Exploring principal component analysis and convolutional neural network (PCA-CNN) based architecture for enhanced emotion classification in EEG signal extraction

Emotions play a vital role in recognizing a person’s thoughts and vary significantly with stress levels. Emotion and stress classification have gained considerable attention in robotics and artificial intelligence applications. While numerous methods based on machine learning techniques provide average classification performance, recent deep learning approaches offer enhanced results. This research presents a hybrid deep learning model that extracts features using AlexNet and DenseNet models, followed by feature fusion and dimensionality reduction via Principal Component Analysis (PCA). The reduced features are then classified using a multi-class Support Vector Machine (SVM) to categorize different types of emotions. The proposed model was evaluated using the DEAP and EEG Brainwave datasets, both well-suited for emotion analysis due to their comprehensive EEG signal recordings and diverse emotional stimuli. The DEAP dataset includes EEG signals from 32 participants who watched 40 one-minute music videos, while the EEG Brainwave dataset categorizes emotions into positive, negative, and neutral based on EEG recordings from participants exposed to six different film clips. The proposed model achieved an accuracy of 95.54% and 97.26% for valence and arousal categories in the DEAP dataset, respectively, and 98.42% for the EEG Brainwave dataset. These results significantly outperform existing methods, demonstrating the model’s superior performance in terms of precision, recall, F1-score, specificity, and Mathew correlation coefficient. The integration of AlexNet and DenseNet, combined with PCA and multi-class SVM, makes this approach particularly effective for capturing the intricate patterns in EEG data, highlighting its potential for applications in human-computer interaction and mental health monitoring, marking a significant advancement over traditional methods.

Emotion recognition (ER) is crucial for understanding human behaviours, social interactions, and psychological well-being. Electroencephalography (EEG) has emerged as a promising tool for capturing the neural correlates of emotions. This work is a systematic review of articles in ER using EEG signals. A total of 120 articles from 1041 articles were selected based on PRISMA guidelines using defined inclusion and exclusion criteria, published between 2018 and 2024. This article aims to provide an in-depth understanding of the current landscape of ER from EEG signals utilizing deep learning (DL). This review offers valuable guidance for researchers and practitioners seeking more refined and reliable emotion classification systems. To explore the effectiveness of DL models in EEG-based ER, several potential DL models, such as convolutional neural network, long short-term memory (LSTM), gated recurrent unit (GRU), hybrid bidirectional LSTM (BiLSTM), bidirectional GRU, and advanced DL models such as convolutional recurrent neural network and EEG-Conformer models are applied to two popular datasets, SEED and GAMEEMO, respectively, to depict the full process of ER. Additionally, the performance of DL models is also compared with the performance of basic machine learning (ML) models such as SVM, k-nearest neighbors, logistic regression, and boosting algorithms such as AdaBoost, XGBoost and LightGBM. Through extensive experiments and performance evaluations, the performance of different models when applied to the datasets mentioned above is compared. The accuracy, precision, recall, and F1-scores are analysed to determine the most effective model for EEG-based ER. The findings of this study demonstrate that the performance of hybrid DL models is more efficacious than that of ML models. The best-performing model (BiLSTM) classified the emotions, with an accuracy of 90.54% when applied to the GAMEEMO dataset. This research contributes to the growing body of literature on ER and provides insights into the feasibility of using EEG signals to understand emotional states, and presents a structured roadmap for future exploration. The findings can aid in the development of more accurate and reliable ER systems, which can have wide-ranging applications in psychology, social sciences, and human-computer interactions.

