Depression Detection using Extreme Learning Machine

• Published in: 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN) pp. 42 - 47
• Main Authors: Dutta, Prajna, Gupta, Deepak, Maurya, Jyoti
• Format: Conference Proceeding
• Language: English
• Published: IEEE 03-05-2024
• Subjects: Accuracy; Depression Detection; Extreme Learning Machine; Extreme learning machines; Machine Learning; Neurological diseases; Pervasive computing; Prevention and mitigation; Social networking (online); Surveys
• DOI: 10.1109/ICPCSN62568.2024.00015

Depression is the most well-known type of physiological or mental health problem that affects a large number of people globally. Extreme learning machine (ELM) techniques are currently preferred to solve wide range of health disease detection and prediction issues. ELM is a single hidden layer feed-forward neural network (SLFN), which converges much faster than the other traditional Machine Learning (ML) methods and yields promising results. Many research works already exist on the application of Machine Learning (ML) models to the Depression Detection dataset but little to no work was found wherein Extreme Learning Machine was used for Depression Detection. This research work has applied Extreme Learning Machine (ELM) and other ML techniques for depression detection and compared the results obtained and found that, ELM has delivered the best performance with an accuracy of 91.73%.