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) presents significant challenges in patient safety due to memory loss and disorientation, often leading to wandering and life-threatening situations. Recent advancements in wireless sensor networks (WSNs) combined with artificial intelligence (AI) techniques have enabled the development of efficient patient localization systems. This systematic review explores recent advances in Alzheimer’s patient localization using adaptive dual-channel pulse-coupled neural networks (PCNNs) integrated with WSNs. The review focuses on localization accuracy, energy efficiency, scalability, and real-time tracking capabilities. Traditional localization approaches such as RSSI-based fingerprinting and time-based positioning have been enhanced using machine learning and neural network models. Adaptive dual-channel PCNNs offer improved feature extraction, noise resistance, and multi-sensor data fusion capabilities, making them highly suitable for complex indoor environments. The integration of IoT-enabled wearable devices and low-power communication protocols has further enhanced system reliability. Comparative analysis reveals that hybrid AI-WSN approaches outperform conventional techniques in terms of localization precision and robustness. However, challenges remain in terms of energy consumption, security, and real-world deployment scalability. This review provides insights into emerging trends, research gaps, and future directions for developing intelligent and reliable Alzheimer’s patient monitoring systems.