Automated accurate emotion recognition system using rhythm-specific deep convolutional neural network technique with multi-channel EEG signals

Aims: Plants are often exposed to environmental stresses.In order to survive, plants must adapt to these hostile environments by developing morphological, structural, and physiological traits that enable the plants to becomecompatible with their habitats.While there are many methods that would allow researchers can gain insight into the plants' adaptive strategies, there has not a comparative analysis of these methods.To fill this gap in the literature, we collected articles from the thirteen years on seven methods that are commonly used to evaluate plant stress tolerance:(1) average membership function value, (2) cluster analysis, (3) fuzzy comprehensive evaluation (based on membership function and weights), (4) principal component analysis, (5) composite evaluation (combining membership function and principal component analysis), ( 6) convolutional neural network, and (7) grey relational analysis.Our objectives are to examine these methods' main principles, key steps, advantages, and disadvantages.The overall goal is to select appropriate evaluation methods according to different research purposes and data characteristics, and to provide some theoretical basis for the accurate evaluation of plant resilience.Review results: Our results indicated that fuzzy mathematics is an important theoretical foundation in the three methods (i.e., average membership function value, fuzzy comprehensive evaluation (based on membership function and weights), and composite evaluation (combining membership function and principal component analysis) are based on fuzzy mathematics theory).By using trait fuzzification, these methods enable researchers to establish models demonstrating how plant traits may affect plant resilience.We found that over half the models enable trait selection (i.e., average membership function value, principal component analysis, composite evaluation (combining membership function and principal component analysis), and grey relational analysis).Conclusion: Average membership function value and gray relational analysis are often used for small sample data sets, and principal component analysis and convolutional neural network are often used for large sample data sets.Principal component analysis and cluster analysis can enable researchers to present their data in easily-interpretable visuals.Currently, the most commonly used method in the domestic biological field is the composite evaluation (combining membership function and principal component analysis).This literature review revealed that these seven methods have strengths that can be used to complement each other during evaluations of plant traits, allowing researchers to select evaluation methods that are tailored to specific research objectives and data characteristics.

Emotion recognition using EEG signals is a critical task with wide-ranging applications in mental health monitoring, disorders of consciousness, and neurofeedback systems. However, EEG signals are inherently noisy and high-dimensional, posing persistent challenges to accurate emotion classification. Most existing approaches rely on limited preprocessing or employ Principal Component Analysis (PCA) solely for dimensionality reduction, often overlooking the residual artifacts that degrade classifier performance. This study introduces a novel PCA-RF framework that repurposes PCA for dual objectives: targeted noise suppression and feature dimensionality reduction. Uniquely, PCA is applied after frequency-specific filtering to more effectively eliminate residual ocular and cardiac artifacts, thus improving the quality of EEG feature representations. These compact and denoised features are then processed by a Random Forest (RF) classifier, which robustly captures the nonlinear dynamics of the EEG data. Evaluated on the DEAP dataset, the proposed PCA-RF approach achieved state-of-the-art performance, with 96.57% accuracy for arousal and 96.03% for valence classification. The key contribution of this work lies in its strategic integration of PCA for both artifact suppression and feature optimization, setting it apart from conventional pipelines and delivering a reliable and accurate solution for EEG-based emotion recognition.

In recent decades, the automatic emotion state classification is an important technology for human-machine interactions. In Electroencephalography (EEG) based emotion classification, most of the existing methodologies cannot capture the context information of the EEG signal and ignore the correlation information between dissimilar EEG channels. Therefore, in this study, a deep learning based automatic method is proposed for effective emotion state classification. Firstly, the EEG signals were acquired from the real time and databases for emotion analysis using physiological signals (DEAP), and further, the band-pass filter from 0.3 Hz to 45 Hz is utilized to eliminate both high and low-frequency noise. Next, two feature extraction techniques power spectral density and differential entropy were employed for extracting active feature values, which effectively learn the contextual and spatial information of EEG signals. Finally, principal component analysis and artificial neural network were developed for feature dimensionality reduction and emotion state classification. The experimental evaluation showed that the proposed method achieved 96.38% and 97.36% of accuracy on DEAP, and 92.33% and 89.37% of accuracy on a real-time database for arousal and valence emotion states. The achieved recognition accuracy is higher compared to the support vector machine on both databases.

