EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities

Emotions are fundamental for human beings and play an important role in human cognition. Emotion is commonly associated with logical decision making, perception, human interaction, and to a certain extent, human intelligence itself. With the growing interest of the research community towards establishing some meaningful “emotional” interactions between humans and computers, the need for reliable and deployable solutions for the identification of human emotional states is required. Recent developments in using electroencephalography (EEG) for emotion recognition have garnered strong interest from the research community as the latest developments in consumer-grade wearable EEG solutions can provide a cheap, portable, and simple solution for identifying emotions. Since the last comprehensive review was conducted back from the years 2009 to 2016, this paper will update on the current progress of emotion recognition using EEG signals from 2016 to 2019. The focus on this state-of-the-art review focuses on the elements of emotion stimuli type and presentation approach, study size, EEG hardware, machine learning classifiers, and classification approach. From this state-of-the-art review, we suggest several future research opportunities including proposing a different approach in presenting the stimuli in the form of virtual reality (VR). To this end, an additional section devoted specifically to reviewing only VR studies within this research domain is presented as the motivation for this proposed new approach using VR as the stimuli presentation device. This review paper is intended to be useful for the research community working on emotion recognition using EEG signals as well as for those who are venturing into this field of research.

Download Full-text

EEG-based emotion recognition with deep convolutional neural networks

Biomedical Engineering / Biomedizinische Technik ◽

10.1515/bmt-2019-0306 ◽

2020 ◽

Vol 0 (0) ◽

Author(s):

Mehmet Akif Ozdemir ◽

Murside Degirmenci ◽

Elif Izci ◽

Aydin Akan

Keyword(s):

Neural Networks ◽

Emotion Recognition ◽

Convolutional Neural Networks ◽

Spatial Information ◽

Emotional State ◽

Human Interaction ◽

Emotional States ◽

Eeg Signals ◽

Deep Convolutional Neural Networks ◽

Spectral Topology

AbstractThe emotional state of people plays a key role in physiological and behavioral human interaction. Emotional state analysis entails many fields such as neuroscience, cognitive sciences, and biomedical engineering because the parameters of interest contain the complex neuronal activities of the brain. Electroencephalogram (EEG) signals are processed to communicate brain signals with external systems and make predictions over emotional states. This paper proposes a novel method for emotion recognition based on deep convolutional neural networks (CNNs) that are used to classify Valence, Arousal, Dominance, and Liking emotional states. Hence, a novel approach is proposed for emotion recognition with time series of multi-channel EEG signals from a Database for Emotion Analysis and Using Physiological Signals (DEAP). We propose a new approach to emotional state estimation utilizing CNN-based classification of multi-spectral topology images obtained from EEG signals. In contrast to most of the EEG-based approaches that eliminate spatial information of EEG signals, converting EEG signals into a sequence of multi-spectral topology images, temporal, spectral, and spatial information of EEG signals are preserved. The deep recurrent convolutional network is trained to learn important representations from a sequence of three-channel topographical images. We have achieved test accuracy of 90.62% for negative and positive Valence, 86.13% for high and low Arousal, 88.48% for high and low Dominance, and finally 86.23% for like–unlike. The evaluations of this method on emotion recognition problem revealed significant improvements in the classification accuracy when compared with other studies using deep neural networks (DNNs) and one-dimensional CNNs.

Download Full-text

Emotion Recognition in EEG Signals Using Decision Fusion Based Electrode Selection

Studies in Health Technology and Informatics - Public Health and Informatics ◽

10.3233/shti210139 ◽

2021 ◽

Author(s):

Himanshu Kumar ◽

Nagarajan Ganapathy ◽

Subha D. Puthankattil ◽

Ramakrishnan Swaminathan

Keyword(s):

