© 2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.

org (ISSN-2349-5162)

STRESS DETECTION USING MACHINE

LEARNING TECHNIQUES
R. Swarna Malika1,
II M.SC CS , Department of Computer Science1, K.R. College of Arts and Science,India1.
1

Ravi2,
Assistant Professor2, Department of Computer Science2, K.R. College of Arts and Science2

ABSTRACT
In this paper we can detect the stress by using the machine learning algorithm. Nowadays, stress is a major problem for many
youngsters. The time period that was formerly thought to be the most carefree is currently under a lot of stress. The stress increased a
wide variety of problems such as depression, suicide, heart attack, and stroke. The body's natural response to change is a series of
physical, emotional, and intellectual responses. Three classification algorithms, logistic regression, random forest, and the decision tree
algorithm are applied. The stress dataset was downloaded from Kaggle. By comparing three algorithms, Random forest gives the best
accuracy.
Keywords-Classification, Stress, Machine learning,Depression,Suicide.
1. INTRODUCTION
Stress is either an emotional or physical pressure. Any incident or study that gives you anxiety, rage, or frustration can trigger it. The
body's reaction to a demand or challenge is stress. Similar to when it helps you avoid danger or fulfil a deadline; short-term stress can
be beneficial. Everyone experiences stress; it is a natural human reaction. In actuality, the mortal body is built to observe stress and
respond to it. When experience changes or challenges (stressors), body adapt to novel circumstances. Stress can help us stay awake,
motivated, and prepared to avert danger. For instance, if you have a big test coming up, your body may work harder and stay awake
longer as a result of a stress response. But when stresses persist without relief or rest periods, stress becomes an issue. The autonomic
nerve system of the body regulates several bodily functions, including breathing, heart rate, and eyesight.
DEFINITION MACHINE LEARNING
Artificial intelligence (AI) has a subfield called machine learning that enables computers to learn and develop on their without having
been specifically programmed. Machine learning concentrates on the creation of computer programmers that can access data and learn
on their own. The learning process starts with observations or data, such as examples, direct experience, or instruction, so that we can
seek for data patterns and use the instances to inform future judgments. The fundamental goal is for computers to learn on their own,
without the need for human involvement, and to change their behavior accordingly. We use a classification algorithm in this paper.
2. LITERATURE REVIEW
SS Panicker, et. al. [1], 2019 was defined as a various automated/semi-automated medical diagnosis system based on human
physiology have been gaining enormous popularity and importance in recent years. Physiological features exhibit several unique
characteristics that contribute to reliability, accuracy and robustness of systems. There has also been significant research focusing on
detection of conventional positive and negative emotions after presenting laboratory-based stimuli to participants.
Aishwarya Bannore et al. [2] in 2021 defined Stress is a subjective phenomenon that is difficult to measure comprehensively. However,
we can classify and quantify stress and how it affects one's personal health, including various biological and psychological
vulnerabilities.

