Emotion Recognition through Physiological Signals for Human-Machine Communication
Open accessAbstract
The ability to recognize emotion is one of the hallmarks of emotion intelligence.This paper proposed to recognize emotion using physiological signals obtained from multiple subjects.IAPS (International Affective Picture System) images were used to elicit target emotions.Five physiological signals: Blood volume pulse (BVP), Electromyography (EMG), Skin Conductance (SC), Skin Temperature (SKT) and Respiration (RESP) were selected to extract 30 features for recognition.Two pattern classification methods, Fisher discriminant and SVM method are used and compared for emotional state classification.The experimental results indicate that the proposed method provides very stable and successful emotional classification performance as 92% over six emotional states. 20www.intechopen.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prior research has linked several physiological signals-including heart rate, heart rate variability, electro-dermal activity, eye tracking, skin temperature, and EEG-to mental effort, cognitive load, task difficulty, emotions, and stress.
“Various studies have shown that biometric data such as heart rate (HR), heart rate variability (HRV), electro-dermal activity (EDA), eye tracking, skin temperature or electroencephalography (EEG) can be used to assess mental effort and cognitive load [85,66,28,13], task difficulty [79,22], emotions [48,27,62], or stress [29,70,84].”
From Sensing Interruptibility in the Office: A Field Study on the Use of Biometric and Computer Interaction Sensors (2018) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Pattern classification and scene analysis
Grenander, U., Duda, R., & Hart, P. (1974) · A Wiley-Interscience publication · doi:10.2307/1573081 · Cited by 17,399 · see citing works
Picard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382 · see citing works
An overview of statistical learning theory
Vapnik, V. N. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.788640 · Cited by 6,305 · cited 3× · see citing works
“An example of five physiological signals (BVP, EMG, SC, SKT and Resp) acquired during the induction of the six emotions (left: Subjectl, right: Subject 2) www.intechopen.com theory, pioneered by Vapnik [21], instead of heuristics or analogies with natural learning systems.”
BackgroundInfluentialThe emotion probe. Studies of motivation and attention.
Lang, P. J. (1995) · American Psychologist · doi:10.1037/0003-066x.50.5.372 · Cited by 2,846 · cited 1× · see citing works
“various positions on a two-dimensional plane spanned by these two axes to construct a 2D emotion model [7].”
Toward machine emotional intelligence: analysis of affective physiological state
Picard, R. W., Vyzas, E., & Healey, J. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.954607 · Cited by 2,334 · cited 6× · see citing works
“A significant series of work has been conducted by Picard and colleagues at MIT Lab.”
BackgroundMethodInfluentialLagopoulos, J. (2007) · Acta Neuropsychiatrica · doi:10.1111/j.1601-5215.2007.00247.x · Cited by 1,424 · cited 1×
“It is also called galvanic skin response [18].”
BackgroundMorris, J. D. (1995) · Journal of Advertising Research · doi:10.1080/00218499.1995.12466497 · Cited by 608 · see citing works
Wagner, J., Kim, J., & André, E. (2005) · IEEE International Conference on Multimedia and Expo · doi:10.1109/icme.2005.1521579 · Cited by 560 · see citing works
Using Noninvasive Wearable Computers to Recognize Human Emotions from Physiological Signals
Lisetti, C., & Nasoz, F. (2004) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/s1110865704406192 · Cited by 432 · cited 1× · see citing works
“Various stimuli can be used such as images, sounds, videos [14] or video games.”
BackgroundEmotion recognition in human–computer interaction
Fragopanagos, N., & Taylor, J. G. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.03.006 · Cited by 414 · cited 1× · see citing works
“The experimental results indicate that the proposed method provides very stable and successful emotional classification performance as 92% over six emotional states.”
MethodEmotion recognition from physiological signals using wireless sensors for presence technologies
Nasoz, F., Alvarez, K., Lisetti, C. L., & Finkelstein, N. (2004) · Cognition, Technology & Work · doi:10.1007/s10111-003-0143-x · Cited by 390 · see citing works
AIE volume 11 issue 2 Cover and Back matter
Reeves, B., Nass, C., William, J., Clancey, D., C., Lee, Troelstra, A., H., et al. (1997) · Artificial intelligence for engineering design, analysis and manufacturing · doi:10.1017/s0890060400001876 · Cited by 304 · cited 3×
“experiments of Reeves and Nass [1], they show that humans impose their interpersonal behavioral patterns onto their computers.”
BackgroundInfluentialParsing affective space: Perspectives from neuropsychology and psychophysiology.
Davidson, R. (1993) · Neuropsychology · doi:10.1037/0894-4105.7.4.464 · Cited by 241 · cited 1× · see citing works
“Recently, the low consistency of physiological configurations supported the hypothesis that the autonomic nervous system ANS activation during emotions indicates the demands of a specific action tendency and action disposition, instead of reflecting emotions [8].”
BackgroundDigital processing of affective signals
Healey, J., & Picard, R. W. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1998.679699 · Cited by 122 · see citing works
Ethological modeling and architecture for an entertainment robot
Arkin, R., Fujita, M., Takagi, T., & Hasegawa, R. (2001) · Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164) · doi:10.1109/robot.2001.932592 · Cited by 93 · cited 1× · see citing works
“For example, it is accepted that emotional ability is an essential factor for the next-generation personal robot, such as the Sony AIBO [4].”