Random Forest ◽

Emotion Recognition ◽

Evidence Theory ◽

Decision Fusion ◽

Intellectual Ability ◽

Emotional States ◽

Human Beings ◽

Eeg Signals ◽

Electrode Selection

Emotions are essential for the intellectual ability of human beings defined by perception, concentration, and actions. Electroencephalogram (EEG) responses have been studied in different lobes of the brain for emotion recognition. An attempt has been made in this work to identify emotional states using time-domain features, and probabilistic random forest based decision fusion. The EEG signals are collected for this from an online public database. The prefrontal and frontal electrodes, namely Fp1, Fp2, F3, F4, and Fz are considered. Eleven features are extracted from each electrode, and subjected to a probabilistic random forest. The probabilities are employed to Dempster-Shafer’s (D-S) based evidence theory for electrode selection using decision fusion. Results demonstrate that the method suggested is capable of classifying emotional states. The decision fusion based electrode selection appears to be most accurate (arousal F-measure = 77.9%) in classifying the emotional states. The combination of Fp2, F3, and F4 electrodes yields higher accuracy for characterizing arousal (65.1%) and valence (57.9%) dimension. Thus, the proposed method can be used to select the critical electrodes for the classification of emotions.

Download Full-text

Status of Centrifugal Impeller Internal Aerodynamics—Part II: Experiments and Influence of Viscosity

Journal of Engineering for Power ◽

10.1115/1.3230333 ◽

1980 ◽

Vol 102 (3) ◽

pp. 738-746 ◽

Cited By ~ 3

Author(s):

D. Adler

Keyword(s):

Viscous Flow ◽

Experimental Work ◽

State Of The Art ◽

Centrifugal Impeller ◽

Future Research ◽

Research Topics ◽

Flow Problems ◽

Recent Developments ◽

Internal Aerodynamics ◽

The Subject

Recent developments in internal viscous aerodynamics of centrifugal impellers and related flows are critically reviewed. The overall picture which emerges provides the reader with a state-of-the-art perspective on the subject. Gaps in understanding are identified to stimulate future research. Topics included in this review are: experimental work carried out in the last decade, the structure of turbulence in curved rotating passages and solution of viscous flow problems in impellers.

Download Full-text

Recognition of Emotional States using Multiscale Information Analysis of High Frequency EEG Oscillations

Entropy ◽

10.3390/e21060609 ◽

2019 ◽

Vol 21 (6) ◽

pp. 609 ◽

Cited By ~ 4

Author(s):

Gao ◽

Cui ◽

Wan ◽

Keyword(s):

Emotion Recognition ◽

High Frequency ◽

Low Frequency ◽

Support Vector ◽

Discrete Wavelet ◽

Emotional States ◽

Circumplex Model ◽

Information Analysis ◽

Eeg Signals ◽

High Frequency Oscillations

Exploring the manifestation of emotion in electroencephalogram (EEG) signals is helpful for improving the accuracy of emotion recognition. This paper introduced the novel features based on the multiscale information analysis (MIA) of EEG signals for distinguishing emotional states in four dimensions based on Russell's circumplex model. The algorithms were applied to extract features on the DEAP database, which included multiscale EEG complexity index in the time domain, and ensemble empirical mode decomposition enhanced energy and fuzzy entropy in the frequency domain. The support vector machine and cross validation method were applied to assess classification accuracy. The classification performance of MIA methods (accuracy = 62.01%, precision = 62.03%, recall/sensitivity = 60.51%, and specificity = 82.80%) was much higher than classical methods (accuracy = 43.98%, precision = 43.81%, recall/sensitivity = 41.86%, and specificity = 70.50%), which extracted features contain similar energy based on a discrete wavelet transform, fractal dimension, and sample entropy. In this study, we found that emotion recognition is more associated with high frequency oscillations (51–100Hz) of EEG signals rather than low frequency oscillations (0.3–49Hz), and the significance of the frontal and temporal regions are higher than other regions. Such information has predictive power and may provide more insights into analyzing the multiscale information of high frequency oscillations in EEG signals.

Download Full-text

State of the Art in Alcohol Sensing with 2D Materials

Nano-Micro Letters ◽

10.1007/s40820-019-0363-0 ◽

2020 ◽

Vol 12 (1) ◽

Cited By ~ 12

Author(s):

Ramin Boroujerdi ◽

Amor Abdelkader ◽

Richard Paul

Keyword(s):

