Artificial Intelligence Techniques for Alzheimer’s Patient Localization Using Adaptive Dual-Channel Pulse-Coupled Neural Networks in Wireless Sensor Networks: Trends and Challenges

Abstract

Alzheimer’s disease is a progressive neurodegenerative disorder that affects cognitive abilities, memory, and spatial awareness, often leading to wandering behavior and increased safety risks. Accurate localization of Alzheimer’s patients is essential for ensuring their safety and improving healthcare monitoring systems. This paper presents a comprehensive review of artificial intelligence-based localization techniques using Wireless Sensor Networks (WSNs) integrated with Adaptive Dual-Channel Pulse-Coupled Neural Networks (PCNN). WSN-based systems utilize sensor nodes and RSSI measurements to determine patient positions in indoor environments where GPS is ineffective.Recent advancements in machine learning and deep learning have significantly enhanced localization accuracy by addressing issues such as signal noise and environmental interference. Adaptive Dual-Channel PCNN improves feature extraction and noise reduction by processing multi-source data simultaneously. This study reviews research conducted in recent years, comparing techniques such as ANN, CNN, LSTM, and hybrid models. Comparative analysis shows that hybrid and adaptive models outperform traditional approaches in terms of accuracy and robustness. The paper identifies key challenges including energy efficiency, computational complexity, scalability, and privacy concerns. Future directions include integrating edge computing, federated learning, and lightweight AI models to develop efficient and secure patient localization systems.