BackgroundHirsh, H., Coen, M. H., Mozer, M., Hasha, R., & Flanagan, J. (1999) · IEEE Intelligent Systems · doi:10.1109/5254.757622 · Cited by 56 · see citing works
Signal processing for recognition of human frustration
Fernandez, R., & Picard, R. W. (1998) · Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181) · doi:10.1109/icassp.1998.679705 · Cited by 50 · see citing works
Herbelin, B., Benzaki, P., Riquier, F., Renault, O., Grillon, H., & Thalmann, D. (2005) · International Journal on Disability and Human Development · doi:10.1515/ijdhd.2005.4.4.269 · Cited by 43 · cited 1× · see citing works
“This strategy has been widely used for emotion assessment from facial expressions and to some extent from physiological signals [13].”
BackgroundEmotional interaction model for a service robot
Kim, H.-R., Lee, K.-W., & Kwon, D. (2005) · ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005. · doi:10.1109/roman.2005.1513857 · Cited by 26 · cited 1×
“Given the importance and potential of the emotions, affective interfaces using the emotion of the human user are gradually more desirable in intelligent user interfaces such as human-robot interactions [2].”
BackgroundKerr, D. (2006) · doi:10.1300/j161v01n04_04 · Cited by 5 · cited 1×
“It can also play a significant role in 'intelligent room' [5] and 'affective computer tutor' [6].”
Background
Flagged first, then by citations
5 of the 25 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- B. Reeves and C. Nass, The Media Equation. Cambridge University Press, 1996.
- R. W. Levenson, Emotion and the autonomic nervous system: A prospectus for research on autonomic specificity, In H. L. Wagner, editor, Social Psychophysiology and Emotion: Theory and Clinical Applications, 1988, pp. 17-42.
- F. Nasoz, K. Alvarez, C. Lisetti,& N. Finkelstein, Emotion recognition from physiological signals for presence technologies, International Journal of Cognition, Technology, and Work -Special Issue on Presence, Vol. 6(1),2003.
Cited by
Sorted by citations
Emotion Recognition from Physiological Signal Analysis: A Review
Egger, M., Ley, M., & Hanke, S. (2019) · Electronic Notes in Theoretical Computer Science · doi:10.1016/j.entcs.2019.04.009 · Cited by 563 · see citing works
EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities
Suhaimi, N. S., Mountstephens, J., & Teo, J. (2020) · Computational Intelligence and Neuroscience · doi:10.1155/2020/8875426 · Cited by 361 · see citing works
“According to previous researchers, over the last decade of research on emotion recognition using physiological signals, many have deployed numerous methods of classifiers to classify the different types of emotional states [132].”
BackgroundPhysiological signals based human emotion Recognition: a review
Jerritta, S., Murugappan, M., Nagarajan, R., & Khairunizam, W. (2011) · IEEE International Colloquium on Signal Processing & Its Applications (CSPA) · doi:10.1109/cspa.2011.5759912 · Cited by 349 · see citing works
“In case of user dependent system, a maximum of 95 % accuracy has been obtained for recognizing four emotions (Joy, Anger, Sad, Pleasure) and 92% accuracy for recognizing six emotions (Amusement, Contentment, Disgust, Fear, Sad, Neutral) has been obtained[10] [41].”
BackgroundMethodUsing psycho-physiological measures to assess task difficulty in software development
Fritz, T., Begel, A., Müller, S. C., Yigit-Elliott, S., & Züger, M. (2014) · Proceedings of the 36th International Conference on Software Engineering · doi:10.1145/2568225.2568266 · Cited by 262 · see citing works
“Each subject performed eight code comprehension tasks as we recorded various psycho-physiological and subjective measurements1.”
MethodBousefsaf, F., Maaoui, C., & Pruski, A. (2013) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2013.05.010 · Cited by 161 · see citing works
Self-citationWearable Emotion Recognition System based on GSR and PPG Signals
Udovičić, G., Đerek, J., Russo, M., & Sikora, M. (2017) · International Workshop on Multimedia for Personal Health and Health Care (MMHealth) · doi:10.1145/3132635.3132641 · Cited by 129 · see citing works
Selvaraj, J., Murugappan, M., Khairunizam, W., & Yaacob, S. (2013) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-12-44 · Cited by 130 · see citing works
“Visual based elicitation using images, audio based elicitation using music and audio-visual elicitation using short film video clips are commonly used [2,15,28,29].”
BackgroundMethodInfluentialAn Ensemble Learning Approach for Electrocardiogram Sensor Based Human Emotion Recognition
Dissanayake, T., Rajapaksha, Y., Ragel, R., & Nawinne, I. (2019) · Sensors · doi:10.3390/s19204495 · Cited by 93 · see citing works
“(2010) [51] amusement, contentment, disgust, fear, sadness, neutral I 3 10 46.”
Machine learning for human emotion recognition: a comprehensive review
Younis, E. M. G., Mohsen, S., Houssein, E. H., & Ibrahim, O. A. S. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09426-2 · Cited by 94 · see citing works
Züger, M., Müller, S. C., Meyer, A. N., & Fritz, T. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174165 · Cited by 66 · see citing works
“Various studies have shown that biometric data such as heart rate (HR), heart rate variability (HRV), electro-dermal activity (EDA), eye tracking, skin temperature or electroencephalography (EEG) can be used to assess mental effort and cognitive load [85, 66, 28, 13], task difficulty [79, 22], emotions [48, 27, 62], o…”
BackgroundJerritta, S., Murugappan, M., Khairunizam, W., & Yaacob, S. (2013) · Journal of the Chinese Institute of Engineers · doi:10.1080/02533839.2013.799946 · Cited by 76 · see citing works
“The six emotions were elicited using IAPS for only fi ve minutes in contrast to this study where 15 subjects took part in ten trials, which lasted for around 40 min (Maaoui and Pruski 2010).”
