Evaluation Model of the Mental Health Education Effectiveness Based on Deep Neural Networks
release_3smlbcwmxrgglpqaairevs4nmq
by
Junmei Luo, Shuchao Deng
2024 Volume 31, Issue 1, p57-72
Abstract
This research develops a deep neural network model called DNN-MHE to evaluate mental health education effects. A questionnaire survey collected data on 916 students' mental health knowledge, attitudes, and behaviors. DNN-MHE uses five fully connected layers to predict mental health metrics. Experiments demonstrate that DNN-MHE achieves 99.46% accuracy, outperforming RNN, CNN, and shallow MLP models. Ablation studies validate the impact of training iterations, number of neurons, and number of data samples on performance. Overall, DNN-MHE enables accurate and efficient analysis of mental health education with practical implications for improving university programs.
In application/xml+jats
format
Archived Files and Locations
application/pdf 966.5 kB
file_khxavzyqtnhr5h4t2zimp6v5xa
|
cit.fer.hr (publisher) web.archive.org (webarchive) |
article-journal
Stage
published
Date 2024-01-08
Open Access Publication
In DOAJ
In ISSN ROAD
Not in Keepers Registry
ISSN-L:
1330-1136
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar