Yun Sha
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
Research Subjects
Yun Sha has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Xuejun Liu
College of Information Engineering Beijing Institute of Petrochemical Technology Beijing China
5 shared publications - Yong Yan
Beijing Inst Petrochem Technol, Coll Informat Engn, 19 Qingyuan North Rd, Beijing 102617, Peoples R China
4 shared publications - Hai-Ying Luan
Beijing Res Inst Automat Machinery Ind CO LTD, Fluid Power & Automot Equipment Ctr, Beijing 100120, Peoples R China
2 shared publications - Jian-Ping Chen
College of Information Engineering, Beijing Institute of Petrochemical Technology, 19 Qingyuan North Road, Daxing District, Beijing, China
2 shared publications - Jiayi Liu
Information Engineering College, Beijing Institute of Petrochemical Technology, Beijing 102617, China
2 shared publications Xuejun Liu
College of Information Engineering, Beijing Institute of Petrochemical Technology, 19 Qingyuan North Road, Daxing District, Beijing 102617, China
2 shared publications
Latest Publications
- Open Access
- 19 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 547-552
CTU-DDPM: Generating Industrial Control System Time-Series Data with a CNN-Transformer Hybrid Diffusion Model
- 19 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 547-552
Open AccessCTU-DDPM: Generating Industrial Control System Time-Series Data with a CNN-Transformer Hybrid Diffusion Model
- Open Access
- 23 October 2024
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 60 (20)
FAFTransformer: Multivariate time series prediction method based on multi‐period feature recombination
Multivariate time series forecasting is widely used in various fields in real life. Many time series prediction models have been proposed. The current forecasting model lacks the mining of correlation between sequences based on different periods and correlation of periodical features between different periods when dealing with data. In this paper, we propose a multivariate data prediction model FAFTransformer based on the reorganization of multi‐periodic features, which first extracts the multi‐periodic information of the time series using the method of frequency domain analysis. The temporal dependencies within sequences are then captured using convolution based on different periods, and the correlations between sequences are learned by combining the multivariate attention mechanism to obtain the intra‐sequence and inter‐sequence correlations under the same period. Finally, period fusion is proposed to capture the correlation of period characteristics between different periods. The experimental results show that the model achieves the best results on multiple datasets compared to the latest seven predictive models for time‐series data.
- 23 October 2024
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 60 (20)
Open AccessFAFTransformer: Multivariate time series prediction method based on multi‐period feature recombination
Multivariate time series forecasting is widely used in various fields in real life. Many time series prediction models have been proposed. The current forecasting model lacks the mining of correlation between sequences based on different periods and correlation of periodical features between different periods when dealing with data. In this paper, we propose a multivariate data prediction model FAFTransformer based on the reorganization of multi‐periodic features, which first extracts the multi‐periodic information of the time series using the method of frequency domain analysis. The temporal dependencies within sequences are then captured using convolution based on different periods, and the correlations between sequences are learned by combining the multivariate attention mechanism to obtain the intra‐sequence and inter‐sequence correlations under the same period. Finally, period fusion is proposed to capture the correlation of period characteristics between different periods. The experimental results show that the model achieves the best results on multiple datasets compared to the latest seven predictive models for time‐series data.
- Open Access
Anomaly Detection Method for Industrial Control System Operation Data Based on Time–Frequency Fusion Feature Attention Encoding
Anomaly detection in industrial control system (ICS) data is one of the key technologies for ensuring the security monitoring of ICSs. ICS data are characterized as complex, multi-dimensional, and long-sequence time-series data that embody ICS business logic. Due to its complex and varying periodic characteristics, as well as the presence of long-distance and misaligned temporal associations among features, current anomaly detection methods in ICS are insufficient for feature extraction. This paper proposes an anomaly detection method named TFANet, based on time–frequency fusion feature attention encoding. Considering that periodic variations are more concentrated in the frequency domain, this method first transforms the time-domain data into the frequency domain, obtaining both amplitude and phase data. Then, these data, together with the original time-series data, are used to extract features from two perspectives: long-term temporal changes and long-distance associations. Finally, the six features learned from both the time and frequency domains are fused, and the feature weights are calculated using an attention mechanism to complete the anomaly classification. In multi-classification tasks on three ICS datasets, the proposed method outperforms three popular time-series models—iTransformer, Crossformer, and TimesNet—across five metrics: accuracy, precision, recall, F1 score, and AUC-ROC, with average improvements of approximately 19%, 37%, 31%, 35%, and 22%, respectively.
