Emotion Recognition in the Wild: Results and Limitations from Active and Healthy Ageing Cases in a Living Lab

Konstantinidis, Evdokimos I.; Billis, Antonis; Savvidis, Theodore; Xefteris, Stefanos; Bamidis, Panagiotis D.

doi:10.1007/978-3-319-49655-9_51

Cited by 8 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The control and adjustment of such smart AAL environments are usually based on the mobile terminals and wearable IoT devices as in [46]. Some researchers are even trying to employ (though still not very successfully) emotion recognition for the smart home and AAL applications [47].…”

Section: Iot Technologies For Ambient Assistive Livingmentioning

confidence: 99%

A Review of Internet of Things Technologies for Ambient Assisted Living Environments

2019

View full text Add to dashboard Cite

The internet of things (IoT) aims to extend the internet to real-world objects, connecting smart and sensing devices into a global network infrastructure by connecting physical and virtual objects. The IoT has the potential to increase the quality of life of inhabitants and users of intelligent ambient assisted living (AAL) environments. The paper overviews and discusses the IoT technologies and their foreseen impacts and challenges for the AAL domain. The results of this review are summarized as the IoT based gerontechnology acceptance model for the assisted living domain. The model focuses on the acceptance of new technologies by older people and underscores the need for the adoption of the IoT for the AAL domain.

show abstract

Section: Iot Technologies For Ambient Assistive Livingmentioning

confidence: 99%

A Review of Internet of Things Technologies for Ambient Assisted Living Environments

2019

View full text Add to dashboard Cite

show abstract

“…In this research, a multimodal emotion recognition system was developed ( Figure 1) using an infrared sensor from Microsoft called Kinect [37][38][39][40][41]. The 3D data from face, head, hand gestures, and body movement were used for the visual channel.…”

Section: System Overviewmentioning

confidence: 99%

“…These participants displayed naturalistic emotions while standing in front of the Kinect sensor [37][38][39][40][41] at 1.5 to 4 m ( Figure 2). The audiovisual color and depth data were used to capture spontaneously expressed emotions from each of the six basic emotion categories.…”

Section: Data Collectionmentioning

confidence: 99%

“…Hence, this paper uses concatenation of features from face, hand, head, body, audio, and the behavioral rule-based features to form a joint feature vector for multimodal emotion recognition system implementation. In recent years, researchers [37][38][39] have increasingly used Kinect for emotion recognition studies. Konstantinidis et al [37] used the sensor for emotions among elders in assisted living; however, the study evaluated the emotions in controlled lab conditions.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, researchers [37][38][39] have increasingly used Kinect for emotion recognition studies. Konstantinidis et al [37] used the sensor for emotions among elders in assisted living; however, the study evaluated the emotions in controlled lab conditions. Researchers [38] have proposed deep learning techniques for emotion recognition; however, the study did not address the absence of features from certain modalities at an instance of time.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Three-Dimensional, Kinematic, Human Behavioral Pattern-Based Features for Multimodal Emotion Recognition

Patwardhan¹

2017

MTI

View full text Add to dashboard Cite

This paper presents a multimodal emotion recognition method that uses a feature-level combination of three-dimensional (3D) geometric features (coordinates, distance and angle of joints), kinematic features such as velocity and displacement of joints, and features extracted from daily behavioral patterns such as frequency of head nod, hand wave, and body gestures that represent specific emotions. Head, face, hand, body, and speech data were captured from 15 participants using an infrared sensor (Microsoft Kinect). The 3D geometric and kinematic features were developed using raw feature data from the visual channel. Human emotional behavior-based features were developed using inter-annotator agreement and commonly observed expressions, movements and postures associated to specific emotions. The features from each modality and the behavioral pattern-based features (head shake, arm retraction, body forward movement depicting anger) were combined to train the multimodal classifier for the emotion recognition system. The classifier was trained using 10-fold cross validation and support vector machine (SVM) to predict six basic emotions. The results showed improvement in emotion recognition accuracy (The precision increased by 3.28% and the recall rate by 3.17%) when the 3D geometric, kinematic, and human behavioral pattern-based features were combined for multimodal emotion recognition using supervised classification.

show abstract

Personalized and Intelligent Sleep and Mood Estimation Modules with Web based User Interface for Improving Quality of Life

Tonchev

Balabanov

Manolova

et al. 2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Emotion Recognition in the Wild: Results and Limitations from Active and Healthy Ageing Cases in a Living Lab

Cited by 8 publications

References 14 publications

A Review of Internet of Things Technologies for Ambient Assisted Living Environments

A Review of Internet of Things Technologies for Ambient Assisted Living Environments

Three-Dimensional, Kinematic, Human Behavioral Pattern-Based Features for Multimodal Emotion Recognition

Personalized and Intelligent Sleep and Mood Estimation Modules with Web based User Interface for Improving Quality of Life

Contact Info

Product

Resources

About