BackgroundMethodM., M., & Mutawa, A. (2021) · PLoS ONE · doi:10.1371/journal.pone.0247131 · Cited by 61 · see citing works
Paschalidis, E., Choudhury, C., & Hess, S. (2018) · Transportation Research Part F: Traffic Psychology and Behaviour · doi:10.1016/j.trf.2018.09.019 · Cited by 61 · see citing works
“observation, μ is the heart rate mean value across the whole urban task and σ is its standard deviation (Picard et al., 2001; Healey and Picard, 2005; Maaoui and Pruski, 2010).”
BackgroundEmotion Recognition Involving Physiological and Speech Signals: A Comprehensive Review
Ali, M., Mosa, A. H., Machot, F. A., & Kyamakya, K. (2017) · Studies in systems, decision and control · doi:10.1007/978-3-319-58996-1_13 · Cited by 59 · see citing works
Emotions Detection on an Ambient Intelligent System Using Wearable Devices
Costa, Â., Rincón, J., Carrascosa, C., Julián, V., & Novais, P. (2019) · Workshop on Affective Computing and Context Awareness in Ambient Intelligence · doi:10.1016/j.future.2018.03.038 · Cited by 56 · see citing works
“The modulation of a user profile that emulates one’s decision process must have the ability of representing emotional states [4, 5, 6].”
BackgroundToward User-Independent Emotion Recognition Using Physiological Signals
Albraikan, A. A., Tobón, D. P., & Saddik, A. E. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2867221 · Cited by 55 · see citing works
“Other works have reported an accuracy of 70% for classifying three emotions (calm, positively excited, and negatively excited) [18], 75% for classifying four emotions (neutral, sadness, fear and pleasure) [25], 45% for classifying six emotions (amusement, contentment, disgust, fear, neutral, and sadness) [21], and 50%…”
BackgroundA Globally Generalized Emotion Recognition System Involving Different Physiological Signals
Ali, M., Machot, F. A., Mosa, A. H., Jdeed, M., Machot, E. A., & Kyamakya, K. (2018) · Sensors · doi:10.3390/s18061905 · Cited by 49 · see citing works
“For the purpose of building reference databases to be used for both training and validation testings, different works used images [18,19], music [11], cognitive tasks [20], complicated mathematical problems [21], movie clips [22], questionnaires [9] and other methods to elicit emotions.”
BackgroundMethodJerritta, S., Murugappan, M., Khairunizam, W., & Yaacob, S. (2013) · Expert Systems · doi:10.1111/exsy.12014 · Cited by 50 · see citing works
Physiological Detection of Affective States in Children with Autism Spectrum Disorder
Sarabadani, S., Schudlo, L. C., Samadani, A., & Kushki, A. (2018) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2018.2820049 · Cited by 65 · see citing works
“The International Affective Picture System (IAPS) is the gold standard method of eliciting various levels of arousal and valence [23], [24], [40], [41], [30].”
MethodEmotion recognition based on physiological signals using valence-arousal model
Basu, S., Jana, N., Bag, A., Mahadevappa, M., Mukherjee, J., Kumar, S., & Guha, R. (2015) · International Conference on Intelligent Information Processing · doi:10.1109/iciip.2015.7414739 · Cited by 42 · see citing works
“The stimuli used most are images [7][8][9], sound [10][1], music [8], movie clip [11][12][13], multi-modal outputs [14], etc.”
BackgroundRelationship between driving styles and biological behavior of drivers in negative emotional state
Habibifar, N., & Salmanzadeh, H. (2022) · Transportation Research Part F: Traffic Psychology and Behaviour · doi:10.1016/j.trf.2022.01.010 · Cited by 36
Al-Qazzaz, N., Sabir, M. K., Ali, S. H. B. M., Ahmad, S. A., & Grammer, K. (2019) · Italian National Conference on Sensors · doi:10.3390/s20010059 · Cited by 32 · see citing works
“In contrast with alternative stimuli methods, audio-visual production of emotional states has been found to be superior and more pervasively adopted [13,15,16].”
BackgroundiAware: A Real-Time Emotional Biofeedback System Based on Physiological Signals
Albraikan, A., Hafidh, B., & Saddik, A. E. (2018) · IEEE Access · doi:10.1109/access.2018.2885279 · Cited by 31 · see citing works
“The reported accuracy was 70% for classifying three emotions (calm, positively excited, and negatively excited) [11], 75% for classifying four emotions (neutral, sadness, fear and pleasure) [12], 45% for classifying six emotions (amusement, contentment, disgust, fear, neutral, and sadness) [13], and 50% for classifyin…”
BackgroundWearable Technology for Detecting Significant Moments in Individuals with Dementia
Kwan, C. L., Mahdid, Y., Motta‐Ochoa, R., Lee, K., Park, M., & Blain‐Moraes, S. (2019) · BioMed Research International · doi:10.1155/2019/6515813 · Cited by 32 · see citing works
“,ese technologies use advanced features calculated fromANS signals to train featurebased machine learning algorithms to detect discrete states of emotion [39, 40] or deploy an end-to-end deep learning approach for the dimensional recognition of emotions [41].”