The electroencephalogram (EEG) has great attraction in emotion recognition studies due to its resistance to deceptive actions of humans. This is one of the most significant advantages of brain signals in comparison to visual or speech signals in the emotion recognition context. A major challenge in EEG-based emotion recognition is that EEG recordings exhibit varying distributions for different people as well as for the same person at different time instances. This nonstationary nature of EEG limits the accuracy of it when subject independency is the priority. The aim of this study is to increase the subject-independent recognition accuracy by exploiting pretrained state-of-the-art Convolutional Neural Network (CNN) architectures. Unlike similar studies that extract spectral band power features from the EEG readings, raw EEG data is used in our study after applying windowing, pre-adjustments and normalization. Removing manual feature extraction from the training system overcomes the risk of eliminating hidden features in the raw data and helps leverage the deep neural network’s power in uncovering unknown features. To improve the classification accuracy further, a median filter is used to eliminate the false detections along a prediction interval of emotions. This method yields a mean cross-subject accuracy of 86.56% and 78.34% on the Shanghai Jiao Tong University Emotion EEG Dataset (SEED) for two and three emotion classes, respectively. It also yields a mean cross-subject accuracy of 72.81% on the Database for Emotion Analysis using Physiological Signals (DEAP) and 81.8% on the Loughborough University Multimodal Emotion Dataset (LUMED) for two emotion classes. Furthermore, the recognition model that has been trained using the SEED dataset was tested with the DEAP dataset, which yields a mean prediction accuracy of 58.1% across all subjects and emotion classes. Results show that in terms of classification accuracy, the proposed approach is superior to, or on par with, the reference subject-independent EEG emotion recognition studies identified in literature and has limited complexity due to the elimination of the need for feature extraction.

Multimodal emotion recognition has become a hot topic in human-computer interaction and intelligent healthcare fields. However, combining information from different human different modalities for emotion computation is still challenging. In this paper, we propose a three-dimensional convolutional recurrent neural network model (referred to as 3FACRNN network) based on multimodal fusion and attention mechanism. The 3FACRNN network model consists of a visual network and an EEG network. The visual network is composed of a cascaded convolutional neural network-time convolutional network (CNN-TCN). In the EEG network, the 3D feature building module was added to integrate band information, spatial information and temporal information of the EEG signal, and the band attention and self-attention modules were added to the convolutional recurrent neural network (CRNN). The former explores the effect of different frequency bands on network recognition performance, while the latter is to obtain the intrinsic similarity of different EEG samples. To investigate the effect of different frequency bands on the experiment, we obtained the average attention mask for all subjects in different frequency bands. The distribution of the attention masks across the different frequency bands suggests that signals more relevant to human emotions may be active in the high frequency bands γ (31-50 Hz). Finally, we try to use the multi-task loss function Lc to force the approximation of the intermediate feature vectors of the visual and EEG modalities, with the aim of using the knowledge of the visual modalities to improve the performance of the EEG network model. The mean recognition accuracy and standard deviation of the proposed method on the two multimodal sentiment datasets DEAP and MAHNOB-HCI (arousal, valence) were 96.75 ± 1.75, 96.86 ± 1.33; 97.55 ± 1.51, 98.37 ± 1.07, better than those of the state-of-the-art multimodal recognition approaches. The experimental results show that starting from the multimodal information, the facial video frames and electroencephalogram (EEG) signals of the subjects are used as inputs to the emotion recognition network, which can enhance the stability of the emotion network and improve the recognition accuracy of the emotion network. In addition, in future work, we will try to utilize sparse matrix methods and deep convolutional networks to improve the performance of multimodal emotion networks.

In order to effectively solve the problems such as fault with single features, carrying the lack of information resulting in poor effect of fault judgment in traditional transformer fault diagnosis method. In view of this, this paper will consider the insulation resistance of the core 12 fault symptoms and fault characteristic gases as the combination of fault characteristics, effectively solve the problem of the existence of the feature quantity; At the same time, the principal component analysis and self-organizing neural network combination is introduced to this paper, this paper puts forward a new method of transformer fault diagnosis based on principal component analysis and self-organizing neural network. Firstly, using the principal component analysis for the main components of 17 kinds of feature extraction, extracted features can effectively present the characteristics of 10 kinds of fault classification, on this basis, the 10 methods of feature extraction was obtained as input vector of self-organizing neural network and identification of fault types. The example analysis shows that this method has a good diagnostic effect, which can effectively improve the accuracy of fault diagnosis and verify the validity and feasibility of this method.

