A Novel Optimizer Based Deep Neural Network Model for IoMT

View at publisher Summarise with VIRAT
Authors: Buditi Sriveni, Naveen Kumar Navuri, Korra Srinivas, Tirumala Paruchuri, Jaganathan Muthusamy
Cited by: 0
References: 16

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Intelligent diagnostics and real-time monitoring in the field of Internet of Things (IoMT) is changing modern healthcare, which also raises the risk of cyber threats, which makes important to get a strong intrusion detection systems (IDS). The current research used the MSCAD dataset to show the efficiency of eight popular optimizer for training the deep neural network model, by considering the real IoMT network conditions. Analyzing different performance metrices shows that the DNN optimized with Adam performs the best as compared to others, achieving a precision of 0.97753. This level of accuracy shows just how important it is to choose the right optimizer when building effective deep learning-based intrusion detection systems for medical networks. The proposed DNN-Adam method provides useful information for creating secure and successful cybersecurity solutions for limited resources, real-time healthcare systems by enhancing detection accuracy, reliability and flexibility in the IoMT environment.

Fields of Study & Subjects

Network Security and Intrusion Detection Internet of Things and AI Artificial Immune Systems Applications

Publication details

Journal / source
International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT)
Pages
684–689
Publication date
4 February 2026
Language
EN