Scopus Indexed Publications

Paper Details

A Performance Analysis of Depression Ratio using Machine Learning Approaches
Maria Sultana Keya,

Depression is much more than just tiredness or unpleasantness for a few days. Some individuals believe that depression is a minor ailment rather than a serious medical disease. However, depression is not a weakness that can be “snapped out of” by “getting yourself together.” Depression is a disease which can be recovered by taking proper treatment and support. Depression symptom may be easily detected when a man or woman goes into depression. For the purpose of medication and assistance purpose, prediction of prognosis of the depression is important. In this research paper, five Machine Learning algorithms such as Decision Tree Classifier (DTC), Random Forest Classifier (RFC), Multi-layer Perceptron Classifier (MLP), Support Vector Machine (SVM), and AdaBoost Classifier are used to apply to for prediction of depression prognosis. As a result, it is found that SVM machine learning algorithm performs the best. It has an accuracy rate of 85 percent. Also indicated is the age at which men and women are most likely to become depressed. Support Vector Machine classifiers also have low FP (False Positive) and FN (False Negative) rates. Some visualization is applied to generate a view of depression rate in different types of people. This study also used principal component analysis to Figure out the selective data for analysis algorithms.

Support vector machines , Machine learning algorithms , Data visualization , Learning (artificial intelligence) , Depression , Performance analysis , Prognostics and health management
Journal or Conference Name
2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS)
Publication Year