Ali, M., Machot, F. A., Mosa, A., & Kyamakya, K. (2016) · Lecture notes in mobility · doi:10.1007/978-3-319-44766-7_11 · Cited by 30 · see citing works
FedCMD: A Federated Cross-modal Knowledge Distillation for Drivers’ Emotion Recognition
Bano, S., Tonellotto, N., Cassará, P., & Gotta, A. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3650040 · Cited by 24 · see citing works
“The authors of [32] have developed a model in which they extract several statistical features of different physiological signals such as BVP (blood pressure) , EMG, EDA, RSP (respiration) , and ST and feed them into Support Vector Machine (SVM) and Fisher’s LDA (linear discriminant analysis)…”
BackgroundK., T., Aziz, N. A. A., Raja, J., Hossen, J., & H., J. M. Z. (2022) · Emerging Science Journal · doi:10.28991/esj-2022-06-05-017 · Cited by 27 · see citing works
“[111] Blood Volume Pulse, EMG, SKT 10 (International Affective Picture System) Fear, Disgust Contentment, Neutral, Sadness, Amuse Images Statistical features (Mean, Standard deviation, etc.”
MethodGoshvarpour, A., Abbasi, A., Goshvarpour, A., & Daneshvar, S. (2017) · Signal, Image and Video Processing · doi:10.1007/s11760-017-1092-9 · Cited by 27
“More recently, time-domain features in combination with Fisher and SVM classifiers were examined [16].”
MethodObjective model assessment for short-term anxiety recognition from blood volume pulse signal
Handouzi, W., Maaoui, C., Pruski, A., & Moussaoui, A. (2014) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2014.07.008 · Cited by 26 · see citing works
Self-citationAffective recognition from EEG signals: an integrated data-mining approach
Mendoza-Palechor, F., Menezes, M., Sant'Anna, A., Ortíz-Barrios, M., Samara, A., & Galway, L. (2018) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-018-1065-z · Cited by 26 · see citing works
“These statistics have been also used in Picard et al. (2001), Maaoui and Pruski (2010), Lan et al. (2014), Menezes et al. (2017) and Nugent et al. (2016).”
MethodLima, R., Chirico, A., Varandas, R. S. P., Gamboa, H. F. S., Gaggioli, A., & Badia, S. B. I. (2024) · Virtual Reality · doi:10.1007/s10055-024-00989-y · Cited by 27 · see citing works
“Maaoui and Pruski (2010) used blood volume pulse (BVP), EMG, SKT, EDA and RESP sensors to classify amusement, contentment, disgust, fear, sad and Neutral.”
Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression
Lee, J.-E., & Yoo, S. (2020) · Italian National Conference on Sensors · doi:10.3390/s20020573 · Cited by 23
“Negative emotion causes stress and lowers attention and concentration [2].”
BackgroundDesign of Prototype-Based Emotion Recognizer Using Physiological Signals
Park, B. (2013) · ETRI Journal · doi:10.4218/etrij.13.0112.0751 · Cited by 20 · see citing works
“For an induced emotion, the physiological signals (SKT, PPG, EDA, and ECG [7], [21]) of the subject are measured to determine their baseline and emotional states.”
BackgroundXiao, X., Fang, C.-Y., Lin, H., Liu, L., Tian, Y.-F., & He, Q.-H. (2022) · Computational Urban Science · doi:10.1007/s43762-021-00030-x · Cited by 20 · see citing works
“( 2) In the past, many studies have used body sensors to recognize emotions and have achieved very high accuracies (Maaoui & Pruski, 2010).”
BackgroundImproving Driving Safety by Detecting Negative Emotions with Biological Signals: Which Is the Best?
Habibifar, N., & Salmanzadeh, H. (2021) · Transportation Research Record · doi:10.1177/03611981211041594 · Cited by 20 · see citing works
Physiological signal-based emotion recognition system
Hassani, S., Bafadel, I., Bekhatro, A., Blooshi, E. A., Ahmed, S. G., & Ahmad, M. A. (2017) · IEEE International Conference on Engineering Technologies and Applied Sciences (ICETAS) · doi:10.1109/icetas.2017.8277912 · Cited by 21 · see citing works
“In the area of computing, the sky is the limit for the application that can benefit from the proposed system: emotional gaming where the diverse stages of emotions are utilized to make the gaming software more sentimental and easy to use[2], human-robot interactions[8], intelligent room[8], emotional computer tutor [8…”
BackgroundEmotion recognition from electrocardiogram signals using Hilbert Huang Transform
Jerritta, S., Murugappan, M., Khairunizam, W., & Yaacob, S. (2012) · IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (CSUDET) · doi:10.1109/student.2012.6408370 · Cited by 22 · see citing works
“The sensitivity of the systems developed varies vastly from 37% to 100% depending on the number of subjects, number of emotions and type of features representing the emotional bio-data[8-10].”
BackgroundAlqahtani, F., & Ramzan, N. (2019) · Sensors · doi:10.3390/s19030460 · Cited by 17 · see citing works
“Based on these finalized features, emotional states are classified [103].”
