RETRACTED: Detecting the Type of Attack in Healthcare Cloud Computing System Using Termite Deep Belief Neural Network (TDBNN) for Future Smart Cities

Authors:

Abstract
Following an investigation undertaken by the publisher, we have determined that this paper was accepted on the basis of a compromised peer review process. We hereby retract the paper. The corresponding author has been notified of the retraction. The retraction statement can be found here: https://doi.org/10.1520/JTE20269996. With the popularity of smart electronic devices, along with the development of clouds and cloudlet technology, there has been an increasing need to provide better medical care. The processing chain of medical data mainly includes data collection, data storage, data sharing, etc. The traditional healthcare system often requires the delivery of medical data to the cloud, which involves users’ sensitive information and causes communication energy consumption. Practically, medical data sharing is a critical and challenging issue. This issue motivates construction to maintain the security and privacy of healthcare data by applying the neural network approach. During this process, the system examines the various intermediate attacks; malwares for detecting the threats also eliminate the unauthorized access in the cloud storage-based healthcare system. In this paper, A termite colony optimization deep belief neural network (TDBNN) is proposed for the feature selection process with the combination of Levenberg-Marquardt for the back-propagation stage, which hence detects the list of attacks that occurred in the cloud and categorizes it. The proposed TDBNN is compared with two well-known, state-of-the-art methods, the recurrent neural network oppositional crow search algorithm and voting extreme learning machine, in terms of precision, sensitivity, specificity, f1-score, and kappa score. The proposed method achieves 99.03 % accuracy, 99.03 % precision, 99.03 % sensitivity, 99.76 % specificity, a 99.03 % f1-score, and a 98.79 % of kappa score.

This publication has 23 references indexed in Scilit: