Intrusion Detection System is one of the most important security features of modern computer networks that can detect network penetration through a series of functions. This system is independently used (e.g. Snort) or with various security equipment (such as Antivirus, UTM, etc.) on the network and detects an attack based on two techniques of abnormal detection and signature-based detection. Currently, most of the researches in the field of intrusion detection systems have been done based on abnormal behavior using a variety of methods including statistical techniques, Artificial Intelligence (AI), data mining, and machine learning. In this study, we can achieve an effective accuracy using a candidate class of the KDD dataset and deep learning techniques. تفاصيل المقالة

Mobile robot navigation is one of the basic problems in robotics. In this paper, a new approach is proposed for autonomous mobile robot navigation in an unknown environment. The proposed approach is based on learning virtual parallel paths that propel the mobile robot toward the track using a multi-layer, feed-forward neural network. For training, a human operator navigates the mobile robot in some different paths in the environment. Both of human operator navigating data and virtual parallel paths train the neural network. The neural network is able to map the coordinate of a position to a mobile robot orientation and velocity. After training, the mobile robot can plan a track between start and target position without the need of any human operator. When the environment surrounding the mobile robot is unknown, sensors are used to detect obstacles and avoid collision. The simulated mobile robot is equipped with a rangefinder sensor. The simulation shows promising results and high speed for real-time implementation in unknown and partially dynamic environments. تفاصيل المقالة