University, China
2 shared publications - Xin Liu
CSSC(Wuhan) LINGJIU HI-TECH CO.,LTD., China
2 shared publications - Zhixiang Yang
Wuhan Digital Engineering Research Institute
2 shared publications - Jiaxuan Wang
Wuhan Institute of Posts and Telecommunications, Wuhan, Hubei, China
1 shared publication - Jun Tan
Jianghan University, China and CSSC(Wuhan) LINGJIU HI-TECH CO.,LTD., China
1 shared publication - Xiaotao Yang
CSSC LINGJIU HI-TECH(Wuhan) Co., LTD., China
1 shared publication
Latest Publications
- Open Access
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 451-456
Entity Similarity Matching Algorithm Based on Gain Coefficient and User Query Text
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 451-456
Open AccessEntity Similarity Matching Algorithm Based on Gain Coefficient and User Query Text
- Open Access
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 140-146
Research on the classification method of hierarchical SVM decision tree based on adaptive mutation particle swarm optimization algorithm
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 140-146
Open AccessResearch on the classification method of hierarchical SVM decision tree based on adaptive mutation particle swarm optimization algorithm
- Open Access
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 507-511
Chemical motion target monitoring method based on LK optical flow and momentum method
In response to the current shortcomings of slow detection speed and poor performance in chemical motion target detection, this article provides a chemical motion target monitoring method based on LK optical flow and momentum methods. Firstly, the real-time video stream of the camera is obtained, and the image is captured at frame rate and cropped according to the region of interest. Then, the sparse optical flow two-dimensional vector is calculated, converted into a two-dimensional image, and the pixel total is calculated. The momentum method is used to calculate the momentum and update it in real time, and the ratio of the pixel total to the momentum is calculated. If it exceeds the threshold, it is judged that the motion target detection is abnormal, and an alarm message is issued. This method will maximize the advantages of video surveillance technology, achieve artificial intelligence analysis and judgment of video images, save a lot of human resources and costs, improve the efficiency and reliability of monitoring, and provide important guarantees for the safe operation and management of chemical product production.
- 24 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 507-511
Open AccessChemical motion target monitoring method based on LK optical flow and momentum method
In response to the current shortcomings of slow detection speed and poor performance in chemical motion target detection, this article provides a chemical motion target monitoring method based on LK optical flow and momentum methods. Firstly, the real-time video stream of the camera is obtained, and the image is captured at frame rate and cropped according to the region of interest. Then, the sparse optical flow two-dimensional vector is calculated, converted into a two-dimensional image, and the pixel total is calculated. The momentum method is used to calculate the momentum and update it in real time, and the ratio of the pixel total to the momentum is calculated. If it exceeds the threshold, it is judged that the motion target detection is abnormal, and an alarm message is issued. This method will maximize the advantages of video surveillance technology, achieve artificial intelligence analysis and judgment of video images, save a lot of human resources and costs, improve the efficiency and reliability of monitoring, and provide important guarantees for the safe operation and management of chemical product production.
- Open Access
- 5 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 53-60
Neural Network Optimization Objective Vector Representation based on Genetic Algorithm and Its Multi-objective Optimization Method
Deep learning algorithms mostly have network parameters that can affect their training results, and the combination of neural network architectures also has a significant impact on the algorithm performance. The performance of deep learning algorithms is usually proportional to the overall number of network parameters, leading to excessive resource consumption for exploring neural network architectures with a large number of hyper-parameters. To solve this problem, a vector representation is proposed which for neural network architectures, and a multi-objective optimization model is established based on genetic algorithms in this paper, and it is short for “NNOO Vector Representation based on GA and Its Optimization Method”. The multi-objective optimization model can automatically optimize the neural network architecture and hyper-parameters in the network, improve the network accuracy, and reduce the overall number of network parameters. It is shown in the test results with the MNIST data set, and the accuracy is 95.61% for the traditional empirical setting network, and the average accuracy is 86.2% for the network optimized by TensorFlow’s optimization algorithm. While the network accuracy is improved to 96.86% with the proposed optimization method in this paper and the network parameters are reduced by 32.6% compared with the traditional empirical network, and the network parameters are reduced by13.2% compared with the network by TensorFlow’s optimization algorithm. Therefore, the method is presented which has obvious practical application value in neural network optimization problems and provides a new way of thinking for large and deep network optimization problems.
