Discrete Wavelet Transform coefficients for emotion recognition from EEG signals

Epilepsy is one of the frequent brain disorder that may consequence in the brain dysfunction and cognitive disorders. Epileptic seizures can occur due to transient and unexpected electrical interruptions of brain. EEG (ElectroEncephaloGram) is one of the non-invasive methods for analyzing the human brain dynamics that affords a direct evaluation of cortical behavior. Seizures are featured by short and episodic neuronal synchronous discharges with considerably enlarged amplitude. This uneven synchrony may happen in the brain accordingly i.e., partial seizures visible only in few channels of the EEG signal or generalized seizures, which are seen in every channel of the EEG signal involving the whole brain. Existing analysis of epilepsy depends on difficult visual screening by extremely trained clinicians. Data recordings create very lengthy data, and therefore the inspection and identification of epilepsy takes more time for diagnosis. At present time computerized systems are usually established to make the diagnosis simpler. This paper discusses an implementation of automated epileptic EEG detection system using neural networks. In this paper, a statistical parameter regarded as Sample Entropy (SampEn), is used as a method for feature extraction for performing the task of classifying EEG signals, which are normal, ictal and interictal. Here the value of SampleEn plays a vital role in the diagnosis of Epileptic seizures. It is been observed that the value of SampEn falls suddenly during an Epileptic Seizure, and hence this information delineates the exact occurrence of Epilepsy. Classification strategies are based on models like Back-propagation Neural Network (BPNN),Support Vector Machine(SVM) and Extreme Learning Machine (ELM). Hybrid ELM (HELM) is the classification method devised in the current paper and is the first of its kind to be implemented for EEG classification. This classification method uses the Analytical Hierarchy Process (AHP) method to select the input weights and hidden biases, the ELM algorithm to analytically determine the output weights and the Levenberg-Marquardt (LM) algorithm to learn the network. Experimental results show that automatic epilepsy detection using sample entropy (SampEn) and Hybrid ELM achieves better accuracy in lesser time.

Epilepsy is the most common neurological disorder characterized by recurrent seizures due to the abnormality of brain neuronal discharge. One of the tools to help neurologists diagnose epilepsy relies on EEG signals extensively because it can represent the brain's neuron activity. Due to the EEG signal being considered a complex biological signal, the signal complexity-based feature extraction method is suitable for characterizing epileptic EEG signals. One method for extracting EEG signals is entropy which is able to quantify signal complexity. Several previously proposed methods were wavelet entropy and IMF entropy. This study proposed multi-distance signal level difference (MSLD) entropy as a feature extraction method to extract the EEG signal complexity. The decomposed signal from MSLD was then extracted using entropy measurement. In the classification process, a Support Vector Machine (SVM) was applied to classify the normal, pre-ictal, and ictal signals of EEG signals. The highest accuracy of 96% was obtained using cubic SVM as the classifier. The proposed method provides an alternative method for analyzing EEG or other biomedical signals based on signal complexity.

Emotion recognition from single-channel EEG signals using a two-stage correlation and instantaneous frequency-based filtering method

This study employed electronic nose (E-nose) to detect tea plants with different types of damage (undamaged, mechanically damaged, damages caused by Ectropis obliqua and Ectropis grisescens). Gas chromatography–mass spectrometry was employed as an auxiliary technique for proving the potential of E-nose detection. A new feature extraction method was applied for obtaining comprehensive features of E-nose dataset. Feature selection method based on principal component analysis (PCA) was applied for further feature selection. Four dimensionality reduction methods [PCA, locality preserving projections (LPP), kernel principal component analysis and locally linear embedding] and three classification algorithms [multilayer perceptron neural network, extreme learning machine and support vector machine (SVM)] were employed, and the best combination of dimensionality reduction method and classification algorithm was determined. The results showed that the combination of LPP and SVM was the best, and its correct discrimination rate was as high as 100%, which proved the advantage of the new signal processing method and the feasibility of E-nose in discriminating among tea plants with different types of damage.

The ability to identify or predict a target audience from the increasingly crowded social space will provide a company some competitive advantage over other companies. In this paper, we analyze various training datasets, which include Twitter contents of an account owner and its list of followers, using features generated in different ways for two machine learning approaches - the Extreme Learning Machine (ELM) and Support Vector Machine (SVM). Various configurations of the ELM and SVM have been evaluated. The results indicate that training datasets using features generated from the owner tweets achieve the best performance, relative to other feature sets. This finding is important and may aid researchers in developing a classifier that is capable of identifying a specific group of target audience members. This will assist the account owner to spend resources more effectively, by sending offers to the right audience, and hence maximize marketing efficiency and improve the return on investment.

