EEG-Based Emotion Recognition in Music Listening

Lin, Yuan-Pin; Wang, Chi-Hong; Jung, Tzyy‐Ping; Wu, Tien-Lin; Jeng, Shyh‐Kang; Duann, Jeng Ren; Chen, Jyh-Horng

doi:10.1109/tbme.2010.2048568

Cited by 818 publications

(215 citation statements)

References 33 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…Most of previous studies have used SVM as the emotion classifier in their EEG-ER systems [14,15,17,19–24,32,33]. However, the performance of SVM tends to decline due to the problem of imbalanced emotional datasets described as follows:…”

Section: Problem Descriptions and Solutionsmentioning

confidence: 99%

“…In previous EEG-ER systems, various features have been used, including common spatial pattern [14], higher order crossings [15], time-domain statistical features [15,19], EEG spectral power [8,17,19–21,24,25,33], wavelet entropy [26], and coherence feature [28]. Among these features, EEG spectral power appears to be the most frequently used feature, however, two limitations should be noted.…”

Section: Problem Descriptions and Solutionsmentioning

confidence: 99%

“…For a single-trial EEG-ER system, the input is the EEG signal recorded during one single trial [17–23,27,28], while the input for a non-single trial EEG-ER system is the averaged EEG signals of multiple trials [14–16,24]. For instance, the input of the method in [27] is raw EEG signals of 7-s in duration acquired during one trial, while the input to the EEG-ER system in [24] is the averaged 2.5-s EEG epochs collected from 40 trials.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Emotion Recognition from Single-Trial EEG Based on Kernel Fisher’s Emotion Pattern and Imbalanced Quasiconformal Kernel Support Vector Machine

Liu

Cheng

et al. 2014

Sensors

View full text Add to dashboard Cite

Electroencephalogram-based emotion recognition (EEG-ER) has received increasing attention in the fields of health care, affective computing, and brain-computer interface (BCI). However, satisfactory ER performance within a bi-dimensional and non-discrete emotional space using single-trial EEG data remains a challenging task. To address this issue, we propose a three-layer scheme for single-trial EEG-ER. In the first layer, a set of spectral powers of different EEG frequency bands are extracted from multi-channel single-trial EEG signals. In the second layer, the kernel Fisher's discriminant analysis method is applied to further extract features with better discrimination ability from the EEG spectral powers. The feature vector produced by layer 2 is called a kernel Fisher's emotion pattern (KFEP), and is sent into layer 3 for further classification where the proposed imbalanced quasiconformal kernel support vector machine (IQK-SVM) serves as the emotion classifier. The outputs of the three layer EEG-ER system include labels of emotional valence and arousal. Furthermore, to collect effective training and testing datasets for the current EEG-ER system, we also use an emotion-induction paradigm in which a set of pictures selected from the International Affective Picture System (IAPS) are employed as emotion induction stimuli. The performance of the proposed three-layer solution is compared with that of other EEG spectral power-based features and emotion classifiers. Results on 10 healthy participants indicate that the proposed KFEP feature performs better than other spectral power features, and IQK-SVM outperforms traditional SVM in terms of the EEG-ER accuracy. Our findings also show that the proposed EEG-ER scheme achieves the highest classification accuracies of valence (82.68%) and arousal (84.79%) among all testing methods.

show abstract

Section: Problem Descriptions and Solutionsmentioning

confidence: 99%

Section: Problem Descriptions and Solutionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Emotion Recognition from Single-Trial EEG Based on Kernel Fisher’s Emotion Pattern and Imbalanced Quasiconformal Kernel Support Vector Machine

Liu

Cheng

et al. 2014

Sensors

View full text Add to dashboard Cite

show abstract

“…However, the maximum amplitude of beta waves showed a decline of up to 40. Yun-Pin et al [45] performed the EEG based experiments to study the ongoing brain activity between emotional states and brain activity. This study was applied to machine-learning algorithms to categorize EEG dynamics according to subject self-reported emotional states during music listening.…”

Section: Literature Surveymentioning

confidence: 99%

Mood Recognition System Using EEG Signal of Song Induced Activities

Deore¹,

Mehrotra

2014

Brain-Computer Interfaces

View full text Add to dashboard Cite

Music is referred to as language of emotions. Music induces emotion in the brain. These emotions are subject not only types of music, but also the sensitivity of the person subjected to music. Dissimilar cases of songs as relax, patriotism, happiness, romantic or sadness will induce different types of brain activities generating different EEG signals. EEG signal is applied to measure electrical activity of the brain. These EEG signal contain precious information of the different moods of subject. In this work, we proposed a mood recognition system using EEG signal of Song Induced activity. The main purpose is to analyze alpha rhythm of EEG signal related to the left hemisphere, and right hemisphere regions of the brain. We have selected 10 male subjects in the age group of 20-25. The electrodes placed on the scalp of the subject as per the International 10-20 standard. Each test was conducted for 25 min, with eye closed and each subject was asked to concentrate on the given tasks. In this study, we have created EEG dataset containing data of five mental tasks of ten different subjects. We determine the alpha rhythms in the left hemisphere are more predominant over the right hemisphere for emotions. Thus we conclude that the left region of the brain gives more response to the emotions rather than the right region. Here we reduce the EEG database from brain region to left hemisphere. Further we reduce it to single electrode as F7 which reside in left region. The database generated in our study may be used to interface the brain with computer to mood recognition system. This will have wide varieties of applications in the future. For example, the entertainment industries may use it for composition of songs as per their effect on the brain. This study also shows that alpha power frequency carries useful information related to mood recognition. These features are separated using Linear Discriminate Analysis.

