Two-Dimensional Stockwell Transform and Deep Convolutional Neural Network for Multi-Class Diagnosis of Pathological Brain.

Since the brain lesion detection and classification is a vital diagnosis task, in this paper, the problem of brain magnetic resonance imaging (MRI) classification is investigated. Recent advantages in machine learning and deep learning allows the researchers to develop the robust computer-aided diagnosis (CAD) tools for classification of brain lesions. Feature extraction is an essential step in any machine learning scheme. Time-frequency analysis methods provide localized information that makes them more attractive for image classification applications. Owing to the advantages of two-dimensional discrete orthonormal Stockwell transform (2D DOST), we propose to use it to extract the efficient features from brain MRIs and obtain the feature matrix. Since there are some irrelevant features, two-directional two-dimensional principal component analysis ((2D)2PCA) is used to reduce the dimension of the feature matrix. Finally, convolution neural networks (CNNs) are designed and trained for MRI classification. Simulation results indicate that the proposed CAD tool outperforms the recently introduced ones and can efficiently diagnose the MRI scans.

Complex dynamical behaviors of a novel exponential hyper-chaotic system and its application in fast synchronization and color image encryption.

This paper proposes a novel exponential hyper-chaotic system with complex dynamic behaviors. It also analyzes the chaotic attractor, bifurcation diagram, equilibrium points, Poincare map, Kaplan-Yorke dimension, and Lyapunov exponent behaviors. A fast terminal sliding mode control scheme is then designed to ensure the fast synchronization and stability of the new exponential hyper-chaotic system. Stability analysis was performed using the Lyapunov stability theory. One of the main features of the proposed controller is the finite time stability of the terminal sliding surface designed with high-order power function of error and derivative of error. The approach was implemented for image cryptosystem. Color image encryption was carried out to confirm the performance of the new hyper-chaotic system. For image encryption, the DNA encryption-based RGB algorithm was used. Performance assessment of the proposed approach confirmed the ability of the proposed hyper-chaotic system to increase the security of image encryption.