Fangming Ruan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fangming Ruan has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Yanli Chen
School of Big Data and Computer Science, Guizhou Normal University, Guiyang, China
2 shared publicationsCheng Yang
School of Big Data and Computer Science, Guizhou Normal University, Guiyang, China
1 shared publicationChongzhen Zhang
School of Big Data and Computer Science
1 shared publicationKai Xu
Liupanshui Vocational College, Liupanshui, China
1 shared publication- Kui Zhou
Fiberhome StarrySky Company, Nanjing, China
1 shared publication Runze Chen
School of Big Data and Computer Science
1 shared publication
Latest Publications
- 30 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Plasma Science
- Vol. 51 (9) , 2602-2607
Analysis of Microgap Electrostatic Discharge Parameters With Algorithms of Neural Network and Wavelet Transform
Special relationship exists between environmental conditions and discharge characteristic parameters in microgap electrostatic discharge (ESD) events. Potential relations between input and output of neural network can be explored if taken discharge environmental factors as neural network input. The characteristic parameters of discharge results are affected by environmental conditions, and hence, discharge parameters can be described with an output of neural network. Circumstances factors effect on discharge parameters in microgap ESD result was analyzed with two algorithms of neural network wavelet transform combined with Kalman filter. Nonlinear relationship between circumstances conditions and discharge result effect was a feature in microgap ESD events. Strong positive relationship existed between discharge parameters and circumstances factors of electrode moving speed, gas pressure, and temperature. Characteristic parameters measured in real ESD experiment were compared to predictive parameters of calculation result from neural network algorithm. The analysis of accuracies was given on the prediction of discharge process trend compared to discharge current data measured in experiment. Noise in discharge current waveforms can be suppressed effectively with the method of wavelet transform combined with Kalman filter.
- 30 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Plasma Science
- Vol. 51 (9) , 2602-2607
Analysis of Microgap Electrostatic Discharge Parameters With Algorithms of Neural Network and Wavelet Transform
Special relationship exists between environmental conditions and discharge characteristic parameters in microgap electrostatic discharge (ESD) events. Potential relations between input and output of neural network can be explored if taken discharge environmental factors as neural network input. The characteristic parameters of discharge results are affected by environmental conditions, and hence, discharge parameters can be described with an output of neural network. Circumstances factors effect on discharge parameters in microgap ESD result was analyzed with two algorithms of neural network wavelet transform combined with Kalman filter. Nonlinear relationship between circumstances conditions and discharge result effect was a feature in microgap ESD events. Strong positive relationship existed between discharge parameters and circumstances factors of electrode moving speed, gas pressure, and temperature. Characteristic parameters measured in real ESD experiment were compared to predictive parameters of calculation result from neural network algorithm. The analysis of accuracies was given on the prediction of discharge process trend compared to discharge current data measured in experiment. Noise in discharge current waveforms can be suppressed effectively with the method of wavelet transform combined with Kalman filter.
- Open Access
- 25 January 2021
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-15
A Novel Framework Design of Network Intrusion Detection Based on Machine Learning Techniques
Traditional machine learning-based intrusion detection often only considers a single algorithm to identify intrusion data, lack of the flexibility method, low detection rate, no handing high-dimensional data, and cannot solve these problems well. In order to improve the performance of intrusion detection system, a novel general intrusion detection framework was proposed in this paper, which consists of five parts: preprocessing module, autoencoder module, database module, classification module, and feedback module. The data processed by the preprocessing module are compressed by the autoencoder module to obtain a lower-dimensional reconstruction feature, and the classification result is obtained through the classification module. Compressed features of each traffic are stored in the database module which can both provide retraining and testing for the classification module and restore these features to the original traffic for postevent analysis and forensics. For evaluation of the framework performance proposed, simulation was conducted with the CICIDS2017 dataset to the real traffic of the network. As the experimental results, the accuracy of binary classification and multiclass classification is better than previous work, and high-level accuracy was reached for the restored traffic. At the last, the possibility was discussed on applying the proposed framework to edge/fog networks.
- 25 January 2021
- Published by Wiley in Security and Communication Networks
- Vol. 2021, 1-15
Open AccessA Novel Framework Design of Network Intrusion Detection Based on Machine Learning Techniques
Traditional machine learning-based intrusion detection often only considers a single algorithm to identify intrusion data, lack of the flexibility method, low detection rate, no handing high-dimensional data, and cannot solve these problems well. In order to improve the performance of intrusion detection system, a novel general intrusion detection framework was proposed in this paper, which consists of five parts: preprocessing module, autoencoder module, database module, classification module, and feedback module. The data processed by the preprocessing module are compressed by the autoencoder module to obtain a lower-dimensional reconstruction feature, and the classification result is obtained through the classification module. Compressed features of each traffic are stored in the database module which can both provide retraining and testing for the classification module and restore these features to the original traffic for postevent analysis and forensics. For evaluation of the framework performance proposed, simulation was conducted with the CICIDS2017 dataset to the real traffic of the network. As the experimental results, the accuracy of binary classification and multiclass classification is better than previous work, and high-level accuracy was reached for the restored traffic. At the last, the possibility was discussed on applying the proposed framework to edge/fog networks.