Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

AI-Driven Hybrid Detection and Classification Framework for Secure Sleep Health IoT Networks.

Prajoona Valsalan¹, Mohammad Maroof Siddiqui¹

¹Department of Electrical and Computer Engineering, Dhofar University, Salalah 211, Oman.

|May 27, 2026

Summary

Related Concept Videos

Sleep Apnea

Sleep Apnea

Sleep apnea is a condition where breathing stops intermittently during sleep, often leading to significant health issues. Each episode can last from 10 to 20 seconds or more and is frequently accompanied by a brief arousal from sleep. This disturbance, largely unnoticed by the individual, can lead to severe daytime fatigue. Commonly, individuals seek help after being informed by their partners about loud snoring and noticeable breathing pauses during sleep.
The condition is more prevalent among...

Understanding Sleep

Understanding Sleep

Sleep, an essential biological state, involves significant reductions in physical activity, sensory awareness, and interaction with the environment. This complex physiological process is primarily regulated by specific brain regions, notably the hypothalamus and pons, which govern the sleep-wake cycle or circadian rhythm.
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Physics-Guided Deep Learning for Interpretable Biomedical Image Reconstruction and Pattern Recognition in Diagnostic Frameworks.

Bioengineering (Basel, Switzerland)·2026

Same author

IoT Based Expert System for Diabetes Diagnosis and Insulin Dosage Calculation.

Healthcare (Basel, Switzerland)·2023

Same author

Hyperspectral Image Classification Model Using Squeeze and Excitation Network with Deep Learning.

Computational intelligence and neuroscience·2022

Same author

A Torn ACL Mapping in Knee MRI Images Using Deep Convolution Neural Network with Inception-v3.

Journal of healthcare engineering·2022

This study introduces a novel framework for secure sleep monitoring, integrating AI for sleep staging and anomaly detection. It achieves high accuracy and low latency, promising real-time, edge-deployable digital sleep health solutions.

Area of Science:

Digital health and cybersecurity
Artificial intelligence in medicine
Sleep science and chronobiology

Background:

Sleep disorders pose a growing global health challenge, linked to numerous chronic diseases.
Wearable sensors and the Internet of Medical Things (IoMT) enable continuous, home-based sleep monitoring.
Current systems face cybersecurity risks due to sensitive data transmission, with separate approaches for signal analysis and intrusion detection.

Purpose of the Study:

To address the gap in integrated architectures for sleep monitoring that balance physiological modeling accuracy with communication security.
To develop a unified framework for simultaneous sleep-stage classification and network anomaly detection.
To evaluate the performance of a novel AI-driven approach for secure and efficient digital sleep health ecosystems.

Keywords:

CNN-BiLSTM Internet of Medical Things Sleep Health IoT edge computing hybrid deep learning network anomaly detection sleep stage classification wearable security

Related Experiment Videos

Main Methods:

A hybrid framework combining Convolutional Neural Networks (CNN) for spatial features, Bidirectional Long Short-Term Memory (BiLSTM) for temporal patterns, and Random Forest for classification.
A dual-task learning approach optimizing both sleep-stage prediction and network anomaly detection.
Multi-objective optimization for performance and security in Sleep Health Internet of Things (S-HIoT) systems.

Main Results:

Achieved high accuracy: 99.8% for sleep staging and 98.6% for anomaly detection on public datasets (Sleep-EDF, CICIoMT2024).
Demonstrated low inference latency (<45 ms), suitable for real-time deployment on edge devices.
Validated a comprehensive framework for secure, intelligent, and clinically robust digital sleep health.

Conclusions:

The proposed integrated framework effectively bridges sleep signal modeling with cybersecurity mechanisms.
This approach offers a promising solution for secure, real-time digital sleep health monitoring.
Future research should explore explainable AI, federated learning, and edge optimization for enhanced S-HIoT systems.