Spatio-temporal deep forest for emotion recognition based on facial electromyography signals

Xu, Muhua; Cheng, Juan; Li, Chang; Liu, Yu; Chen, Xun

doi:10.1016/j.compbiomed.2023.106689

Cited by 8 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies used SVM individually [6,7,13] or for comparison [5,9,12,16], but never SVM outperformed the other classifiers considered in their analysis. Further, studies reported higher [6,9,10,12] or lower [5,11,13,16] classification accuracy than our studies, however; these studies have used different dataset, different feature extraction methods and emotional classes. Hence, our results may not be directly compared with the outcomes of their studies.…”

Section: Effect Of Machine Learningcontrasting

confidence: 79%

“…Research has shown that when individuals are exposed to pictures of happy faces, there is a spontaneous increase in activity of the zygomatic major muscle, which is responsible for elevating the lips to form a smile. Studies have used the fEMG signals from the zygomaticus major in addition to other muscle regions for emotion classification [5,8,[10][11][12]16]. Our reHowever, to the best of the authors' knowledge, only our earlier study has included information from this location for emotion classification.sults suggest that tEMG conveys significant information (35.48%, 11 features) about the different emotions.…”

Section: Effect Of Locationsmentioning

confidence: 66%

“…In comparison, RF achieved the highest classification accuracy of 74.79% using the combination of all domain features extracted from the zEMG, cEMG and tEMG combined signals. A recent study reported that spatiotemporal deep forest outperformed the SVM, LDC, RF, Kurtogram-CNN, and WT-DBN [10]. Many studies used SVM individually [6,7,13] or for comparison [5,9,12,16], but never SVM outperformed the other classifiers considered in their analysis.…”

Section: Effect Of Machine Learningmentioning

confidence: 99%

“…Deep learning utilizes multi-layer neural networks to autonomously extract complex patterns and data representations. However, training deep neural networks frequently necessitates significant computational resources and large datasets [10]. Our study employs Logistic Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) to classify emotional states and optimize the placement location of fEMG electrodes, contributing to this evolving field.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evaluating the Effectiveness of Machine Learning in Identifying the Optimal Facial Electromyography Location for Emotion Detection

Kumar,

PJ,

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction: Emotional state recognition is crucial for identifying emotions and providing valuable insights into detecting prolonged stress or negative emotions in individuals. In this study, we explore the feasibility of utilizing facial electromyography (fEMG) signals to accurately recognize the emotions and determine the optimal recording location. Materials and methods: To investigate various emotions, we used the continuously annotated signals of emotion dataset, consisting of fEMG signals captured from three distinct muscle locations: zygomaticus major (zEMG), corrugator supercilii (cEMG), and trapezius (tEMG). These fEMG signals underwent analysis through feature extraction in the time, frequency, and time-frequency domains. We identified the optimal muscle location for recognizing emotions using different machine learning models, such as logistic regression (LR), support vector machine, and random forest (RF), and validated the results using a 10-fold cross-validation approach. Additionally, we identified the most influential features for distinguishing between the emotions using the RF feature ranking method. Results: Our findings showed that we attained the highest average accuracy of 74.79% for emotion classification by utilizing 31 top-ranked features from the time, frequency, and time-frequency domains of three fEMG signals (zEMG, cEMG, and tEMG) with the RF classifier. Moreover, we achieved an average accuracy of 74.17% by utilizing the top 10 time-domain features extracted from the zEMG signals with the LR classifier. In summary, this study demonstrates promising outcomes in utilizing fEMG signals for efficient emotion recognition and presents an innovative approach to the field of affective computing.

show abstract

Section: Effect Of Machine Learningcontrasting

confidence: 79%

Section: Effect Of Locationsmentioning

confidence: 66%

Section: Effect Of Machine Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating the Effectiveness of Machine Learning in Identifying the Optimal Facial Electromyography Location for Emotion Detection

Kumar,

PJ,

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Various physiological signals have been investigated for the purpose of emotion recognition. These include, body movement (Zhang et al, 2021 ), facial expression (Song, 2021 ), respiration (Siddiqui et al, 2021 ), galvanic skin response (Kipli et al, 2022 ), blood volume pulse (Semerci et al, 2022 ), skin temperature (Semerci et al, 2022 ), electromyography (Xu et al, 2023 ), photoplethysmographic (Cosoli et al, 2021 ), electrocardiogram (Hasnul et al, 2021 ), and EEG (Li et al, 2021 ). The non-invasive nature, affordability, and ability to capture data in real-time have contributed to the extensive utilization of EEG in the field of emotion identification (Alarcao and Fonseca, 2017 ), with a particular emphasis on music emotion categorization (Lin et al, 2006 ).…”

Section: Introductionmentioning

confidence: 99%

Music-evoked emotions classification using vision transformer in EEG signals

Wang,

Lian,

Cheng

et al. 2024

Front. Psychol.

View full text Add to dashboard Cite

IntroductionThe field of electroencephalogram (EEG)-based emotion identification has received significant attention and has been widely utilized in both human-computer interaction and therapeutic settings. The process of manually analyzing electroencephalogram signals is characterized by a significant investment of time and work. While machine learning methods have shown promising results in classifying emotions based on EEG data, the task of extracting distinct characteristics from these signals still poses a considerable difficulty.MethodsIn this study, we provide a unique deep learning model that incorporates an attention mechanism to effectively extract spatial and temporal information from emotion EEG recordings. The purpose of this model is to address the existing gap in the field. The implementation of emotion EEG classification involves the utilization of a global average pooling layer and a fully linked layer, which are employed to leverage the discernible characteristics. In order to assess the effectiveness of the suggested methodology, we initially gathered a dataset of EEG recordings related to music-induced emotions.ExperimentsSubsequently, we ran comparative tests between the state-of-the-art algorithms and the method given in this study, utilizing this proprietary dataset. Furthermore, a publicly accessible dataset was included in the subsequent comparative trials.DiscussionThe experimental findings provide evidence that the suggested methodology outperforms existing approaches in the categorization of emotion EEG signals, both in binary (positive and negative) and ternary (positive, negative, and neutral) scenarios.

show abstract

Set-pMAE: spatial-spEctral-temporal based parallel masked autoEncoder for EEG emotion recognition

Pan,

Lu,

Lin

et al. 2024

Cogn Neurodyn

View full text Add to dashboard Cite

Spatio-temporal deep forest for emotion recognition based on facial electromyography signals

Cited by 8 publications

References 37 publications

Evaluating the Effectiveness of Machine Learning in Identifying the Optimal Facial Electromyography Location for Emotion Detection

Evaluating the Effectiveness of Machine Learning in Identifying the Optimal Facial Electromyography Location for Emotion Detection

Music-evoked emotions classification using vision transformer in EEG signals

Set-pMAE: spatial-spEctral-temporal based parallel masked autoEncoder for EEG emotion recognition

Contact Info

Product

Resources

About