Paraffin odor intensity is an important quality indicator when a paraffin inspection is performed. Currently, paraffin odor level assessment is mainly dependent on an artificial sensory evaluation. In this paper, we developed a paraffin odor analysis system to classify and grade four kinds of paraffin samples. The original feature set was optimized using Principal Component Analysis (PCA) and Partial Least Squares (PLS). Support Vector Machine (SVM), Random Forest (RF), and Extreme Learning Machine (ELM) were applied to three different feature data sets for classification and level assessment of paraffin. For classification, the model based on SVM, with an accuracy rate of 100%, was superior to that based on RF, with an accuracy rate of 98.33–100%, and ELM, with an accuracy rate of 98.01–100%. For level assessment, the R2 related to the training set was above 0.97 and the R2 related to the test set was above 0.87. Through comprehensive comparison, the generalization of the model based on ELM was superior to those based on SVM and RF. The scoring errors for the three models were 0.0016–0.3494, lower than the error of 0.5–1.0 measured by industry standard experts, meaning these methods have a higher prediction accuracy for scoring paraffin level.

Human emotion is the mind's reaction to external stimuli. Since human emotions are dynamic and hard to predict in the real world, studies focusing on this area have gained a lot of importance. Emotion recognition using EEG(electroencephalogram) signals has recently seen prevalent use of many deep learning and machine learning techniques.In this paper, we have used a real time dataset which includes 15 subjects (7 Males and 8 Females) and their EEG signals are recorded using video stimuli. The real time data is preprocessed and features are extracted from the preprocessed data using different feature extraction methods. The accuracy and loss of model are calculated and compared with raw and preprocessed data. The proposed model - EEGEM (Electroencephalogram Ensemble Model) is compared with other machine and deep learning techniques. EEGEM is a ensemble model with the combination of LSTM and CNN together to achieve the desired output. The accuracy achieved using this model is 95.56% and it has outperformed other existing models.

EEG-based human recognition is increasingly becoming a popular modality for biometric authentication. Two important features of EEG signals are liveliness and the robustness against falsification. However, a comprehensive study on human authentication using EEG signal is still remains. On the other hand, low-cost wireless EEG recording devices are now growing in the market places. Although these devices have the potential to many applications, researches have yet to be done to find the feasibility of these devices. In this study, we propose a method for human identification using EEG signals obtained from such low-cost devices. EEG signal is first preprocessed to remove noise and artifacts using Bandpass FIR filter. These signals are then divided into disjoint segments. Three feature extraction methods, namely multiscale shape description (MSD), multiscale wavelet packet statistics (WPS) and multiscale wavelet packet energy statistics (WPES) are then applied. These features are finally used to train a supervised error-correcting output code multiclass model (ECOC) using support vector machine (SVM) classifier, which ultimately can recognize humans from test EEG signals. A preliminary experiment with 9 EEG records from 9 subjects shows the true positive rate of 94.44% of the proposed method.

Emotion recognition is a challenging task, and the use of multimodal fusion methods for emotion recognition has become a trend. Fusion vectors can provide a more comprehensive representation of changes in the subject's emotional state, leading to more accurate emotion recognition results. Different fusion inputs or feature fusion methods have varying effects on the final fusion outcome. In this paper, we propose a novel Multimodal Feature Fusion Neural Network model (MFFNN) that effectively extracts complementary information from eye movement signals and performs feature fusion with EEG signals. We construct a dual-branch feature extraction module to extract features from both modalities while ensuring temporal alignment. A multi-scale feature fusion module is introduced, which utilizes cross-channel soft attention to adaptively select information from different spatial scales, enabling the acquisition of features at different spatial scales for effective fusion. We conduct experiments on the publicly available SEED-IV dataset, and our model achieves an accuracy of 87.32% in recognizing four emotions (happiness, sadness, fear, and neutrality). The results demonstrate that the proposed model can better explore complementary information from EEG and eye movement signals, thereby improving accuracy, and stability in emotion recognition.

Background. Migraine disease is the second most common cause of headaches. Despite the high prevalence, the exact etiology of migraine is yet unknown. In this study, to evaluate the behavior change of electroencephalography (EEG) signals in migraine patients, various features of the EEG signals of migraine patients and healthy controls (HCs) were extracted and compared. Methods. This cross-sectional analytical study was conducted on 21 HCs and 18 migraine patients. Various features, such as fractal dimension (FD), approximate entropy (ApEn), and largest Lyapunov exponent (LLE), were calculated from the EEG signals of migraine patients and HCs. Then different frequency sub-bands of delta, theta, alpha, beta, and gamma were extracted using the wavelet transform, and the energy of these sub-bands was computed. By calculating the mean and variance of the features and applying statistical tests, the feature changes were compared between two groups, and channels with significant differences were identified. Results. The mean of ApEn, FD and energy of all frequency sub-bands in most of the analyzed channels was higher in migraine patients than in HCs. The mean LLE was mostly lower in migraine patients than in healthy controls. According to the statistical tests, the energy of theta and delta frequency sub-bands with 36 and 35 channels was the feature with the highest number of channels, with a significant difference. In this study, P values less than 0.05 were considered statistically significant. Conclusion. Migraine patients may have a less sophisticated brain dynamic system due to an increase in irregularity and randomness, as indicated by an increase in ApEn and a decrease in FD in their EEG signals compared to HCs. Anxiety, tension, and other intense sentiments and emotions, as well as the creation of new neural circuits in the brain, can all contribute to an overall increase in energy across all frequency sub-bands in migraine patients. Practical Implications. Considering the EEG signal behavior as the response of a dynamic system, we can say that the brain function of migraine patients, even in the inter-ictal phase, leaves the definite chaotic state, which is a healthy brain behavior, and enters the random state.