BackgroundSmart watch based body-temperature authentication
Enamamu, T., Clarke, N., Haskell-Dowland, P., & Li, F. (2017) · 2017 International Conference on Computing Networking and Informatics (ICCNI) · doi:10.1109/iccni.2017.8123790 · Cited by 19
“The use of GSR is more prevalent compare to skin temperature for human emotional recognition [28, 29, 30, 31, 32].”
BackgroundMethodUsing Non-invasive Wearables for Detecting Emotions with Intelligent Agents
Rincón, J., Costa, Â., Novais, P., Julián, V., & Carrascosa, C. (2016) · International Conference on European Transnational Education · doi:10.1007/978-3-319-47364-2_8 · Cited by 19
“In order to create a fluid emotional communication between human and machines, the machines need first to detect the emotion of the human with the final purpose of improving human-computer interactions [2].”
BackgroundOh, S., & Kim, D.-K. (2022) · Applied Sciences · doi:10.3390/app12031286 · Cited by 18 · see citing works
Emotion Detection from QRS Complex of ECG Signals Using Hurst Exponent for Different Age Groups
Jerritta, S., Murugappan, M., Khairunizam, W., & Yaacob, S. (2013) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2013.159 · Cited by 16 · see citing works
“The results are higher than the previous research works used for classifying the six emotional states [21, 25].”
ResultRecent Survey on Emotion Recognition Using Physiological Signals
Joy, E., Joseph, R. B., Lakshmi, M., Joseph, W., & Rajeswari, M. (2021) · 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs51430.2021.9441999 · Cited by 17
“When the classification of six emotions has been performed, then it reduces to 45 percentages [11].”
MethodImplementation of physiological signal based emotion recognition algorithm
Joesph, C., Rajeswari, A., Premalatha, B., & Balapriya, C. (2020) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde48307.2020.9153878 · Cited by 22 · see citing works
“The recognition accuracy was found to be 70% for an SVM with linear kernel [2] Choubelia Maaoui and Alain Pruski have implemented emotion recognition using physiological signals in [3].”
BackgroundMethodShort-term anxiety recognition from blood volume pulse signal
Handouzi, W., Maaoui, C., Pruski, A., & Moussaoui, A. (2014) · 2014 IEEE 11th International Multi-Conference on Systems, Signals & Devices (SSD14) · doi:10.1109/ssd.2014.6808747 · Cited by 16 · see citing works
“Yx = T�2 :2:f';1 2IX(t + 2) - X(t) I [4, 6]”
BackgroundInfluentialSelf-citationClassification of Heart Rate Signals during Meditation using Lyapunov Exponents and Entropy
Goshvarpour, A., & Goshvarpour, A. (2012) · International Journal of Intelligent Systems and Applications · doi:10.5815/ijisa.2012.02.04 · Cited by 15 · see citing works
Al-Qazzaz, N., Sabir, M. K., Al-timemy, A. H., & Grammer, K. (2022) · Medical and Biological Engineering and Computing · doi:10.1007/s11517-021-02452-5 · Cited by 14 · see citing works
“Audio-visual elicitation utilizing short-film video clips is usually used to elicit various conditions of emotions better compared to the other modalities [4, 6, 7].”
BackgroundAffective State during Physiotherapy and Its Analysis Using Machine Learning Methods
Romaniszyn‐Kania, P., Pollak, A. M., Bugdol, M. D., Bugdol, M. N., Kania, D., Mańka, A., Danch–Wierzchowska, M., & Mitas, A. W. (2021) · Sensors · doi:10.3390/s21144853 · Cited by 18 · see citing works
“A multimodal approach was using similar bio-signals like in the presented article (BVP, EDA, EMG, temperature, and respiration) to develop a classifier to recognize negative emotions [43].”
MethodParticipatory design of biomusic with users on the autism spectrum
Grond, F., Cascio, M. A., Motta‐Ochoa, R., Tembeck, T., Veen, D. T., & Blain‐Moraes, S. (2019) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2019.8925484 · Cited by 14 · see citing works
“The feasibility of classifying emotions based on patterns of physiological signals has long been established [7] [8] [9] [10] [11] [12] [13] [14] [15].”
BackgroundEEG Based Aptitude Detection System for Stress Regulation in Health Care Workers
Khan, T., Javed, H., Amin, M., Usman, O., Hussain, S. I., Mehmoood, A., & Maple, C. (2021) · Scientific Programming · doi:10.1155/2021/4620487 · Cited by 12
A Review of Intelligent Systems for Driving Risk Assessment
Mase, J. M., Chapman, P., & Figueredo, G. P. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3318113 · Cited by 10 · see citing works
Modeling and Analysis of Human Comfort in Human–Robot Collaboration
Yan, Y., Su, H.-T., & Jia, Y.-Y. (2023) · Biomimetics · doi:10.3390/biomimetics8060464 · Cited by 11
MsWH: A Multi-Sensory Hardware Platform for Capturing and Analyzing Physiological Emotional Signals
Asiain, D., de León, J. P., & Beltrán, J. R. (2022) · Italian National Conference on Sensors · doi:10.3390/s22155775 · Cited by 11 · see citing works
“, to increase the autonomy of people with disabilities) [47,48], rehabilitation processes [49], stress detection [34,50,51], monitoring of daily activity [52,53] and emotion detection [32,38,54–57].”
