Human Emotions Research Articles

EEG Emotion Recognition Network Based on Attention and Spatiotemporal Convolution.

Human emotions are complex psychological and physiological responses to external stimuli. Correctly identifying and providing feedback on emotions is an important goal in human-computer interaction research. Compared to facial expressions, speech, or other physiological signals, using electroencephalogram (EEG) signals for the task of emotion recognition has advantages in terms of authenticity, objectivity, and high reliability; thus, it is attracting increasing attention from researchers. However, the current methods have significant room for improvement in terms of the combination of information exchange between different brain regions and time-frequency feature extraction. Therefore, this paper proposes an EEG emotion recognition network, namely, self-organized graph pesudo-3D convolution (SOGPCN), based on attention and spatiotemporal convolution. Unlike previous methods that directly construct graph structures for brain channels, the proposed SOGPCN method considers that the spatial relationships between electrodes in each frequency band differ. First, a self-organizing map is constructed for each channel in each frequency band to obtain the 10 most relevant channels to the current channel, and graph convolution is employed to capture the spatial relationships between all channels in the self-organizing map constructed for each channel in each frequency band. Then, pseudo-three-dimensional convolution combined with partial dot product attention is implemented to extract the temporal features of the EEG sequence. Finally, LSTM is employed to learn the contextual information between adjacent time-series data. Subject-dependent and subject-independent experiments are conducted on the SEED dataset to evaluate the performance of the proposed SOGPCN method, which achieves recognition accuracies of 95.26% and 94.22%, respectively, indicating that the proposed method outperforms several baseline methods.

Intelligent wearable olfactory interface for latency-free mixed reality and fast olfactory enhancement

Olfaction feedback systems could be utilized to stimulate human emotion, increase alertness, provide clinical therapy, and establish immersive virtual environments. Currently, the reported olfaction feedback technologies still face a host of formidable challenges, including human perceivable delay in odor manipulation, unwieldy dimensions, and limited number of odor supplies. Herein, we report a general strategy to solve these problems, which associates with a wearable, high-performance olfactory interface based on miniaturized odor generators (OGs) with advanced artificial intelligence (AI) algorithms. The OGs serve as the core technology of the intelligent olfactory interface, which exhibit milestone advances in millisecond-level response time, milliwatt-scale power consumption, and the miniaturized size. Empowered by robust AI algorithms, the olfactory interface shows its great potentials in latency-free mixed reality (MR) and fast olfaction enhancement, thereby establishing a bridge between electronics and users for broad applications ranging from entertainment, to education, to medical treatment, and to human machine interfaces.

Predicting game-induced emotions using EEG, data mining and machine learning

BackgroundEmotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal’s changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers’ performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions.ResultsThe RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases’ results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm’s capabilities in precisely determining the emotion label for each participant’s EEG features’ instance.ConclusionThe findings in this study fill the existing gap of game-induced emotion recognition field by providing an in-depth evaluation on the ruleset algorithm’s performance and feasibility of applying the generated rules on the game-induced EEG data for justifying the emotional state prediction result.

EmoSonics: Emotion Detection via Voice and Speech Recognition

Understanding emotions from speech is like deciphering a rich tapestry of human expression in the realm of human-computer interaction. It's akin to listening to someone's tone and inflection to discern whether they're happy, surprised, or experiencing a range of other feelings. Researchers use a variety of techniques, from analyzing speech patterns to utilizing advanced technologies like fMRI, to decode these emotional cues. Emotions aren't just simple labels; they're complex and nuanced, demanding sophisticated methods for accurate interpretation. Some methods break emotions down into simple categories, while others embrace the intricacies of human emotion, treating them as continuous variables. Ultimately, the goal is to enhance communication between humans and computers by enabling machines to understand and respond appropriately to our emotional states. This pursuit underscores the significance of emotion detection in speech analysis and highlights the need for continually evolving methodologies in human-computer interaction research.

