Multi-physiological signal fusion for objective emotion recognition in educational human-computer interaction.

In the fast pace of life, emotion recognition systems are essential to help monitor mental health and well-being. The continuous development of the Internet of Things (IoT) and Human-Computer Interaction (HCI) improve the availability and accessibility to devices that can capture the facial expressions of a user, while wearable devices can also capture physiological signals and use them for emotion recognition. Meanwhile, machine learning and deep learning methods can provide emotion prediction models. However, the training of the models relies heavily on massive amounts of labeled data. The accuracy of data labels affects the success of the overall system. Research targeting emotion recognition uses the participants' self-reports as labels. However, participants often fail to give accurate self-reports, thus affecting the accuracy of the analysis. In this study, we examine the performance of the self-reports and external annotations for emotion recognition based on visual and physiological signals. Specifically, we use video data, as well as the Electrodermal Activity (EDA), Electroencephalogram (EEG), and Electrocardiogram (ECG) signals collected from wearable devices. We use two machine learning and three deep learning methods to process the signals and train the classifiers. The results show that the classifiers trained with external annotations offer better emotion recognition accuracy than self-reports. Also, the classifiers trained on facial expression offer better emotion prediction accuracy than the physiological signals, and the Deep Convolutional Network model shows the best results.

Emotion intelligence is a popular research topic that stems to bridge the gap between human-machine interaction. The use of such systems varies, however, the goal remains the same, to develop a robust and accurate model for detecting and identifying emotions. Physiological signals, such as electrodermal activity (EDA) and heart rate (HR), when coupled with facial expression analyses can bolster the efficacy of the recognition system. To this end, the aim of this study is to analyse EDA and HR signals to identify reactions to emotional stimuli. The data used in this work was collected from different subjects taking part in a separate study on emotion induction methods. The obtained physiological signals were processed to identify the stimulus trigger instances and detect trends between the different administered emotional stimuli. The results showed that the EDA signal was able to pinpoint the emotional trigger with a root mean squared error (RMSE) of 0.9871. The HR signal showed inconsistencies, however, a clear trend was observed between the emotion reaction and relaxation phase. This preliminary study assessment highlights the possibility of implementing data fusion in emotion recognition systems.

Aiming at problems such as the difficulty of recognizing emotions in the elderly and the inability of traditional machine-learning models to effectively capture the nonlinear relationship between physiological signal data, a Recursive Map (RM) combined with a Vision Transformer (ViT) is proposed to recognize the emotions of the elderly based on Electroencephalogram (EEG), Electrodermal Activity (EDA), and Heart Rate Variability (HRV) signals. The Dung Beetle Optimizer (DBO) is used to optimize the variational modal decomposition of EEG, EDA, and HRV signals. The optimized decomposed time series signals are converted into two-dimensional images using RM, and then the converted image signals are applied to the ViT for the study of emotion recognition of the elderly. The pre-trained weights of ViT on the ImageNet-22k dataset are loaded into the model and retrained with the two-dimensional image data. The model is validated and compared using the test set. The research results show that the recognition accuracy of the proposed method on EEG, EDA, and HRV signals is 99.35%, 86.96%, and 97.20%, respectively. This indicates that EEG signals can better reflect the emotional problems of the elderly, followed by HRV signals, while EDA signals have poorer effects. Compared with Support Vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbors (KNN), the recognition accuracy of the proposed method is increased by at least 9.4%, 11.13%, and 12.61%, respectively. Compared with ResNet34, EfficientNet-B0, and VGG16, it is increased by at least 1.14%, 0.54%, and 3.34%, respectively. This proves the superiority of the proposed method in emotion recognition for the elderly.