BackgroundComplexity and Entropy Analysis to Improve Gender Identification from Emotional-Based EEGs
Al-Qazzaz, N., Sabir, M. K., Ali, S. H. B. M., Ahmad, S. A., & Grammer, K. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/8537000 · Cited by 11 · see citing works
“Audiovisual elicitations utilizing short film video clips are usually used to elicit various conditions of emotion better compared to the other modalities [4, 6–9].”
BackgroundMethodA feedforward neural network for drone accident prediction from physiological signals
Sakib, M. N., Chaspari, T., & Behzadan, A. H. (2021) · Smart and Sustainable Built Environment · doi:10.1108/sasbe-12-2020-0181 · Cited by 18 · see citing works
Emotion Recognition from Sensory and Bio-Signals: A Survey
Vora, K., Shah, S., Harsoda, H., Sheth, J., Agarwal, S., Thakkar, A., & Mankad, S. H. (2018) · Proceedings of the 2nd International Conference on Data Engineering and Communication Technology · doi:10.1007/978-981-13-1610-4_35 · Cited by 11 · see citing works
Short-Term Anxiety Recognition Induced by Virtual Reality Exposure for Phobic People
Handouzi, W., Maaoui, C., Pruski, A., Moussaoui, A., & Bendiouis, Y. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.536 · Cited by 11 · see citing works
Self-citationDetecting emotions through non-invasive wearables
Rincón, J., Julián, V., Carrascosa, C., Costa, Â., & Novais, P. (2018) · Logic Journal of the IGPL · doi:10.1093/jigpal/jzy025 · Cited by 10
“In order to create a fluid emotional communication between human and machines, the machines need first to detect the emotion of the human with the final purpose of enhancing decison-making processes while improving human-computer interactions [ 2 ] .”
BackgroundOptimal Geometrical Set for Automated Marker Placement to Virtualized Real-Time Facial Emotions
Maruthapillai, V., & Murugappan, M. (2016) · PLoS ONE · doi:10.1371/journal.pone.0149003 · Cited by 10 · see citing works
Recognition of Facial Emotion through Face Analysis based on Quadratic Bezier Curves
Lee, Y.-H., Ahn, H., Cho, H.-J., & Lee, J.-H. (2015) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8i35/86092 · Cited by 10 · see citing works
Guo, C., Chen, V. Y., Qian, C., Ma, Y., Dinh, H., & Anasingaraju, S. (2016) · Interacción · doi:10.1007/978-3-319-40244-4_38 · Cited by 8 · see citing works
Bakhshi, A., Wong, A. S. W., & Chalup, S. (2020) · European Conference on Artificial Intelligence · doi:10.3233/faia200190 · Cited by 8 · see citing works
“Combination of different modalities such as physiological signals [20], audio [48, 26], video [12], hand gestures [24], and body movement [6] leads to many advancements in the field of affect recognition such as safe driving, security, and mobile health [22].”
BackgroundLi, S.-J., Li, W., Xing, Z., Yuan, W., Wei, X., Zhang, X.-W., & Hu, B. (2022) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2100489 · Cited by 7 · see citing works
Multi Modal Aptitude Detection System for Smart Office
Tehseen, M., Javed, H., Mehmood, A., Amin, M., Hussain, I., & Jan, B. (2019) · IEEE Access · doi:10.1109/access.2019.2893202 · Cited by 7 · see citing works
The Impact of Physical Activities on the Physiological Response to Emotions
Heinisch, J. S., Hübener, I., & David, K. (2018) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2018.8480086 · Cited by 9 · see citing works
“The response to affects and physical activities may vary with each user [7], [8].”
BackgroundMeasuring Human Comfort in Human–Robot Collaboration via Wearable Sensing
Yan, Y., Su, H.-T., & Jia, Y.-Y. (2024) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2024.3383296 · Cited by 6
“Maaoui ’ s work [18] used two methods, support vector machine (SVM) and Fisher discriminant, to recognize human emotions of amusement, contentment, disgust, fear, neutral, and sadness with multiple physiological signals, e.g., BVP, EDA, and skin temperature (SKT).”
MethodA Deep Learning Approach for Classifying Emotions from Physiological Data
AlZoubi, O., AlMakhadmeh, B., Tawalbeh, S. K., Yassein, M. B., & Hmeidi, I. (2020) · International Conference on Information and Communication Systems (ICICS) · doi:10.1109/icics49469.2020.239534 · Cited by 6 · see citing works
“Similarly, an experiment was conducted to detect six emotional states (Amusement, Contentment, Disgust, Fear, Neutrality, and Sad-ness) of subjects [28].”
MethodTowards Estimation of Emotions From Eye Pupillometry With Low-Cost Devices
Rafique, S., Kanwal, N., Karamat, I., Asghar, M., & Fleury, M. (2021) · IEEE Access · doi:10.1109/access.2020.3048311 · Cited by 6 · see citing works
A Multi-modal Approach for Emotion Recognition Through the Quadrants of Valence–Arousal Plane
Dutta, S., MISHRA, B. K., Mitra, A., & Chakraborty, A. (2023) · SN Computer Science · doi:10.1007/s42979-023-01925-8 · Cited by 5
“The stimuli that are mainly used for such experiments are movie clips [4, 5], sound [6], music [7], images [7–9], etc.”