SIGNSense: Auditory -Optic Impairment Communication Bridge

Language experts have recognized sign languages as natural languages with the ability to convey human emotions and ideas. Translation from written language into sign videos or extraction of spoken language sentences from sign videos is the aim of sign language translation. Sign language is the principal means of communication for the deaf and hard of hearing community, which comprises 32 million children and 328 million adults worldwide who suffer from hearing impairment. However, the inability of current systems to accurately translate and transmit sign language motions in real-time prevents effective and spontaneous communication. This research provides a revolutionary technique that enables real-time recognition of ISL gestures by integrating natural language processing with cross-modal integration. The methodology uses cutting-edge methods like the Single Shot Multibox Detector (SSD) with MobileNetV2 architecture for data collection, preprocessing, model selection, and training. In real-time inference, the trained model attains an impressive 94% accuracy rate, showcasing strong performance and encouraging outcomes for enhancing communication accessibility for people with hearing impairments

La colère : définition et concepts

Anger is a universal emotion whose daily experience varies in frequency, intensity and duration among individuals. Multiple emotional terms such as “frustrated” or “furious” can characterize it and nuance its experience. It thus encompasses a number of cognitive and behavioral manifestations (directly observable or not), and internal modifications such as physiological activation. It is also associated with facial expressions. As a subjective experience, its expression is therefore multidimensional. It leads, for example, to action tendencies such as shouting or withdrawing from a situation. The latter can extend to aggressive behavior. Several related terms are used to characterize its different facets, such as hostility, irritability and aggressiveness. These aggressive affects are closely related and sometimes overlap, leading to confusion. Rightly so, they are often correlated and mutually supportive. However, they refer either to a state of mood or an attitude, and are distinct from anger as an emotion. Aggression is also to be distinguished from violent acts, which are characterized by the risk of causing significant harm to others. Impulsivity is also mentioned, but is seen more as a personality trait that seems to correlate with the experience of anger. What's more, it's considered by many to be an aversive emotion. Compared to other emotions such as sadness or fear, however, it is more likely to lead to an active approach. It is also triggered in a variety of situations, notably when the individual feels blocked or frustrated in achieving a goal. The question of injustice and the responsibility of others will also be central. In fact, beliefs and evaluations of situations will play a vital role, whether or not they are conscious. The ruminations that provoke and result from it can also play an important role in regulating it. Finally, many social and cultural aspects influence its expression. Anger is a universal human emotion, regardless of culture. However, certain display rules will influence the emotional response of anger to maintain a certain social framework. In other words, anger plays a part in regulating social behavior within groups. What's more, the literature is homogeneous on the effect of gender, but it is acknowledged that there are differences between men and women in the way anger is displayed. The social context and social desirability play a definite role in distinguishing certain reactions according to the gender of the individuals expressing anger. To our knowledge, to date, no French-language journal has presented the concept of anger, despite the fact that it is an emotion that can have harmful consequences on the quality of life of individuals and in the sphere of relationships. Some authors refer to anger as the “unrecognized” emotion that deserves more attention. The aim of this review is therefore to define the emotion of anger and explore related concepts. However, there are certain limitations to this review. Indeed, the literature highlights a strong link between anger and certain psychological disorders. Other elements, such as the consequences of dysfunctional anger or the assessment tools available, should be studied in greater depth.

Portable Facial Expression System Based on EMG Sensors and Machine Learning Models.

One of the biggest challenges of computers is collecting data from human behavior, such as interpreting human emotions. Traditionally, this process is carried out by computer vision or multichannel electroencephalograms. However, they comprise heavy computational resources, far from final users or where the dataset was made. On the other side, sensors can capture muscle reactions and respond on the spot, preserving information locally without using robust computers. Therefore, the research subject is the recognition of the six primary human emotions using electromyography sensors in a portable device. They are placed on specific facial muscles to detect happiness, anger, surprise, fear, sadness, and disgust. The experimental results showed that when working with the CortexM0 microcontroller, enough computational capabilities were achieved to store a deep learning model with a classification store of 92%. Furthermore, we demonstrate the necessity of collecting data from natural environments and how they need to be processed by a machine learning pipeline.

Implementation of Engagement Detection for Human-Robot Interaction in Complex Environments.

This study develops a comprehensive robotic system, termed the robot cognitive system, for complex environments, integrating three models: the engagement model, the intention model, and the human-robot interaction (HRI) model. The system aims to enhance the naturalness and comfort of HRI by enabling robots to detect human behaviors, intentions, and emotions accurately. A novel dual-arm-hand mobile robot, Mobi, was designed to demonstrate the system's efficacy. The engagement model utilizes eye gaze, head pose, and action recognition to determine the suitable moment for interaction initiation, addressing potential eye contact anxiety. The intention model employs sentiment analysis and emotion classification to infer the interactor's intentions. The HRI model, integrated with Google Dialogflow, facilitates appropriate robot responses based on user feedback. The system's performance was validated in a retail environment scenario, demonstrating its potential to improve the user experience in HRIs.