State Of The Art ◽

2D Materials ◽

Chemical Species ◽

Weight Ratio ◽

Layered Compounds ◽

Single Atom ◽

Future Research ◽

Essential Factor ◽

New Materials ◽

Recent Developments

AbstractSince the discovery of graphene, the star among new materials, there has been a surge of attention focused on the monatomic and monomolecular sheets which can be obtained by exfoliation of layered compounds. Such materials are known as two-dimensional (2D) materials and offer enormous versatility and potential. The ultimate single atom, or molecule, thickness of the 2D materials sheets provides the highest surface to weight ratio of all the nanomaterials, which opens the door to the design of more sensitive and reliable chemical sensors. The variety of properties and the possibility of tuning the chemical and surface properties of the 2D materials increase their potential as selective sensors, targeting chemical species that were previously difficult to detect. The planar structure and the mechanical flexibility of the sheets allow new sensor designs and put 2D materials at the forefront of all the candidates for wearable applications. When developing sensors for alcohol, the response time is an essential factor for many industrial and forensic applications, particularly when it comes to hand-held devices. Here, we review recent developments in the applications of 2D materials in sensing alcohols along with a study on parameters that affect the sensing capabilities. The review also discusses the strategies used to develop the sensor along with their mechanisms of sensing and provides a critique of the current limitations of 2D materials-based alcohol sensors and an outlook for the future research required to overcome the challenges.

Download Full-text

Machine-Learning-Based Emotion Recognition System Using EEG Signals

Computers ◽

10.3390/computers9040095 ◽

2020 ◽

Vol 9 (4) ◽

pp. 95

Author(s):

Rania Alhalaseh ◽

Suzan Alasasfeh

Keyword(s):

Signal Processing ◽

Feature Extraction ◽

Emotion Recognition ◽

Emotional States ◽

Eeg Signals ◽

Processing Stage ◽

Brain Signals ◽

Specificity And Sensitivity ◽

Mode Decomposition ◽

Proposed Model

Many scientific studies have been concerned with building an automatic system to recognize emotions, and building such systems usually relies on brain signals. These studies have shown that brain signals can be used to classify many emotional states. This process is considered difficult, especially since the brain’s signals are not stable. Human emotions are generated as a result of reactions to different emotional states, which affect brain signals. Thus, the performance of emotion recognition systems by brain signals depends on the efficiency of the algorithms used to extract features, the feature selection algorithm, and the classification process. Recently, the study of electroencephalography (EEG) signaling has received much attention due to the availability of several standard databases, especially since brain signal recording devices have become available in the market, including wireless ones, at reasonable prices. This work aims to present an automated model for identifying emotions based on EEG signals. The proposed model focuses on creating an effective method that combines the basic stages of EEG signal handling and feature extraction. Different from previous studies, the main contribution of this work relies in using empirical mode decomposition/intrinsic mode functions (EMD/IMF) and variational mode decomposition (VMD) for signal processing purposes. Despite the fact that EMD/IMFs and VMD methods are widely used in biomedical and disease-related studies, they are not commonly utilized in emotion recognition. In other words, the methods used in the signal processing stage in this work are different from the methods used in literature. After the signal processing stage, namely in the feature extraction stage, two well-known technologies were used: entropy and Higuchi’s fractal dimension (HFD). Finally, in the classification stage, four classification methods were used—naïve Bayes, k-nearest neighbor (k-NN), convolutional neural network (CNN), and decision tree (DT)—for classifying emotional states. To evaluate the performance of our proposed model, experiments were applied to a common database called DEAP based on many evaluation models, including accuracy, specificity, and sensitivity. The experiments showed the efficiency of the proposed method; a 95.20% accuracy was achieved using the CNN-based method.

Download Full-text

A Review of Toxins from Cnidaria

Marine Drugs ◽

10.3390/md18100507 ◽

2020 ◽

Vol 18 (10) ◽

pp. 507 ◽

Cited By ~ 1

Author(s):

Isabella D’Ambra ◽

Chiara Lauritano

Keyword(s):

State Of The Art ◽

Skin Irritation ◽

The State ◽

Future Research ◽

Human Beings ◽

Lethal Effects ◽

Ancient Times ◽

Definition Of ◽

Available Information

Cnidarians have been known since ancient times for the painful stings they induce to humans. The effects of the stings range from skin irritation to cardiotoxicity and can result in death of human beings. The noxious effects of cnidarian venoms have stimulated the definition of their composition and their activity. Despite this interest, only a limited number of compounds extracted from cnidarian venoms have been identified and defined in detail. Venoms extracted from Anthozoa are likely the most studied, while venoms from Cubozoa attract research interests due to their lethal effects on humans. The investigation of cnidarian venoms has benefited in very recent times by the application of omics approaches. In this review, we propose an updated synopsis of the toxins identified in the venoms of the main classes of Cnidaria (Hydrozoa, Scyphozoa, Cubozoa, Staurozoa and Anthozoa). We have attempted to consider most of the available information, including a summary of the most recent results from omics and biotechnological studies, with the aim to define the state of the art in the field and provide a background for future research.

