Child Mental Health Detection
International Journal of Drug Delivery Technology · 23.05.2026 · 16 (31s)
DOI: 10.25258/ijddt.16.31s.78 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 23.05.2026. Verfasst von Govind Chauhan und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Through the utilization of AI the monitoring of mental health issues among children is revealed which opens a way for the early detection of such disorders as autism and ADHD that are characterized by emotional and developmental difficulties. The traditional techniques are based on long and subjective assessments, while AI is able to process large volumes of data made up of different types of indicators such as facial expressions, speech, and behaviour to identify emotional outliers. In this paper, the performance of CNN, LSTM, and hybrid deep learning models in detecting children's emotional states is compared. The hybridization of the two networks, one being CNN + ResNet50 and the other CNN + LSTM, leads to the generation of the highest accuracy and reliability, which in turn supports diagnosis in real-time. The findings imply that AI can stamp down the duration of child mental health screening, make it impartial, and thus, increase the availability of the service.
Zitieren
APA
Chauhan, G., Gupta, P., Harsh, H., Sharma, L., Verma, J. N., & Kumar, B. (2026). Child Mental Health Detection. International Journal of Drug Delivery Technology, 16(31s). https://doi.org/10.25258/ijddt.16.31s.78
Vancouver
Chauhan G, Gupta P, Harsh H, Sharma L, Verma JN, Kumar B. Child Mental Health Detection. International Journal of Drug Delivery Technology. 2026;16(31s). doi:10.25258/ijddt.16.31s.78
BibTeX
@article{Chauhan2026,
author = {Chauhan, Govind and Gupta, Pushkar and Harsh, Harsh and Sharma, Latika and Verma, Jagat Narayan and Kumar, Bhoopendra},
title = {Child Mental Health Detection},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {31s},
doi = {10.25258/ijddt.16.31s.78}
}
EUVIMED