TY - JOUR
KW - Fuzzy
KW - Clustering
KW - Anomaly Detection
KW - Intrusion Detection
KW - Principal Component Analysis
KW - Robust Spatial Kernel Fuzzy C-Means
AU - B S Harish
AU - S V A Kumar
AB - This paper presents a network anomaly detection method based on fuzzy clustering. Computer security has become an increasingly vital field in computer science in response to the proliferation of private sensitive information. As a result, Intrusion Detection System has become an indispensable component of computer security. The proposed method consists of three steps: Pre-Processing, Feature Selection and Clustering. In pre-processing step, the duplicate samples are eliminated from the sample set. Next, principal component analysis is adopted to select the most discriminative features. In clustering step, the network samples are clustered using Robust Spatial Kernel Fuzzy C-Means (RSKFCM) algorithm. RSKFCM is a variant of traditional Fuzzy C-Means which considers the neighbourhood membership information and uses kernel distance metric. To evaluate the proposed method, we conducted experiments on standard dataset and compared the results with state-of-the-art methods. We used cluster validity indices, accuracy and false positive rate as performance metrics. Experimental results inferred that, the proposed method achieves better results compared to other methods.
IS - Regular Issue
M1 - 6
N2 - This paper presents a network anomaly detection method based on fuzzy clustering. Computer security has become an increasingly vital field in computer science in response to the proliferation of private sensitive information. As a result, Intrusion Detection System has become an indispensable component of computer security. The proposed method consists of three steps: Pre-Processing, Feature Selection and Clustering. In pre-processing step, the duplicate samples are eliminated from the sample set. Next, principal component analysis is adopted to select the most discriminative features. In clustering step, the network samples are clustered using Robust Spatial Kernel Fuzzy C-Means (RSKFCM) algorithm. RSKFCM is a variant of traditional Fuzzy C-Means which considers the neighbourhood membership information and uses kernel distance metric. To evaluate the proposed method, we conducted experiments on standard dataset and compared the results with state-of-the-art methods. We used cluster validity indices, accuracy and false positive rate as performance metrics. Experimental results inferred that, the proposed method achieves better results compared to other methods.
PY - 2017
SP - 54
EP - 59
T2 - International Journal of Interactive Multimedia and Artificial Intelligence
TI - Anomaly based Intrusion Detection using Modified Fuzzy Clustering
UR - http://www.ijimai.org/journal/sites/default/files/files/2017/05/ijimai20174_6_8_pdf_14933.pdf
VL - 4
SN - 1989-1660
ER -