EEG-based automatic emotion recognition: Feature extraction, selection and classification methods

Ackermann, Philipp; Kohlschein, Christian; Bitsch, Jó Ágila; Wehrle, Klaus; Jeschke, Sabina

doi:10.1109/healthcom.2016.7749447

Cited by 100 publications

(58 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The recognition rate for the arousal emotion was on average 53.28% and for the valence emotion was 57.19%. This finding was comparable to recent other research results using the same database, such as the leave-subject-out scheme of the person (53.42% for arousal and 52.05% for valence) [37], using a random subset 10-fold leave-p-out cross-validation (all between 40% and 50% accuracy) [50].…”

Section: Exp #5: Comparison Of Bpnn and Pnn Classifierssupporting

confidence: 78%

“…This research utilized two non-linear classifiers, namely the BPNN and the PNN. The result of using these classifier was also comparable to other recent research using other linear and non-linear classifier, such as SVM [50,53] and DLN [37]. However, newer classifiers, such as group sparse canonical correlation analysis (GCCA) [54] and sparse deep belief networks (SDBN) [55], have never been used, giving room to further future works.…”

Section: Discussionsupporting

confidence: 60%

“…The proposed bispectrum-based feature extraction gave a comparable result with some recent research using different feature extraction methods, such as Discrete Wavelet Transform -Relative Wavelet Energy (DWT-RWE) [3], Short Time Fourier Transform (STFT) [50], Power Spectral Density (PSD) [37] and Empirical Mode Decomposition (EMD) with Sample Entropy (SampEn) [53]. Future studies in the EEG-based emotion recognition system should focus on improving the feature calculation from the bispectrum values.…”

Section: Discussionsupporting

confidence: 53%

See 2 more Smart Citations

Development of Filtered Bispectrum for EEG Signal Feature Extraction in Automatic Emotion Recognition Using Artificial Neural Networks

2017

View full text Add to dashboard Cite

Abstract:The development of automatic emotion detection systems has recently gained significant attention due to the growing possibility of their implementation in several applications, including affective computing and various fields within biomedical engineering. Use of the electroencephalograph (EEG) signal is preferred over facial expression, as people cannot control the EEG signal generated by their brain; the EEG ensures a stronger reliability in the psychological signal. However, because of its uniqueness between individuals and its vulnerability to noise, use of EEG signals can be rather complicated. In this paper, we propose a methodology to conduct EEG-based emotion recognition by using a filtered bispectrum as the feature extraction subsystem and an artificial neural network (ANN) as the classifier. The bispectrum is theoretically superior to the power spectrum because it can identify phase coupling between the nonlinear process components of the EEG signal. In the feature extraction process, to extract the information contained in the bispectrum matrices, a 3D pyramid filter is used for sampling and quantifying the bispectrum value. Experiment results show that the mean percentage of the bispectrum value from 5 × 5 non-overlapped 3D pyramid filters produces the highest recognition rate. We found that reducing the number of EEG channels down to only eight in the frontal area of the brain does not significantly affect the recognition rate, and the number of data samples used in the training process is then increased to improve the recognition rate of the system. We have also utilized a probabilistic neural network (PNN) as another classifier and compared its recognition rate with that of the back-propagation neural network (BPNN), and the results show that the PNN produces a comparable recognition rate and lower computational costs. Our research shows that the extracted bispectrum values of an EEG signal using 3D filtering as a feature extraction method is suitable for use in an EEG-based emotion recognition system.

show abstract

Section: Exp #5: Comparison Of Bpnn and Pnn Classifierssupporting

confidence: 78%

Section: Discussionsupporting

confidence: 60%

Section: Discussionsupporting

confidence: 53%

See 1 more Smart Citation

Development of Filtered Bispectrum for EEG Signal Feature Extraction in Automatic Emotion Recognition Using Artificial Neural Networks

2017

View full text Add to dashboard Cite

show abstract

“…They thus aimed at a physiological means for measuring the mental state of a person using certain devices such as pulse meters etc. [9] Later in 2016 Priyanka S. Ghare and A.N. Paithane in their paper -Human emotion recognition using nonlinear and non-stationary EEG signal proposed a GUI based method for automatic emotional recognition.…”

Section: Literature Surveymentioning

confidence: 99%

Electroencephalogram with Machine Learning for Estimation of Mental Confusion Level

2019

IJEAT

View full text Add to dashboard Cite

Estimating the mental state of an individual is crucial to many applications. A quantitative measure of the confusion one faces while doing a task can be useful in determining which subtask is the most difficult. This paper thus aims to develop an algorithm to estimate the confusion score using EEG signals collected using a Neurosky Mindwave Headset. Also, a full contextual audio based confusion score is generated to improve the system's resilience. In this paper, the final algorithm is used to propose an EEG based system to enable the UI/UX testing which can help in confusion estimation and thus provide a qualitative means to measure the attention and concentration level of people which can be extended to various applications. The raw EEG data collected from the device was used to calculate the confusion score using various Machine Learning algorithms. This brain computer interface (BCI) system can be extended for calculating the confusion score of a person which can be used for various applications such as teaching, child health monitoring, suicide prevention, mental health analysis etc. The brain computer interface thus calculates the confusion score and based on the threshold value of the attention and concentration level it performs certain actions such as sending messages and alerts to emergency contacts. This is further extended to solve the problem of Usability testing in Human Computer Interaction.

show abstract

“…In [10] authors Pascal Ackermann, Christian Kohlschei_, Jo´ A´ gila Bitsch, Klaus Wehrle and Sabina Jeschke in this paper "EEG-based Automatic Emotion Recognition: Feature Extraction, Selection and Classification Methods" Automatic emotion recognition is an interdisciplinary research field which deals with the algorithmic detection of human affect evaluation of human emotion is often done using oral feedback or questionnaires during doctor-patient sessions. EEG channel locations and frequency bands are best suited for is an issue of ongoing research.…”

Section: International Journal Of Computer Applications (0975 -8887)mentioning

confidence: 99%

A Survey on Emotion Recognition from EEG Signals for Autism Spectrum Disorder

Mohanapriya¹,

Malathi²,

Revathi³

2018

IJCA

View full text Add to dashboard Cite

Children with Autism Spectrum Disorder (ASD) cannot express their emotions explicitly; this makes it difficult for the parents and caretakers associated with these children to understand the child's behavior, leading to a major setback in the child's early developmental stages. To identify the autism for child initial stages can help early diagnosis. Delayed detection of child autism leads to incurable. This paper analysis the existing works on detection of autism spectrum disorder from EEG signal. Various filtering technique and classification are presented. The experiment for were conducted for support vector machine (SVM), k-nearest neighbor (KNN), linear discriminant analysis (LDA), deep learning, Naive Bayes, Random Forest, deep-learning classification algorithms. Here the deep learning algorithm gives better results for autism recognition with the emotions such as happy, calm, anger and scared. As the no of medical records increases the conventional techniques is not suitable for handle large number data.

show abstract

EEG-based automatic emotion recognition: Feature extraction, selection and classification methods

Cited by 100 publications

References 15 publications

Development of Filtered Bispectrum for EEG Signal Feature Extraction in Automatic Emotion Recognition Using Artificial Neural Networks

Development of Filtered Bispectrum for EEG Signal Feature Extraction in Automatic Emotion Recognition Using Artificial Neural Networks

Electroencephalogram with Machine Learning for Estimation of Mental Confusion Level

A Survey on Emotion Recognition from EEG Signals for Autism Spectrum Disorder

Contact Info

Product

Resources

About