Real-Time Analysis of Biomedical Signals in IoT-Enabled Healthcare Systems Using a Hybrid CNN-LSTM Model

Biomedical signal analysis is essential in IoT-enabled healthcare systems, facilitating real-time health monitoring and early anomaly detection. However, current methodologies frequently encounter challenges related to latency, precision, and resource limitations. This research presents a hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) to solve these difficulties. The suggested system effectively handles streaming biological signals from wearable devices, providing substantial improvements compared to baseline techniques. Our model attained exceptional performance, with 98.5% accuracy, 97.2% precision, 98.1% recall, and an AUC of 0.992. In comparison to conventional models such as SVM and Random Forest, our methodology minimises latency (0.12 seconds per sample) while preserving elevated classification accuracy. This paper contributes to the advancement of real-time healthcare applications by merging deep learning with edge computing to optimise biomedical signal processing. The suggested approach overcomes current methodologies, establishing it as a strong option for implementation in IoT-enabled health systems, facilitating more precise and prompt medical interventions.