Human Stress Monitoring System Using Convolution Neural Network (original) (raw)
Related papers
IASET Publications, 2022
With the help of face photos and facial landmarks, we suggest a stress recognition algorithm in this work. A device for gathering the necessary data is needed along the event of stress detection utilising a natural or biological signal or thermal picture, thus being important area for research. To address this flaw, we put forth an algorithm that can identify a person's behaviour from still videos or photos taken using a normal camera, including creating in-depth neural network, uses facial identifications infused along benefiting that when someone is being stressed, their eye, mouth, and head movements differ along how they normally behave. Likewise, by identifying a candidate's behaviour during an online interview, we can determine whether or not they are qualified. The suggested algorithm recognises behaviour more accurately, according to experimental data.
Human Face Detection and Emotion Recognition using Neural Network
A Journal of TUTA, Paschimanchal campus, 2018
Automatic facial emotion recognition is the active research area and challenging task in computer vision. Computers are used to gain high level understanding from digital images and videos. Automatic face detection and emotion recognition plays important role in human machine interaction. Tradition approaches of machine learning requires complex feature extraction process and produced poor results. In this paper, Convolution neural network of deep learning is proposed to exactly and accurately interpret information available in human faces. Basic emotions of human faces such as happy, sad, disgusting, fear, angry and disgusting will be evaluated. The neural network architecture is trained with large dataset and tested to obtain the best results with high accuracy.
Stress Alarm Raiser Based on Facial Expressions
International Journal of Innovative Research in Computer Science and Technology
This paper presents the development of a stress detector using facial expression analysis in Python, utilizing the Deep Face library. Also, after detecting whether the person is in stress or not, it allows the user to inform about his stress to the preferred his/her family member by sending an automated WhatsApp message and showing some remedies to reduce stress.
IMPLEMENTATION OF STRESS DETECTION SYSTEM
In this proposed system, students will be continuously monitored through a camera. Facial expressions of every student will be captured and will be further processed. Depending upon the expressions and the processed data, results will be obtained i.e. if the student is stressed or no. A notification will be sent to the teacher, counsellor or the person incharge to guide the students. We propose a method which will help the child to cope up and deal with personal or other psychological problems. Our project will help the student to cope up and perform well in academics, will improve the student's self-confidence, will help the institution to prepare and train quality students and achieve good results.
Development Of Facial Stress Level Detection System For Driving Safety Using Deep Learning
Science and Technology Publishing, 2022
In this research work, a deep learning approach using a YOLO convolutional neural network (YCNN) algorithm was used to determine the facial stress level of drivers for their overall safety and that of others. A camera is placed on the dashboard that continuously tracks the face of the driver's image at real time and the model extracts basic features that helps to determine if the driver is drowsy or distracted. An alarm is triggered that alerts the driver when his/her face is off the car screen. Eye aspect ratio is used to calculate when the driver is gradually sleeping off or when eyes are closed. 10,000 images of drivers were obtained and splitted for the training, testing and validation phases in the ratio of 60: 20: 20. The results obtained after testing indicates 94% accuracy of the model. The model has a wide application in the areas of human computer communication, facial expression recognition, driver fatigue determination and autonomous or self-driving vehicles.
Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network
Sensors
Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.
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.
Facial Recognition Development to Detect Corporate Employees Stress Level
2019 IEEE International Conference on Engineering, Technology and Education (TALE), 2019
Authors' Contribution STK and AR contributed in study design, sampling, experimentation, results analyses and manuscript writing. SG and NS contributed in study design and sampling. SAK and MA contributed in results analyses and manuscript writing. MK and NL contributed in sampling and experimentation. SY contributed in sampling and study management.
Classification of Stress Recognition using Artificial Neural Network
— This paper presents the results of a study developing expert system to support stress recognition based on Artifical Neural Network (ANN). Developed ANN is trained using data from Physionet database and collected data from other researchers. The implemented system for stress recognition uses drivers ECG signal, Galvanic Skin Response and Respiration Rate as parameters. Developed neural network was validated with 77 samples. Samples are obtained from subjects using Pasco sensors in 7D cinemas. Out of 77 samples, in 71% of subjects higher level of stress is recognized, while 29% of subjects are classified as subjects with normal vital functions. An accuracy of 99% and specificity of 98% is obtained.
Effective Facial Emotion Recognition using Convolutional Neural Network Algorithm
International Journal of Recent Technology and Engineering (IJRTE), 2019
This paper presents the idea related to automated live facial emotion recognition through image processing and artificial intelligence (AI) techniques. It is a challenging task for a computer vision to recognize as same as humans through AI. Face detection plays a vital role in emotion recognition. Emotions are classified as happy, sad, disgust, angry, neutral, fear, and surprise. Other aspects such as speech, eye contact, frequency of the voice, and heartbeat are considered. Nowadays face recognition is more efficient and used for many real-time applications due to security purposes. We detect emotion by scanning (static) images or with the (dynamic) recording. Features extracting can be done like eyes, nose, and mouth for face detection. The convolutional neural network (CNN) algorithm follows steps as max-pooling (maximum feature extraction) and flattening.