Random Forest and LSTM Hybrid Model for Detecting DDoS Attacks in Healthcare IoT Networks

The growing integration of Internet of Things (IoT) devices in healthcare has revolutionized patient care and operational efficiency. However, this advancement comes with vast cybersecurity demanding situations, as IoT devices are exceedingly susceptible to diverse cyber-attacks, which include statistics breaches, denial-of-provider (DoS) attacks, and unauthorized get right of entry to. This look at proposes a robust cyber-assault detection machine through leveraging Random Forest (RF) and Long Short-Term Memory (LSTM) algorithms, which integrate static sample popularity with sequential facts analysis. RF is utilized for its performance in coping with dependent statistics, along with network visitors and tool logs, at the same time as LSTM excels in analyzing time-collection facts, allowing the detection of evolving threats. The proposed hybrid RF-LSTM version became evaluated using real-global IoT healthcare datasets. RF established high accuracy in detecting static anomalies, accomplishing an accuracy of ninety four% and a precision of ninety three%. LSTM excelled in coping with temporal dependencies, reaching an F1 score of 91% and minimizing fake negatives. The integration of both algorithms more desirable the gadget's capability to stumble on a huge variety of attacks, reaching an common detection accuracy of ninety seven% in real-time scenarios. This research highlights the capability of hybrid fashions in ensuring IoT safety and mitigating cyber threats in healthcare environments, making sure patient protection and information integrity.