Paraphrasing

Introduction
Wireless sensor networks (WSNs) contain tiny sensor nodes or devices that have radio, processor, memory; battery as well as sensor hardware. The widespread deployment of these. While the Wireless Sensor Networks are generally not guarded, and the transmitted medium is wireless, this increase the vulnerability to attacks.
NSL KDD dataset [ref] is a standard dataset for detection of the anomaly, particularly for intrusion detection. The dataset consists of 41 features representing different features of the network traffic. The network traffic is classified according to two main classes, the normal class and the anomaly class. The anomaly class represents intrusions or attacks found in the network at the time of recording the network traffic. Based on these attacks, the NSL KDD dataset is further classified into four main attack categories including DoS, probing, users to root (U2R), and remote to local (R2L). The DoS attack makes services unavailable to legitimate users by bombarding attack packets on computing or network resources. Examples of DoS attacks include backland, smurf, teardrop, and neptune attacks. This paper focused on DoS attacks due to its high rank among the various types of attack in terms of computer crime cost, as mentioned in the 2014 report [7]. A DoS attack is considered a major problem for legitimate users accessing services via the Internet. DoS attacks make services unavailable to users by draining network or system resources. Although a lot of research has been done by network security experts to overcome the DoS attack problem, DoS attacks are becoming more frequent and have a greater adverse impact with the passage of time.

Related work
Wang, 2017 [13], proposed an SVM based intrusion detection method that consider pre-processing data using transforming the original features by the logarithms of the marginal density ratios.
Feature selection as an essential part of any IDS can help make the process of training the model less complex and faster while preserving or even improving the overall performance of the system. Shahbaz et al. [15] proposed an efficient feature selection algorithm that considers the correlation between a subset of features and the behavior class label to solve the problem of dimensionality reduction and to determining good features. The results showed that the proposed model has considerably less training time while maintaining accuracy and precision. In addition, different feature selection techniques are tested with different classifiers in terms of detection rate. The comparison results indicate that J48 classifier performs better with the proposed feature selection technique. Redundant and irrelevant features in data have caused a long-term problem in network traffic classification. To address this problem, Ambusaidi et al. [18] proposed a supervised filter-based feature selection algorithm that analytically selects the optimal feature for classification. The Flexible Mutual Information Feature Selection (FMIFS) that has been proposed to reduce the redundancy among features. FMIFS is then combined with the Least Square Support Vector Machine based IDS(LSSVM) method to build an IDS. The performance of the model is evaluated using three intrusion detection datasets, namely KDD Cup 99, NSL-KDD and Kyoto 2006+ datasets. The evaluation results showed that feature selection algorithm contributes more critical features for LSSVM-IDS to achieve better accuracy and lower computational cost compared with the state-of-the-art methods.