Currently, the used of deep learning method has attracted widespread attention in machine learning, especially in Biometric. Many deep learning methods have been proposed like convolutional neural network (CNN), AlexNet and principal component analysis network (PCANet). Among the methods employed, PCANet is believed to be the most effective method because of its promising performance in biometric. However, the current filter generation approach in PCANet does not consider the characteristics of the image, such as vein lines for finger vein recognition. To address this limitation, we proposed a new filter generation method that can consider the essential features of the image, such as the use of vein lines for finger vein recognition. The filter of the proposed method was generated by finding the correlation between two view images, which was original grayscale image and vein line image using canonical correlation analysis (CCA) method. Then, we evaluated this proposed method with the three public finger vein image database, FV-USM, SDUMLA-HMT and THU-FVT2. The results showed that the proposed method produced higher accuracy compared to other state-of-the-art features of finger vein recognition biometric method.

Medical image classification plays an important role in disease diagnosis since it can provide important reference information for doctors. The supervised convolutional neural networks (CNNs) such as DenseNet provide the versatile and effective method for medical image classification tasks, but they require large amounts of data with labels and involve complex and time-consuming training process. The unsupervised CNNs such as principal component analysis network (PCANet) need no labels for training but cannot provide desirable classification accuracy. To realize the accurate medical image classification in the case of a small training dataset, we have proposed a light-weighted hybrid neural network which consists of a modified PCANet cascaded with a simplified DenseNet. The modified PCANet has two stages, in which the network produces the effective feature maps at each stage by convoluting inputs with various learned kernels. The following simplified DenseNet with a small number of weights will take all feature maps produced by the PCANet as inputs and employ the dense shortcut connections to realize accurate medical image classification. To appreciate the performance of the proposed method, some experiments have been done on mammography and osteosarcoma histology images. Experimental results show that the proposed hybrid neural network is easy to train and it outperforms such popular CNN models as PCANet, ResNet and DenseNet in terms of classification accuracy, sensitivity and specificity.

Objective: To extract statistical features from EEG signal for human emotion recognition. Methods: Emotions, the “inner” state of a person play a vital role in analysing the state of mind. In this paper, a new method for human emotion recognition using Multi Wavelet Transform (MWT) and random forest (ensemble technique) for classification of human emotions from EEG signals has been proposed. The experiment is conducted on EEG database for emotions i.e., DEAP data set. In present work, the data set used contains EEG recording from 4 participants (S01, S02, S03, S04) from 15 channel (FP1, FP2, F3, P3, F4, T7, T8, P4, O1, PZ, PO3, O2, P7, CP2, and C4) having 40 trails each. The paper explore the capability of proposed features namely Mean, Standard deviation, Variance, Shannon entropy, Hjorth parameters and Band power. Findings: The feature set obtained using Multi-Wavelet are then used as input for MLP, KNN, MC-SVM with Puk kernel function and Random Forest (ensemble) classifier for the classification of emotions. The classification accuracy for different emotion state happy 99.8%, sad 98.3%, exciting 95%, hate 96.4% are obtained by the proposed method. Overall 98.1% for classification of emotions (happy, sad, exciting, hate) from EEG signals. Application: The findings are helpful in monitoring alertness, cognitive engagement of patients with impaired motor functions; recognition of emotions; investigating sleep disorders and physiology. In future, efficient feature extraction algorithm using different multiwavelet functions and with a different set of features which include the temporal dynamics of brain signals in the human cognitive system can be considered.