Download Full-text

Recognizing More Emotions with Less Data Using Self-supervised Transfer Learning

10.20944/preprints202008.0645.v1 ◽

2020 ◽

Author(s):

Jonathan Boigne ◽

Biman Liyanage ◽

Ted Östrem

Keyword(s):

Neural Network ◽

Emotion Recognition ◽

Transfer Learning ◽

Network Performance ◽

State Of The Art ◽

Research Community ◽

Training Data ◽

Linguistic Knowledge ◽

Speech Emotion Recognition ◽

Learning Method

We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher accuracy than a strong baseline trained on 8 times more data. Our method leverages knowledge contained in pre-trained speech representations extracted from models trained on a more general self-supervised task which doesn’t require human annotations, such as the wav2vec model. We provide detailed insights on the benefits of our approach by varying the training data size, which can help labeling teams to work more efficiently. We compare performance with other popular methods on the IEMOCAP dataset, a well-benchmarked dataset among the Speech Emotion Recognition (SER) research community. Furthermore, we demonstrate that results can be greatly improved by combining acoustic and linguistic knowledge from transfer learning. We align acoustic pre-trained representations with semantic representations from the BERT model through an attention-based recurrent neural network. Performance improves significantly when combining both modalities and scales with the amount of data. When trained on the full IEMOCAP dataset, we reach a new state-of-the-art of 73.9% unweighted accuracy (UA).

Download Full-text

Emotion Recognition from EEG Signals Using Multidimensional Information in EMD Domain

BioMed Research International ◽

10.1155/2017/8317357 ◽

2017 ◽

Vol 2017 ◽

pp. 1-9 ◽

Cited By ~ 63

Author(s):

Ning Zhuang ◽

Ying Zeng ◽

Li Tong ◽

Chi Zhang ◽

Hanming Zhang ◽

...

Keyword(s):

Emotion Recognition ◽

Recognition Performance ◽

Frequency Component ◽

High Frequency Component ◽

Discrete Wavelet ◽

Emotional States ◽

Intrinsic Mode Functions ◽

Eeg Signals ◽

Mode Decomposition ◽

Multidimensional Information

This paper introduces a method for feature extraction and emotion recognition based on empirical mode decomposition (EMD). By using EMD, EEG signals are decomposed into Intrinsic Mode Functions (IMFs) automatically. Multidimensional information of IMF is utilized as features, the first difference of time series, the first difference of phase, and the normalized energy. The performance of the proposed method is verified on a publicly available emotional database. The results show that the three features are effective for emotion recognition. The role of each IMF is inquired and we find that high frequency component IMF1 has significant effect on different emotional states detection. The informative electrodes based on EMD strategy are analyzed. In addition, the classification accuracy of the proposed method is compared with several classical techniques, including fractal dimension (FD), sample entropy, differential entropy, and discrete wavelet transform (DWT). Experiment results on DEAP datasets demonstrate that our method can improve emotion recognition performance.

Download Full-text

Education

The Oxford Handbook of Modern Greek Politics ◽

10.1093/oxfordhb/9780198825104.013.34 ◽

2020 ◽

pp. 534-549

Author(s):

Theofanis Exadaktylos

Keyword(s):

Higher Education ◽

Financial Crisis ◽

Policy Implementation ◽

State Of The Art ◽

Future Research ◽

Policy Area ◽

Political Debates ◽

Recent Developments ◽

New Curricula

The purpose of this chapter is to provide a ‘state of the art’ contribution about education in Greece, reviewing recent developments and reforms. As a policy area, education remains highly controversial in Greece from developing new curricula to the politicization of higher education. The chapter reflects on the pedagogical and political debates of the recent decades focusing on issues of policy implementation. It highlights the most recent round of reforms since 2011 including those resulting from the advent of Syriza to power, and looks at the period of the financial crisis to discuss issues of funding, the bailout agreements, and neoliberal ideas behind higher education. The chapter concludes by offering some suggestions for future research and sets out some of the respective challenges.

Download Full-text