ORTHOGONAL REGRESSED STEEPEST DESCENT DEEP PERCEPTIVE NEURAL LEARNING FOR IoT- AWARE SECURED BIG DATA COMMUNICATION

The Internet of Things (IoT) is a collection of interconnected intelligent devices that exists within the larger network known as the Internet. With the increasing popularity of IoT devices, massive data is generated day by day. The collected data need to be continuously uploaded to the cloud server. Besides, the transmission of data in the cloud environment is performed via the internet, which faces numerous threats. However, the security issue always lacks an effective big data communication. Therefore, a novel technique called Orthogonal Regressed Steepest Descent Deep Structured Perceptive Neural Learning based Secured Data Communication (ORSDDSPNL-SDC) is introduced with higher accuracy and lesser time consumption. The ORSDDSPNL-SDC technique comprises three phases, namely registration, user authentication, and secure data communication. In the ORSDDSPNL-SDC technique, the registration phase is carried out for creating the new ID, and password for each user in the cloud. The IoT device's data is then sent to a cloud server by the cloud user for storage. After that, the orthogonal regressed steepest descent multilayer deep perceptive neural learning is applied to examine the user_ ID with already registered ID based on Szymkiewicz–Simpson coefficient. Then the Maxout activation function is to classify the user as authorized or unauthorized. Finally, the steepest descent function is applied for minimizing the classification error and increasing the classification accuracy. In this way, the authorized or unauthorized user is identified. Then the secured communication is performed with the authorized cloud users. Experimental evaluation is carried out on the factors such as classification accuracy, classification time and error rate, and space complexity with respect to a number of users. The qualitative results and discussion indicate that the proposed ORSDDSPNL-SDC offers elevated performance with regard to achieving higher classification accuracy and minimum error as well as computation time when compared to the existing methods.