• PDF / 1,562,369 Bytes
• 10 Pages / 595.276 x 790.866 pts Page_size
• 47 Downloads / 205 Views

DOWNLOAD

REPORT

---

ORIGINAL ARTICLE

Toward an efficient fuzziness based instance selection methodology for intrusion detection system Rana Aamir Raza Ashfaq1,2 • Yu-lin He1 • De-gang Chen3

Received: 3 May 2016 / Accepted: 2 June 2016 Ó Springer-Verlag Berlin Heidelberg 2016

Abstract Building a high quality classifier is one of the key problems in the field of machine learning (ML) and pattern recognition. Many ML algorithms have suffered from high computational power in the presence of large scale data sets. This paper proposes a fuzziness based instance selection technique for the large data sets to increase the efficiency of supervised learning algorithms by improving the shortcomings of designing an effective intrusion detection system (IDS). The proposed methodology is dependent on a new kind of single layer feedforward neural network (SLFN), called random weight neural network (RWNN). At the first stage, a membership vector corresponding to every training instance is obtained by using RWNN for computing the fuzziness. Secondly, the training instances (along with their fuzziness values) according to the actual class labels are grouped separately. After this, the instances having low fuzziness values in each group are extracted, which are used to build a reduced data set. The instances outputted by the proposed method are used as an input for ML classifiers, which result in reducing the learning time and also increasing the learning & Yu-lin He [email protected] Rana Aamir Raza Ashfaq [email protected]; [email protected] De-gang Chen [email protected] 1

College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China

2

Department of Computer Science, Bahauddin Zakariya University, Multan, Pakistan

3

Department of Mathematics and Physics, North China Electric Power University, Beijing 102206, China

capability. The proposed methodology exhibits that the reduced data set can easily learn the boundaries between class labels. The most obvious finding from this study is a considerable increase in the accuracy rate with unseen examples when compared with other instance selection method, i.e., IB2. The proposed method provides the better generalization and fast learning capability. The reasonability of the proposed methodology is theoretically explained and experiments on well known ID data sets support its usefulness. Keywords Instance selection  Intrusion detection system  Random weight neural network  Sample reduction  Fuzziness

1 Introduction Artificial intelligence (AI) based intrusion detection systems (IDSs) have attracted much concerns from researchers in recent decades. Many AI based IDSs could suffer from high computational power due to large scale data sets. Various AI classification techniques, e.g., naive Bayes (NB) [28, 35], k-nearest neighbor (k-NN) [24], neural networks (NNs) [8, 50], support vector machines (SVMs) [8, 54] and random forests [14] have been employed in the field of intrusion detection (ID). Intrusion detection system (IDS) monitors the behavior of n