Automated Identification of Human Emotions by Gestures and Poses

Заболеева-зотова, А. В.; Bobkov, A.; Розалиев, В. Л.; Petrovsky, Alexey B.

doi:10.1109/brics-cci-cbic.2013.57

Cited by 7 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method for calculating the proportion value was based on (14). For example, given 5600 original samples, we set aside 80% for training, is 5600 × 0.8 = 4480 samples.…”

Section: B Classification Results Using Mixed Samplesmentioning

confidence: 99%

See 1 more Smart Citation

Improving Distinguishability of Photoplethysmography in Emotion Recognition Using Deep Convolutional Generative Adversarial Networks

Chang

2022

IEEE Access

View full text Add to dashboard Cite

We propose an emotion recognition framework based on ResNet, bidirectional long-and short-term memory (BiLSTM) modules, and data augmentation using a ResNet deep convolutional generative adversarial network (DCGAN) with photoplethysmography (PPG) signals as input. The emotions identified in this study were classified into two classes (positive and negative) and four classes (neutral, angry, happy, and sad). The framework achieved high recognition rates of 90.34% and 86.32% in two-and four-class emotion recognition tasks, respectively, outperforming other representative methods. Moreover, we show that the ResNet DCGAN module can synthesize samples that do not just look like those in the training set, but also capture discriminative features of the different classes. The distinguishability of the classes was enhanced when these synthetic samples were added to the original samples, which in turn improved the test accuracy of the model when trained using these mixed samples. This effect was evaluated using various quantitative and qualitative methods, including the inception score (IS), Fréchet inception distance (FID), GAN quality index (GQI), linear discriminant analysis (LDA), and Mahalanobis distance (MD).

show abstract

“…The method for calculating the proportion value was based on (14). For example, given 5600 original samples, we set aside 80% for training, is 5600 × 0.8 = 4480 samples.…”

Section: B Classification Results Using Mixed Samplesmentioning

confidence: 99%

“…In automated emotion recognition, many studies have focused on visual or auditory signals such as facial expressions [2], [3], [4], [5], [6], speech [7], [8], [9], text [10], [11], [12], and gestures [13], [14], [15]. This is intuitive because these signals are most often involved in humanhuman interactions.…”

Section: Introductionmentioning

confidence: 99%

Improving Distinguishability of Photoplethysmography in Emotion Recognition Using Deep Convolutional Generative Adversarial Networks

Chang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The author of this theory is Altshuller (1984), and the theory was developed in the writings of his students (Zlotin and Zusman 2006;Zlotin and Zusman 2011). In the context of our study, the method of generating engineering solutions, developed by Polovinkin (1988) at the end of the last century, named «blagodatnye systems» and improved by his students (Zaboleeva-Zotova et al 2013;Ukustov et al 2013), is of interest.…”

Section: Cognitive Methods and Their Role In The Pursuit Of Academic mentioning

confidence: 96%

Export of Educational Services as a Component of University Leadership in the Innovation Field

Perederiy¹,

Borovaya²,

Kobazeva³

2019

Proceedings of the 5th International Conference on Social, Economic, and Academic Leadership (ICSEALV 2019)

View full text Add to dashboard Cite

Our paper examines the features of the impact of the export of educational services of a technical university on its position in the educational institutions' ratings, reflecting the nature of its innovative activities. It has been proved that the conditions, under which innovation activity of the university and export of educational services are being conducted, are closely related and based on a common institutional framework. The approaches to the development of methods of university's innovation activity management in terms of organizing international cooperation and export of educational services have been proposed.

show abstract

“…[2; 5; 6; 7] The proposed approach to emotion identification are based on recognition and analysis of human gestures and poses. [8] First of all, we recognize a person on video images using a technology for markerless motion capture with the digital video camera Microsoft Kinect. Video pictures are presented in the special animation format -the BVH-file, which describes poses of body skeleton and contains motion data.…”

Section: Identification Of Human Body Movementsmentioning

confidence: 99%

Methods and Models for Identifying Human Emotions by Recognition Gestures and Motion

Розалиев¹,

Заболеева-зотова²

2013

Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation

Self Cite

View full text Add to dashboard Cite

Automated Identification of Human Emotions by Gestures and Poses

Cited by 7 publications

References 4 publications

Improving Distinguishability of Photoplethysmography in Emotion Recognition Using Deep Convolutional Generative Adversarial Networks

Improving Distinguishability of Photoplethysmography in Emotion Recognition Using Deep Convolutional Generative Adversarial Networks

Export of Educational Services as a Component of University Leadership in the Innovation Field

Methods and Models for Identifying Human Emotions by Recognition Gestures and Motion

Contact Info

Product

Resources

About