AMBITION IN LOVE IN NICHOLAS SPARKS’ NOVEL THE NOTEBOOK

This article examines how the first character by the name of Noah Calhoun in Nicholas Sparks' novel, The Notebook, passionately pursues love-driven ambition. Ambition here means having strong determination to achieve personal goals. It is a central theme in the protagonist's journey. Using a descriptive qualitative approach, this study carefully looks at Noah's various efforts to find love, using ideas from Bridge and Krutus. He sees ambition as a powerful force that drives people to achieve great things. Through this method, the research explores how the protagonist's ambitions in love unfold, showing a deep dive into human hopes and emotions. The study reveals Noah 's ambitious actions in his pursuit of Allie. It shows how he writes letters to her, builds their dream home, and works to bring back her memories. Noah's unwavering dedication and determination showcase his strong love, leading to a heartwarming conclusion where love conquers all obstacles. Overall, this research sheds light on the role of ambition in romantic relationships, highlighting Noah's steadfast pursuit of love amidst life's challenges. His resilience reminds us of how ambition can shape our relationships and stories.

EMOTIONAL INTIMACY IN DANIELLE STEEL'S NOVEL FINE THINGS

This qualitative study delves into the portrayal of emotional intimacy in Danielle Steel's novel, Fine Things using Robert Sternberg's Triangular Theory of Love as a theoretical framework. The research method involved textual analysis of excerpts from the novel, focusing on instances of emotional intimacy depicted among characters. The literature review section provides a comprehensive overview of Sternberg's Triangular Theory of Love, emphasizing its three components: intimacy, passion, and decision/commitment. The analysis highlights the importance of emotional intimacy in various types of relationships, emphasizing its role in fostering closeness, understanding, and trust. The discussion section presents findings from the textual analysis, showcasing excerpts that illustrate the complexities of emotional intimacy among characters in the novel. Examples include moments of vulnerability, communication, and affection shared between romantic partners, family members, and friends. Key findings reveal the nuanced portrayal of emotional intimacy, ranging from expressions of love and support to instances of conflict and betrayal. The conclusion drawn from the analysis underscores the profound impact of emotional intimacy on individuals and their relationships, highlighting its role in shaping the dynamics of love, loss, and personal growth depicted in the novel. Implications of this study extend to a deeper understanding of emotional intimacy in fictional narratives and its relevance to real-life relationships. By applying Sternberg's Triangular Theory of Love to literary analysis, this study contributes to the on-going discourse on the complexities of human emotions and intimate connections portrayed in literature.

On the Absurdity and Reality in Kafka's "The Castle"

The 20th-century capitalist world was turbulent and crisis-ridden, and Western literary creation as a whole presented a state of nihilism, loneliness, loss, and anxiety. Many writers regarded ugliness as beauty, using absurdity to represent reality, among whom Kafka was one. "The Castle," as a representative of his short stories, constructs many bizarre events that do not exist in real life, enhancing the absurdity of the work. The author combines absurdity with reality, integrating philosophical parables and his own real-life reflections into the work, aiming to express the ruthless satire on human indifference as well as a deep call for genuine human emotions.

Differences in the Definition of an Author under Copyright Laws of the United Kingdom, the United States, and Germany in the Context of Artificial Intelligence

In modern copyright law, which began with Queen Anne s Law, the author plays a very important role as the subject of the work. As such, identifying the author s identity is a matter of priority. ??As science and technology advances, granting author status to anyone has been discussed under copyright law since Burrow-Giles Lithographic Co. v. Sarony in 1884, and the development of artificial intelligence technology is again an issue of legal issues concerning the confirmation of author status of artificial intelligence products. Though it was thought that artificial intelligence products should be protected by law, the problem is that only creations expressing human thoughts or emotions can be protected under the current copyright law. In addition, only human beings can be recognized as authors in precedents and theories. ??This paper introduces the author problem of the distant, recent issue of artificial intelligence products and review the author s concept through content on the author s concept of Anglo-American and continental law countries.

