A user-independent real-time emotion recognition system for software agents in domestic environments

León, Enrique Chávez; Clarke, Graham S.; Callaghan, Vic; Sepúlveda, Francisco

doi:10.1016/j.engappai.2006.06.001

Cited by 106 publications

(56 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The reason is that the physiological response patterns are different among individuals [5]. Leon has optimized classifiers with training using biological data for each person to eliminate individual differences in physiological response [6]. Since personalized classification method requires time for the training using individual biological data, new users cannot use it immediately.…”

Section: Existing Researchmentioning

confidence: 99%

“…However, the transition pattern of biological data for the occurrence of specific emotion varies with individuals [5]. If we want to estimate emotions from physiological responses, it is necessary to train a classifier with the biological data brought by emotions of each student in advance for a certain period of time [6]. In a classifier trained with biological data of any student, the estimation accuracy would be significantly low, while training of a classifier with biological data of each student is a big burden for the student.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Emotion for Each Personality by Analyzing BVP

Takemoto¹,

Yusuke²,

Shimakawa³

2018

JMEA

View full text Add to dashboard Cite

This research estimates emotions of university students from their BVP (blood volume pulse). Negative emotion of university students causes school dropout, which is becoming a serious problem in Japan. It is indispensable for school staffs and counselors to know when and where students have negative emotion in the campus. Since BVP signals along with emotion changes vary with personality types, we build a model dependent on personality type, to estimate student emotion from characteristics of blood volume signals. Experimental results show that the model for each personality type improves the accuracy of emotion estimation for new students. Positive or negative emotion estimated from BVP signals contributes to enhancement of campus environment by school counselors.

show abstract

Section: Existing Researchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimating Emotion for Each Personality by Analyzing BVP

Takemoto¹,

Yusuke²,

Shimakawa³

2018

JMEA

View full text Add to dashboard Cite

show abstract

“…There was some classification work dealing with physiological signals using neural networks [17] and linear discriminant analysis [15]; they achieved moderate generalization performance across subjects. To the best of our knowledge we report the first systematic empirical analysis of domain adaptation methods to address the distribution differences due to the subject based variability in physiological signals.…”

Section: Related Workmentioning

confidence: 99%

Multisource domain adaptation and its application to early detection of fatigue

Chattopadhyay

Sun

Wang³

et al. 2012

ACM Trans. Knowl. Discov. Data

138

105

View full text Add to dashboard Cite

We consider the characterization of muscle fatigue through noninvasive sensing mechanism such as surface electromyography (SEMG). While changes in the properties of SEMG signals with respect to muscle fatigue have been reported in the literature, the large variation in these signals across different individuals makes the task of modeling and classification of SEMG signals challenging. Indeed, the variation in SEMG parameters from subject to subject creates differences in the data distribution. In this paper, we propose a transfer learning framework based on the multi-source domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed framework, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the proposed framework is a novel weighting scheme that addresses the conditional probability distribution differences across multiple domains (subjects). We have validated the proposed framework on Surface Electromyogram signals collected from 8 people during a fatigue-causing repetitive gripping activity. Comprehensive experiments on the SEMG data set demonstrate that the proposed method improves the classification accuracy by 20% to 30% over the cases without any domain adaptation method and by 13% to 30% over the existing state-of-the-art domain adaptation methods.

show abstract

“…Algunos ejemplos que se pueden mencionar incluyen el trabajo de Picard et al (2001) y de Leon et al (2007). La ventaja de este tipo de sistemas es que permiten vincular la experiencia emocional con factores externos e identificar aquellos de estos factores que se asocian con situaciones afectivas adversas.…”

Section: Detección Fisiológica De Emocionesunclassified

Una experiencia de innovación colaborativa en tecnología centrada en la persona: la detección emocional y sus posibles contribuciones al apoyo de personas con discapacidad intelectual y del desarrollo

Agirre¹,

Villeda²,

Cano³

et al. 2013

Redis

View full text Add to dashboard Cite

El artículo pretende llamar la atención sobre lo interesante que puede resultar la colaboración entre las entidades que se dedican al desarrollo de tecnología social y las que proporcionan apoyos a personas con discapacidad intelectual y del desarrollo (DID). Este tipo de trabajo conjunto permite ofrecer una tecnología innovadora y verdaderamente centrada en la persona que satisfaga sus necesidades reales en sus entornos naturales. En nuestro caso, Tecnalia y Uliazpi vienen colaborando desde hace varios años en la identificación de necesidades y en el desarrollo de soluciones tecnológicas que las puedan satisfacer. En este artículo se presenta asimismo un proyecto producto de esta colaboración. Se trata de un sistema de detección emocional que puede apoyar la labor del profesional de apoyo a la hora de reconocer e intervenir sobre las situaciones que promueven el bienestar o el malestar de personas que no lo pueden comunicar con sus propios medios.

show abstract

A user-independent real-time emotion recognition system for software agents in domestic environments

Cited by 106 publications

References 27 publications

Estimating Emotion for Each Personality by Analyzing BVP

Estimating Emotion for Each Personality by Analyzing BVP

Multisource domain adaptation and its application to early detection of fatigue

Una experiencia de innovación colaborativa en tecnología centrada en la persona: la detección emocional y sus posibles contribuciones al apoyo de personas con discapacidad intelectual y del desarrollo

Contact Info

Product

Resources

About