A User Independent, Biosignal Based, Emotion Recognition Method

Rigas, George; Katsis, Christos D.; Ganiatsas, G.; Fotiadis, Dimitrios I.

doi:10.1007/978-3-540-73078-1_36

Cited by 55 publications

(36 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Picard et al [8] recorded physiological signals from a single subject (an actor) on multiple days. Conversely, other researchers [6], [32], [33] have attempted to build user-independent models that have the potential to generalize to new users. This is an important step for building practical affect sensitive applications, but yields significant challenges as physiological patterns vary from person to person and from situation to situation.…”

Section: User-independent Versus User-dependent Modelsmentioning

confidence: 99%

“…Some studies [6], [33] that attempted user-independent modeling used withinparticipants cross validation where instances from the same subject are in both the training and testing sets. A betweenparticipants validation method (i.e., where the same subject is either in the training or test set but not in both) is more appropriate.…”

Section: User-independent Versus User-dependent Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals

AlZoubi

D’Mello

Calvo

2012

IEEE Trans. Affective Comput.

112

View full text Add to dashboard Cite

Signals from peripheral physiology (e.g., ECG, EMG, and GSR) in conjunction with machine learning techniques can be used for the automatic detection of affective states. The affect detector can be user-independent, where it is expected to generalize to novel users, or user-dependent, where it is tailored to a specific user. Previous studies have reported some success in detecting affect from physiological signals, but much of the work has focused on induced affect or acted expressions instead of contextually constrained spontaneous expressions of affect. This study addresses these issues by developing and evaluating user-independent and user-dependent physiology-based detectors of nonbasic affective states (e.g., boredom, confusion, curiosity) that were trained and validated on naturalistic data collected during interactions between 27 students and AutoTutor, an intelligent tutoring system with conversational dialogues. There is also no consensus on which techniques (i.e., feature selection or classification methods) work best for this type of data. Therefore, this study also evaluates the efficacy of affect detection using a host of feature selection and classification techniques on three physiological signals (ECG, EMG, and GSR) and their combinations. Two feature selection methods and nine classifiers were applied to the problem of recognizing eight affective states (boredom, confusion, curiosity, delight, flow/engagement, surprise, and neutral). The results indicated that the user-independent modeling approach was not feasible; however, a mean kappa score of 0.25 was obtained for user-dependent models that discriminated among the most frequent emotions. The results also indicated that k-nearest neighbor and Linear Bayes Normal Classifier (LBNC) classifiers yielded the best affect detection rates. Single channel ECG, EMG, and GSR and three-channel multimodal models were generally more diagnostic than two-channel models.

show abstract

Section: User-independent Versus User-dependent Modelsmentioning

confidence: 99%

Section: User-independent Versus User-dependent Modelsmentioning

confidence: 99%

Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals

AlZoubi

D’Mello

Calvo

2012

IEEE Trans. Affective Comput.

112

View full text Add to dashboard Cite

show abstract

“…This database has emotional data collected from three males over 25 days using musical emotional induction (Cheng and Liu 2008;Cong and Chetouani 2009;Jonghwa and Ande 2008). Researchers have also used other modes of emotion elicitation like visual stimuli using the international affective picture system (IAPS) database (Rigas et al 2007), audio stimuli using the international affective digital sounds (Stevenson and James 2008), audio-visual movie clips, and emotional recall paradigms to elicit various emotions (André et al 2004;Chanel et al 2009;Fatma et al 2004;Lan and Jihua 2006;Rigas et al 2007;Roberts and Coan 2005). In (Arroyo-Palacious and Romano 2008), EMG signals are used to classify the positive (happy and surprise) and negative (sad, disgust, fear, and anger) emotions.…”

Section: Related Workmentioning

confidence: 99%

Emotion recognition from facial EMG signals using higher order statistics and principal component analysis

Jayaraman

Murugappan

Khairunizam

et al. 2013

Journal of the Chinese Institute of Engineers

View full text Add to dashboard Cite

Higher order statistics (HOS) is an efficient feature extraction method used in diverse applications such as bio signal processing, seismic data processing, image processing, sonar, and radar. In this work, we have investigated the application of HOS to derive a set of features from facial electromyography (fEMG) signals for classifying six emotional states (happy, sad, afraid, surprised, disgusted, and neutral). fEMG signals were collected from different types of subjects in a controlled environment using audio-visual (film clips/ video clips) stimuli. Acquired fEMG signals were preprocessed using moving average filter and a set of statistical features were extracted from fEMG signals. Extracted features were mapped into corresponding emotions using k-nearest neighbor classifier. Principal component analysis was utilized to analyze the efficacy of HOS features over conventional statistical features on retaining the emotional information retrieval from fEMG signals. The results of this work indicate an improved mean emotion recognition rate of 69.5% from this proposed methodology to recognize six emotional states.

show abstract

“…In [28] the authors propose a method for the recognition of happiness, disgust and fear using input signals such as facial electromyograms, electrocardiogram, the respiration and the electrodermal skin response. The authors of [29] propose yet another emotion recognition system that resorts to electrocardiogram, skin temperature variation and electrodermal activity as input signals.…”

Section: Related Workmentioning

confidence: 99%

An imaginary friend that connects with the user's emotions

Reis

Correia

2011

Proceedings of the 8th International Conference on Advances in Computer Entertainment Technology

View full text Add to dashboard Cite

In this paper we present a metaphor of an Imaginary Friend that walks along with the user. Due to a special bond with the user, the Imaginary Friend can see the emotions that the human companion is feeling glowing around her. As the user moves around she leaves behind emotion cookies that the Imaginary Friend will collect and treasure. In order to enable rich and playful interactions in the virtual-real continuum the implementation of the Imaginary Friend responds to motion, to the electrodermal activity and resorts to GPS coordinates. The Imaginary Friend was tested with several users to evaluate the connection between humans and this creature that lives in the border that separates imagination and reality.

show abstract

A User Independent, Biosignal Based, Emotion Recognition Method

Cited by 55 publications

References 6 publications

Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals

Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals

Emotion recognition from facial EMG signals using higher order statistics and principal component analysis

An imaginary friend that connects with the user's emotions

Contact Info

Product

Resources

About