Application of neural networks in identification of measurement anomaly detection
Journal Title: International Research Journal of Applied and Basic Sciences - Year 2013, Vol 4, Issue 8
Abstract
Most current Intrusion Detection Systems (IDS) examine all data features to detect intrusion. Also existing intrusion detection approaches have some limitations, namely impossibility to process large number of audit data for real-time operation, low detection and recognition accuracy. To overcome these limitations, we apply modular neural network models to detect and recognize attacks in computer networks. It is based on combination of principal component analysis (PCA) neural networks and multilayer perceptrons (MLP). PCA networks are employed for important data extraction and to reduce high dimensional data vectors. We present two PCA neural networks for feature extraction: linear PCA (LPCA) and nonlinear PCA (NPCA). MLP is employed to detect and recognize attacks using feature-extracted data instead of original data. The proposed approaches are tested using KDD-99 dataset. The experimental results demonstrate that the designed models are promising in terms of accuracy and computational time for real world intrusion detection.
Authors and Affiliations
Morteza salari akhgar| Department of computer, Ghorveh Branch, Islamic Azad University, GHorveh, Iran, Hamdollah Ghamgin| Zanjan Branch, Islamic Azad University, Zanjan, Iran., Mohammad Taghi Jafari| Zanjan Branch, Islamic Azad University, Zanjan, Iran.
Keywords
Related Articles
- EP ID EP5576
- DOI -
- Views 326
- Downloads 9
Non-pharmacological Treatment of Addiction
Drug abuse is a chronic, recurrent disorder which causes both physical and psychological damages to the patients. Due to the direct, complex effect of drugs on the nervous system, the patients experience annoying symptom...
The approach of stochastic frontier analysis for determining technical efficiency of Date gardens in bam
Dates in the city of Kerman s one of the strategic products. Given that this product has a large role in the employment of people in this country. In as much evaluate the performance of the product is important. In this...
An Optimal Mammogram Image Compression based on Neural Network Classifier and the Newton Algorithm
In Telemedicine, digital utilization for medical diagnosis increase the storage resource requirement for archive the images and uncompressed data requires considerable storage capacity and transmission bandwidth. Success...
The Position of Green Space in Promoting Urban Space Quality
The ever-increasing growth of urbanization, irregular population growth, multiplicity of motor vehicles, extra use of fossil energies, expansion of constructed buildings and separation of cities from the nature, as well...
A Reversible Data Hiding Scheme Using Multi-layer Embedding for Intelligent Transportation Systems Images
This paper proposes a lossless or reversible data hiding method which is based on the pixel difference histogram shifting for images in intelligent transportation systems (ITS) in spatial domain. Pixel differences are ge...