Realtime Emotional Reflective User Interface Based on Deep Convolutional Neural Networks and Generative Adversarial Networks (original) (raw)
Related papers
Electronics
Physiological measurements have been widely used by researchers and practitioners in order to address the stress detection challenge. So far, various datasets for stress detection have been recorded and are available to the research community for testing and benchmarking. The majority of the stress-related available datasets have been recorded while users were exposed to intense stressors, such as songs, movie clips, major hardware/software failures, image datasets, and gaming scenarios. However, it remains an open research question if such datasets can be used for creating models that will effectively detect stress in different contexts. This paper investigates the performance of the publicly available physiological dataset named WESAD (wearable stress and affect detection) in the context of user experience (UX) evaluation. More specifically, electrodermal activity (EDA) and skin temperature (ST) signals from WESAD were used in order to train three traditional machine learning clas...
Positive Vibes: A Real-time Facial Emotion Detector And Output Based Task Recommender
Emotions are an essential element of human interaction and communication. Although emotions are known to everyone, it is difficult to describe feelings. The Greek philosopher Aristotle thought of the emotion as a stimulus that explores the experience of gain or pleasure. Artificial Intelligence has been witnessing the tremendous growth in closing the gap between human and mechanical skills. The Computer Vision agenda empowers machines to view the world the way people do, see it in the same way and apply this information for many tasks such as image and video recognition, image analysis and segmentation, Media Recreation, Recommendation Programs, Natural Language Processing (NLP), etc. Emotional Awareness draws your attention on key research to solve many problems. However, there is research done on the detection of emotions and ways to experience stress, but not on ways to reduce stress technically. Therefore, the purpose of this paper is to create a system that detects a person's emotions through facial expressions using Deep Learning techniques such as Convolutional Neural Networks and to provide appropriate recommendations based on Emotions. Using real-time facial expressions, a number of emotions will be detected such as sadness, happiness, anger, fear, surprise and neutrality. Detailed facial expressions will be captured, and appropriate emotions will get detected using the CNN algorithm. Emotional analysis by CNN will help inculcate positive vibes among people by proposing mood enhancing activities.
IRJET- Positive Vibes: A Real-time Facial Emotion Detector And Output Based Task Recommender
IRJET, 2021
Emotions are an essential element of human interaction and communication. Although emotions are known to everyone, it is difficult to describe feelings. The Greek philosopher Aristotle thought of the emotion as a stimulus that explores the experience of gain or pleasure. Artificial Intelligence has been witnessing the tremendous growth in closing the gap between human and mechanical skills. The Computer Vision agenda empowers machines to view the world the way people do, see it in the same way and apply this information for many tasks such as image and video recognition, image analysis and segmentation, Media Recreation, Recommendation Programs, Natural Language Processing (NLP), etc. Emotional Awareness draws your attention on key research to solve many problems. However, there is research done on the detection of emotions and ways to experience stress, but not on ways to reduce stress technically. Therefore, the purpose of this paper is to create a system that detects a person's emotions through facial expressions using Deep Learning techniques such as Convolutional Neural Networks and to provide appropriate recommendations based on Emotions. Using real-time facial expressions, a number of emotions will be detected such as sadness, happiness, anger, fear, surprise and neutrality. Detailed facial expressions will be captured, and appropriate emotions will get detected using the CNN algorithm. Emotional analysis by CNN will help inculcate positive vibes among people by proposing mood enhancing activities.
EMERALD—Exercise Monitoring Emotional Assistant
Sensors
The increase in the elderly population in today’s society entails the need for new policies to maintain an adequate level of care without excessively increasing social spending. One of the possible options is to promote home care for the elderly. In this sense, this paper introduces a personal assistant designed to help elderly people in their activities of daily living. This system, called EMERALD, is comprised of a sensing platform and different mechanisms for emotion detection and decision-making that combined produces a cognitive assistant that engages users in Active Aging. The contribution of the paper is twofold—on the one hand, the integration of low-cost sensors that among other characteristics allows for detecting the emotional state of the user at an affordable cost; on the other hand, an automatic activity suggestion module that engages the users, mainly oriented to the elderly, in a healthy lifestyle. Moreover, by continuously correcting the system using the on-line mon...
