Improving the Accuracy of the Intrusion Detection System in the IoT by Machine Learning and Clustering Algorithms

 The recent rise of the Internet of Things (IoT) has led to increasing attacks in IoT. Manufacturers of IoT devices are interested in reducing costs by ignoring security regulations that cause widespread damage and impede the growth of the IoT. The proliferation of IoT-based attacks will continue as long as IoT manufacturers incorporate accountability and security mechanisms into their devices. The proliferation of IoT-based attacks will continue as long as IoT manufacturers incorporate accountability and security mechanisms into their devices. Until then, the Internet of Things has the potential to become an environment for future cyber-attacks, which will pose great challenges.

 In this research, the solutions for establishing security in the Internet of Things have been investigated and have provided a solution based on the combination of support vector machine and K-means algorithm. First, preprocessing is applied to the data set and the data that has no effect on the result are deleted. Then, the support vector machine algorithm is applied to the data set and the intrusion or non-intrusion status is determined. This proposed method achieves better results by applying k-means to the data set, and the combination of support vector machine algorithms and k-means improves the accuracy of the proposed method.

 The results showed that the proposed method is more efficient than previous methods. this study sought to improve the security challenge in wireless sensor networks. The proposed method of this research is to use a combination of support vector machine and chi-mean, which showed very good performance compared to previous methods. According to the studies and the proposed method, it can be found that the best method in detecting and detecting intrusion is the use of K-Means algorithm, which can be achieved with 98.35% accuracy using the support vector machine method and K-Means algorithm.

 The most important criterion for determining the performance of an algorithm is the Accuracy criterion. This criterion calculates the total accuracy of a category. This criterion indicates what percentage of the total data set is properly categorized. This criterion is the evaluation based on the accuracy and the accuracy of the proposed method is better than the previously presented methods.