Subject-Independent Odor Pleasantness Classification Using Brain and Peripheral Signals

Kroupi, Eleni; Vesin, Jean‐Marc; Ebrahimi, Touradj

doi:10.1109/taffc.2015.2496310

Cited by 60 publications

(29 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the affective information from image, video, and audio stimuli has been extensively studied, olfactory stimuli [26], written words [27][28][29][30][31][32], food stimuli (enriched by emotional stimuli) [33], and games have been used as elicitation methods in a number of studies as ways to assess human emotional state by investigating physiological signals [34][35][36][37].…”

Section: Design Innovation (Experimental) Papermentioning

confidence: 99%

“…Although the answer to what are the most emotion-relevant EEG features is still under investigation, power features from different frequency bands are still the most popular in the context of emotion recognition. Studies [26,197,218] have shown that power spectral density (PSD) extracted from EEG signals performs well on distinguishing affective states.…”

Section: Eeg Correlates Of Emotion (Signals)mentioning

confidence: 99%

“…Recently, EEG-based emotion recognition was proposed as a technique that can be used to support a classification task, such as the EEG-based emotional state clustering task [50], image classification [219], and Odor Pleasantness Classification Using Brain and Peripheral Signals [26].…”

Section: Domain Description Referencesmentioning

confidence: 99%

See 2 more Smart Citations

Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review

et al. 2017

View full text Add to dashboard Cite

Abstract:Recent developments and studies in brain-computer interface (BCI) technologies have facilitated emotion detection and classification. Many BCI studies have sought to investigate, detect, and recognize participants' emotional affective states. The applied domains for these studies are varied, and include such fields as communication, education, entertainment, and medicine. To understand trends in electroencephalography (EEG)-based emotion recognition system research and to provide practitioners and researchers with insights into and future directions for emotion recognition systems, this study set out to review published articles on emotion detection, recognition, and classification. The study also reviews current and future trends and discusses how these trends may impact researchers and practitioners alike. We reviewed 285 articles, of which 160 were refereed journal articles that were published since the inception of affective computing research. The articles were classified based on a scheme consisting of two categories: research orientation and domains/applications. Our results show considerable growth of EEG-based emotion detection journal publications. This growth reflects an increased research interest in EEG-based emotion detection as a salient and legitimate research area. Such factors as the proliferation of wireless EEG devices, advances in computational intelligence techniques, and machine learning spurred this growth.

show abstract

Section: Design Innovation (Experimental) Papermentioning

confidence: 99%

Section: Eeg Correlates Of Emotion (Signals)mentioning

confidence: 99%

See 1 more Smart Citation

Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Although the most informative EEG features for emotion classification are still being researched, the power features obtained from different bands are widely recognized as the most popular features. In these studies [20][21][22], power spectral density (PSD) from EEG signals worked well for identifying emotional states. However, feature extraction usually generates high-dimensional and abundant features.…”

Section: Introductionmentioning

confidence: 99%

EEG-Based Emotion Recognition Using Logistic Regression with Gaussian Kernel and Laplacian Prior and Investigation of Critical Frequency Bands

Pan

Cheng

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Emotion plays a nuclear part in human attention, decision-making, and communication. Electroencephalogram (EEG)-based emotion recognition has developed a lot due to the application of Brain-Computer Interface (BCI) and its effectiveness compared to body expressions and other physiological signals. Despite significant progress in affective computing, emotion recognition is still an unexplored problem. This paper introduced Logistic Regression (LR) with Gaussian kernel and Laplacian prior for EEG-based emotion recognition. The Gaussian kernel enhances the EEG data separability in the transformed space. The Laplacian prior promotes the sparsity of learned LR regressors to avoid over-specification. The LR regressors are optimized using the logistic regression via variable splitting and augmented Lagrangian (LORSAL) algorithm. For simplicity, the introduced method is noted as LORSAL. Experiments were conducted on the dataset for emotion analysis using EEG, physiological and video signals (DEAP). Various spectral features and features by combining electrodes (power spectral density (PSD), differential entropy (DE), differential asymmetry (DASM), rational asymmetry (RASM), and differential caudality (DCAU)) were extracted from different frequency bands (Delta, Theta, Alpha, Beta, Gamma, and Total) with EEG signals. The Naive Bayes (NB), support vector machine (SVM), linear LR with L1-regularization (LR_L1), linear LR with L2-regularization (LR_L2) were used for comparison in the binary emotion classification for valence and arousal. LORSAL obtained the best classification accuracies (77.17% and 77.03% for valence and arousal, respectively) on the DE features extracted from total frequency bands. This paper also investigates the critical frequency bands in emotion recognition. The experimental results showed the superiority of Gamma and Beta bands in classifying emotions. It was presented that DE was the most informative and DASM and DCAU had lower computational complexity with relatively ideal accuracies. An analysis of LORSAL and the recently deep learning (DL) methods is included in the discussion. Conclusions and future work are presented in the final section.

show abstract

“…Previous investigations, in fact, failed to report different (either linear or nonlinear/complex) heartbeat dynamics between ultra short-time (i.e., lasting less 10s), pleasant and unpleasant olfactory stimuli. In addition, classification models devised to automatically recognize hedonic differences between odors using heartbeat dynamics have not achieved sufficient accuracy [10].…”

Section: Introductionmentioning

confidence: 99%

Instantaneous Assessment of Hedonic Olfactory Perception Using Heartbeat Nonlinear Dynamics: a Preliminary Study

Greco¹,

Nardelli²,

Lanatà³

et al. 2017

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Emotional perception to hedonic olfactory stimuli is under direct control of the limbic system, whose dynamics is known to affect autonomic nervous system activity on cardiovascular control. Mainly due to methodological limitations, previous investigations failed to uncover specific trends in heartbeat dynamics between ultra shorttime (i.e., lasting < 10s), pleasant and unpleasant olfactory stimuli. To this extent, in this study we computed instantaneous estimates from heartbeat series gathered from 32 healthy subjects (age: 26±2; 16M) undergoing hedonic olfactory elicitation. Each subject exhibited a similar olfactory perception threshold, and scored five 5s stimuli in terms of arousal and valence level using the selfassessment manikin test. We analyzed the heartbeat series using our recently proposed inhomogeneous point-process nonlinear framework, obtaining instantaneous estimates defined in the time (mean and standard deviation), frequency (power in the LF and HF bands, as well as LF/HF ratio), and nonlinear/complexity (bispectra, sample and approximate entropy, and Lyapunov exponent) domains. A feature set comprising average estimates within the 5s windows was taken as an input of a K-Nearest Neighborhood classification algorithm, whose cross-validation relied on a leave-one-subject-out procedure. Results demonstrate that our framework allows to finely characterize affective olfactory elicitation with an average recognition accuracy of 71.88%. Feature selection highlighted that the most discriminating power was contributed by instantaneous LF power, instantaneous Lyapunov exponents, and instantaneous approximate entropy.

show abstract

Subject-Independent Odor Pleasantness Classification Using Brain and Peripheral Signals

Cited by 60 publications

References 53 publications

Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review

Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review

EEG-Based Emotion Recognition Using Logistic Regression with Gaussian Kernel and Laplacian Prior and Investigation of Critical Frequency Bands

Instantaneous Assessment of Hedonic Olfactory Perception Using Heartbeat Nonlinear Dynamics: a Preliminary Study

Contact Info

Product

Resources

About