Context-aware computing has become an essential component of modern wearable technology, enabling devices to sense, interpret, and respond to users’ environments and affective states. By integrating contextual intelligence, smart systems can adapt their own behavior to better align with user needs, enhancing efficiency, personalization, and user experience. A critical aspect of context awareness is the ability to recognize a user’s internal state, particularly emotions, which influence decision-making, communication, and overall well-being. While emotion recognition is traditionally approached through multimodal sensing—using cameras, microphones, or physiological sensors such as Electroencephalography (EEG), Electrocardiography (ECG), and Electro-dermal Activity (EDA)—these methods often require multiple sensors, leading to challenges related to power consumption, complexity, and privacy. The demand for a more efficient and unobtrusive approach to emotion and context recognition has driven research toward minimal-sensor solutions that can extract meaningful affective and contextual information with reduced hardware requirements. Restricting sensing sources of contextual information by using only limited number of sensors might come at the expense of constraining the ultimate goal of context-awareness. Such expense can be mitigated by “doing more with less” i.e. delving into the opportunities of using a single sensor for multiple purposes. What is desirable is a minimal-sensor solution capable of capturing both motion and physiological signals for both robust emotion recognition and additional context estimation. Among wearable sensors, chest-worn Inertial Measurement Units (IMUs) stand out as promising candidates for comprehensive context estimation, as they are well-positioned to capture motion patterns, and physiological vibrations, being the subtle cardio-respiratory signals. This raises the question of whether a single chest-worn IMU could serve as a minimal yet effective sensor for simultaneously estimating both emotional and contextual information, offering a practical alternative to traditional multi-sensor approaches. To address the challenge of using chest-worn IMU for multiple context sensing, I investigated the potential of using Seismocardiography (SCG) and Accelerometry-Derived Respiration (ADR) to estimate emotional states. First, I explored the existing capabilities of chest-worn IMUs in capturing cardio-respiratory vibrations and motion data, which I used as a knowledge base for embedding such IMUs in context sensing. Data plays a crucial role in this problem, therefore I developed a flexible software interface, ColEmo, to facilitate the scalable collection of emotion-related data and introduced a novel dataset, EmoWear, integrating physiological and motion data for emotion recognition and context awareness. Then, I examined the feasibility of using SCG for emotion recognition, comparing its performance with traditional physiological signals and evaluating its effectiveness as a single-sensor solution. This thesis presents a detailed analysis of the potential of chest-worn IMUs for emotion and context recognition. It reports on the design and validation of a SCG-based wearable system, the development and characteristics of the EmoWear dataset, and the implementation of the ColEmo platform for emotion data collection. The research also examines machine learning techniques applied to the SCG and ADR signals, assessing their effectiveness in estimating emotional states. My findings indicate that SCG-based emotion recognition achieves performance comparable to conventional physiological counterparts, demonstrating the feasibility of using a single IMU sensor for affective computing. The publicly-available EmoWear dataset provides a valuable resource for future research, highlighting the potential of combining motion and physiological data for enhanced context awareness. Additionally, the ColEmo software interface, which I published open-source, proves to be an effective tool for multi-modal emotion data collection, facilitating further advancements in wearable emotion recognition. The results pave the way for a minimal-sensor approach for context information estimation that can significantly reduce system complexity while maintaining high performance. These findings confirm that chest-worn IMUs present an opportunity to further improve emotion recognition in addition to the motion-based context information estimation. My research highlights the need for standardized methodologies in affective computing and demonstrates the viability of motion-based physiological sensing for emotion estimation. By using a single chest-worn IMU, this work presents an alternative to multi-sensor systems, reducing power consumption, and privacy concerns while maintaining robust performance. Future research should focus on refining IMU-based emotion recognition using deep learning techniques and larger datasets to enhance classification accuracy. Further validation in real-world settings is necessary to assess the practical applicability of the proposed system. The EmoWear dataset should be explored for additional context-awareness applications, such as activity recognition and stress monitoring, to maximize its utility. The ColEmo platform offers opportunities for expansion beyond emotion recognition, including cognitive load estimation, stress monitoring, and human-computer interaction. This research moves wearable technology forward by using fewer sensors, helping make affective computing more efficient, versatile, and respectful of privacy.

Emotion recognition from speech plays a crucial role in enhancing human–computer interaction by enabling systems to interpret and respond to users’ emotional states. This study develops and evaluates a Speech Emotion Recognition (SER) system using three machine learning techniques; Support Vector Machines (SVM), Multilayer Perceptron (MLP), and Convolutional Neural Networks (CNNs). The system is trained and tested on the RAVDESS dataset, which contains 1,440 professionally recorded audio samples representing a wide range of emotions. Our approach involves careful preprocessing of the audio signals, extraction of key acoustic features, and comparative performance evaluation of the three models using standard metrics. Results show that each model exhibits unique strengths and limitations, with CNNs achieving the most robust feature learning and generalization. The study underscores the importance of diverse feature representation for accurate emotion classification and provides insight into how different model architectures handle emotional nuances in speech. Identified challenges such as dataset diversity, feature selection, and computational complexity are discussed, along with recommendations for future research to improve SER systems’ real-world adaptability. This work contributes to ongoing efforts toward developing emotionally aware technologies that can enhance natural human–machine communication.

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.

