• Tanvi Sharma
• Kakoli Banerjee
• Sonali Mathur

Depression or depressive disorder is a mental disorder that is prevalent in current times. Some of the time people feel down or low in their lives. However, when this inclination perseveres for longer time, it influences general intellectual capacity of the mind. It may prompt some genuine cerebrum working handicaps, for example, alarm assaults, tension, dread and so on. Wretchedness is not quite the same as misery/pain. It is regularly accepted that downturn is a consequence of substance awkwardness however that doesn't catch the unpredictability of the illness. Moreover, misery contributes significantly to the worldwide weight of malady and impacts individuals in each and every society around the globe. While the worldwide weight of misery presents a significant challenge to general wellbeing, at the clinical level, at the financial level, and at the social level, there are several evidence-based and distinct approaches that can efficiently tackle or reduce this burden. Understanding mechanisms that contribute to chronic impairment induced by significant depressive disorder is still not known. Therefore, in recent years, Machine Learning (ML) methods have appeared as interesting techniques to address such complicated issues. This study describes the current functionality procedures of distinct methods, including some models with distinct parameters, benefits, and drawbacks. The primary focus of this paper is to underscore a relative examination of methods that can be used for overall identification and assessment of depression. The purpose of this study is to present a better and more effective assessment of different methods to propose the best procedure from all current methods. Moreover, this research work presents comparison of the features and techniques that are used in prediction of depression. Also, the point of this paper is to explore to accomplish better customized treatment for the indications of melancholy.

Depression, Machine Learning, Vocal, Motion and Facial Expressions, Depression Detection

"An Evaluation of Machine Learning Techniques in Predicting Depression using Motion and Facial Expressions", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 8, page no.614-621, August 2020, Available :http://www.jetir.org/papers/JETIR2008385.pdf

"An Evaluation of Machine Learning Techniques in Predicting Depression using Motion and Facial Expressions", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 8, page no. pp614-621, August 2020, Available at : http://www.jetir.org/papers/JETIR2008385.pdf