Open AccessAnomaly Detection Method for Industrial Control System Operation Data Based on Time–Frequency Fusion Feature Attention Encoding
Anomaly detection in industrial control system (ICS) data is one of the key technologies for ensuring the security monitoring of ICSs. ICS data are characterized as complex, multi-dimensional, and long-sequence time-series data that embody ICS business logic. Due to its complex and varying periodic characteristics, as well as the presence of long-distance and misaligned temporal associations among features, current anomaly detection methods in ICS are insufficient for feature extraction. This paper proposes an anomaly detection method named TFANet, based on time–frequency fusion feature attention encoding. Considering that periodic variations are more concentrated in the frequency domain, this method first transforms the time-domain data into the frequency domain, obtaining both amplitude and phase data. Then, these data, together with the original time-series data, are used to extract features from two perspectives: long-term temporal changes and long-distance associations. Finally, the six features learned from both the time and frequency domains are fused, and the feature weights are calculated using an attention mechanism to complete the anomaly classification. In multi-classification tasks on three ICS datasets, the proposed method outperforms three popular time-series models—iTransformer, Crossformer, and TimesNet—across five metrics: accuracy, precision, recall, F1 score, and AUC-ROC, with average improvements of approximately 19%, 37%, 31%, 35%, and 22%, respectively.
- Open Access
- 5 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (17) , 8889
Adaptive Industrial Control System Attack Sample Expansion Algorithm Based on Generative Adversarial Network
The scarcity of attack samples is the bottleneck problem of anomaly detection of underlying business data in the industrial control system. Predecessors have done a lot of research on temporal data generation, but most of them are not suitable for industrial control attack sample generation. The change patterns of the characteristics of the underlying business data attack samples can be divided into three types: oscillation type, step type, and pulse type. This paper proposes an adaptive industrial control attack sample expansion algorithm based on GAN, which expands the three types of features in different ways. The basic network structure of data expansion adopts GAN. According to the characteristics of oscillation type changes, momentum is selected as the optimizer. Aiming at the characteristics of step type changes, the Adam optimization method is improved. For pulse type features, attack samples are generated according to the location and length of the pulse. Compared with previous time-series data generation methods, this method is more targeted for each feature and has higher similarities.
- 5 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (17) , 8889
Open AccessAdaptive Industrial Control System Attack Sample Expansion Algorithm Based on Generative Adversarial Network
The scarcity of attack samples is the bottleneck problem of anomaly detection of underlying business data in the industrial control system. Predecessors have done a lot of research on temporal data generation, but most of them are not suitable for industrial control attack sample generation. The change patterns of the characteristics of the underlying business data attack samples can be divided into three types: oscillation type, step type, and pulse type. This paper proposes an adaptive industrial control attack sample expansion algorithm based on GAN, which expands the three types of features in different ways. The basic network structure of data expansion adopts GAN. According to the characteristics of oscillation type changes, momentum is selected as the optimizer. Aiming at the characteristics of step type changes, the Adam optimization method is improved. For pulse type features, attack samples are generated according to the location and length of the pulse. Compared with previous time-series data generation methods, this method is more targeted for each feature and has higher similarities.
