Mechanism of situation element acquisition based on deep auto-encoder network in wireless sensor networks

In order to reduce the time complexity of situation element acquisition and to cope with the low detection accuracy of small class samples caused by imbalanced class distribution of attack samples in wireless sensor networks, a situation element extraction mechanism based on deep auto-encoder network is proposed. In this mechanism, the deep auto-encoder network is introduced as basic classifier to identify data type. In hierarchical training of the auto-encoder, a training method based on cross-entropy loss function and back-propagation algorithm is proposed to overcome the problem of weights updating too slow by the traditional variance cost function, and the momentum factors are added to improve the convergence performance. Meanwhile, in the stage of fine-tuning and classification of the deep network, an active online sampling algorithm is proposed to select the sample online for updating the network weights, so as to eliminate redundancy of the total samples, balance the amounts of all sample types, and improve the classification accuracy of small sample. Through the simulation and analysis of the instance data, the scheme has a good accuracy of situation factors extraction.

[1]  Jian Wang,et al.  Large-Scale Network Intrusion Detection Algorithm Based on Distributed Learning: Large-Scale Network Intrusion Detection Algorithm Based on Distributed Learning , 2010 .

[2]  Saad B. Qaisar,et al.  Quarter-Sphere SVM: Attribute and Spatio-Temporal correlations based Outlier & Event Detection in wireless sensor networks , 2012, 2012 IEEE Wireless Communications and Networking Conference (WCNC).

[3]  Xin Yao,et al.  Multiclass Imbalance Problems: Analysis and Potential Solutions , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[5]  Sushil Jajodia,et al.  Applications of Data Mining in Computer Security , 2002, Advances in Information Security.

[6]  Khalil El-Khatib,et al.  Impact of Feature Reduction on the Efficiency of Wireless Intrusion Detection Systems , 2010, IEEE Transactions on Parallel and Distributed Systems.

[7]  Nicolas Le Roux,et al.  Deep Belief Networks Are Compact Universal Approximators , 2010, Neural Computation.

[8]  Laurence T. Yang,et al.  Deep Computation Model for Unsupervised Feature Learning on Big Data , 2016, IEEE Transactions on Services Computing.

[9]  Robert K. Cunningham,et al.  Fusing A Heterogeneous Alert Stream Into Scenarios , 2002, Applications of Data Mining in Computer Security.

[10]  David A. Cohn,et al.  Neural Network Exploration Using Optimal Experiment Design , 1993, NIPS.

[11]  Xu Yang,et al.  Improving the Particle Swarm Algorithm and Optimizing the Network Intrusion Detection of Neural Network , 2015, 2015 Sixth International Conference on Intelligent Systems Design and Engineering Applications (ISDEA).

[12]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[13]  Pedro Antonio Gutiérrez,et al.  Graph-Based Approaches for Over-Sampling in the Context of Ordinal Regression , 2015, IEEE Transactions on Knowledge and Data Engineering.

[14]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[16]  Kuheli Roy Sarkar.  Assessing insider threats to information security using technical, behavioural and organisational measures , 2010, Inf. Secur. Tech. Rep..

[17]  Wang Jian,et al.  Large-Scale Network Intrusion Detection Algorithm Based on Distributed Learning , 2008 .

[18]  Ivan Martinovic,et al.  Key Generation in Wireless Sensor Networks Based on Frequency-selective Channels - Design, Implementation, and Analysis , 2010, ArXiv.

[19]  Hien M. Nguyen,et al.  A comparative study on sampling techniques for handling class imbalance in streaming data , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.

[20]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[21]  Giuseppe De Pietro,et al.  Situation Awareness in Applications of Ambient Assisted Living for Cognitive Impaired People , 2013, Mob. Networks Appl..

[22]  Wenyuan Wang,et al.  An Over-sampling Expert System for Learing from Imbalanced Data Sets , 2005, 2005 International Conference on Neural Networks and Brain.

[23]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[24]  Kai Hwang,et al.  Skyline Discovery and Composition of Multi-Cloud Mashup Services , 2016, IEEE Transactions on Services Computing.

[25]  Hiroshi Mineno,et al.  Adaptive data aggregation scheme in clustered wireless sensor networks , 2008, Comput. Commun..

[26]  Geoffrey E. Hinton,et al.  Deep, Narrow Sigmoid Belief Networks Are Universal Approximators , 2008, Neural Computation.

[27]  Haibo Zhang,et al.  Event-Centric Situation Trust Data Aggregation Mechanism in Distributed Wireless Network , 2014, Int. J. Distributed Sens. Networks.

[28]  S. S. Halilcevic,et al.  The short term electricity prices forecasting using Markov chains , 2011, 2011 8th International Conference on the European Energy Market (EEM).