Article
Multidisciplinary Sciences
Badar Almarri, Sanguthevar Rajasekaran, Chun-Hsi Huang
Summary: This paper introduces a subject-independent emotion recognition framework that reduces subject-to-subject variability by adequate preprocessing, transforming, and feature extraction prior to analyzing emotion data. By utilizing unsupervised algorithms and support vector machine, the study outperforms other subject-independent studies in accurately classifying human affection based on EEG benchmarks.
Review
Computer Science, Theory & Methods
Xiang Li, Yazhou Zhang, Prayag Tiwari, Dawei Song, Bin Hu, Meihong Yang, Zhigang Zhao, Neeraj Kumar, Pekka Marttinen
Summary: Emotion recognition technology using EEG signals is crucial in Artificial Intelligence, with applications in emotional health care, human-computer interaction, and multimedia content recommendation. This paper reviews recent representative works in EEG-based emotion recognition research from the perspective of researchers taking the first step in this field. It introduces the scientific basis of EEG-based emotion recognition and categorizes reviewed works into different technical routes, providing readers with a better understanding of the motivation behind these studies. The paper also discusses existing challenges and future research directions.
ACM COMPUTING SURVEYS
(2023)
Article
Neurosciences
Daniel S. Weisholtz, Gabriel Kreiman, David A. Silbersweig, Emily Stern, Brannon Cha, Tracy Butler
Summary: This study found that emotional valence can be decoded from intracranial electroencephalography signals in the left medial orbitofrontal cortex and middle temporal gyrus, suggesting the presence of task-independent emotional valence information in these regions.
SOCIAL COGNITIVE AND AFFECTIVE NEUROSCIENCE
(2022)
Article
Engineering, Electrical & Electronic
Dongrui Wu, Bao-Liang Lu, Bin Hu, Zhigang Zeng
Summary: A brain-computer interface (BCI) allows direct communication between a user and a computer through the central nervous system. An affective BCI (aBCI) monitors and regulates the emotional state of the brain, which has various applications in human cognition, communication, decision-making, and health. This tutorial provides a comprehensive and up-to-date guide on aBCIs, covering basic concepts, components of a closed-loop aBCI system, representative applications, and challenges and opportunities in aBCI research and applications.
PROCEEDINGS OF THE IEEE
(2023)
Article
Chemistry, Analytical
Rajamanickam Yuvaraj, Prasanth Thagavel, John Thomas, Jack Fogarty, Farhan Ali
Summary: Advances in signal processing and machine learning have accelerated EEG-based emotion recognition research. This study compared the classification accuracy of various sets of EEG features to identify emotional states. By evaluating the performance on five independent datasets, it was found that the FD-CART feature-classification method achieved the highest accuracy for valence and arousal. These findings suggest the reliability of the FD features derived from EEG data for emotion recognition, and may contribute to the development of a real-time EEG-based emotion recognition system.
Review
Computer Science, Artificial Intelligence
Sicheng Zhao, Xingxu Yao, Jufeng Yang, Guoli Jia, Guiguang Ding, Tat-Seng Chua, Bjorn W. Schuller, Kurt Keutzer
Summary: This survey comprehensively reviews the development of affective image content analysis (AICA) in the past two decades, focusing on the state-of-the-art methods and addressing three main challenges. It provides an overview of emotion representation models, available datasets, and compares representative approaches in emotion feature extraction, learning methods, and AICA-based applications. The survey also discusses future research directions and challenges in the field.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Business
Zhiwei Xu, Miao Zhang, Pengfei Zhang, Jiawen Luo, Mengting Tu, Yuanhang Lai
Summary: The controversy exists in the similarity-attraction mechanism of brand personality because consumers' preference for brand personality is inconsistent with their own personality. The psychological reasons behind this paradoxical situation are unknown. This study uses EEG and GSR to measure physiological responses and self-assessment questionnaires to examine the brand personality images displayed to subjects with different Big Five personality traits, based on the circumplex model of emotion theory in neuroscience. The findings have significant practical value for guiding brand personality design and identifying target consumer groups.
