Matyas–Meyer–Oseas Skein Cryptographic Hash Blockchain-Based Secure Access Control for E-Learning in Cloud

Abstract

A learning system is that depends on formalized teaching with the assist of electronic resources which is called e-learning. E-learning employs electronic technologies to access educational curriculum. E-learning is a promising and growing area that permits the rapid integration of smart learning and the teaching process. Since cloud computing is the main paradigm to deliver more efficiently learning content in an integrated environment. E-learning comprises all kinds of educational technology but security analysis is required to achieve higher data confidentiality, fine-grained access control. In order to increase security of data access, A Matyas–Meyer Skein Cryptographic Hash Blockchain and Modified Connectionist Double Q-learning (MMSCHB-MCDQL) technique is introduced. The main aim of the MMSCHB-MCDQL technique is to increase the secure access and academic performance analysis using e-learning data. The IoT devices are deployed for sensing and monitoring the student activities during the e-learning process. At first, the sensing data are collected from the IoT devices and apply the Matyas–Meyer–Oseas Skein Cryptographic Hash Blockchain technique for secure data transmission. A Skein Cryptographic Hash is applied to a blockchain technology to generate the hash for each input data using Matyas–Meyer–Oseas compression function. In addition, the smart contract theory is applied to Blockchain technology to guarantee access control without believing external third parties and it helps to achieve a higher data confidentiality rate. After that, a Modified Connectionist Double Q-learning algorithm is applied for analyzing the student activities to make optimal action with higher accuracy. Based on the learning process, the student’s performance levels are correctly predicted. Experimental evaluation is carried out on certain factors such as data confidentiality rate, execution time, and prediction accuracy with respect to a number of student data. The experimental results and discussion demonstrate that the proposed MMSCHB-MCDQL technique offers an efficient solution for secure decentralized access control in the cloud. The experimental results evidence that the MMSCHB-MCDQL technique improves data confidentiality rate and prediction accuracy by 9.5% and 10% and reduces the execution time by 15% as compared to the conventional methods.