
Proposed a Framework for Depression Monitoring System by Detecting the Facial Expression using Soft Computing Algorithm
Author(s) -
Sonia Sodhi,
Manisha Jailia
Publication year - 2021
Publication title -
international journal of preventive medicine and health (ijpmh)
Language(s) - English
Resource type - Journals
ISSN - 2582-7588
DOI - 10.54105/ijpmh.b1003.051221
Subject(s) - gadget , computer science , soft computing , health care , cloud computing , facial expression , machine learning , artificial intelligence , human–computer interaction , algorithm , artificial neural network , economics , economic growth , operating system
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.