Stress Prediction Using Machine Learning and IoT

As the globalization, are expanding individuals twist towards the cutting-edge life Stress issue turns into a significant issue among in experts and understudies life. The term pressure is causing different mental issue face to face. Understudies of various courses and distinctive expert college are expanding ambushed with this pressure. The points of this examination are to research natural, social, mental and scholarly postgraduate and doctoral understudies. The quantity of tests of this investigation are 220 undergrad and postgraduate understudies. The information of my examination was gathered independent from anyone else – planned poll and by PSS Scale and the overview has organized inquiries which were gathered through google dox. There are many pressure expectation calculations has been proposed like SVM, KNN, RANDOM FOREST, NAVIE BAYES, LOGISTIC REGRESSION, DECISION TREE. Different machine learning methods are utilized that related in this field. Too, it talks about the application territories and difficulties for stress forecast with knowledge into the past research work.

Download Full-text

Psychological Stress Prediction on Social Media using Convolutional Neural Network

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b1583.0982s1119 ◽

2019 ◽

Vol 8 (2S11) ◽

pp. 3464-3468

Keyword(s):

Neural Network ◽

Machine Learning ◽

Social Media ◽

Deep Learning ◽

Convolutional Neural Network ◽

Psychological Stress ◽

Business Environment ◽

Media Analysis ◽

The Social ◽

Stress Prediction

Psychological stress which is a mental illness also causes physical problems to the human. Nowadays social media plays an important role in the world for communication to share their thoughts with their friends and family. The social media analysis is the process of detecting and predicting the user's thoughts and opinions which also one of the important perspective in the developing business environment. The overwhelming stress and long term stress sometimes lead to suicidal ideation. By analyzing the social media content to predict the overwhelming stress state of the users in the earlier stage will reduce the psychological stress and suicidal rate too. In this paper, we address the problem of stress prediction by using social media. The machine learning and deep learning methods to perform the classification of stress analysis. Here both image and text- tweet data are used and the images are processed with the Optical Character Recognition and the text data are processed by using the Natural Language Processing and Convolutional Neural Network for classifying the tweet content of the user as stressed or non-stressed. Furthermore, with the advancement of the machine learning and deep learning method of classification gives a better result in terms of performance and accuracy of the prediction.

Download Full-text

Physiological Stress Prediction using Machine Learning Classifiers

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.a4556.119119 ◽

2019 ◽

Vol 9 (1) ◽

pp. 675-677

Keyword(s):

Machine Learning ◽

Nearest Neighbor ◽

Physiological Stress ◽

Classification Algorithms ◽

K Nearest Neighbor ◽

Nearest Neighbor Algorithm ◽

Machine Learning Classifiers ◽

Learning Classifiers ◽

Stress Prediction ◽

K Nearest Neighbor Algorithm

The aim of this study is to predict the stress of a person using Machine Learning classifiers. This system classifies the stress of a person as either High or Low. There are various classification algorithms present, out of which 9 classification algorithms have been chosen for this study. The algorithms implemented are K-Nearest Neighbor classifier, Support Vector Machine with an RBF kernel, Decision Tree algorithm, Random Forest algorithm, Bagging Classifier, Adaboost algorithm, Voting classifier, Logistic Regression and MLP classifier. The different algorithms are applied on the same dataset. The dataset is obtained from a GitHub repository labelled Stress classifier with AutoML. The different accuracies of each algorithm are found, and the classification algorithm with the best accuracy is determined. On comparison, it was found that the K-Nearest Neighbor algorithm has the best accuracy with an accuracy rate of 79.3% for physiological stress prediction. While other algorithms had varying accuracies, K-Nearest Neighbor algorithm was the most consistent.

Download Full-text