Anomaly Detection in IoT-Based Healthcare Networks Using Hybrid Deep Learning Models
Keywords:
IoT Networks, Healthcare, Anomaly Detection, Deep Learning, CNN, LSTM, Cyber threats, Data manipulation.Abstract
The abstract states that IoT in healthcare is rapidly advancing, enhancing patient care through remote monitoring and automated diagnosis. However, these systems face security threats such as brute force attacks, spoofing, DDoS attacks, and data manipulation, which can compromise patient data and system performance. To address these challenges, the project proposes a hybrid deep learning model that integrates CNN for feature extraction, LSTM for sequence pattern detection, and Autoencoders for recognizing abnormal behaviors. This model enhances detection accuracy, reduces false alerts, and ensures a faster response to threats. The model is tested on IoT healthcare datasets and effectively detects threats like malware injection, unauthorized access, and network intrusions, thereby improving security and ensuring reliable healthcare data protection.
