Emotion recognition based on sparse learning feature selection method for social communication

Yan, Yixin; Li, Chenyang; Meng, Shaoliang

doi:10.1007/s11760-019-01448-x

Cited by 6 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the traditional filtering feature selection method, when the dimension of features becomes very high, the amount of calculation will become very timeconsuming. In recent years, the sparse learning algorithm [24] has shown a good application prospect in the field of signal analysis. rough proper modeling, sparse learning can be well applied to feature selection.…”

Section: Feature Selection Methods Of Eeg Signalmentioning

confidence: 99%

Mental and Emotional Recognition of College Students Based on Brain Signal Features and Data Mining

2022

Security and Communication Networks

View full text Add to dashboard Cite

Nowadays, people pay more and more attention to the psychological situation of college students. Using data mining technology to model and analyze the collected psychological data of college students is a research hotspot in psychology and computer science. In addition, the essence of human emotional change is the higher nervous activity in the cerebral cortex. Electroencephalography (EEG) has become an important feature signal for emotion recognition because of its high time resolution and portability and practicality. Therefore, to solve the problem that the accuracy and generalization of the existing research models are not ideal, a method of college students’ psychological emotion recognition based on EEG signal features and data mining is proposed. Firstly, a feature selection method based on sparse learning is used to find out a few features from the high-dimensional feature space that contribute greatly to the reconstruction of category information so as to quickly acquire a few key emotion-related features. Then, the entropy-weighted clustering algorithm is combined with sparse learning feature selection, and the local structure of heterogeneous data is divided. Experimental results show that, compared with traditional methods, the proposed method has stronger applicability and higher accuracy of five categories of emotions, which provides a valuable reference for the evaluation of depression and anxiety of college students based on brain signal characteristics.

show abstract

Section: Feature Selection Methods Of Eeg Signalmentioning

confidence: 99%

Mental and Emotional Recognition of College Students Based on Brain Signal Features and Data Mining

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Likewise, [30] proposes a dynamic search strategy to optimize the set of statistical functions. The sparse selection algorithm proposed by [31] selects feature properties based on a sparse learning methodology. The selected function is used in sentiment ranking modeling with a fair ranking performance for SEED and DEAP datasets.…”

Section: Introductionmentioning

confidence: 99%

Semi-Skipping Layered Gated Unit and Efficient Network: Hybrid Deep Feature Selection Method for Edge Computing in EEG-Based Emotion Classification

et al. 2021

View full text Add to dashboard Cite

In this article, we propose a novel feature selection method based on hybrid neural networks for emotional classification avoiding expensive computation. With the development of neural networks for machine learning tools, the Electroencephalogram (EEG)-based classification of human emotions is increasingly important in providing health-care for Edge Computing in support of multiple Internet of Things (IoT) applications. However, classifying emotions through EEG signals is very challenging due to the low temporal boundaries and non-linear nature of EEG signals. Regarding non-linearity, we propose a hierarchical Semi-skipping Layered Gated Unit (SLGU) besides Efficient Network (ENet) for feature extraction. For faster processing, we have introduced a semi-skipping layer for Gated Recurrent Units (GRU) in Recurrent Neural Networks (RNN). The entered layer automatically skips the divergent factor during network training. Preprocessed EEG signals are sent to the hybrid SLGU-ENet model for deep feature extraction. To overcome the computational cost, an optimal function reduction method called the Bag of Visualized Characteristics (BoVC) is used. The entire facility is verified against two publicly available datasets. The results show that the classification performance of the proposed model achieves superior classification precision in a short processing time compared to the state-of-the-art models. The proposed algorithm required around 1.2-5 seconds, suitable for real-time IoT applications.INDEX TERMS Edge computing, efficient network, electroencephalogram (EEG), emotion classification, Internet of Things, recurrent neural network.

show abstract

A novel binary chaotic genetic algorithm for feature selection and its utility in affective computing and healthcare

Tahir

Tubaishat

Al-Obeidat

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Emotion recognition based on sparse learning feature selection method for social communication

Cited by 6 publications

References 25 publications

Mental and Emotional Recognition of College Students Based on Brain Signal Features and Data Mining

Mental and Emotional Recognition of College Students Based on Brain Signal Features and Data Mining

Semi-Skipping Layered Gated Unit and Efficient Network: Hybrid Deep Feature Selection Method for Edge Computing in EEG-Based Emotion Classification

A novel binary chaotic genetic algorithm for feature selection and its utility in affective computing and healthcare

Contact Info

Product

Resources

About