Recent Advances in Alzheimer’s Patient Localization Using Adaptive Dual-Channel Pulse-Coupled Neural Networks in Wireless Sensor Networks: A Systematic Review

Abstract

Alzheimer’s disease (AD) is a progressive neurological disorder that significantly affects cognitive functions, leading to memory loss and disorientation. One of the major challenges associated with AD is patient wandering, which poses serious safety risks. Recent advancements in Wireless Sensor Networks (WSNs), Internet of Things (IoT), and artificial intelligence (AI) have enabled the development of intelligent patient localization systems. This paper presents a systematic review of recent advances (2020–2023) in Alzheimer’s patient localization using adaptive dual-channel Pulse-Coupled Neural Networks (PCNNs) integrated with WSNs. Traditional localization methods such as RSSI, ToA, and AoA suffer from environmental noise and limited accuracy. AI-based approaches, particularly neural networks, have significantly improved localization performance. Adaptive dual-channel PCNN models provide enhanced feature extraction, noise suppression, and multi-sensor data fusion capabilities. Comparative analysis reveals that hybrid AI-WSN models outperform conventional techniques in terms of localization accuracy and robustness. Furthermore, IoT-enabled wearable devices enable continuous monitoring and real-time tracking of patients, improving safety and caregiver response. However, challenges such as energy efficiency, scalability, and data security remain. This review highlights key developments, compares existing techniques, and identifies future research directions for designing efficient and reliable Alzheimer’s patient localization systems.