JOURNAL OF RETAILING AND CONSUMER SERVICES
(2023)
Article
Computer Science, Artificial Intelligence
Desmond C. Ong, Harold Soh, Jamil Zaki, Noah D. Goodman
Summary: Affective Computing is a fast-growing field that proposes a probabilistic programming approach to translate psychological theories of emotion into computational models. Probabilistic programming languages offer flexibility, modularity, integration with deep learning libraries, and ease of adoption, providing a standardized platform for theory-building and experimentation.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2021)
Article
Computer Science, Information Systems
Fei Yan, Abdullah M. Iliyasu, Kaoru Hirota
Summary: This study aims to interpret and manipulate robots' emotions within the framework of quantum mechanics, encoding emotion information as superposition states and using unitary operators to manipulate emotion transitions. Fusion of multi-robots' emotions through quantum entanglement reduces the qubit requirements and quantum gate usage, demonstrating the feasibility and effectiveness of the proposed framework in transitioning emotional intelligence formulations to the quantum era.
Article
Computer Science, Artificial Intelligence
Eanes Torres Pereira, Herman Martins Gomes, Luciana Ribeiro Veloso, Moises Araujo Mota
Summary: There is disagreement on the optimal duration of EEG signal sequences for emotion recognition and challenges related to human factors in attention and fatigue. This study proposes an experimental evaluation of different EEG datasets with varying signal durations. Statistical analysis suggests that signals longer than 60 seconds may lead to better classification results for emotion recognition, but the impact of longer stimulus media on humans remains unexplored.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2021)
Review
Computer Science, Artificial Intelligence
Renan Vinicius Aranha, Cleber Gimenez Correa, Fatima L. S. Nunes
Summary: The study focuses on the impact of Affective Computing in promoting user engagement in computer applications, with a systematic literature review of available articles discussing emotion recognition techniques and challenges to be overcome in the field.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2021)
Article
Computer Science, Information Systems
Hongwen Hui, Fuhong Lin, Lei Yang, Chao Gong, Haitao Xu, Zhu Han, Peng Shi
Summary: The combination of Internet of Things (IoT) and artificial intelligence (AI) technology is important in psychology and medical treatment. In this study, an affective robotics based on IoT and AI technology is developed to serve humans emotionally. The research introduces a human-robot interaction architecture that includes emotion recognition, affective computing, and emotion control. A mathematical formulation method is also provided to quantify emotional states.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Biomedical
Sergey N. Makarov, Matti Hamalainen, Yoshio Okada, Gregory M. Noetscher, Jyrki Ahveninen, Aapo Nummenmaa
Summary: A new numerical modeling approach combining boundary element and fast multipole methods was proposed, providing unprecedented spatial resolution for noninvasive and higher-resolution intracranial recordings. The algorithm demonstrated efficient and accurate forward-problem solutions, making it suitable for modern high-resolution and submillimeter iEEG applications.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Abhishek Iyer, Srimit Sritik Das, Reva Teotia, Shishir Maheshwari, Rishi Raj Sharma
Summary: This paper proposes a novel method for human emotion recognition using EEG signals. The method involves separating the EEG signals into different frequency bands, calculating differential entropy, and utilizing a CNN and LSTM based hybrid model for accurate emotion detection. Experimental results show that the proposed approach performs better than other methods for EEG-based emotion analysis.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Biomedical
Tao Xu, Jiabao Wang, Gaotian Zhang, Ling Zhang, Yun Zhou
Summary: This study investigates confusion during reasoning learning using EEG and proposes a joint labeling technique to address label noise. The findings show significant differences in EEG signals between confused and non-confused states, indicating higher attention and cognitive load in the confused state. The research provides practical insights for recognizing and analyzing confusion in the learning process.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Health Care Sciences & Services
Sylvie Bernaerts, Nele A. J. De Witte, Vicky Van der Auwera, Bert Bonroy, Luiza Muraru, Panagiotis Bamidis, Christos Frantzidis, Chrysoula Kourtidou-Papadeli, Nancy Azevedo, Jokin Garatea, Idoia Munoz, Rosa Almeida, Raquel Losada, Joyce Fung, Eva Kehayia, Anouk Lamontagne, Elaine de Guise, Cyril Duclos, Johanne Higgins, Sylvie Nadeau, Lucie Beaudry, Evdokimos Konstantinidis
Summary: This study aims to harmonize health and well-being living lab procedures and infrastructures in Europe and beyond, particularly in the context of rehabilitation, as well as investigate the potential of innovative technologies for rehabilitation through living lab methodologies.
JMIR RESEARCH PROTOCOLS
(2022)
Article
Computer Science, Information Systems
Mikel Hernandez, Gorka Epelde, Andoni Beristain, Roberto Alvarez, Cristina Molina, Xabat Larrea, Ane Alberdi, Michalis Timoleon, Panagiotis Bamidis, Evdokimos Konstantinidis
Summary: This paper presents the application of synthetic data generation techniques in the health and wellbeing domain, noting that its current use is mainly limited to research activities. The authors demonstrate the initial design and implementation of a synthetic data generation approach integrated into the VITALISE Living Lab controlled data processing workflow, and validate its utility in accelerating artificial intelligence research.