- 30 June 2022
- Published by ICI Bucharest in Studies in Informatics and Control
- Vol. 31 (2) , 5-14
Industrial Intrusion Detection Classifier Pruning via Hybrid-order Difference of Weights Based on Poisson Distribution
- 30 June 2022
- Published by ICI Bucharest in Studies in Informatics and Control
- Vol. 31 (2) , 5-14
Industrial Intrusion Detection Classifier Pruning via Hybrid-order Difference of Weights Based on Poisson Distribution
- RetractedOpen Access
- 28 April 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-10
Feature Sequencing Method of Industrial Control Data Set Based on Multidimensional Evaluation Parameters
The industrial control data set has many features and large redundancy, which has a certain impact on the training speed and classification results of the neural network anomaly detection algorithm. However, features are independent of each other, and dimension reduction often increases the false positive rate and false negative rate. The feature sequencing algorithm can reduce this effect. In order to select the appropriate feature sequencing algorithm for different data sets, this paper proposes an adaptive feature sequencing method based on data set evaluation index parameters. Firstly, the evaluation index system is constructed by the basic information of the data set, the mathematical characteristics of the data set, and the association degree of the data set. Then, the selection model is obtained by the decision tree training with the data label and the evaluation index, and the suitable feature sequencing algorithm is selected. Experiments were conducted on 11 data sets, including Batadal data set, CICIDS 2017, and Mississippi data set. The sequenced data sets are classified by ResNet. The accuracy of the sequenced data sets increases by 2.568% on average in 30 generations, and the average time reduction per epoch is 24.143%. Experiments show that this method can effectively select the feature sequencing algorithm with the best comprehensive performance.
- 28 April 2022
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-10
RetractedOpen AccessFeature Sequencing Method of Industrial Control Data Set Based on Multidimensional Evaluation Parameters
The industrial control data set has many features and large redundancy, which has a certain impact on the training speed and classification results of the neural network anomaly detection algorithm. However, features are independent of each other, and dimension reduction often increases the false positive rate and false negative rate. The feature sequencing algorithm can reduce this effect. In order to select the appropriate feature sequencing algorithm for different data sets, this paper proposes an adaptive feature sequencing method based on data set evaluation index parameters. Firstly, the evaluation index system is constructed by the basic information of the data set, the mathematical characteristics of the data set, and the association degree of the data set. Then, the selection model is obtained by the decision tree training with the data label and the evaluation index, and the suitable feature sequencing algorithm is selected. Experiments were conducted on 11 data sets, including Batadal data set, CICIDS 2017, and Mississippi data set. The sequenced data sets are classified by ResNet. The accuracy of the sequenced data sets increases by 2.568% on average in 30 generations, and the average time reduction per epoch is 24.143%. Experiments show that this method can effectively select the feature sequencing algorithm with the best comprehensive performance.
- Open Access
- 20 March 2022
- Published by Hindawi Limited in Mobile Information Systems
- Vol. 2022, 1-13
SingleNet: A Lightweight Convolutional Neural Network for Safety Detection of an Industrial Control System
The traditional industrial control security research mainly focuses on network intrusion detection or trapping system and lacks abnormal detection after intrusion, and the abnormal detection algorithm ability of the underlying operation data of industrial control is insufficient. The modern industrial control system is a side-cloud collaborative architecture that accesses the Internet, the edge side is usually an industrial computer with weak computing power, and the deep learning algorithm requires a lot of computing resources and is difficult to use directly on the edge side. In this paper, a lightweight convolutional neural network anomaly detection algorithm SingleNet suitable for the edge side of the industrial control system is proposed, which convolutes the data of each sensor for a period of time and calculates the feature correlation between points in the association calculation layer. Experimental results show that the accuracy rate on the oil depot dataset is increased from 73 to 99.4, the training time is shortened from 2 hours to 3 minutes, and the model size is compressed from 101MB to 1.6MB. The accuracy rate is improved from 87 to 99.2 on the Mississippi dataset, the training time is shortened from 15 minutes to 3 minutes, and the model size is compressed from 10.6MB to 1.63MB. The accuracy rate is improved from 85 to 99.4 on the Batadal dataset, the training time is shortened from 18 minutes to 3 minutes, and the model size is compressed from 15.5MB to 1.62MB. Compared with several lightweight algorithms recently proposed, SqueezeNet, MobileNet, and ShuffleNet, the proposed algorithm has significantly improved the performance indicators of training speed, accuracy, model size, and iteration time on the industrial control datasets. Both the training and testing of the algorithm can be done on the CPU, making it possible to apply deep learning to the edge side of the industrial control system.