JETIRFV06012 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 54

© 2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
R. SAKTHIVEL et al. [3] in 2021 today’s sedentary life leads to a plethora of lifestyle-related illnesses. This has led to the quest to
predict diseases before they occur. In the past, research on stress prediction was carried out conventionally in a laboratory-based
environment.
Qian Liu et al. [4] in 2022 Stress detection is a basic and essential task for examining the mental health of a given population. With the
rapid digitalization leading to text-based forms of communication gaining dominance over spoken ones, there is now the chance to
develop analytical studies for stress detection directly from textual inputs in social media.
Sanchita paul et al. [5] Stress is an escalated psycho-physiological state of the human body emerging in response to a challenging
event or a demanding condition. Environmental factors that trigger stress are called stressors. In case of prolonged exposure to
multiple stressors impacting simultaneously, a person’s mental and physical health can be adversely affected which can further lead to
chronic health issues.
Alisha Banga et al. [6] in 2019 Nowadays, there is a big problem with mental stress, especially in young people. The time period that
was formerly thought to be the most carefree is currently under a lot of stress. Today's increased stress causes a variety of issues,
including depression, suicide, heart attacks, and stroke.
M. Vani et al. [7] in 2020 Stress is a common part of everyday life that most people have to deal with on various occasions. However,
having long-term stress, or a high degree of stress, will hinder our safety and disrupt our normal lives. Detecting mental stress earlier
can prevent many health problems associated with stress.
Laavanya Rachakond et al. [8] Given the way people live nowadays, they merely sleep without realising the benefits it offers the body.
The Smart-Yoga Pillow (SaYoPillow) is a suggested edge gadget that aims to fully materialise the concept of "Smart-Sleeping" and
assist in understanding the relationship between stress and sleep. It is suggested to develop an edge processor using a model that
examines both sleeping patterns and the physiological changes that take place when we sleep. SaYoPillow is a revolutionary product
with up to 96% accuracy, security features, and consideration of sleeping patterns for stress relief.
A Dharun et al. [9] in 2018 Stress disorders are a common issue among working IT professionals in the industry today. With changing
lifestyle and work cultures, there is an increase in the risk of stress among the employees. Though many industries and corporates
provide mental health related schemes and try to ease the workplace atmosphere, the issue is far from control.
Purnendu Shekhar Pandey [10] in 2017 According to a cardiac surgeon, it is difficult to predict age from heart rate as it is nonlinear, but
we can use a person's heart beat to predict whether that personis fit, unfit and overtrained or not, provided we have that person's age.
E. Fuchs et al. [11] in 2011 It has become clear from the continually rising number of papers in the field of stress research that the
traditional application of the stress concept has significant flaws. In our opinion, it is improper to use the term "stress" to situations
ranging from even the most mildly stimulating challenges to extremely unpleasant ones.
Giorgos Giannakakis et al. [12] 2016 This review investigates the effects of psychological stress on the human body measured through
bio signals. When a potentially threatening stimulus is perceived, a cascade of physiological processes occurs mobilizing the body and
nervous system to confront the imminent threat and ensure effective adaptation.
Martin Griss et al. [13] 2017 Continuous stress monitoring may help users better under- stand their stress patterns and provide
physicians with more reliable data for interventions. Previously, studies on mental stress detection were limited to a laboratory
environment where participants generally rested in a sedentary position.

S. Sriramprakash et al. [14] 2017 tress detector classifies a stressed individual from a normal one by acquiring his/her physiological
signals through appropriate sensors such as Electrocardiogram (ECG), Galvanic Skin Response (GSR) etc, these signals are pre-
processed to extract the desired featureswhich depicts the stress level in working individuals.
3. DATASET
S.No Attribute Type Range
1 Humidity Numeric 10.5 - 29.82
2 Temperature Numeric 79.9 – 98.79
3 Step count Numeric 1 – 200
4 Stress Level Numeric 0 – Normal, 1 - Stress

JETIRFV06012 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 55

© 2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
4. METHODOLOGY
The following diagram shows the Machine learning of stress detection.

Fig 4.1 Methodology of the research work

There are three algorithms used in this model. They are Decision tree, Random forest, Logistic Regression. Compare the algorithm and
find the accuracy value. In this project, random forest algorithm gives the best accuracy.
5. CLASSIFICATION ALGORITHMS
There are three algorithms used in this model. They are Decision tree, Random forest, Logistic Regression. Compare the algorithm and
find the accuracy value. In this project, the random forest algorithm gives the best accuracy.
DECISIONTREE
The most effective and well-liked technique for categorization and prediction is the decision tree. A decision tree is a type of tree
structure that resembles a flowchart, where each internal node represents a test on an attribute, each branch a test result, and each leaf
node (terminal node) a class label. It is among the most popular and useful techniques for supervised learning. They can be applied to
jobs requiring classification and regression. It is a tree-structured classifier, where internal nodes stand in for the dataset's features,
branches for the decision-making processes, and leaves for the best results. The Decision Node and Leaf Node are the two nodes of a
decision tree.

Figure 5.1.1 Decision Tree

LOGISTICREGRESSIONALGORITHM
One of the most often used Machine Learning algorithms is logistic regression. It falls under the category of supervised learning. Using
a predetermined set of independent factors, it is used to predict the categorical dependent variable. In a categorical dependent variable,
the output is predicted via logistic regression. As a result, the result must be a discrete or categorical value. It can be either True or
False, Yes or No, 0 or 1, etc., but rather than providing an exact value between 0 and 1, it provides probabilistic values that fall between
0 and 1. Assigning observations to a discrete set of classes is done using the classification process known as logistic regression. Email
spam or not spam is one example of a classification problem.

JETIRFV06012 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 56

© 2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)

Figure 5.2.1 Logistic Regression

RANDOM FOREST
The favored algorithm for machine learning A component of the supervised learning approach is Random Forest. It can be used for
ML problems involving both regression and classification. Its foundation is the idea of ensemble learning, which is a technique for
combining several classifiers to handle challenging problems and improve model performance 0. Instead of relying exclusively on one
decision tree, the random forest uses the forecasts from each decision tree and is based on the majority votes of predictions to predict
the outcome. The greater number of trees in the forest prevents higher accuracy and over fitting. This approach aims to identify the
greatest feature from all the features at random.