show abstract

“…Bos (2006) obtiene una precisión del 70% para dos clases basadas en la clasificación de Bayes. Por todo ellos se pasa a estudiar diferentes aspectos relacionados con las señales EEG tales como la arquitectura del cerebro, la electroencefalografía, los dispositivos de medición y por último los estudios sobre emociones.…”

Section: Respuesta Neuronalunclassified

Incorporación de nuevos escenarios de uso en el proceso de diseño (SIPD): propuesta metodológica y valoración de la percepción de los usuarios

Royo¹

View full text Add to dashboard Cite

Programa de doctorado en TecnologíasIndustriales y Materiales TESIS DOCTORALIncorporación de nuevos escenarios de uso en el proceso de diseño (SIPD): propuesta metodológica y valoración de la percepción de los usuarios AUTORA: Marta Royo González DIRECTORES: Dra. Elena Mulet EscrigDr. Vicente Chulvi Ramos Castellón, Junio 2016Este trabajo se lo dedico:A mis directores de tesis. A Elena, por enseñarme el rigor, el conocimiento, a investigar….por las horas de charla y por darme una oportunidad… por ser mi amiga. Y Vicent, por enseñarme que las cosas no son complicadas, por tu paciencia y por volvernos a encontrar en el camino.A Julia por ser la chispa, la energía, el empujón que me sacudió la vida.A Raúl, por ser la serenidad, la calma y el apoyo incondicional, gracias.A Carlos, por mostrarme que se puede.A Paco, por ser tan buena gente y por tu voz.A Julio, por tu visión de la vida, por hacerme pensar y reír.Y los proyectos de investigación en los que se ha visto involucrada la tesis: "Interconexiones entre el diseño y el arte actual" (P1-1A2013-04) financiado por la Universitat Jaume I y el proyecto "Avances en contenido digital para juegos serios" (TIN2013-47276-C6-6-R) financiado por el MIMECO.A todos mis compañeros del departamento de EMC. A Quique y Ximo, director y secretario, a Loles por sus consejos y Antonio por los buenos momentos en los Congresos. A los compañeros de ESID, y en especial a Luis y Leo por embarcarme en nuevos retos.A Mario, por ser un artista total y libre, y por captar la esencia de la tesis con tus imágenes, sin ti, este trabajo no hubiera sido lo mismo.A Sara, por estar siempre, y ayudarme tanto.Mar, Miriam, Salva, Jaume, Rosa, Marian… A María, Laura y Augusto por vuestra ayuda en el experimento. Y a Marc porque siempre estás ahí A Marcela de Baby Essentials, por el apoyo a esta idea, y por tu visión de la empresa y de la mujer.Al Servei de Comunicacions y a Fernando.A mi familia.Mis padres que me enseñaron el valor del esfuerzo, la responsabilidad, la familia y la felicidad, gracias por todo.A mis hermanos que son la salsa de mi vida, pasión y sentimientos en estado puro, grandes y auténticos.A Jose, por ser mi compañero, por estar ahí, por tu amor y apoyo.A Gonzalo "el motor de mi vida" la personita que hace que el mundo se vea de otro color.A mis amigos, y en especial a Isa y su familia, porque hace tiempo tú ya creíste en mí.A todas las personas que han pasado por mi vida y han dejado huella y a muchos alumnos que me han dado grandes lecciones. El objetivo de la tesis es desarrollar pautas que permitan conceptualizar y evaluar nuevos conceptos de productos que alargan su vida de uso mediante el aumento del valor de uso función, implementando nuevas funcionalidades que cubran necesidades futuras del usuario, prolongando su utilización en el tiempo o incrementando la frecuencia de utilización del mismo. GraciasEl punto de partida de esta tesis ha sido el análisis de cada una de las estrategias de diseño que aumentan la duración de productos: ecoeficiencia, ecodiseño, PSS/IPSO. Una v...

show abstract

EEG-Based Emotion Recognition in Music Listening

Cited by 818 publications

References 33 publications

Emotion Recognition from Single-Trial EEG Based on Kernel Fisher’s Emotion Pattern and Imbalanced Quasiconformal Kernel Support Vector Machine

Emotion Recognition from Single-Trial EEG Based on Kernel Fisher’s Emotion Pattern and Imbalanced Quasiconformal Kernel Support Vector Machine

Mood Recognition System Using EEG Signal of Song Induced Activities

Incorporación de nuevos escenarios de uso en el proceso de diseño (SIPD): propuesta metodológica y valoración de la percepción de los usuarios

Contact Info

Product

Resources

About