BackgroundFrequency study of facial electromyography signals with respect to emotion recognition
Selvaraj, J., Murugappan, M., Khairunizam, W., & Yaacob, S. (2014) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2013-0118 · Cited by 7 · see citing works
“3 [22] Masseter 0–10 [28] Corrugator supercilli, zygomaticus major Frequency > 20 [21] Facial muscles 15–90 [16] Facial muscles 0–100 [11] Not specified 20–125 [24] Corrugator supercilli, zygomaticus major 10–256 [5] Corrugator supercilli, zygomaticus major 20–256 [27] Corrugator supercilli, zygomaticus major 20–400 […”
BackgroundEvaluating Just-In-Time Vibrotactile Feedback for Communication Anxiety
Raether, J., Nirjhar, E., & Chaspari, T. (2022) · International Conference on Multimodal Interaction · doi:10.1145/3536221.3556590 · Cited by 4 · see citing works
“Increased HR is an indicator of increased state anxiety, while higher HRV values indicate one’s increased ability to recover from the stressor event [85].”
BackgroundInfluentialA Model of Socially Connected Things for Emotion Detection
Dutta, S., Dash, S., & Mitra, A. (2020) · International Conference on Computer Science, Engineering and Applications (ICCSEA) · doi:10.1109/iccsea49143.2020.9132887 · Cited by 5 · see citing works
A Survey on Predicting Resident Intentions Using Contextual Modalities in Smart Home
Hegde, R. M. D., & Kenchannavar, H. H. (2019) · International Journal of Advanced Pervasive and Ubiquitous Computing · doi:10.4018/ijapuc.2019100104 · Cited by 4 · see citing works
Wemotion: A System to Detect Emotion Using Wristbands and Smartphones
Le-Quang, B., Dao, M.-S., & Nazmudeen, M. (2018) · Communications in Computer and Information Science · doi:10.1007/978-981-13-5758-9_8 · Cited by 4 · see citing works
On-body Sensing and Signal Analysis for User Experience Recognition in Human-Machine Interaction
Haratian, R., & Timotijevic, T. (2018) · International Conference on Frontiers of Signal Processing (ICFSP) · doi:10.1109/icfsp.2018.8552058 · Cited by 3 · see citing works
“An emotion recognition system based on physiological signals is introduced in [13].”
BackgroundEmotions Recognition and Signal Classification
Fathalla, R. S., & Alshehri, W. S. (2020) · International Journal of Synthetic Emotions · doi:10.4018/ijse.2020010101 · Cited by 8 · see citing works
Design and Evaluation of a Human-Comfort-Aware Robot Behavior Controller
Yan, Y., & Jia, Y. (2025) · American Control Conference · doi:10.23919/acc63710.2025.11107903 · Cited by 3
“Similarly, Maaoui [16] applied support vector machines (SVM) and Fisher discriminant analysis to recognize human emotions—including amusement, content-ment, disgust, fear, neutrality, and sadness—based on physiological signals such as BVP, EDA, and skin temperature (SKT).”
Initializing the weights of a multilayer perceptron for activity and emotion recognition
Mohíno-Herranz, I., Gil‐Pita, R., García-Gómez, J., Alonso-Diaz, S., Rosa-Zurera, M., & Seoane, F. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124305 · Cited by 2 · see citing works
inHarmony: a Digital Twin for Emotional Well-being
Albraikan, A. (2019) · doi:10.20381/ruor-23480 · Cited by 3
“Other works have reported an accuracy of 70% for classifying three emotions (calm, positively excited, and negatively excited) [87], 75% for classifying four emotions (neutral, sadness, fear and pleasure) [85], 45% for classifying six emotions (amusement, contentment, disgust, fear, neutral, and sadness) [88], and 50%…”
BackgroundAn efficient multi modal emotion recognition system: ISAMC
Arora, S., Chandel, S., & Chandra, S. (2014) · Impetus · doi:10.1109/impetus.2014.6775870 · Cited by 3
Training Pattern Classifiers with Physiological Cepstral Features to Recognise Human Emotion
Abayomi, A., Olugbara, O., Adetiba, E., & Heukelman, D. (2015) · World Congress on Nature and Biologically Inspired Computing · doi:10.1007/978-3-319-27400-3_24 · Cited by 3 · see citing works
Depression diagnosis through emotional induction and physiological signals: A systematic review
Liu, J., He, X., Sun, X. S., & Jo, D. (2025) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2025.106243 · Cited by 2 · see citing works
Emotion Classification in Voice Data Using Different Machine Learning Methods
Shanthi, J. M., Rao, P. S., Sharma, H., Thomas, G. A. S., & Gupta, A. A. (2024) · International Conference on Advanced Infocomm Technology · doi:10.1109/icait61638.2024.10690711 · Cited by 1 · see citing works
“Stress and a decrease in concentration are produced by negative emotions that might arise for a number of causes [7].”
BackgroundAbayomi, A., Olugbara, O., & Heukelman, D. (2021) · International Journal of Integrated Engineering · doi:10.30880/ijie.2021.13.06.001 · Cited by 2 · see citing works
“Human emotion is related to physiological signals and are influenced by physiological changes, external events and relationship with others, therefore representing a complex and dynamic state of human mind [1].”
