An Algorithm of Clustering by Density Peaks Using in Anomaly Detection

Chunyong Yin,Sun Zhang,Zhichao Yin,Jin Wang 보안공학연구지원센터 2015 International Journal of Security and Its Applicat Vol.9 No.12

With the development of the networks, the security of computer networks is becoming more and more serious. The information openness, sharing and interconnection are three important characteristics of computer networks. However, the amounts of intruders and attackers have been grows with the popularization of computers. Therefore, the focus of network security is preventing systems from being invaded effectively. Intrusion detection as a key technology of network security active defense system is designed to distinguish normal behaviors and attack behaviors. Intrusion detection is divided into misuse detection and anomaly detection, and using clustering algorithm is one of the most effective methods for anomaly detection. In this paper, a clustering algorithm based on fast search and find of density peaks is used to distinguish the normal and abnormal network connections to achieve the purpose of anomaly detection. The performance of the algorithm is tested by a data set selected from KDD CUP99. Experiment results show that this algorithm is more suitable than the traditional K-means in data sets containing a large amount of data and uneven density distribution.

A Mobile Recommendation Algorithm Based on Statistical Analysis of User Data

Chunyong Yin,Hui Zhang,Jun Xiang,Zhichao Yin,Jin Wang 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.12

Recommendation technology is used to help people solve the problem of information overload. Recent years, it has been widely applied to the movie ratings, e-commerce and many other fields. Researchers have noticed its powerful application prospect. But with the exponential growth of information data, the recommendation systems also have to improve the ability of data processing and this leads to that the traditional collaborative filtering recommendation algorithms cannot meet the needs of the users. To solve the problem, we designed an algorithm based on the theory of statistical analysis. This algorithm classified the data simply firstly, and then system could give users the relatively satisfactory personalized recommendations by the statistical analysis of different attributes on the data sets.

Short Text Classification Algorithm Based on Semi-Supervised Learning and SVM

Chunyong Yin,Jun Xiang,Hui Zhang,Zhichao Yin,Jin Wang 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.12

Short text is a popular text form, which is widely used in real-time network news, short commentary, micro-blog and many other fields. With the development of the application such as QQ, mobile phone text messages and movie websites, the size of data is also becoming larger and larger. Most data is useless for us while other data is significant for us. Therefore, it is necessary for us to extract the useful short text from the big data. However, there are many problems with the short text classification, such as fewer features, irregularity and so on. To solve these problems, we should pretreat the short text set first, and then choose the significant features. This paper use semi-supervised learning method and SVM classifier to improve the traditional methods and it can classify a large number of short texts to mining the useful massage from the short text. The experimental results in this paper also show a good promotion.

A Feature Selection Algorithm based on Hoeffding Inequality and Mutual Information

Chunyong Yin,Lu Feng,Luyu Ma,Zhichao Yin,Jin Wang 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.11

With the rapid development of the Internet, the application of data mining in the Internet is becoming more and more extensive. However, the data source’s complex feature redundancy leads that data mining process becomes very inefficient and complex. So feature selection research is essential to make data mining more efficient and simple. In this paper, we propose a new way to measure the correlation degree of internal features of dataset which is a mutation of mutual information. Additionally we also introduce Hoeffding inequality as constraint of constructing algorithm. During the experiments, we use C4.5 classification algorithm as test algorithm and compare HSF with BIF(feature selection algorithm based on mutual information). Experiments results show that HSF performances better than BIF[1] in TP and FP rate, what’s more the feature subset obtained by HSF can significantly improve the TP, FP and memory usage of C4.5 classification algorithm.

Botnet Detection Based on Genetic Neural Network

Chunyong Yin,Ardalan Husin Awlla,Zhichao Yin,Jin Wang 보안공학연구지원센터 2015 International Journal of Security and Its Applicat Vol.9 No.11

Botnet have turned into the most serious security dangers on the present Internet framework. A botnet is most extensive and regularly happens in today's cyber-attacks, bringing about the serious risk of our system resources and association's properties. Botnets are accumulations of compromised computers (Bots) which are remotely regulated by its creator (BotMaster) under a typical Command-and-Control (C&C) framework. Botnets cannot just be implemented utilizing existing well-known applications and additionally developed by unknown or inventive applications. This makes the botnet detection a challenging issue. In this paper proposed an anomaly detection model based on genetic neural network system, which joined the significant global searching capability of genetic algorithm with the precise local searching element of back propagation feed forward neural networks to improve the initial weights of neural network.

A Feature Selection Algorithm towards Efficient Intrusion Detection

Chunyong Yin,Luyu Ma,Lu Feng,Zhichao Yin,Jin Wang 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.11

Feature selection algorithm plays a crucial role in intrusion detection, data mining and pattern recognition. According to some evaluation criteria, it gets optimal feature subset by deleting unrelated and redundant features of the original data set. Aiming at solving the problems about the low accuracy, the high false positive rate and the long detection time of the existing feature selection algorithm. In this paper, we come up with a feature selection algorithm towards efficient intrusion detection, this algorithm combines the correlation algorithm and redundancy algorithm to chooses the optimal feature subset. Experimental results show that the algorithm shows almost and even better than the traditional feature selection algorithm on the different classifiers.

Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network

Zhichao Wang,Hong Xia,Jiyu Zhang,Bo Yang,Wenzhe Yin Korean Nuclear Society 2023 Nuclear Engineering and Technology Vol.55 No.6

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

First principles study of carrier activity, lifetime and absorption spectrum to investigate effects of strain on the photocatalytic performance of doped ZnO

Hou Qingyu,Qi Mude,Yin Xiang,Wang Zhichao,Sha Shulin 한국물리학회 2022 Current Applied Physics Vol.33 No.-

Doping of isovalent (S, Se, and Te) elements in ZnO is a new doping method. However, the factors affecting the photocatalytic performance of a doped system by triaxial strain are often ignored. In this study, we have applied strain on model and performed first-principle calculation to investigate the effect of triaxial strain on the stability of the doped system, red shift of the absorption spectrum, electric dipole moment, and carrier lifetime. Calculation results showed that all doped systems exhibited high binding energy and stability under unstrained conditions. However, when the applied strain was increased, the energy of all the systems increased, and the stability decreased. The stability, red shift of absorption spectrum, electric dipole moment, and carrier lifetime of all doped systems were studied. When the tensile strain was 5%, the red shift of the absorption spectrum and the electric dipole moment of the doped system (Zn36SO35) were the largest. Moreover, the carrier lifetime of the doped system (Zn36SO35) was the longest. Considering the red shift of the absorption spectrum, electric dipole moment, and carrier lifetime, the photocatalytic performance of the doped system (Zn36SO35) was the best, when the tensile strain was 5%.