Facial emotion recognition is a significant and expanding field of research, offering practical applications across various domains, including healthcare, education, and human-computer interaction. For example, in healthcare, this technology enables clinicians and therapists to analyze patient images to identify emotional states indicative of stress or depression. Similarly, in an educational setting, it provides teachers and researchers insights into student engagement and learning behavior through the analysis of classroom or e-learning images. The recent advancement of deep learning, especially Convolutional Neural Networks (CNNs), has substantially enhanced the accuracy and operational efficiency of automated emotion detection systems.This research investigates image-based emotion recognition utilizing CNN architectures, specifically implementing a novel CNNEmotionsModel within Apple's Machine Learning framework. A key focus of this study is demonstrating the viability of real-time mobile deployment using SwiftUI and UIKit to create a highly accessible and userfriendly iOS application. The paper concludes by examining the real-world utility of emotion recognition technologies and outlining

With the rapid development in social media, single‐modal emotion recognition is hard to satisfy the demands of the current emotional recognition system. Aiming to optimize the performance of the emotional recognition system, a multimodal emotion recognition model from speech and text was proposed in this paper. Considering the complementarity between different modes, CNN (convolutional neural network) and LSTM (long short‐term memory) were combined in a form of binary channels to learn acoustic emotion features; meanwhile, an effective Bi‐LSTM (bidirectional long short‐term memory) network was resorted to capture the textual features. Furthermore, we applied a deep neural network to learn and classify the fusion features. The final emotional state was determined by the output of both speech and text emotion analysis. Finally, the multimodal fusion experiments were carried out to validate the proposed model on the IEMOCAP database. In comparison with the single modal, the overall recognition accuracy of text increased 6.70%, and that of speech emotion recognition soared 13.85%. Experimental results show that the recognition accuracy of our multimodal is higher than that of the single modal and outperforms other published multimodal models on the test datasets.

Introduction; Emotion recognition is a transformative technology that enhances human-computer interaction by enabling systems to interpret and respond to human emotions effectively. Objective; This paper investigates the current landscape of emotion recognition technologies, emphasizing the diverse sources of emotional data, including facial expressions, voice, physiological signals, and textual content. Method; We explore the methodologies and algorithms employed for emotion classification, ranging from traditional machine learning techniques to advanced deep learning models such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Result; This study provides a comparative analysis of various emotion recognition approaches, evaluating their accuracy, robustness, and computational efficiency. Conclusion; This paper contributes to the ongoing discourse on emotion recognition by offering a comprehensive overview of current trends, challenges, and opportunities for advancing the field.

Emotion recognition is considered as one of the most vital and challenging studies in the domain of computer vision. Due to the ongoing pandemic the people’s emotional and mental state is getting affected due to less physical interaction and increased virtual interaction. The motivation of the work lies in the recognition and monitoring of the emotional state of the human beings in live environment with higher accuracy rate and fast recognition time so as to keep them aware about their emotional state in the pandemic situation. Emotion recognition is achieved using the proposed deep convolution neural network (DCNN) using custom Gabor filter with 85.8% accuracy. Emotion recognition is also being investigated and compared with other deep learning models such as AlexNet, VGG-Net for testing the efficacy. When the emotion of the person will be found sad or angry then an alert sound is played and an email alert is automatically sent.KeywordsEmotion recognitionDeep learningGabor filterPandemicReal-time alertDCNNPreprocessing

Automatic artifact recognition and correction for electrodermal activity based on LSTM-CNN models

In this work, an attempt has been made to discriminate arousal and valence dimensions in Electrodermal Activity (EDA) signals using Spiking Deep Belief Network (SDBN). EDA signals having different arousal and valence dimensions are obtained from public online database. These signals are divided into equal parts and normalized using channel normalization. Later, signals are subjected to SDBN for event-related features and classification. A leave-one-out cross validation is used to investigate the classification performance. The result shows that the SDBN classifiers are able to discriminate the emotional states. The network yields better classification performance for emotional dimensions of arousal and valence. It appears that the proposed approach can be used to differentiate autonomic and pathological conditions.

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.

Emotion recognition from physiological signals has immense applications in healthcare and human–computer interaction. We developed an electrodermal activity (EDA)-graph signal processing pipeline that produces highly sensitive features for detecting the affective dimensions (arousal and valence) of emotions. Using the Continuously Annotated Signals of Emotion dataset, we compared our graph-based EDA features (EDA-graph) with traditional time- and frequency-domain EDA features and features derived from other signals (heart rate variability, pulse transit time, electromyography, skin temperature, and respiration) for detecting affective dimensions using machine learning regression models. The EDA-graph features showed superior performance in continuous affective dimension recognition compared to the most accurate state-of-the-art models, achieving RMSE values of 0.801 for arousal and 0.714 for valence. Furthermore, we used a variety of traditional and recently published datasets collected in laboratory and ambulatory settings to perform a comprehensive evaluation of the robust generalization capabilities of our approach across different emotional contexts. The models demonstrated exceptional performance in classifying emotional states across the datasets, achieving 98.2% accuracy in detecting positive, negative, and mixed emotions; 92.75% in discriminating between emotions (relaxed, amused, bored, scared, and neutral); and 86.54% in detecting stress vs. no stress. These results highlight the potential of a graph-based analysis of EDA in emotion recognition systems in different contexts, especially for real-world applications.

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.