Article
Medicine, General & Internal
Roberto Billardello, Georgios Ntolkeras, Assia Chericoni, Joseph R. Madsen, Christos Papadelis, Phillip L. Pearl, Patricia Ellen Grant, Fabrizio Taffoni, Eleonora Tamilia
Summary: Accurate delineation of resected brain cavities on magnetic resonance images (MRIs) is crucial for neuroimaging/neurophysiology studies in epilepsy surgery. This study proposes and validates a semiautomated MRI segmentation pipeline that generates accurate models of resection and anatomical labels. The pipeline includes a graphical user interface (GUI) for user-friendly usage. Results show that the pipeline achieves high accuracy and robustness with minimal user interaction.
Article
Environmental Sciences
Evangelos Paraskevopoulos, Marios Avraamides, Panagiotis D. Bamidis, Christian Dobel, Sotiria Gilou, Christos I. Ioannou, Dimitris Kikidis, Birgit Mazurek, Winfried Schlee, Andria Shimi, Eleftheria Vellidou
Summary: There is significant variation in tinnitus treatment, diagnosis, and management across Europe. The lack of national clinical guidelines and a common language among all involved disciplines has led to diversification in healthcare practices. The Tin-TRAC project aims to develop a common educational platform to unify tinnitus diagnosis and treatment strategies in Europe, thereby reducing practice diversification.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Clinical Neurology
Ludovica Corona, Eleonora Tamilia, M. Scott Perry, Joseph R. Madsen, Jeffrey Bolton, Scellig S. D. Stone, Steve M. Stufflebeam, Phillip L. Pearl, Christos Papadelis
Summary: Non-invasive neuroimaging can predict epileptic brain networks and surgical outcomes for patients with drug-resistant epilepsy.
Article
Chemistry, Analytical
Konstantinos Mitsopoulos, Vasiliki Fiska, Konstantinos Tagaras, Athanasios Papias, Panagiotis Antoniou, Konstantinos Nizamis, Konstantinos Kasimis, Paschalina-Danai Sarra, Diamanto Mylopoulou, Theodore Savvidis, Apostolos Praftsiotis, Athanasios Arvanitidis, George Lyssas, Konstantinos Chasapis, Alexandros Moraitopoulos, Alexander Astaras, Panagiotis D. D. Bamidis, Alkinoos Athanasiou
Summary: This article introduces the system architecture and validation of the NeuroSuitUp body-machine interface (BMI) which consists of wearable robotics jacket and gloves. The system was validated through exercises using a Stereoscopic camera Computer Vision approach for the jacket and multiple grip activities for the glove. The results showed acceptable correlation and no significant differences in sensor data during actuation state, indicating positive user experience and no difficulties reported.
Article
Multidisciplinary Sciences
Sakar Rijal, Ludovica Corona, M. Scott Perry, Eleonora Tamilia, Joseph R. Madsen, Scellig S. D. Stone, Jeffrey Bolton, Phillip L. Pearl, Christos Papadelis
Summary: Normal brain functioning relies on complex interactions among different regions forming networks. This study investigates the use of functional connectivity in quantifying epileptogenicity and predicting surgical outcome in children with drug resistant epilepsy (DRE). The findings suggest that functional connectivity can distinguish epileptogenic states and predict outcome in patients with DRE.
SCIENTIFIC REPORTS
(2023)
Article
Clinical Neurology
Rupesh Kumar Chikara, Saeed Jahromi, Eleonora Tamilia, Joseph R. Madsen, Steve M. Stufflebeam, Phillip L. Pearl, Christos Papadelis
Summary: The study aims to evaluate the diagnostic accuracy of electromagnetic source imaging (EMSI) in localizing spikes and predicting surgical outcome in children with drug resistant epilepsy (DRE) due to focal cortical dysplasia (FCD). We analyzed MEG and HD-EEG data from 23 children and compared the localization accuracy and predictive performance of EMSI, ESI, and MSI. The results showed that EMSI had superior localization accuracy and predictive performance compared to individual modalities.
