Brain Informatics Technology

17Computationally Intelligent Techniques for Neuroscience Applications

Vidhya R.¹, Dhanya D.², Renu D. S.³ and Jani Anbarasi L.^4*

¹School of Computer Science and Engineering, Presidency University, Bengaluru, Karnataka, India

²Department of Artificial Intelligence and Data Science, Mar Ephraem College of Engineering and Technology, Tamil Nadu, India

³Department of Computer Science and Engineering, Mar Ephraem College of Engineering and Technology, Tamil Nadu, India

⁴School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India

Abstract

Neuroimaging is essential for evaluating brain pathology, especially in Alzheimer’s disease (AD), when the gradual decline in cognitive functions results in increased challenge in executing daily activities. Alzheimer’s disease steadily deteriorates cognitive function, ultimately leading to dementia. Recent advances have combined neuroimaging data into cataloguing outlines for Alzheimer’s disease, providing crucial tools for diagnosis and prediction. Medical image analysis has substantial issues restricting from the heterogeneous characteristics of the images, which exhibit low contrast and intricate backgrounds. In deep learning, particularly within convolutional neural networks (CNNs), architectures frequently have the vanishing gradient problem, wherein the gradient of the loss function lessens towards zero, obstructing the learning process. To address this, the paper presents a deep learning (DL) architecture ...