A Novel Development of Artificial Intelligence Enabled Learning Methodology for Human Depression Prediction Scheme

• Published in: 2024 International Conference on Intelligent Systems for Cybersecurity (ISCS) pp. 1 - 6
• Main Authors: Ramkumar, G., Priyadharshini, R, Selvi, K., Kalaiselvi, K., Rathika, S., Kanagavalli, N.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 03.05.2024
• Subjects: Accuracy; Computer architecture; Deep learning; Depression; Grey Wolf Optimization (GWO); Human Depression Prediction; Internet; LeNet; Mental health; Prediction algorithms
• DOI: 10.1109/ISCS61804.2024.10581026

Human Depression Prediction is essential for several reasons, primarily centered around improving mental health outcomes and providing timely interventions. Firstly, early detection of depression allows for prompt and targeted interventions, enabling individuals to receive appropriate support and treatment before their condition worsens. The Human Depression Prediction Scheme (HDPS) introduces an innovative method for predicting depression by synergizing the capabilities of deep learning through the LeNet architecture with the optimization prowess of the Grey Wolf Optimization (GWO) algorithm. The proposed scheme achieves a commendable accuracy of 95%, attesting to its effectiveness in discerning depressive tendencies. Notably, the HDPS is implemented in Google Colab, emphasizing its accessibility and ease of use. This integration of advanced technologies and optimization techniques positions HDPS as a promising tool for early detection of depression, offering both high accuracy and practical implementation in a widely accessible computing environment.