Fig 5.3.1 Random Forest

6. EXPERIMENTAL RESULT
Comparison of Classification Algorithms

7. CONCLUSION AND FUTURE SCOPE

This work reports the impact of different Machine Learning techniques for stress detection. The Performance analysis of three
algorithms, namely Random forest, Logistic Regression and Decision Tree is performed and accuracy is obtained. When it comes to
accuracy, it is observed that the Random forest algorithm outperforms more than the Logistic Regression and Decision Tree algorithms.
Hence, by usingthe Random forest, the prediction of stress detection is performed and the result is obtained.
The future work of this research can be made to additional improvement using k-fold cross- validation, which has an impact on the
JETIRFV06012 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 57
© 2023 JETIR March 2023, Volume 10, Issue 3 www.jetir.org (ISSN-2349-5162)
additional improvement metrics. The automation of stress detection using actual real time data from health care organizations and
agencies, which can be built using big data. They can be fed as streaming data and by using the data, investigation of the patients in
real time can be prepared. We can detect the stress by using the sensor.
8. REFERENCES
[1] Suja SreeithPanicker,PrakasamGayathriA survey of machine learning techniques in physiology based mental stress detection
systems,Volume 39, Issue 2, April–June 2019.
[2] Aishwarya Bannore; Tejashree Gore; Apoorva Raut; Kiran Talele (10 November 2021)Mental stress detection using machine
learning algorithm, International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME).
[3] RavinderAhuja,AlishaBanga (2019) Mental Stress Detection in University Students using Machine Learning Algorithms Volume
152.
[4] V. C. Magaa and M. Muoz-Organero, “Reducing Stress on Habitual Journeys,” in Proc. 5thIEEE Int. Conf. Consum. Electron. –
Berlin (ICCE-Berlin), 2015, pp. 153–157.
[5] R. W. McCarley, “Neurobiology of REM and NREM Sleep,” Sleep Med., vol. 8, no. 4, pp. 302
– 330, 2007.
[6] L. Ciabattoni, F. Ferracuti, S. Longhi, L. Pepa, L. Romeo, and F. Verdini, “Real-Time Mental Stress Detection based on
Smartwatch,” in Proc. IEEE Int. Conf. Consum. Electron. (ICCE), 2017, pp. 110–111.
[7] SergioMuñoz, Carlos A.Iglesias “A text classification approach to detect psychological stress combining a lexicon-based feature
framework with distributional representations” Volume 59, Issue 5, September 2022.
[8] Sami elzeiny, marwa qaraqemachine learning approaches to automatic stress detection 2018 ieee/acs 15th international conference
on computer systems and applications (AICCSA).
[9] GiorgosGiannakakis,Dimitris GrigoriadisKaterinaGiannakaki,Olympia Simantiraki,Alexandro “Review on Psychological Stress
Detection Using Biosignals” IEEE Transactions on Affective Computing (Volume :13, ISSUE:1,01 JAN-MARCH 2022).
[10] Jacqueline Wijsman , Bernard Grundlehner,Hao Liu, Hermie Hermens, Julien Penders “Towards mental stress detection using
wearable physiological sensors” on IEEE Engineering in Medicine and Biology Society.
[11] Jing Zhai , Armando Barreto “Stress Detection in Computer Users Based on Digital Signal Processing of Noninvasive
Physiological Variables” 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.
[12] Shalom Greene,Himanshu Thapliyal,Allison Caban-HoltA Survey of Affective Computing for Stress Detection: Evaluating
technologies in stress detection for better health IEEE Consumer Electronics Magazine ( Volume: 5, Issue: 4, October 2016).
[13] Alberto de Santos Sierra,Carmen Sanchez Avila,Javier Guerra Casanova, Gonzalo Bailador del Pozo[11] Peng Cen1 , Kexin
Zhang1 and Desheng Zheng1, *” Sentiment Analysis Using Deep Learning”, Approach Journal on Artificial Intelligence, vol.2, no.1,
pp.17-27, 2020.
[12] Dirash A R1, Dr. S K Manju Bargavi2, “LSTM Based Sentiment Analysis”, International Journal of Trend in Scientific Research
and Development (IJTSRD) Volume 5 Issue 4.
[13] Ditiman Hazarika 1 , Gopal Konwar 1 , Shuvam Deb 1 , Dr.Dibya Jyoti Bora 2, “Sentiment Analysis on Twitter by Using
TextBlob for Natural Language Processing”, Proceedings of the International Conference on Research, Vol. 24.

JETIRFV06012 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 58