Cloud-Based Emotion Recognition and Sleep Time Analysis for Mental Health

Deshmukh, Jay Suresh (2025) Cloud-Based Emotion Recognition and Sleep Time Analysis for Mental Health. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (928kB) | Preview

Abstract

The signs of poor mental health like depression, stress, anxiety can be seen in everyone but stay undetected. This disorder can be connected with sleep cycle which can lead towards emotional instability. On the primary basis emotion recognition models is focused towards facial expression but does not analyze the sleep pattern of a person. This factor is also an important information for detecting the mental health. In this research we will propose cloud-based solution for emotion recognition which will combine facial expression and track the sleep time data so that we can find any early sign in mental health. For tracing the facial emotion, we will use Convolutional Neural Network (CNN’s), Super Vector Machines (SVMs) and Leave-One-Out-Cross-Validation (LOOCV) for model evaluation and performance estimation, and to track the sleep we will use APIs like Fitbit, Google Fit which are cloud based. This will help us to know the morning emotional state and the amount of sleep time the user consumed. With the help of Amazon Rekognition for facial analysis, AWS Lambda for realtime processing, S3 bucket for storage, we will deploy this model on AWS Cloud Infrastructure. In this research we will understand and recognize the emotion along with sleep cycle to increase the accuracy of mental health detection through cloud-based solution. This will help us to understand and recognize the mental health which will reduce the burden on mental health care system. This research presents a novel cloud-based approach that combines sleep time and facial emotion recognition for monitoring mental health risk factor. Keywords: Facial Emotion Recognition, Sleep time tracking, SVMs, LOOCV, Cloud Computing, Mental Health, Convolutional Neural Networks (CNN), AWS.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Shaguna UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing B Philosophy. Psychology. Religion > Psychology > Emotions R Medicine > RA Public aspects of medicine > RA790 Mental Health
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	21 Nov 2025 14:50
Last Modified:	21 Nov 2025 14:50
URI:	https://norma.ncirl.ie/id/eprint/8954

Actions (login required)

View Item