Pop-ups can be ugly: temporary architecture built with emotions

Pop-ups are temporary installations, constructions, or structures that suddenly appear in urban contexts to draw attention for commercial, artistic, or social purposes. Temporary pavilions, whose existence is bound to their capability to engage with unknown citizens or passers-by and offer them a spatial experience, are also identified as pop-ups. However, what are the features that make a temporary structure a pop-up? What architectural elements do designers outsource when conceiving and materialising pop-up architecture? At what point does a pop-up become something else? This paper aims to answer these questions by providing insights into design explorations that extend the meaning of pop-ups and enquiring, through a survey and interviews, the boundaries of what can be understood as pop-up architecture. Collective definitions address the fundamental role of human emotions in the conceptualisation and materialisation of these temporary structures, suggesting the secondary role of aesthetics when engaging with users.

A Study on Behavioural Finance

This research paper delves into the intriguing field of behavioral finance, exploring how psychological factors influence financial decision-making processes. Behavioral finance seeks to understand why people make irrational financial decisions despite being aware of the consequences. It bridges the gap between economics and psychology, offering insights into human behavior that traditional finance models often overlook. The study examines various aspects of behavioral finance, including cognitive biases, market anomalies, and investor behavior under different market conditions. Through a comprehensive review of existing literature and empirical studies, this paper aims to shed light on the complex interplay between human emotions, cognitive limitations, and financial markets. The findings contribute to a deeper understanding of investor behavior, potentially informing strategies for financial advisors and investors alike. This research underscores the importance of incorporating psychological principles into financial analysis, highlighting the potential for improved investment outcomes through a more nuanced understanding of human behavior.

Human Emotion Detection Using CNN and Transfer Learning

Facial emotion detection is a critical component in human-computer interaction, mental health assessment, and security systems. In this project, we propose a robust facial emotion detection system leveraging state-of-the-art deep learning techniques. Our system utilizes Convolutional Neural Networks (CNNs) to extract meaningful features from facial images and classify them into five distinct emotional categories: neutral, surprise, sad, happy, and angry. We conducted extensive experiments on a diverse dataset consisting of over 10,000 annotated facial images collected from various sources. Through data augmentation techniques such as rotation, translation, and flipping, we expanded the dataset to enhance model training. Additionally, we employed transfer learning by fine-tuning a pre-trained CNN model, ResNet50, on our dataset to leverage its learned features. This project presents a system for real-time emotion monitoring using computer vision techniques. The system utilizes the Haar Cascade Classifier for face detection in live webcam video streams. Furthermore, we evaluated the system's performance across different lighting conditions, poses, and facial occlusions to assess its robustness in real-world scenarios. Our results indicate that the system maintains consistent performance across diverse conditions, making it suitable for deployment in applications requiring real-time facial emotion recognition.

A RULE-BASED APPROACH USING THE ROUGH SET ON COVID-19 DATA

The COVID-19 pandemic has not only caused loss of life but also significantly affected people's emotional state. These emotional impacts have had serious consequences on societies and economies around the world. In order to repair these devastations in society, it is important to analyse these emotional effects in depth. In this study, the effects of the pandemic on human emotions are analysed using soft computing techniques. A rule-based approach is proposed for the analysis with the help of a rough set. The proposed method is based on two main components. The first one is the process of selecting the optimal subset (OFS) from the whole feature set with the help of k best known feature selection approaches. The second component involves the use of rough clustering methods to generate rules on the selected feature subset OFS. In the study, the first real data set called " Real World Concern Dataset", which is obtained from emotional responses to COVID-19, was used. The dataset consists of 5,000 items (2,500 short + 2,500 long). In the experimental studies, the proposed approach was tested with both labelled and unlabelled data, and it was observed that effective results were obtained with an accuracy rate of over 85%. It was also found that people were highly concerned about the future due to the pandemic.

Modeling and Sentiment Analysis of Social Relationships in Elderly Smart Homes Based on Graph Neural Networks

