No abstract

Wireless Sensor Networks (WSNs) are promoting the spread of the Internet for devices in all areas of life, which makes it is a promising technology in the future. In the coming days, as attack technologies become more improved, security will have an important role in WSN. Currently, quantum computers pose a significant risk to current encryption technologies that work in tandem with intrusion detection systems because it is difficult to implement quantum properties on sensors due to the resource limitations. In this paper, quantum computing is used to develop a future-proof, robust, lightweight and resource-conscious approach to sensor networks. Great emphasis is placed on the concepts of using the BB84 protocol with the AES algorithm in WSN security. The results of analysis indicated a high level of security between the data by depending on the generation of secure keys, and reached an accuracy rate of about (80-95) % based on using NIST statistical. The efficiency of the work increased to 0.704 after using the Quantum Bit Error Rate equation, eventually increasing the network performance. This results in the reduction of the overall amount of energy, and the time required for performing the key exchange in the encryption and decryption processes decreased.

In recent days, a wide variety of tools have appeared for performing educational data mining (EDM) . The current education systems show that there are several factors affecting students’ performances. First and foremost, students need motivation in order to learn  and this  motivation results into their success.  The prediction of student performances is an important field of research in Educational Data Mining, particularly through the application of different data mining techniques. The majority of EDM research focuses on prediction algorithms. The current work presents a review of the data mining predicting algorithms and tools that have been adopted in EDM. It also provides insight into the algorithms and powerful data mining tools that most widely used in student performance prediction. This will mainly be of use for  educators, instructors and institutions, increasing the students’ levels of study.