by Vijay Kumar, Muskan Khajuria * , Anshu Singh
Department of Computer Science and Engineering, National Institute of Technology Hamirpur, Hamirpur, 177005, India
* Author to whom correspondence should be addressed.
Journal of Engineering Research and Sciences, Volume 1, Issue 5, Page # 17-24, 2022; DOI: 10.55708/js0105002
Keywords: Depression, Machine Learning, mental health, SMOTE, ADABoost, SelectKBest
Received: 14 February 2022, Revised: 04 April 2022, Accepted: 11 April 2022, Published Online: 12 May 2022
APA Style
Kumar, V., Khajuria, M., & Singh, A. (2022, May). Machine Learning Aided Depression Detection in Community Dwellers. Journal of Engineering Research and Sciences, 1(5), 17–24. https://doi.org/10.55708/js0105002
Chicago/Turabian Style
Kumar, Vijay, Muskan Khajuria, and Anshu Singh. “Machine Learning Aided Depression Detection in Community Dwellers.” Journal of Engineering Research and Sciences 1, no. 5 (May 2022): 17–24. https://doi.org/10.55708/js0105002.
IEEE Style
V. Kumar, M. Khajuria, and A. Singh, “Machine Learning Aided Depression Detection in Community Dwellers,” Journal of Engineering Research and Sciences, vol. 1, no. 5, pp. 17–24, May 2022, doi: 10.55708/js0105002.
Depression is a mental condition that can have serious negative effects on an individual’s thoughts and nd health problems that could lead to grave heart diseases. Depression detection has become necessary in community dwellers considering the lifestyle being followed. Here we use NHANES dataset to compare the performance of various machine learning algorithms in depression detection. The 2015 dataset was used to train the models and testing was done on data from 2017 to analyze the robustness of the model. Feature extraction was also performed on the dataset to observe relevant features. It was found that ADABoost used wit ic Minority Oversampling Technique (SMOTE) gave the best test results in terms of F1 score.
This sidebar is currently being updated and may temporarily overlap with the pages.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.