Spontaneous facial expression database of learners’ academic emotions in online learning with hand occlusion

Lyu, Li Kang; Zhang, Ya; Chi, Meng-Ya; Yang, Fei; Zhang, Shu-Gang; Liu, Peng; Lü, Weigang

doi:10.1016/j.compeleceng.2021.107667

Cited by 15 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to privacy concerns, there are few public databases for students' facial expressions. Most commonly known are JAFFE [5], OL-SFED [6], OLFED-HO [7], etc., among which the former two are selected in this paper. In addition, the RAF-DB [8] expression data path, which is more difficult, is also used to compare with other researchers' models.…”

Section: Resultsmentioning

confidence: 99%

Students’ Facial Expression Recognition Based on Multi-head Attention Mechanism

Dai

Wei

Zeng

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

As there are a far greater number of students in the classroom than teachers, it is difficult for teachers to grasp the learning of all students. Especially during the epidemic period, when online teaching becomes a trend, this problem is more prominent. The issue of how to grasp the learning of each student more comprehensively remains a problem to be solved in teaching. Under such circumstances, students’ facial expression recognition emerges as one of the most important solutions. In this paper, an improved facial expression recognition model based on the multi-head attention mechanism is proposed. The model is tested on two student expression databases, the JAFFE and the OL-SFED, and the recognition rate reaches 99.5% and 100%, respectively. In addition, to compare it with the models developed by other researchers, it is also tested on the RAF-DB, recording the best recognition rate of 90.35% and an average recognition rate of 83.66%, which represents the best level so far.

show abstract

Section: Resultsmentioning

confidence: 99%

Students’ Facial Expression Recognition Based on Multi-head Attention Mechanism

Dai

Wei

Zeng

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…В работе [18] исследуется создание онлайн-базы данных, содержащей различные эмоции обучающихся во время дистанционного обучения, при этом на фото присутствует окклюзия рук. Обучающиеся часто рефлекторно прикрывают лицо руками во время дистанционного обучения, что, естественно, пагубно влияет на уровень распознавания их эмоций.…”

Section: степень разработанности темы исследованияunclassified

Decision support in providing personalized services using emotional artificial intelligence

Bogdanova

Kotelnikov

Yulamanova

2023

Automation and Modeling in Design and Management

View full text Add to dashboard Cite

An approach to personalized service rendering based on using affective computing technologies is described. The proposed approach consists of considering clients’ emotional states and their individual characteristics in the process of providing services. Rendering services is supplemented by the formalization stages of the client’s emotional state and emotional support. The paper considers online learning as the subject area of research. A general description of the online learning process is given. It is concluded that there is no correction of the learners’ emotional state during the lesson. The dependence of the learners’ knowledge level on their emotional state is revealed. A review of existing approaches to considering learners’ emotional states in the process of online learning is given. Learners’ specific behaviour during the lesson is analysed. The features of academic emotions are also considered. The objective is set to increase the online learning effectiveness by taking into account learners’ emotional states and their individual characteristics and by providing emotional support in the learning process. An approach is proposed to formalise learners’ emotional states based on using facial muscle movements as a universal way of recognizing emotions. The stages of recognizing learners’ emotions during the lesson are also described in detail. The task is set to select emotional support based on the learners’ classification according to their emotional state and their individual characteristics using the nearest neighbour method.

show abstract

“…The commonly used databases are shown in Table 1 [7] . Other databases used for expression recognition research include the DML-SUT expression database of Sharif University of Technology in Iran, the BU-3DFE expression database of the State University of New York at Binghamton, USA, the expression database of the University of Maryland, USA, the UT-Dallas expression database of the University of Texas, USA, the University of Central Lancashire, UK ADSIP 3-D expression database, the NIR KMU-FED dataset for actual driving scenes, the MMEW dataset of six face micro-expression recognition datasets from Shandong University [8] , and databases dedicated to micro-expression recognition research such as SAMM, SMIC, SMIC2, CAS(ME)2 [9] , York DDT, and CASME. There have been many research results related to expression databases, and there are some problems.…”

Section: Domestic and Foreign Relevant Databasesmentioning

confidence: 99%

A Learning Sentiment Database for Machine Learning

Zhang

Shi

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Learners’ affective states play a crucial role in learning evaluation, and the external expressions that can directly reflect affect are facial expressions. However, the sample size of the database for the learning process of learners is limited, and most of the existing expression databases are the expressions of ordinary people, which is difficult to support an in-depth study of the emotional states of learners in learning scenarios. In order to better study the influence of learners’ emotion on the learning state, we built a learning expression database for machine learning, and at the same time labeled the data with expression-emotion state, and finally formed a database of 8,000 expression images containing 36 learners, which is important for studying learners’ emotion state under learning scenarios.

show abstract

Spontaneous facial expression database of learners’ academic emotions in online learning with hand occlusion

Cited by 15 publications

References 14 publications

Students’ Facial Expression Recognition Based on Multi-head Attention Mechanism

Students’ Facial Expression Recognition Based on Multi-head Attention Mechanism

Decision support in providing personalized services using emotional artificial intelligence

A Learning Sentiment Database for Machine Learning

Contact Info

Product

Resources

About