Iyanda A. R.

Work place: Department of Computer Science and Engineering, Faculty of Technology, Obafemi Awolowo University, Ile-Ife, Nigeria

E-mail: abiyanda@oauife.edu.ng

Website:

Research Interests: Natural Language Processing

Biography

Dr. Abimbola R. Iyanda holds a B.Sc. degree in Computer Engineering, M.Sc. and Ph. D. degrees in Computer Science from Obafemi Awolowo University, Ile-Ife, Nigeria. The thrust of her research is in the area of Computing and Intelligent Systems Engineering with a focus on Natural Language Processing and Human Computer Interactions aiming at domesticating computer technology and the computational rendering of indigenous ideas. She is a Member of the Nigerian Society of Engineers, Association of Professional Women Engineer in Nigeria, Council for the Regulation of Engineering in Nigeria, Organization for Women in Science for the Developing World (OWSD) and Nigeria Computer Society. Her present employment is with the Computer Science and Engineering Department, Obafemi Awolowo University, Ile-Ife, Nigeria.

Author Articles
An Optimized Convolutional Neural Network Model for Detecting Depressive Symptoms from Image Posts

By Awoyelu T. M. Iyanda A. R. Mosaku S. K.

DOI: https://doi.org/10.5815/ijitcs.2024.04.03, Pub. Date: 8 Aug. 2024

This paper presents an optimized model that uses an optimized CNN to detect depressive symptoms from image posts. This is with a view to detecting depression symptoms in individuals. Visual data were collected in their raw form and assessed as having or not having a mental condition. The images were processed, and the relevant features retrieved from them. An optimized convolutional neural network (CNN) was used to simulate the defined classification model of the image posts. The model was implemented using Python Programming Language. Precision, recall, accuracy, and the area under the Receiver Operating Characteristics (ROC) curve were used as performance indicators to assess the model's efficacy. The collected findings indicate that 77% accuracy is achieved by the optimized model. As a result, 77% of the cases were accurately predicted by the model, suggesting that the model is generally accurate in its predictions. The research will contribute to a decrease in the incidence, prevalence, and recurrence of mental health illnesses as well as the disabilities they cause.

[...] Read more.
Other Articles