Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource Faculty Publications Article Faculty Publications -Articles Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Creator An entity primarily responsible for making the resource Vats, Prashant; Tak, Tan Kuan; Upreti, Kamal; Mahajan, Shubham; Kshirsagar, Pravin R.; Upadhyay, Govind Murari Title A name given to the resource Early detection of mental health disorders using machine learning models: An analysis based on behavioral and voice data Date A point or period of time associated with an event in the lifecycle of the resource 01-01-2026 Source A related resource from which the described resource is derived Computers and Electrical Engineering;Volume;132;Issue;;Article No.;110996; Identifier An unambiguous reference to the resource within a given context <a href="https://doi.org/10.1016/j.compeleceng.2026.110996" target="_blank" rel="noreferrer noopener">https://doi.org/10.1016/j.compeleceng.2026.110996</a> <br /><br /><a href="https://www.scopus.com/pages/publications/105029671103?origin=resultslist" target="_blank" rel="noreferrer noopener">https://www.scopus.com/pages/publications/105029671103?origin=resultslist</a> Coverage The spatial or temporal topic of the resource, the spatial applicability of the resource, or the jurisdiction under which the resource is relevant Vats P., Department of Computer Science and Engineering, Manipal University Jaipur, Rajasthan, Jaipur, 303007, India; Tak T.K., Engineering Cluster, Singapore Institute of Technology, 828608, Singapore; Upreti K., Department of Computer Science, CHRIST (Deemed to be University), Uttar Pradesh, Delhi NCR, 201003, India; Mahajan S., Amity School of Engineering and Technology (ASET), Amity University, Haryana, Gurugram, 122413, India; Kshirsagar P.R., Electronics &amp; Telecommunication Engineering, J D College of Engineering &amp; Management, Maharashtra, Nagpur, 441501, India; Upadhyay G.M., Department of Computer Applications, Manipal University Jaipur, Rajasthan, Jaipur, 303007, India Description An account of the resource Mental illnesses are to be detected promptly and correctly to intervene effectively and in time. In this paper, a multi-stage NeuroVibeNet model of early mental disorders detection based on multimodal behavioral and voice data is proposed. It starts with the preprocessing of data that is high-quality and consistent, such as mean imputation, min-max normalization, outlier detection, noise reduction, and short-time energy extraction. The majority of the advanced methods employed in extracting temporal, spectral, and complex features include multiscale entropy, soft dynamic time warping, spectral contrast analysis, formant frequency analysis, and a one-dimensional convolutional neural network autoencoder. The feature selection is done via a sparse autoencoder that is used to maximize relevance and minimize redundancy. The chosen features are fed into the NeuroVibeNet architecture, where TabNet is used to process behavioral data, and Capsule Networks are used to process voice data to allow learning representations with attention and hierarchy. Lastly, a voting-based ensemble classifier uses the two modalities to combine the predictions to make strong classification decisions. The structure is coded in Python and tested on three benchmark datasets with the accuracy of 0.9839, 0.9856, and 0.9855, which is better than the current approaches. Copyright 2026. Published by Elsevier Ltd. Subject The topic of the resource Behavioral data; Capsule network; Feature selection; Median imputation; Noise reduction; Tabular neural network; Voice data Publisher An entity responsible for making the resource available Elsevier Ltd Relation A related resource ISSN: 457906; CODEN: CPEEB Language A language of the resource English Type The nature or genre of the resource Article Rights Information about rights held in and over the resource Restricted Access; Hardcopy may be available in the library Format The file format, physical medium, or dimensions of the resource online