IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Enhanced Sleep Disorder Prediction Using Improved Harris Hawk Optimization and Ensemble Deep Learning Model

Enhanced Sleep Disorder Prediction Using Improved Harris Hawk Optimization and Ensemble Deep Learning Model
View Sample PDF
Author(s): G. Surekha (Bharath Institute of Higher Education and Research, Chennai, India)and Edwin Shalom Soji (Bharath Institute of Higher Education and Research, India)
Copyright: 2026
Pages: 20
Source title: AI in Health and Human-Centric Systems
Source Author(s)/Editor(s): Ahmed J. Obaid (University of Kufa, Iraq), Muthmainnah (Universitas Al Asyariah Mandar, Indonesia), S. Suman Rajest (Dhaanish Ahmed College of Engineering, India)and Michael Baron (Analytics Institute of Australia, Australia)
DOI: 10.4018/979-8-3373-6796-5.ch003

Purchase

View Enhanced Sleep Disorder Prediction Using Improved Harris Hawk Optimization and Ensemble Deep Learning Model on the publisher's website for pricing and purchasing information.

Abstract

Sleep disorder diagnosis is considered a milestone toward timely intervention and treatment. Diagnostic tools, such as polysomnography, are highly resource-intensive and plagued by issues with access. A developed sleep disorder prediction framework integrating feature selection through improved Harris Hawk Optimization algorithms and a deep ensemble learning model is proposed here. Filtering redundant data noise during feature selection in an improved HHO is used to consider only selecting relevant features during the model-building process. In this effort, the applicability of deep learning models, specifically ensemble CNNs and LSTM networks, to extracting spatial and temporal dependencies in the signal of the sleep disorder is attempted. The method proposed here is tested using publicly available sleep disorder datasets and aims to arrive at better classification accuracy, sensitivity, and specificity than existing techniques.

Related Content

G. Surekha, Edwin Shalom Soji. © 2026. 20 pages.
P. Vidhya, S. Silvia Priscila. © 2026. 28 pages.
G. Surekha, Edwin Shalom Soji. © 2026. 20 pages.
P. Kiruthiga, S. Silvia Priscila. © 2026. 28 pages.
C. Ashwini, S.T.V.T. Anantha Krishnama Charyulu, N. Avinash Chowdary, S.T.V. Sathvik, A. Thenmozhi, Sureshkumar Somayajula, Muhammad Saleem. © 2026. 26 pages.
Divya Divya, Kamlesh Kumar Yadav. © 2026. 20 pages.
S. Kiruthika, S. Silvia Priscila. © 2026. 24 pages.
Body Bottom