Fusion: Practice and Applications FPA 2692-4048 2770-0070 10.54216/FPA https://www.americaspg.com/journals/show/2788 2018 2018 Department of Computer Science, College of Computer and Information Sciences, Majmaah University, Majmaah, 11952, Saudi Arabia Sultan Sultan Indian Institute of Technology, Patna, Bihar, India Deepak Dasaratha Rao Department of Information Systems, College of Computer and Information Sciences, Majmaah University, Majmaah, 11952, Saudi Arabia Olayan Alharbi Department of Computer Science, Faculty of Computer and Information Systems, Islamic University of Madinah, Medinah, 42351, Saudi Arabia Zaid Alzaid IT Programs Center, Faculty of IT Department, Institute of Public Administration, Riyadh, 11141, Saudi Arabia Yasser M. Hausawi Department of Computer Science, College of Computer Science and Engineering, Taibah University, Medina 42353, Saudi Arabia Jaber Almutairi Intrusion detection in the IoMT (Internet of Medical Things) represents the process of keeping track of and discovering unauthorized or malicious actions in medical devices and networks. Some of its benefits include early detection of potential threats, prevention of data breaches, and protection of patient privacy. Aside from these benefits, some difficulties are evident, like alarm fatigue due to false positives, the complexity in the standardizing detection across different devices, and resource limits that hinder qualitative implementations, thus leaving some vulnerabilities in the healthcare infrastructure. This paper proposes a new Efficient Intrusion Detection model based on the Correlation-Based Feature Selection and the OptCNN-LSTM model to address these problems. The proposed methodology comprises five key phases: (i) Data Acquisition (ii) Pre-processing (iii) Feature Extraction (iv) Feature Selection (v) OptCNN-LSTM Model-based intrusion detection. The raw data is first gathered and then preprocessed using z-score normalization and data cleaning. Then, the best features are extracted using central tendency, the degree of dispersion, and correlation. A mixed IHHO-PSO feature with the Correlation-based Feature Selection (CFS) framework is employed to choose the best features amongst the collected features. At last, the OptCNN-LSTM model is performed to detect the intrusion in the IoMT based on features-selected data. The CNN is tuned using the Levy Flight Optimization (LF) which can be further combined with the LSTM to get the expected results. The code is written in Python and the model is then run to determine its performance which is measured in terms of accuracy, precision, f-measure, and a Receiver Operating Characteristic Curve (ROC). Compared to the current models, the proposed model has the highest accuracies 97.6% and 96.5% for learning rates 70 and 80, respectively… 2024 2024 10.54216/FPA.160112 https://www.americaspg.com/articleinfo/3/show/2788