CLINICAL NEUROPHYSIOLOGY
(2023)
Article
Clinical Neurology
Christos Papadelis, Georgios Ntolkeras, Itay Tokatly Latzer, Melissa L. DiBacco, Onur Afacan, Simon Warfield, Xutong Shi, Jean-Baptiste Roullet, K. Michael Gibson, Phillip L. Pearl
Summary: Succinic semialdehyde dehydrogenase deficiency is a rare metabolic disorder that affects the metabolism of gamma-aminobutyric acid. In this study, researchers found abnormal gamma-aminobutyric acid metabolism and brain activity in children with this condition through EEG and proton magnetic resonance spectroscopy. These findings provide insights into the pathophysiology of this disorder and may serve as potential biomarkers for therapeutic trials.
BRAIN COMMUNICATIONS
(2023)
Proceedings Paper
Green & Sustainable Science & Technology
Despoina Petsani, Efstathios Sidiropoulos, Dimitris Bamidis, Nikolaos Kyriakidis, Giuseppe Conti, Leonardo Lizzi, Evdokimos Konstantinidis
Summary: Urban planning is closely related to the accessibility and mobility of a city, particularly for vulnerable populations such as older adults. The field of urban ageing focuses on the impact of urban living on older adults and spans across health, social, and urban disciplines. Using technology to support healthy aging in cities is crucial, with examples including health monitoring, wandering detection, and timely response systems. The PROLONG project has developed a prototype device, a wearable GNSS-IoT tracker, that detects abnormal or dangerous walking patterns in older adults. It provides accurate outdoor localization, fall detection, and real-time gait analysis. The project conducted a design thinking workshop to analyze system requirements and user needs.
SMART ENERGY FOR SMART TRANSPORT, CSUM2022
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Ilias Kyparissidis Kokkinidis, Evangelos Logaras, Emmanouil S. Rigas, Ioannis Tsakiridis, Themistoklis Dagklis, Antonis Billis, Panagiotis D. Bamidis
Summary: This study utilizes Artificial Intelligence-based predictive models to accurately estimate the probability of preterm birth. The results demonstrate that the ensemble voting model performs the best across all performance metrics.
CARING IS SHARING-EXPLOITING THE VALUE IN DATA FOR HEALTH AND INNOVATION-PROCEEDINGS OF MIE 2023
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Evangelos Logaras, Antonis Billis, Evangelos Stamkopoulos, Paraskevas Lagakis, Ilias Dimitriadis, Athena Vakali, Panagiotis D. Bamidis
Summary: This paper presents ClinApp, an intelligent system that schedules and manages medical appointments, as well as collects medical data directly from patients, aiming to improve the efficiency and accuracy of appointment scheduling.
CARING IS SHARING-EXPLOITING THE VALUE IN DATA FOR HEALTH AND INNOVATION-PROCEEDINGS OF MIE 2023
(2023)
Article
Health Care Sciences & Services
Christina Ntafi, Stergiani Spyrou, Panagiotis Bamidis, Mamas Theodorou
Summary: This article examines the importance of legal interoperability for providing high-quality cross-border e-health services and proposes a model based on data protection, transparency, and liability for policy makers at the EU level.
HEALTH INFORMATICS JOURNAL
(2022)
Article
Clinical Neurology
Vasileios Dimakopoulos, Jean Gotman, William Stacey, Nicolas von Ellenrieder, Julia Jacobs, Christos Papadelis, Jan Cimbalnik, Gregory Worrell, Michael R. Sperling, Maike Zijlmans, Lucas Imbach, Birgit Frauscher, Johannes Sarnthein
Summary: This study aims to evaluate the clinical relevance and generalizability of high-frequency oscillation (HFO) analysis in a large cohort from multiple independent epilepsy centers. By applying an automated algorithm to iEEG data recorded during sleep, clinically relevant HFOs are detected and their correlation with postsurgical seizure outcome is assessed.
BRAIN COMMUNICATIONS
(2022)
Article
Engineering, Multidisciplinary
Ioanna Dratsiou, Annita Varella, Evangelia Romanopoulou, Oscar Villacanas, Sara Cooper, Pavlos Isaris, Manex Serras, Luis Unzueta, Tatiana Silva, Alexia Zurkuhlen, Malcolm MacLachlan, Panagiotis D. Bamidis
Summary: As people age, they are more prone to developing multiple chronic diseases and experiencing a decline in physical and cognitive functions, hampering their independence. This emphasizes the importance of innovative technology-based interventions tailored to older adults' needs and promoting healthy lifestyles. The SHAPES project proposes an active and healthy aging framework by integrating various digital solutions into an open Pan-European technological platform. It has the potential to engage older adults in a holistic technological ecosystem that supports a high-quality standard of living.