A Comprehensive Review of Smart Healthcare Patient Monitoring System for IoT-Based Healthcare System Using Enhanced Residual Multi-Scale Diverged Self-Attention Network

Abstract

Smart healthcare systems powered by the Internet of Things (IoT) and Artificial Intelligence (AI) have revolutionized patient monitoring by enabling real-time, remote, and continuous health tracking. IoT devices such as wearable sensors, smart medical equipment, and wireless body area networks collect physiological signals including heart rate, oxygen saturation, temperature, and ECG data. These data are transmitted to cloud or edge platforms, where AI models analyze patterns for early diagnosis and predictive healthcare. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and attention-based architectures, have significantly improved prediction accuracy. Enhanced residual multi-scale diverged self-attention networks provide efficient feature extraction by capturing both local and global dependencies in patient data. These models are capable of handling heterogeneous medical datasets and improving disease prediction accuracy. This paper presents a comprehensive review of IoT-based smart healthcare monitoring systems. It highlights recent methodologies, architectures, challenges, and future directions, focusing on deep learning and self-attention mechanisms for improved patient monitoring.

Smart Healthcare, IoT, Patient Monitoring, Deep Learning, Self-Attention, Residual Networks.