Emotions expressed by humans can be identified from facial expressions, speech signals, or physiological signals. Among them, the use of physiological signals for emotion classification is a notable emerging area of research. In emotion recognition, a person’s electrocardiogram (ECG) and galvanic skin response (GSR) signals cannot be manipulated, unlike facial and voice signals. Moreover, wearables such as smartwatches and wristbands enable the detection of emotions in people’s naturalistic environment. During the COVID-19 pandemic, it was necessary to detect people’s emotions in order to ensure that appropriate actions were taken according to the prevailing situation and achieve societal balance. Experimentally, the duration of the emotion stimulus period and the social and non-social contexts of participants influence the emotion classification process. Hence, classification of emotions when participants are exposed to the elicitation process for a longer duration and taking into consideration the social context needs to be explored. This work explores the classification of emotions using five pretrained convolutional neural network (CNN) models: MobileNet, NASNetMobile, DenseNet 201, InceptionResnetV2, and EfficientNetB7. The continuous wavelet transform (CWT) coefficients were detected from ECG and GSR recordings from the AMIGOS database with suitable filtering. Scalograms of the sum of frequency coefficients versus time were obtained and converted into images. Emotions were classified using the pre-trained CNN models. The valence and arousal emotion classification accuracy obtained using ECG and GSR data were, respectively, 91.27% and 91.45% using the InceptionResnetV2 CNN classifier and 99.19% and 98.39% using the MobileNet CNN classifier. Other studies have not explored the use of scalograms to represent ECG and GSR CWT features for emotion classification using deep learning models. Additionally, this study provides a novel classification of emotions built on individual and group settings using ECG data. When the participants watched long-duration emotion elicitation videos individually and in groups, the accuracy was around 99.8%. MobileNet had the highest accuracy and shortest execution time. These subject-independent classification methods enable emotion classification independent of varying human behavior.

Purpose: Emotions are integral brain states that can influence our behavior, decision-making, and functions. Electroencephalogram (EEG) is an appropriate modality for emotion recognition since it has high temporal resolution and is a non-invasive and cheap technique. Materials and Methods: A novel approach based on Ensemble pre-trained Convolutional Neural Networks (ECNNs) is proposed to recognize four emotional classes from EEG channels of individuals watching music video clips. First, scalograms are built from one-dimensional EEG signals by applying the Continuous Wavelet Transform (CWT) method. Then, these images are used to re-train five CNNs: AlexNet, VGG-19, Inception-v1, ResNet-18, and Inception-v3. Then, the majority voting method is applied to make the final decision about emotional classes. The 10-fold cross-validation method is used to evaluate the performance of the proposed method on EEG signals of 32 subjects from the DEAP database. Results:.The experiments showed that applying the proposed ensemble approach in combinations of scalograms of frontal and parietal regions improved results. The best accuracy, sensitivity, precision, and F-score to recognize four emotional states achieved 96.90% ± 0.52, 97.30 ± 0.55, 96.97 ± 0.62, and 96.74 ± 0.56, respectively. Conclusion: So, the newly proposed model from EEG signals improves recognition of the four emotional states in the DEAP database.

Automatic targets recognition (ATR) for synthetic aperture radar (SAR) image is very important. ATR can be used in traffic management, national frontier safety, and so on. Traditional algorithms for SAR ATR is composed of extraction features and training classifier. The features are essential for the classification accuracy. However, choosing good features by hand is a hard task. The deep convolutional neural networks (CNNs) which can learn features automatically have got a great performance in natural images. However, the CNNs have many parameters and need a lot of data to train such networks. The remote-sensing data of SAR is limited. Then, the authors need a simple network which needs not much data and easy to train. The principal component analysis network (PCANet) is a shallow network that performs well in the recognition task and needs no hand features choosing. Though this network has produced a wide application in the natural images, it is rarely used in the SAR images. The experimental result of the moving and stationary target acquisition and recognition (MSTAR) dataset shows that the PCANet can achieve over 99% accuracy on ten-class targets. This result is better than traditional algorithms and is very close to the results of deep-learning methods.