Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network (original) (raw)
Related papers
Stress detection using deep neural networks
BMC Medical Informatics and Decision Making, 2020
Over 70% of Americans regularly experience stress. Chronic stress results in cancer, cardiovascular disease, depression, and diabetes, and thus is deeply detrimental to physiological health and psychological wellbeing. Developing robust methods for the rapid and accurate detection of human stress is of paramount importance. Prior research has shown that analyzing physiological signals is a reliable predictor of stress. Such signals are collected from sensors that are attached to the human body. Researchers have attempted to detect stress by using traditional machine learning methods to analyze physiological signals. Results, ranging between 50 and 90% accuracy, have been mixed. A limitation of traditional machine learning algorithms is the requirement for hand-crafted features. Accuracy decreases if features are misidentified. To address this deficiency, we developed two deep neural networks: a 1-dimensional (1D) convolutional neural network and a multilayer perceptron neural networ...
Human Stress Monitoring System Using Convolution Neural Network
International Journal of Scientific Research in Science and Technology, 2021
Psychological problems are becoming a major threat to people’s life. Mental stress is a major issue nowadays, especially among youngsters and working people. The age that was considered once most carefree is now under a large amount of stress due to the surroundings. It is important to detect and manage stress before it turns into a severe health issue. Stress increase nowadays leads to many problems like depression, suicide, heart attack, and stroke. In this paper, the stress of the working people is being monitoring in their work environment. Image processing technique is used to monitor the stress of a person. The stress is identified by the face detection mechanism. In this face detection project, a computer system will be able to find and recognize human faces fast and precisely in images or videos that are being captured through a surveillance/web camera. It helps in conversion of the frames of the video into images so that the face of the student can be easily recognized for their face expressions. The dataset is taken from various people and their face expressions. These expressions are stored as values in XML files. These values are used to train the system using Convolution Neural Network algorithm. It predicts the results based on the values in the dataset. The resulting values will be stored in the text document. It will be helpful to their organisation counsellor for further future reference.
Evaluation of stress based on multiple distinct modalities using machine learning techniques
International journal of public health science, 2024
Nowadays, one of the most time-consuming and complex study subjects is predicting working professionals' stress levels. It is thus crucial to estimate active professionals' stress levels to aid their professional development. Several machine learning (ML) and deep learning (DL) methods have been created in earlier articles for this goal. But they also have drawbacks, such as increased design complexity, a high rate of misclassification, a high incidence of mistakes, and reduced efficiency. Considering these issues, the objective of this study is to make a prognosis about the stress levels experienced by working professionals by using a cutting-edge deep learning model known as the convolutional neural networks (CNN). In this paper, we offer a model that combines CNN-based classification with dataset preprocessing, feature extraction, and optimum feature selection using principal component analysis (PCA). When the raw data is preprocessed, duplicate characteristics are eliminated, and missing values are filled.
This paper proposes a framework using artificial intelligence for recognizing human mental stress based on physiological data. It comprises three stages; at first, emotion detection has been carried out from the facial image using a deep learning-based framework employing convolutional neural networks (CNN). Secondly, electrocardiogram (ECG) signals have been acquired with the help of the developed sensor-based system integrating Arduino UNO with AD8232 sensor. Finally, preprocessing has been performed and extracted features from the ECG signals are fed to support vector machines (SVM) for identification of arrhythmia and hence diagnosis of mental stress. All three aspects are connected together via the overall output calculation. A score is added in accordance to the output for each of these three stages. The range of the final score (i.e., the overall output) decides the level of mental stress suffered by the person. The proposed method has been trained on FER-2013 for emotion det...
Machine Learning Based Solutions for Real-Time Stress Monitoring
IEEE Consumer Electronics Magazine, 2020
Stress may be defined as the reaction of the body to regulate itself to changes within the environment through mental, physical, or emotional responses. Recurrent episodes of acute stress can disturb the physical and mental stability of a person. This subsequently can have a negative effect on work performance and in the long term can increase the risk of physiological disorders like hypertension and psychological illness such as anxiety disorder. Psychological stress is a growing concern for the worldwide population across all age groups. A reliable, costefficient, acute stress detection system could enable its users to better monitor and manage their stress to mitigate its long-term negative effects. In this article, we will review and discuss the literature that has used machine learning based approaches for stress detection. We will also review the existing solutions in the literature that have leveraged the concept of edge computing in providing a potential solution in real-time monitoring of stress.