- 5 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 53-60
Open AccessNeural Network Optimization Objective Vector Representation based on Genetic Algorithm and Its Multi-objective Optimization Method
Deep learning algorithms mostly have network parameters that can affect their training results, and the combination of neural network architectures also has a significant impact on the algorithm performance. The performance of deep learning algorithms is usually proportional to the overall number of network parameters, leading to excessive resource consumption for exploring neural network architectures with a large number of hyper-parameters. To solve this problem, a vector representation is proposed which for neural network architectures, and a multi-objective optimization model is established based on genetic algorithms in this paper, and it is short for “NNOO Vector Representation based on GA and Its Optimization Method”. The multi-objective optimization model can automatically optimize the neural network architecture and hyper-parameters in the network, improve the network accuracy, and reduce the overall number of network parameters. It is shown in the test results with the MNIST data set, and the accuracy is 95.61% for the traditional empirical setting network, and the average accuracy is 86.2% for the network optimized by TensorFlow’s optimization algorithm. While the network accuracy is improved to 96.86% with the proposed optimization method in this paper and the network parameters are reduced by 32.6% compared with the traditional empirical network, and the network parameters are reduced by13.2% compared with the network by TensorFlow’s optimization algorithm. Therefore, the method is presented which has obvious practical application value in neural network optimization problems and provides a new way of thinking for large and deep network optimization problems.
- Open Access
- 5 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 18-25
Research on energy consumption prediction based on fast attribute reduction of weighted neighborhood rough set with moving horizon
In actual prediction scenarios, attribute features include time data, weather data, and energy consumption data. The relationship between attribute features is very complex. Exploring the relationship between feature attributes and decision sets with fast attribute reduction can reduce the amount of model training data. Since seasonal and temporal variations greatly influence weather and energy consumption data, the moving horizon method is used to update the features and improve the accuracy of energy consumption prediction.From above, an energy consumption prediction model based on fast attribute reduction of weighted neighborhood rough set with moving horizon long short-term memory neural network(LSTM) is proposed in this paper. In the experiment of predicting the actual energy consumption of a building, the model evaluation results show that 20% of training data is reduced at the expense of 0.4% classification accuracy. Compared with the traditional non-rolling method, the Root Mean Square Error (RMSE) of the moving horizon LSTM prediction method is reduced by 33.08% on average, and the training speed is increased by 5.25% on average. The prediction effect is better. Therefore, this prediction model can be used to predict building energy consumption quickly and accurately and has strong robustness and generalization ability, which provides the theoretical basis and method support for fine management of building energy consumption, building energy conservation, and emission reduction.
- 5 January 2023
- Published by Association for Computing Machinery (ACM)
- p. 18-25
Open AccessResearch on energy consumption prediction based on fast attribute reduction of weighted neighborhood rough set with moving horizon
In actual prediction scenarios, attribute features include time data, weather data, and energy consumption data. The relationship between attribute features is very complex. Exploring the relationship between feature attributes and decision sets with fast attribute reduction can reduce the amount of model training data. Since seasonal and temporal variations greatly influence weather and energy consumption data, the moving horizon method is used to update the features and improve the accuracy of energy consumption prediction.From above, an energy consumption prediction model based on fast attribute reduction of weighted neighborhood rough set with moving horizon long short-term memory neural network(LSTM) is proposed in this paper. In the experiment of predicting the actual energy consumption of a building, the model evaluation results show that 20% of training data is reduced at the expense of 0.4% classification accuracy. Compared with the traditional non-rolling method, the Root Mean Square Error (RMSE) of the moving horizon LSTM prediction method is reduced by 33.08% on average, and the training speed is increased by 5.25% on average. The prediction effect is better. Therefore, this prediction model can be used to predict building energy consumption quickly and accurately and has strong robustness and generalization ability, which provides the theoretical basis and method support for fine management of building energy consumption, building energy conservation, and emission reduction.