Emotion Recognition Based on Various Physiological Signals - A Review

Londhe, Supriya; Borse, Rushikesh

doi:10.21917/ijct.2018.0265

Cited by 7 publications

(4 citation statements)

References 28 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biosensors [10] such as optical sensors, Electrochemical biosensors, and Oxygen sensors are available and can further be utilized in Gephi software for use of ECG for disease prediction. An emotion recognition system [20] is designed with IoT and machine learning techniques with temperature and heart rate parameters [20] to recognize human emotions. A wearable emotion recognition device was used in [9,11,21] auto capture the data from a heart rate [21] and other biosignals.…”

Section: Literature Reviewmentioning

confidence: 99%

Real Time Emotion Recognition with AD8232 ECG Sensor for Classwise Performance Evaluation of Machine Learning Methods

Patil

Pawar

Kulkarni

et al. 2023

IJE

View full text Add to dashboard Cite

Emotions are the accelerators of human intellect and innovation and creativity, so the ability to recognize emotions is in high demand. Real-time hardware has hurdles of Noise and hardware factors as compared to simulations. An electrocardiogram (ECG) sensor (AD8232), a temperature sensor (LM35), and a signal processing circuit is hardware of the proposed real-time emotion identification. The RR intervals are calculated from the ECG data. Emotions prediction using machine learning makes use of RR intervals and body temperature as features. One of the four emotions (namely 1. Happy 2. Stressed 3. Neutral 4. Sad.) is visualized at the serial port of the processor by using WESAD benchmark dataset and the HRV, serial, and pickle libraries.This article's innovation factors are (1) Use of ECG for emotion detection rather than disease detection with Emotion induction method, RR interval capturing and design of RR interval GUI for real time capture of temperature and ECG (2) Display of current emotion on Arduino serial port. (3) Measurement of Class performance using F1 score, macro average, and weighted average instead of general term accuracy. (4) Use of the probability based Navies Bayes as compared to traditional KNN, SVM, Random Forest nethods (5) Class wise performance for example Navies Bayes' specificity or accuracy is lower than SVM's (0.96), but its recall or sensitivity is higher (0.97) vs. (0.94) for stress.In this article, we presented performance parameters in terms of interactive computations, tabular form and graphical display.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Real Time Emotion Recognition with AD8232 ECG Sensor for Classwise Performance Evaluation of Machine Learning Methods

Patil

Pawar

Kulkarni

et al. 2023

IJE

View full text Add to dashboard Cite

show abstract

“…The author appraisedfairlylimited readings which are grounded on examining electroencephalogram (EEG) signs as a biotic indicator in sentiment fluctuations [8].SupriyaLondhe and RushikeshBorse et al deliberated the investigation completed on emotion recognition by means of skin conductance, skin hotness, electrocardiogram, electromyography, and electroencephalogram signs. The author provided an vision on the current state of exploration and investigates challenged in sentiment acknowledgment by biological signs, so that investigation can be innovative for improved recognition [9].BhavyaV andThajudinAhamedproposed an technique to recognize emotion in children using ECG signals. ECG signals are analyzedtogether in phase and regularity domain.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Approach For Emotions Detection

Anupama,

Save,

Biswas

et al. 2023

E3S Web Conf.

View full text Add to dashboard Cite

The design and implementation of intelligent space, global, and healthcare arrangements have developed very essential since they automatically monitor both the surroundings and the individuals in it to offer support and facilities. Furthermost offer additional provision for the physical aspects of people at the cost of emotional aspects. For that reason, providing psychological and expressive healthcare is also imperative to advance excellence of life. Sentiment recognition is important and advantageous in social computer and social machine communication presentations as emotions specify mental state and requirements. Physiological signals-based emotion identification is a significant area of study with a bright potential for applications. Multiple HRV catalogs, comprising time-domain (MEAN, SDNN, and RMSSD) and frequency-domain (LFn, HFn, and LF/HF) indices were derived using RR intermission (RRI) time sequences that were recovered from ECGs. The most effective combination of ECG mood characteristics is chosen for classification using the Tabu Exploration Procedure(Happy, Sad and Fear). In order to categorize the test data, a deep convolutional neural system is finally created.

show abstract

“…However, internal physiological signals are almost impossible to control. Therefore, they can be used as signs of emotional response [ 13 , 17 , 18 , 24 , 25 , 34 – 40 , 48 – 50 ]. The main physiological signals include EDA, electrocardiograms (ECG), electromyograms (EMG), EEG, and HRV.…”

Section: Related Researchmentioning

confidence: 99%

“…Generally, the number of target variables was inversely proportional to the accuracy. Although the number of target variables input to the classifier ranged between two and five in related studies, but the accuracy was not significantly different [ 13 , 25 , 29 , 30 , 47 , 48 ]. Meanwhile, there is no comparability between research results [ 28 , 30 , 53 , 60 , 62 ], and the accuracy of emotion recognition was considerably different.…”

Section: Related Researchmentioning

confidence: 99%

Affective computing of multi-type urban public spaces to analyze emotional quality using ensemble learning-based classification of multi-sensor data

Yuizono²,

Li³

2022

PLoS ONE

View full text Add to dashboard Cite

The quality of urban public spaces affects the emotional response of users; therefore, the emotional data of users can be used as indices to evaluate the quality of a space. Emotional response can be evaluated to effectively measure public space quality through affective computing and obtain evidence-based support for urban space renewal. We proposed a feasible evaluation method for multi-type urban public spaces based on multiple physiological signals and ensemble learning. We built binary, ternary, and quinary classification models based on participants’ physiological signals and self-reported emotional responses through experiments in eight public spaces of five types. Furthermore, we verified the effectiveness of the model by inputting data collected from two other public spaces. Three observations were made based on the results. First, the highest accuracies of the binary and ternary classification models were 92.59% and 91.07%, respectively. After external validation, the highest accuracies were 80.90% and 65.30%, respectively, which satisfied the preliminary requirements for evaluating the quality of actual urban spaces. However, the quinary classification model could not satisfy the preliminary requirements. Second, the average accuracy of ensemble learning was 7.59% higher than that of single classifiers. Third, reducing the number of physiological signal features and applying the synthetic minority oversampling technique to solve unbalanced data improved the evaluation ability.

show abstract

Emotion Recognition Based on Various Physiological Signals - A Review

Cited by 7 publications

References 28 publications

Real Time Emotion Recognition with AD8232 ECG Sensor for Classwise Performance Evaluation of Machine Learning Methods

Real Time Emotion Recognition with AD8232 ECG Sensor for Classwise Performance Evaluation of Machine Learning Methods

Deep Learning Approach For Emotions Detection

Affective computing of multi-type urban public spaces to analyze emotional quality using ensemble learning-based classification of multi-sensor data

Contact Info

Product

Resources

About