Stress Classification and Personalization: Getting the most out of the least
arXiv (Cornell University), 2021
Stress detection and monitoring is an active area of research with important implications for the personal, professional, and social health of an individual. Current approaches for affective state classification use traditional machine learning algorithms with features computed from multiple sensor modalities. These methods are data-intensive and rely on handcrafted features which impede the practical applicability of these sensor systems in daily lives. To overcome these shortcomings, we propose a novel Convolutional Neural Network (CNN) based stress detection and classification framework without any feature computation using data from only one sensor modality. Our method is competitive and outperforms current state-of-the-art techniques and achieves a classification accuracy of 92.85% and an f 1 score of 0.89. Through our leave-one-subject-out analysis, we also show the importance of personalizing stress models.
Mental Stress Assessment Using PPG Signal a Deep Neural Network Approach
Iete Journal of Research, 2020
Due to the pace of modern life and the shift of nature of work from physical to cognitive, mental stress is increasing in every profession. Mental stress has now become a leading cause of work-related illness. There are numerous sedentary occupations, such as those in the IT industry, where individuals are required to work for extended periods of time, leading to stress. Working for extended periods under mental stress can increase the risk of life-threatening diseases like cardiovascular diseases, mental health disorders etc. There is, thus, a requirement for a non-obtrusive tool to detect mental stress. In this work, pulse rate variability (PRV) of 15 subjects during 5 cognitive states (relaxation, deep breathing, and during three mental tasks involving three levels of mental stress) was examined using photoplethysmography (PPG). The result of this study indicates that 18 features (9-time domain and 9 frequency domain) are statistically significant at p < 0.05 as per the Friedman test in 5 cognitive states. The machine-learning algorithm based upon a multi-layer perceptron (MLP) was able to classify with an overall accuracy of 85.1±1.1%. Classification accuracy further improved by using deep neural networks (DNN) to 91±1.1%.
A Survey on Stress Detection Through Speech Analysis Using Machine Learning
International Journal of Scientific Research in Science and Technology, 2022
The project's goal is to develop a model for stress detection of humans using speech. We present a deep learning-based psychological stress detector model using speech signals. The main aim is to differentiate stressed and non-stressed speeches. The deep learning algorithm used here is Convolutional Neural Network(CNN) which is made up of layers that are all related. Speech is transformed into spectrograms and they are fed to the Convolutional Neural Network(CNN) model. Mel-frequency cepstral coefficients are used to extract features from pre-processed data. The results of this model can then be predicted exactly using binary decision criterion. The levels of particular hormones like cortisol are being used to consistently detect stress. In Fact the aim of this project is to automate the process of stress detection without the intervention of a Doctor or Psychiatrist. This project proposes a hybrid deep learning model to analyze whether the person is stressed or unstressed using speech.
Hierarchical deep neural network for mental stress state detection using IoT based biomarkers
Pattern Recognition Letters, 2021
Stress is a psychological condition in which a person feels overwhelmed with pressure. It can be positive, keeping us alert and motivated or negative causing emotional and physical wear-tear. The body's autonomic nervous system has a built-in stress response that causes physiological changes to allow the body to combat stressful situations. Bio-signals are biomarkers depicting these physiological changes during chronically activated situations. Only trained medical practitioners can measure such indicators which can be tedious and time consuming, delaying early identification and timely intervention. With the availability of IoT based sensors for healthcare, these biomarkers can be tracked using various wearable devices. Motivated by the need to design a model for mental stress state detection using sensor-based bio-signals, this research proffers multi-level deep neural network with hierarchical learning capabilities of convolution neural networks. A multivariate time series data consisting of both wrist-based and chest-based sensor bio-signals is trained using a hierarchy of networks to generate high-level features for each bio-signal feature. A model-level fusion strategy is proposed to combine the high-level features into one unified representation and classify the stress states into three categories. A superlative performance accuracy of 87.7% is achieved using the proposed network, which outperforms the state-of-the-art results.