The numbers of diagnosed patients by melanoma are drastic and contribute more deaths annually among young peoples. An approximately 192,310 new cases of skin cancer are diagnosed in 2019, which shows the importance of automated systems for the diagnosis process. Accordingly, this article presents an automated method for skin lesions detection and recognition using pixel‐based seed segmented images fusion and multilevel features reduction. The proposed method involves four key steps: (a) mean‐based function is implemented and fed input to top‐hat and bottom‐hat filters which later fused for contrast stretching, (b) seed region growing and graph‐cut method‐based lesion segmentation and fused both segmented lesions through pixel‐based fusion, (c) multilevel features such as histogram oriented gradient (HOG), speeded up robust features (SURF), and color are extracted and simple concatenation is performed, and (d) finally variance precise entropy‐based features reduction and classification through SVM via cubic kernel function. Two different experiments are performed for the evaluation of this method. The segmentation performance is evaluated on PH2, ISBI2016, and ISIC2017 with an accuracy of 95.86, 94.79, and 94.92%, respectively. The classification performance is evaluated on PH2 and ISBI2016 dataset with an accuracy of 98.20 and 95.42%, respectively. The results of the proposed automated systems are outstanding as compared to the current techniques reported in state of art, which demonstrate the validity of the proposed method.

No abstract

Blockchain and IoT are being deployed at a large scale in various fields including healthcare for applications such as secure storage, transactions, and process automation. IoT devices are resource-constrained, have no capability of security and self-protection, and can easily be hacked or compromised. Furthermore, Blockchain is an emerging technology with immutability features which provide secure management, authentication, and guaranteed access control to IoT devices. IoT is a cloud-based internet service in which processing and collection of user’s data are accomplished remotely. Smart healthcare also requires the facility to provide the diagnosis of patients located remotely. The smart health framework faces critical issues such as data security, costs, memory, scalability, trust, and transparency between different platforms. Therefore, it is important to handle data integrity and privacy as the user’s authenticity is in question due to an open internet environment. Several techniques are available that primarily focus on resolving security issues i.e., forgery, timing, denial of service and stolen smartcard attacks, etc. Blockchain technology follows the rules of absolute privacy to identify the users associated with transactions. The motivation behind the use of Blockchain in health informatics is the removal of the centralized third party, immutability, improved data sharing, enhanced security, and reduced overhead costs in distributed applications. Healthcare informatics has some specific requirements associated with the security and privacy along with the additional legal requirements. This paper presents a novel authentication and authorization framework for Blockchain-enabled IoT networks using a probabilistic model. The proposed framework makes use of random numbers in the authentication process which is further connected through joint conditional probability. Hence, it establishes a secure connection among IoT devices for further data acquisition. The proposed model is validated and evaluated through extensive simulations using the AVISPA tool and the Cooja simulator, respectively. Experimental results analyses show that the proposed framework provides robust mutual authenticity, enhanced access control, and lowers both the communication and computational overhead cost as compared to others.

Cloud computing facilitates the users with on-demand services over the Internet. The services are accessible from anywhere at any time. Despite the valuable services, the paradigm is, also, prone to security issues. A Distributed Denial of Service (DDoS) attack affects the availability of cloud services and causes security threats to cloud computing. Detection of DDoS attacks is necessary for the availability of services for legitimate users. The topic has been studied by many researchers, with better accuracy for different datasets. This article presents a method for DDoS attack detection in cloud computing. The primary objective of this article is to reduce misclassification error in DDoS detection. In the proposed work, we select the most relevant features, by applying two feature selection techniques, i.e., the Mutual Information (MI) and Random Forest Feature Importance (RFFI) methods. Random Forest (RF), Gradient Boosting (GB), Weighted Voting Ensemble (WVE), K Nearest Neighbor (KNN), and Logistic Regression (LR) are applied to selected features. The experimental results show that the accuracy of RF, GB, WVE, and KNN with 19 features is 0.99. To further study these methods, misclassifications of the methods are analyzed, which lead to more accurate measurements. Extensive experiments conclude that the RF performed well in DDoS attack detection and misclassified only one attack as normal. Comparative results are presented to validate the proposed method.

No abstract