The rapid growth of wavelets and machine learning algorithms in the field of medical sciences like cardiology have encouraged researchers for fast and effective classification of heart irregularities. Electrocardiogram (ECG) is a non-linear pattern which confines critical information regarding cardiac functions. It has to be analyzed and examined profoundly for equitable diagnosis. In this paper, Dual Tree Complex Wavelet Transform (DTCWT) and Linear Discriminant Analysis (LDA) are used as a hybrid pair for ECG feature extraction. The Support Vector Machine (SVM) and Extreme Learning Machine (ELM) are effectually employed as classifiers to distinguish ECG as a normal and abnormal class. The simulated outcome shows that linear behavior of SVM and ELM results in better ECG analysis as compared to radial basis function (RBF). In addition, the performance comparison illustrates that SVM outperforms ELM in terms of accuracy while ELM clearly outperforms SVM in the time taken for training and testing of MIT/BIH dataset.

Electroencephalogram (EEG) emotion recognition based on a hybrid feature extraction method in empirical mode decomposition domain combining with optimal feature selection based on sequence backward selection is proposed, which can reflect subtle information of multiscale components of unstable and nonlinear EEG signals and remove the reductant features to improve the performance of emotion recognition. The proposal is tested on DEAP dataset, in which the emotional states in the Valance dimension and Arousal dimension are classified by both ${K}$ -nearest neighbor and support vector machine, respectively. In the experiments, temporal windows of different length and three kinds of rhythms of EEG signal are taken into account for comparison, from which the results show that EEG signal with 1s temporal window achieves highest recognition accuracy of 86.46% in Valence dimension and 84.90% in Arousal dimension, respectively, which is superior to some state-of-the-art works. The proposed method would be applied to real-time emotion recognition in multimodal emotional communication-based humans–robots interaction system.

Nowadays, electroencephalogram (EEG) signals are the major part of recognizing emotions as the signals contain more brain-related information. Several traditional recognition methodologies have been developed, but still, exist with certain challenges that degrade and mislead the recognition process. Some models are facing issues based on insignificant features, poor generalization capability, and computational burden. To alleviate such issues, an effective emotion recognition model is proposed using a heuristic-aided transformer-based approach. Initially, the input EEG signals are gathered and decomposed via the 5-level Discrete Wavelet Transform (DWT). Then, the decomposed signals are fed to the feature extraction process, where the feature extraction is carried out by using Logistic Regression (LR) approach. From the decomposed signals, the Logistic Regression (LR) is used for getting the noteworthy features and then, the same decomposed signals are fed to the optimal weighted feature selection, which is carried out using Adaptive Bald Eagle Search Optimization (ABESO) algorithm. Subsequently, the hybrid weighted feature selection approach is introduced for getting the weighted features, where the weight is optimized with the adoption of the ABESO algorithm. At last, the selected hybrid weighted features are sent to the recognition phase, where the Optimized Block Recurrent Transformer (OBRT), where performance gets enhanced by tuning the parameter with the developed ABESO algorithm. The accuracy and precision rate of the designed approach are attained as 96% and 94%. The performance of the model is assessed and the findings have shown that better performance that makes the system more feasible to recognize human emotions.

The key to electroencephalogram(EEG) emotion recognition lies not only in the quality of the downstream model, but also in whether the features of the upstream input have classification identifiability. Due to the volume conduction effect, only the time domain or frequency domain features of EEG are used for emotion recognition, and the effect is not obvious. Therefore, this study use microstate features based on source localization with spatiotemporal, including time coverage, duration, occurrence and transition probability between different source microstates. We extract the source space microstate features of SEED and SEED-IV data in two ways : cross subject and within subject, respectively, and use them as the input of convolutional neural network(CNN) and support vector machine(SVM) for emotion classification. We also compare the p * values between the sub-features of the source space microstate to explore the physiological mechanism of emotion. The research confirms the significant advantages of source microstate features in emotion recognition, and it also implies the physiological significance between the microstate and emotion in the source space.

Emotion recognition refers to the process of determining and identifying an individual's current emotional state by analyzing various signals such as voice, facial expressions, and physiological indicators etc. Using electroencephalogram (EEG) signals and virtual reality (VR) technology for emotion recognition research helps to better understand human emotional changes, enabling applications in areas such as psychological therapy, education, and training to enhance people's quality of life. However, there is a lack of comprehensive review literature summarizing the combined researches of EEG signals and VR environments for emotion recognition. Therefore, this paper summarizes and synthesizes relevant research from the past five years. Firstly, it introduces the relevant theories of VR and EEG signal emotion recognition. Secondly, it focuses on the analysis of emotion induction, feature extraction, and classification methods in emotion recognition using EEG signals within VR environments. The article concludes by summarizing the research's application directions and providing an outlook on future development trends, aiming to serve as a reference for researchers in related fields.