BackgroundMethodInfluentialEmotion Recognition Using Chaotic Features And Symbolic Dynamic via Neural Networks
Kanani, M., Manthouri, M., & Abdossalehi, M. (2019) · International Conference on Knowledge-Based Engineering and Innovation · doi:10.1109/kbei.2019.8735094 · Cited by 2 · see citing works
“These methods are particularly useful in situations where the dimensions of the data and the composition of their structure are not well understood [8].”
MethodEffects of Facial Expressions and Gestures on the Trustworthiness of a Person
Lutfi, S. L., Lahasan, B. M., Luna-Jiménez, C., Bamasood, Z. A., & Akhtar, Z. (2023) · IEEE Access · doi:10.1109/access.2023.3334270 · Cited by 3 · see citing works
“The ability to ‘‘sense’’ the intentions of the person with whom we interact is based not only on the content of the message, but also on how it is expressed.”
An Introduction to Silent Paralinguistics
Ren, Z., Pistrosch, S., Coşkun, B., Scheck, K., Batliner, A., Schuller, B. W., & Schultz, T. (2025) · arXiv.org · doi:10.48550/arxiv.2508.18127 · Cited by 1
“EMG signals, in combination with other signals such as Electrocardiogram (ECG), electrodermal activity, and respiratory signals, have been used to recognize discrete emotional states [259], [260].”
Vittorio Benussi’s “Emotional Functional Autonomy”: Resumption and Re-Evaluation
Antonelli, M., Cattaruzza, S., & Strano, F. (2020) · International Journal of Clinical and Experimental Hypnosis · doi:10.1080/00207144.2020.1757386 · Cited by 1 · see citing works
“The decision to use this measure, which was not taken directly into account by Benussi, was due to the fact that, unlike breathing, which has a voluntary as well as an autonomic component, skin conductance cannot be consciously controlled by the participant (Maaoui & Pruski, 2010).”
MethodMultimedia emotion prediction using movie script and spectrogram
Kim, J.-S. (2020) · Multimedia tools and applications · doi:10.1007/s11042-020-08777-x · Cited by 1
“Emotions are difficult to judge, because there are differences between individuals, but recognizing emotions is a very important issue [12, 19].”
BackgroundAn Emotion Recognition Based on Physiological Signals
Kumar, A., Garg, N., & Kaur, G. (2019) · International Journal of Innovative Technology and Exploring Engineering · doi:10.35940/ijitee.i1054.0789s19 · Cited by 1
“These classifiers which encompasses Support vector machine (SVM) [3,14,15,31,32,46], K-Nearest Neighbour(KNN)[8,9,14,18, 49,50], Linear Discrminant Analysis(LDA)[8,11],Regression tree[3,9], Naiive Bayes[13], Fisher Linear Dicriminant [31], Artificial Neural Network(ANN)[2], RBF Neural…”
BackgroundMethodInfluentialLee, J.-E., & Yoo, S. (2013) · doi:10.5762/kais.2013.14.8.3925 · Cited by 1
Deep Learning based Emotion Classification using Multi Modal Bio-signals
Lee, J.-E., & Yoo, S. (2020) · doi:10.9717/kmms.2020.23.2.146 · Cited by 1
Multimodal Emotion Recognition
Abhang, P., Gawali, B., & Mehrotra, S. (2016) · doi:10.1016/b978-0-12-804490-2.00006-3 · Cited by 1 · see citing works
Bagirathan, A., Selvaraj, J., Gurusamy, A., & Das, H. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-01985-1
Demirel, B. U., & Holz, C. (2026) · doi:10.48550/arxiv.2608.18711
“While a person’s motion or gaze can be directly observed by vision models [58], physiological signals are subtle or invisible, yet they reveal latent human autonomic [67] and affective [49] processes.”
An efficient hybrid BiLSTM based deep learning model for negative emotion recognition
Paul, S., & Roy, A. (2026) · Microsystem Technologies · doi:10.1007/s00542-026-06025-0
Real-Time Emotion Recognition Using Deep Learning Algorithms
Mettiti, A. E., Oumsis, M., Chehri, A., & Saadane, R. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-fall57202.2022.10012772 · Cited by 1 · see citing works
Recognition of Distress Phase Situation in Human Emotion EEG Physiological Signals
Abayomi, A., Olugbara, O., & Heukelman, D. (2021) · doi:10.1201/9781003147817-2
- Authors
- Maaoui, C., & Pruski, A.
- Affiliations
- Université Paul Verlaine - Metz (FR)
- Venue
- Cutting Edge Robotics 2010
- Publisher
- InTech
- Published
- 2010-09-01
- OpenAlex
- W1593765659
- Cited by
- 109
- References
- 25
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 7 · 2023: 5 · 2022: 11 · 2021: 11 · 2020: 10 · 2019: 12 · 2018: 15 · 2017: 5 · 2016: 8 · 2015: 3 · 2014: 6 · 2013: 9 · 2012: 2
- FWCI
- 14.44
- Type
- book chapter
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-nc-sa
- Locations
- InTech eBooks (publishedVersion, cc-by-nc-sa)
- BiblioBoard Library Catalog (Open Research Library) (submittedVersion, cc-by-sa)
- IntechOpen (submittedVersion, cc-by-nc-sa)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Heart Rate Variability and Autonomic Control
- Keywords
- emotion recognition, physiological signals, human-machine communication, International Affective Picture System, blood volume pulse, electromyography, skin conductance, skin temperature, respiration, emotional state classification, linear discriminant analysis, support vector machine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
