STRESS LEVEL DETECTION

Kommineni Venkata Naga Kaushik
UG Student
Department of Computer Science and Engineering
KL University
Hyderabad,India
kaushik.kommineni@gmail.com

Abstract — Due to the COVID-19 pandemic, to control pandemic situations and its spread, the government took a decision to shut all the educational institutions, which in turn creating a direct impact on many people by causing stress and mental illness.We propose a solution for organizations where they can know the levels of stress faced by the students and could calculate percentage of stress.So for this to be done, students can take up the survey through a google form which consist of the parameters which are helpful in collecting information about mental distress and many other psychological factors faced by the students.The data which is collected from the students is inputted into the model with results the stress levels of the students.
Keywords:K-Means, Principal component analysis (PCA), Logistic Regression.

I. INTRODUCTION

In a pandemic, the people’s outlook of health- care constraints and lifestyles is completely switched. Since then,covid 19 had spread a lot, causing global disturbances.
The administration of educational institutions has closed across the globe to prune the growth of the disease and in welfare of all people.
Considering all these circumstances the people around all countries were affected by entities like food availability and medical facilities.
Many surveys were conducted to study the person’s stress level based on the stress constraints like physiological conditions. A person can be stressed out in scenarios like worrying about losing their employment, family health conditions and about the grades in examinations. These kinds of stressful scenarios increase the stress levels which affects the increase of heart and muscles related issues.
Generally, anxiety and stress are very much common among all the students with a variation of degree. So, by observing each and every student it would be a huge task to go through their profiles. This problem makes us create a new model for predicting stress automatically. For each student who is undergoing various psychological parameters of stress and proposes a solution for that.
So for this to be done, some Machine Learning algorithms and Data Science techniques are used. Maintaining track records of each student’s stress levels, and studying them makes us understand the degrees of stress of the students in organization .
Students are categorized into 2 sublevels in regards with the stress percentage they face : i.e., over-stressed or under-stressed. And according to that, the range of stress is highlighted based on the levels.. Based on this percentage, the authorities give advice to the students.As a result, we create a model for unlabeled data and untrained data that will determine the stress level of students using different Machine Learning and data science techniques.
II. LITERATURE SURVEY

Paper [1], In software engineers, stress has been highlighted as a major issue.This dataset has been collected and submitted to a variety of machine learning algorithms .According to their research, 75% of employees working in the IT field are susceptible to pressure. Boosting and decision trees are just a few of the strategies they’ve worked on.

In Paper [2], The authors used many techniques to evaluate stress, including EEG, GSR, EMG, and SpO2.by these parameters stress levels of a person are calculated automatically.. Sensors are used here to collect the data from a person and then are compared to the indexed value that is given as input to create a baseline of comparison.

In Paper [3], The authors applied a decision tree algorithm to analyze data from students whose stress levels were measured at the start and end of the semester. As a consequence, the model identifies students who are more stressed near the conclusion of the semester rather than at the beginning.

In Paper[4],Distance education was made easier with higher development in technology with time.Many terms like Internet learning, web-based education, etc., have one thing in common i.e., stay connected with the computer through a series of networks . So by any means people are connected to the internet and learn from it such that people are distancing from each other and facing little mental illness.

In Paper [5], The author of this paper created a new model, which uses supervised algorithm labeling of data. Here supervised labeling method is used in contrast to an unsupervised clustering method which analyzes the ambiguous work and assigns or labels the specific work as per its senses.



stress-level-detection
FREE DOWNLOAD

@ engpaper.com published paper
PUBLICATION PROCEDURE WITH US ENGPAPER.COM
ENGPAPER.COM PUBLISHED PAPERS