Proposed a Framework for Depression Monitoring System by Detecting the Facial Expression using Soft Computing Algorithm
Sonia Sodhi1, Manisha Jailia2

1Sonia Sodhi*, Research Scholar, Dept. of Computer Science & Engg., Banasthali Vidyapith University, Rajasthan, India.
2Manisha Jailia, Associcate Professor, Dept. of Computer Science & Engg., Banasthali Vidyapith University, Rajasthan, India.
Manuscript received on March 31, 2021. Revised Manuscript received on April 06, 2021. Manuscript published on May 10, 2021. | PP: 5-7 | Retrieval Number: 100.1/ijpmh.B1003031221 | DOI: 10.35940/ijpmh.B1003.051221
Open Access | Ethics and Policies | Cite  | Mendeley
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC BY-NC-ND license (

Abstract: Healthcare Informatics plays a very important role for manipulating data. In the healthcare discoveries, pattern recognition is important for the prediction of depression, aggression, pain and severe disease diagnostics. In [16][5], the real innovation that has affected and organized human services is cloud computing, which empowers whenever anyplace access to the information put away in a cloud. The mobile devices are continuously observing patients that move around a networked healthcare environment. In traditional healthcare diagnostic system, we depend upon expensive tests and machineries which increase the expenditure of healthcare. It is dire need to reduce the aggregate cost of regular or usual diagnostics incorporates high cost of hospitalization. These expenses can be limited or disposed of with the assistance of remote patient monitoring gadget, a healthcare IoT product. Remote monitoring of person’s health gadget includes the observing of a person from an alternate area. This dispenses the requirement for driving to clinic and to being hospitalized for less severe circumstances. This research will explore the depression monitoring system by detecting the facial expression using suitable soft computing algorithm. We may use different algorithms such as CNN and Multilayer Perceptron to get the best result. On the basis of classification it detects the class of disease. For this purpose, the primary dataset from various facial expressions of a patient will be collected, filtered and apply to classification algorithm to train the model.
Keywords: Convolutional Neural Network, Machine Learning, Learning (Artificial Intelligence).