Depression Predictor Model for Farmers using Machine Learning Techniques
Mallikarjun H M1, Akshay Chhetri2, Apoorva G S3, Gowri Jadhav4, Sheetal B V5
1Dr. Mallikarjun H M, Department of Electronic & Instrumentation Engineering, RNSIT, Bengaluru (Karnataka), India.
2Akshay Chhetri, BE, Department of Electronics and Instrumentation Engineering, RNSIT, Bengaluru (Karnataka), India.
3Apoorva G S, BE, Department of Electronics and Instrumentation Engineering, RNSIT, Bengaluru (Karnataka), India.
4Gowri Jadhav, BE, Department of Electronics and Instrumentation Engineering, RNSIT, Bengaluru (Karnataka), India.
5Sheetal B V, BE, Department of Electronics and Instrumentation Engineering, RNSIT, Bengaluru (Karnataka), India.
Manuscript received on 06 December 2019 | Revised Manuscript received on 14 December 2019 | Manuscript Published on 31 December 2019 | PP: 540-543 | Volume-9 Issue-2S December 2019 | Retrieval Number: B10471292S19/2019©BEIESP | DOI: 10.35940/ijitee.B1047.1292S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: There are a few disorders that are the outcome of unbalanced mental state. A very basic one is depression. Depression is a very serious yet common mental ailment that damagingly distresses how a person thinks or feels or acts. Side effects of physical injuries are obvious and regularly agonizing, because of which they are recognized and paid attention to. Symptoms of mental illnesses are not very comprehendible. A lot of individuals don’t know about them, including the people who are suffering. This research paper proposes a methodology with an approach to machine learning in order to categorize the subject into 4 distinguished levels of depression, namely normal, mildly depressed, moderately depressed and severely depressed. This procedure is proposed to be carried out using PHQ-9 and DASS-21 questionnaire and the electric EEG bands Alpha, Beta, Delta, Gamma and Theta variations will be obtained via the usage of head kit Neurosky’s Mindwave aid.
Keywords: PHQ-9, DASS-21, EEG, SVM.
Scope of the Article: Machine Learning