- 20 March 2022
- Published by Hindawi Limited in Mobile Information Systems
- Vol. 2022, 1-13
Open AccessSingleNet: A Lightweight Convolutional Neural Network for Safety Detection of an Industrial Control System
The traditional industrial control security research mainly focuses on network intrusion detection or trapping system and lacks abnormal detection after intrusion, and the abnormal detection algorithm ability of the underlying operation data of industrial control is insufficient. The modern industrial control system is a side-cloud collaborative architecture that accesses the Internet, the edge side is usually an industrial computer with weak computing power, and the deep learning algorithm requires a lot of computing resources and is difficult to use directly on the edge side. In this paper, a lightweight convolutional neural network anomaly detection algorithm SingleNet suitable for the edge side of the industrial control system is proposed, which convolutes the data of each sensor for a period of time and calculates the feature correlation between points in the association calculation layer. Experimental results show that the accuracy rate on the oil depot dataset is increased from 73 to 99.4, the training time is shortened from 2 hours to 3 minutes, and the model size is compressed from 101MB to 1.6MB. The accuracy rate is improved from 87 to 99.2 on the Mississippi dataset, the training time is shortened from 15 minutes to 3 minutes, and the model size is compressed from 10.6MB to 1.63MB. The accuracy rate is improved from 85 to 99.4 on the Batadal dataset, the training time is shortened from 18 minutes to 3 minutes, and the model size is compressed from 15.5MB to 1.62MB. Compared with several lightweight algorithms recently proposed, SqueezeNet, MobileNet, and ShuffleNet, the proposed algorithm has significantly improved the performance indicators of training speed, accuracy, model size, and iteration time on the industrial control datasets. Both the training and testing of the algorithm can be done on the CPU, making it possible to apply deep learning to the edge side of the industrial control system.
- 30 September 2021
- Published by ICI Bucharest in Studies in Informatics and Control
- Vol. 30 (3) , 39-49
A Method Based on Multiple Population Genetic Algorithm to Select Hyper-Parameters of Industrial Intrusion Detection Classifier
- 30 September 2021
- Published by ICI Bucharest in Studies in Informatics and Control
- Vol. 30 (3) , 39-49
A Method Based on Multiple Population Genetic Algorithm to Select Hyper-Parameters of Industrial Intrusion Detection Classifier
- Open Access
- 1 February 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1828 (1) , 012123
Attack Sample Generation Algorithm Based on Dual Discriminant Model in Industrial Control System
The research of intrusion anomaly detection in industrial control system is facing the problem of few attack samples. This paper proposes an attack data sample generation algorithm based on dual discriminant model. Firstly, a few attack samples are generated by multiple attacks based on the original data set. Secondly, the sparse matrix algorithm is used to expand the data set, and the original data features are distributed to each extended data to ensure the authenticity of the seed data. Finally, a large number of attack samples are generated by the dual discriminant model to complete the sample expansion. The experimental results of Mississippi SCADA natural gas pipeline data set and an industrial control system data set show that, based on keeping the data in a reasonable range, the algorithm can obtain an effectively expanded sample data set. SVM, Random Forest and XGBOOST are used to classify the dataset. The results show that AUC index is better than the negative sample data set generated by traditional GAN algorithm, and is similar to the initial negative sample index.
- 1 February 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1828 (1) , 012123
Open AccessAttack Sample Generation Algorithm Based on Dual Discriminant Model in Industrial Control System
The research of intrusion anomaly detection in industrial control system is facing the problem of few attack samples. This paper proposes an attack data sample generation algorithm based on dual discriminant model. Firstly, a few attack samples are generated by multiple attacks based on the original data set. Secondly, the sparse matrix algorithm is used to expand the data set, and the original data features are distributed to each extended data to ensure the authenticity of the seed data. Finally, a large number of attack samples are generated by the dual discriminant model to complete the sample expansion. The experimental results of Mississippi SCADA natural gas pipeline data set and an industrial control system data set show that, based on keeping the data in a reasonable range, the algorithm can obtain an effectively expanded sample data set. SVM, Random Forest and XGBOOST are used to classify the dataset. The results show that AUC index is better than the negative sample data set generated by traditional GAN algorithm, and is similar to the initial negative sample index.
- 1 January 2012
- Published by Springer Nature
- p. 125-131
Word Semantic Orientation Calculation Algorithm Based on Dynamic Standard Word Set
- 1 January 2012
- Published by Springer Nature
- p. 125-131
Word Semantic Orientation Calculation Algorithm Based on Dynamic Standard Word Set