Detecting Negative Emotions to Counter Depression Using CNN
Proceedings of International Conference on Communication and Artificial Intelligence
The ever-growing stress and the depression cases have recently caught the eyes of many researchers and medical practitioners. From online consultation to wearable devices, detection of depression became easier. The prolonged effect of negativity due to stress or depression appears on the face of the subject, and this fact can be utilized to detect the depression and stress using Convolution Neural Network (CNN) from a video sequence of the subject recorded while answering a questionnaire remotely.
The number of individuals in the modernworld experience elevated stress level, which is non-specific response on the body and plays a significant toll on health, productivity at work, relationships and also effect overall well-being. Many individuals are not aware of the stress triggers and potential health problems caused by prolonged stress. In order to effectively combat stress and its ill effects on health, stress triggers and responses to stress must be recognized and managed in real time. In this paper, applications of machine learning techniques are suggested to categorize and reduce stress is explored. The idea of monitoring stress and reducingstress usesmethods like personalized music, wallpaper themes, favorite games or favorite food ordering and so on. Activities which reduce stress and their degree of reduction are monitored in real time and based on customized stress reduction portfolio is designed using machine learning algorithms.
Developing an affective working companion utilising GSR data
2011
Affective Computing field is in its second decade and is showing great achievements and promising results. Affective computing is mainly related to detecting and modifying a person"s affective state. This paper presents a review on the fields of emotion and affective computing. It reviews some of the work done in the field and proposes a new smart computer system. The proposed system shall use galvanic skin response (GSR) in order to build a model that relates the GSR signals to different emotions. An application shall then be built on top of this model, in order to improve and enhance a person"s mood by suggesting activities that best suits their current mood.
Consumer Wearables and Affective Computing for Wellbeing Support
MobiQuitous 2020 - 17th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services
Wearables equipped with pervasive sensors enable us to monitor physiological and behavioral signals in our everyday life. We propose the WellAff system able to recognize affective states for wellbeing support. It also includes health care scenarios, in particular patients with chronic kidney disease suffering from bipolar disorders. For the need of a large-scale field study, we revised over 50 off-the-shelf devices in terms of usefulness for emotion, stress, meditation, sleep, and physical activity recognition and analysis. Their usability directly comes from the types of sensors they possess as well as the quality and availability of raw signals. We found there is no versatile device suitable for all purposes. Using Empatica E4 and Samsung Galaxy Watch, we have recorded physiological signals from 11 participants over many weeks. The gathered data enabled us to train a classifier that accurately recognizes strong affective states.
Mano Vaidya: Gateway to Relaxation Via Machine Learning
IRJET, 2022
Mental health is an essential issue in the world today. Nowadays, stress has increased a lot in the post-covid world. People are finding it hard to find ways to channel their stress or frustration. We come across many teenagers and youth succumbing to the mere stress faced in this competitive world. This is for several reasons. Chief among them is that people are not finding the right platforms and psychological guidance to overcome stress. In this project, we have planned to make an effort to reduce the stress level of people by utilizing technical advances in the field of computer science. We create an app that contains a closed set of questionnaires from SF-36, which have some weight associated with each question. Using clustering algorithms like k-means, we classify the new user into one of the three stress levels (positive, tolerable, and toxic). We modify the dataset, add the respective clusters in each row, and use the new data set to train classification algorithms like Naïve Bayes and Decision tree. We get the range limits from this and use that in our App to give results. Based on the obtained results, we recommend a few stress-relieving techniques and direct the user towards professional help, if necessary.
Inferring User Facial Affect in Work-like Settings
CERN European Organization for Nuclear Research - Zenodo, 2021
Unlike the six basic emotions of happiness, sadness, fear, anger, disgust and surprise, modelling and predicting dimensional affect in terms of valence (positivity-negativity) and arousal (intensity) has proven to be more flexible, applicable and useful for naturalistic and real-world settings. In this paper, we aim to infer user facial affect when the user is engaged in multiple work-like tasks under varying difficulty levels (baseline, easy, hard and stressful conditions), including (i) an office-like setting where they undertake a task that is less physically demanding but requires greater mental strain; (ii) an assembly-line-like setting that requires the usage of fine motor skills; and (iii) an officelike setting representing teleworking and teleconferencing. In line with this aim, we first design a study with different conditions and gather multimodal data from 12 subjects. We then perform several experiments with various machine learning models and find that: (i) the display and prediction of facial affect vary from non-working to working settings; (ii) prediction capability can be boosted by using datasets captured in work-like context; and (iii) segment-level (spectral representation) information is crucial in improving the facial affect prediction.