With the expansion of Speech Emotion Recognition in the consumer domain, several devices, particularly those designed for managing smart home personal assistants for the elderly, have been widely available on the market. The increasing processing power and connection, together with the growing need to facilitate longer residency through technological interventions, highlight the potential benefits of smart home assistants. Enabling these assistants to recognize human emotions would greatly improve user-assistant communication, allowing the assistant to deliver more constructive and customized feedback to the user. In this research work, Modeling and Sentiment Analysis of Social Relationships in Elderly Smart Homes Based on Graph Neural Networks (SASR-MBHNN-BBOA) is proposed. The input data are collected from Social Recommendation Dataset. Then, input data are pre-processed utilizing Inverse Optimal Safety Filters (IOSF) for cleaning the data and removing the background noise. Then the pre-processed data are given to Memristive Bi-neuron Hopfield Neural Network (MBHNN) for predicting the sentiments like positive, negative and neutral. In general, MBHNN doesn’t express some adoption of optimization approaches for determining optimal parameters to predicting the sentiments accurately. Hence BBOA is proposed to optimize MBHNN classifier which precisely predicts the sentiments in elderly smart home. The proposed SASR-MBHNN-BBOA method is implemented in Python, and it assessed with numerous performance metrics such as accuracy, precision, recall, F1-score, ROC. The outcomes show SASR-MBHNN-BBOA attains 20.8%, 19.5%, and 29.6% higher Accuracy, 28.8%, 22.5%, and 32.6% higher Precision, 15.5%, 27.4%, and 18.2% higher Recall are analysed with existing methods such as, Emotional speech analysis in real time for smart home assistants.(SASR-CNN-SHA), Machine Learning to Investigate Elderly Care Requirements in China via the Lens of Family Caregivers (SASR-ML-IECR),Identifying User Emotions via Audio Conversations with Smart Assistants (SASR-DNN-EASA) methods respectively.

Enhancing Multimodal Emotion Recognition through Attention Mechanisms in BERT and CNN Architectures

Emotion detection holds significant importance in facilitating human–computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. The primary research challenge involves developing models that can accurately interpret and analyze emotions from both auditory and textual data, whereby auditory data require optimizing CNNs to detect subtle and intense emotional fluctuations in speech, and textual data necessitate access to large, diverse datasets to effectively capture nuanced emotional cues in written language. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers to enable profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method here undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field.

Recent Trends in Machine and Deep Learning for Verbal and Non-verbal Emotion Detection

Abstract: Emotion recognition, both verbal and non-verbal, is a crucial component of artificial intelligence, psychology, and human-computer interaction. Emotion recognition is an integral component that significantly contributes to the improvement of communication and interaction. The research endeavors to conduct a thorough analysis and synthesis of the most recent developments in Deep Learning (DL) and Machine Learning (ML) techniques. Specifically, the study concentrates on the recognition of both verbal and non-verbal emotions. In contrast to previous research concentrated on verbal or non-verbal emotion detection separately, the study attempts to reconcile the gap between the two by demonstrating how ML and DL can be utilized effectively to detect emotions. The study also examines new methods, including multimodal data and integration of contextual information. Additionally, the research has examined the ethical implications and difficulties associated with emotion detection technologies. Findings have also revealed the wide-reaching implications for various sectors, including healthcare, education, customer service, and entertainment, where comprehending human emotions plays a crucial role in enhancing user experience and outcomes. In conclusion, the study provides invaluable knowledge to practitioners and researchers, which may facilitate the development of more advanced and accurate systems.

FetchEEG: a hybrid approach combining feature extraction and temporal-channel joint attention for EEG-based emotion classification

Objective. Electroencephalogram (EEG) analysis has always been an important tool in neural engineering, and the recognition and classification of human emotions are one of the important tasks in neural engineering. EEG data, obtained from electrodes placed on the scalp, represent a valuable resource of information for brain activity analysis and emotion recognition. Feature extraction methods have shown promising results, but recent trends have shifted toward end-to-end methods based on deep learning. However, these approaches often overlook channel representations, and their complex structures pose certain challenges to model fitting. Approach. To address these challenges, this paper proposes a hybrid approach named FetchEEG that combines feature extraction and temporal-channel joint attention. Leveraging the advantages of both traditional feature extraction and deep learning, the FetchEEG adopts a multi-head self-attention mechanism to extract representations between different time moments and channels simultaneously. The joint representations are then concatenated and classified using fully-connected layers for emotion recognition. The performance of the FetchEEG is verified by comparison experiments on a self-developed dataset and two public datasets. Main results. In both subject-dependent and subject-independent experiments, the FetchEEG demonstrates better performance and stronger generalization ability than the state-of-the-art methods on all datasets. Moreover, the performance of the FetchEEG is analyzed for different sliding window sizes and overlap rates in the feature extraction module. The sensitivity of emotion recognition is investigated for three- and five-frequency-band scenarios. Significance. FetchEEG is a novel hybrid method based on EEG for emotion classification, which combines EEG feature extraction with Transformer neural networks. It has achieved state-of-the-art performance on both self-developed datasets and multiple public datasets, with significantly higher training efficiency compared to end-to-end methods, demonstrating its effectiveness and feasibility.