Human Emotion Classification Based on EEG Signals Using Naïve Bayes Method

Oktavia, Nur Yusuf; Wibawa, Adhi Dharma; Pane, Evi Sentiana; Purnomo, Mauridhi Hery

doi:10.1109/isemantic.2019.8884224

Cited by 22 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Emotion classifications were also performed through Naive Bayesian, Autoregressive model, ANFIS etc. [61]. Recently, deep learning-based methods, i.e.…”

Section: Discussionmentioning

confidence: 99%

EEG-induced Fear-type Emotion Classification Through Wavelet Packet Decomposition, Wavelet Entropy, and SVM

Uyulan

GÜMÜŞ>

Güleken

2022

Hittite Journal of Science and Engineering

View full text Add to dashboard Cite

Among the most significant characteristics of human beings is their ability to feel emotions. In recent years, human-machine interface (HM) research has centered on ways to empower the classification of emotions. Mainly, human-computer interaction (HCI) research concentrates on methods that enable computers to reveal the emotional states of humans. In this research, an emotion detection system based on visual IAPPS pictures through EMOTIV EPOC EEG signals was proposed. We employed EEG signals acquired from channels (AF3, F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, F8, AF4) for individuals in a visual induced setting (IAPS fear and neutral aroused pictures). The wavelet packet transform (WPT) combined with the wavelet entropy algorithm was applied to the EEG signals. The entropy values were extracted for every two classes. Finally, these feature matrices were fed into the SVM (Support Vector Machine) type classifier to generate the classification model. Also, we evaluated the proposed algorithm as area under the ROC (Receiver Operating Characteristic) curve, or simply AUC (Area under the curve) was utilized as an alternative single-number measure. Overall classification accuracy was obtained at 91.0%. For classification, the AUC value given for SVM was 0.97. The calculations confirmed that the proposed approaches are successful for the detection of the emotion of fear stimuli via EMOTIV EPOC EEG signals and that the accuracy of the classification is acceptable.

show abstract

“…Emotion classifications were also performed through Naive Bayesian, Autoregressive model, ANFIS etc. [61]. Recently, deep learning-based methods, i.e.…”

Section: Discussionmentioning

confidence: 99%

EEG-induced Fear-type Emotion Classification Through Wavelet Packet Decomposition, Wavelet Entropy, and SVM

Uyulan

GÜMÜŞ>

Güleken

2022

Hittite Journal of Science and Engineering

View full text Add to dashboard Cite

show abstract

“…The authors applied the SVM as a classifier and achieved average classification accuracies of 62.16% and 74.21% from 20 non-meditators and 20 yogis respectively. Moreover, N.Y. Oktavia et al [8] in their research observed emotions recognition by exploring emotions cue through EEG signals. This was demonstrated by the highest classification accuracy of 87.5% result obtained using naïve bayes (NB) classification model for distinguishing between happy and sad emotions.…”

Section: Literature Reviewmentioning

confidence: 99%

Efficacy of Dimensionality Reduction Techniques and 2D Features in Classification of EEG Data

Chaudhary

Tyagi

2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

EEG-based BCIs enable a direct path for the human brain to communicate with external devices. The main objective of BCI is to classify brain signals to control some applications of interest. EEG is a paradigm that helps to obtain the brain signals from the different states of the human brain. EEG signal feature extraction is a critical topic in brain signal processing that has attracted great attention nowadays with the emergence of large-scale data. The focus of this paper is to reduce the dimension and redundancy of raw EEG data to facilitate retrieval of selected dynamic information. Three approaches of feature extraction and dimensionality reduction viz. PCA, LDA and ICA have been implemented on EEG datasets recorded during attention and meditation state of the brain. Moreover, as massive amount of information about the relationship between time and frequency coefficients is mostly missing in EEG dataset. hence, 1D feature set has been transformed into 2D images. The efficacy of the proposed methods has been tested through the CNN classifier for the classification of EEG signals. The experimental results show that the proposed method is able to achieve an average classification accuracy of 100%.

show abstract

“…There are, however, two approaches to the classification of emotion through EEG and these include the machine learning and neural network approaches. a) Machine learning approach: Some of the methods usually applied include decision tree (DT) [71], naïve bayes (NB) [72], quadratic discriminant analysis (QDA) [73], k-nearest neighbors (kNN) [58], [74], [75], linear discriminant analysis (LDA) [14], relevance vector machines (RVM) [67], xtreme gradient boosting (XGBoost) [76], support vector machine (SVM) [77]- [79], AdaBoost [80], logistic regression via variable splitting and augmented lagrangian (LORSAL) [81], random forest (RF) [56], [82], and graph regularized extreme learning machine (GELM) [83]. b) Neural network approach: This method include artificial neural network (ANN) [61], [63], [84] deep belief networks [70], [85], convolutional neural network (CNN) [40], [46], [86], [87], long short-term memory (LSTM) [66], generative adversarial networks (GAN) [88], capsule network (CapsNet) [45], [62], and hybrid methods [4], [44], [69].…”

Section: Classification Processmentioning

confidence: 99%

The challenges of emotion recognition methods based on electroencephalogram signals: a literature review

Wirawan

Wardoyo

Lelono

2022

IJECE

View full text Add to dashboard Cite

Electroencephalogram (EEG) signals in recognizing emotions have several advantages. Still, the success of this study, however, is strongly influenced by: i) the distribution of the data used, ii) consider of differences in participant characteristics, and iii) consider the characteristics of the EEG signals. In response to these issues, this study will examine three important points that affect the success of emotion recognition packaged in several research questions: i) What factors need to be considered to generate and distribute EEG data?, ii) How can EEG signals be generated with consideration of differences in participant characteristics?, and iii) How do EEG signals with characteristics exist among its features for emotion recognition? The results, therefore, indicate some important challenges to be studied further in EEG signals-based emotion recognition research. These include i) determine robust methods for imbalanced EEG signals data, ii) determine the appropriate smoothing method to eliminate disturbances on the baseline signals, iii) determine the best baseline reduction methods to reduce the differences in the characteristics of the participants on the EEG signals, iv) determine the robust architecture of the capsule network method to overcome the loss of knowledge information and apply it in more diverse data set.

show abstract

Human Emotion Classification Based on EEG Signals Using Naïve Bayes Method

Cited by 22 publications

References 19 publications

EEG-induced Fear-type Emotion Classification Through Wavelet Packet Decomposition, Wavelet Entropy, and SVM

EEG-induced Fear-type Emotion Classification Through Wavelet Packet Decomposition, Wavelet Entropy, and SVM

Efficacy of Dimensionality Reduction Techniques and 2D Features in Classification of EEG Data

The challenges of emotion recognition methods based on electroencephalogram signals: a literature review

Contact Info

Product

Resources

About