AI and Machine Learning for Healthcare Medical Image Analysis and Disease Diagnosis Intelligent Healthcare Decision Support Systems

He is a highly dedicated and accomplished Computer Science academician with over 19 years of experience in teaching, research, and academic administration. Holds a Ph.D. in Computer Science and Engineering with strong expertise in AI, Machine Learning, Deep Learning, Image Processing, and Medical Image Analysis. Recognized for effective teaching, innovative pedagogy, research contributions, and active involvement in NBA, NAAC, NIRF, and academic governance activities, with a proven ability to contribute to institutional excellence through quality education and impactful research. Reference: Intelligent EEG Signal Processing for Early Alzheimer’s Disease Diagnosis Using Advanced Transforms and Nature-Inspired Optimization Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that demands early and accurate diagnosis for effective clinical intervention. Electroencephalography (EEG) has emerged as a promising non-invasive and cost-effective modality for identifying cognitive impairment; however, EEG-based diagnosis is challenged by noise contamination, signal variability, and difficulty in extracting discriminative features. In this talk, I present an intelligent EEG-based diagnostic framework that integrates advanced signal denoising, transform-domain feature extraction, deep learning, and nature-inspired optimization. The proposed approach employs Savitzky–Golay Denoising to enhance EEG signal quality while preserving critical waveform characteristics. Discriminative features are extracted using a novel Discrete Cosine–Krawtchouk–Tchebichef Transform, which effectively captures both spatial and frequency-domain information. For classification, a Dual-Level Contextual Attention–based Cosine Convolutional Neural Network (DLCA-CCNNet) is utilized to focus on clinically relevant EEG patterns. To further improve performance and convergence stability, the model parameters are optimized using the Pied Kingfisher Optimizer, a nature-inspired metaheuristic algorithm. Experimental evaluation on the publicly available Dementia EEG Dataset demonstrates outstanding diagnostic performance, achieving 99.9% classification accuracy and 99.8% sensitivity in distinguishing Alzheimer’s disease, mild cognitive impairment, and healthy controls. The results highlight the robustness, efficiency, and clinical relevance of the proposed framework. This work underscores the potential of intelligent EEG signal processing systems to support early Alzheimer’s diagnosis and to complement traditional clinical assessment methods in real-world healthcare settings.