Filters








1,359 Hits in 5.5 sec

A deep descriptor for cross-tasking EEG-based recognition

Mariana R.F. Mota, Pedro H.L. Silva, Eduardo J.S. Luz, Gladston J.P. Moreira, Thiago Schons, Lauro A.G. Moraes, David Menotti
2021 PeerJ Computer Science  
Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on  ...  A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual  ...  National Council for Scientific and Technological: 313423/2017-2.  ... 
doi:10.7717/peerj-cs.549 pmid:34084940 pmcid:PMC8157223 fatcat:pcrk2pv7dveuzld5pdsivj4yry

Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition [article]

Yan Yan, Xuankun Wu, Chengdong Li, Yini He, Zhicheng Zhang, Huihui Li, Ang Li, Lei Wang
2022 arXiv   pre-print
The proposed work is the first investigation in the emotion recognition oriented EEG topological feature analysis, which brought a novel insight into the brain neural system nonlinear dynamics analysis  ...  Nonlinear analysis and feature extraction methods for understanding the complex dynamical phenomena are associated with the EEG patterns of different emotions.  ...  [10] proposed a deep neural networks approach to investigate the critical frequency bands and channels for EEG-based emotion recognition. Xin et al.  ... 
arXiv:2203.06895v1 fatcat:d6baepxbffderes6ipdipb2yjm

Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition

Yan Yan, Xuankun Wu, Chengdong Li, Yini He, Zhicheng Zhang, Huihui Li, Ang Li, Lei Wang
2022 IEEE Transactions on Cognitive and Developmental Systems  
The proposed work is the first investigation in the emotion recognition oriented EEG topological feature analysis, which brought a novel insight into the brain neural system nonlinear dynamics analysis  ...  Nonlinear analysis and feature extraction methods for understanding the complex dynamical phenomena are associated with the EEG patterns of different emotions.  ...  [10] proposed a deep neural networks approach to investigate the critical frequency bands and channels for EEG-based emotion recognition. Xin et al.  ... 
doi:10.1109/tcds.2022.3174209 fatcat:ogxcg3dwbnc5bmppwqhl4azkv4

Recognition of Advertisement Emotions with Application to Computational Advertising [article]

Abhinav Shukla, Shruti Shriya Gullapuram, Harish Katti, Mohan Kankanhalli, Stefan Winkler, Ramanathan Subramanian
2019 arXiv   pre-print
Experiments reveal that (a) CNN features outperform audiovisual descriptors for content-centric AR; (b) EEG features are able to encode ad-induced emotions better than content-based features; (c) Multi-task  ...  learning performs best among a slew of classification algorithms to achieve optimal AR, and (d) Pursuant to (b), EEG features also enable optimized ad insertion onto streamed video, as compared to content-based  ...  Audiovisual and EEG-based asl and val scores were estimated via CNN models, and deep CNNs have recently performed comparable to or better than humans in tasks such as object recognition [58] and facial  ... 
arXiv:1904.01778v1 fatcat:rit4hxoo7zdpdhnzyuogvel2ny

Evaluating content-centric vs. user-centric ad affect recognition

Abhinav Shukla, Shruti Shriya Gullapuram, Harish Katti, Karthik Yadati, Mohan Kankanhalli, Ramanathan Subramanian
2017 Proceedings of the 19th ACM International Conference on Multimodal Interaction - ICMI 2017  
video stream based on a study involving 12 users.  ...  To our knowledge, this is the first work to (a) expressly compare user vs content-centered AR for ads, and (b) study the relationship between modeling of ad emotions and its impact on a real-life advertising  ...  A very recent and closely related work to ours [30] discusses how e cient a ect recognition from ads via deep learning and multi-task learning can lead to improved online viewing experience.  ... 
doi:10.1145/3136755.3136796 dblp:conf/icmi/ShuklaGKYKS17 fatcat:63uuvmuh6bae3mayr4hvnn5zim

Cross-individual Recognition of Emotions by a Dynamic Entropy based on Pattern Learning with EEG features [article]

Xiaolong Zhong, Zhong Yin
2021 arXiv   pre-print
However, the type of EEG data constitutes an obstacle for cross-individual EEG feature modelling and classification.  ...  To address this issue, we propose a deep-learning framework denoted as a dynamic entropy-based pattern learning (DEPL) to abstract informative indicators pertaining to the neurophysiological features among  ...  We also would like to thank Google for providing free-cloud services.  ... 
arXiv:2009.12525v2 fatcat:bda4obq2ybhg3cvhum2c6fkhfe

An EEG-Based Image Annotation System [chapter]

Viral Parekh, Ramanathan Subramanian, Dipanjan Roy, C. V. Jawahar
2018 Communications in Computer and Information Science  
The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system.  ...  We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task.  ...  Deep learning features have proven advantages over hand-crafted features like SIFT and HoG [28] . We used a pre-trained VGG-19 model [29] to obtain the feature descriptors for the targets.  ... 
doi:10.1007/978-981-13-0020-2_27 fatcat:ql3ou6u5hvap5okrabefncdz3y

Dual Head and Dual Attention in Deep Learning for End-to-End EEG Motor Imagery Classification

Meiyan Xu, Junfeng Yao, Hualiang Ni
2021 Applied Sciences  
Firstly, a custom form of sequence inputs with spatial and temporal dimensions is adopted for dual headed attention via deep convolution net (DHDANet).  ...  However, it is difficult to recognize multiple tasks for non-trained subjects that are indispensable for the complexities of the task or the uncertainties in the environment.  ...  Acknowledgments: The authors thank all members of the Center for Digital Media Computing and the BCI laboratory at Xiamen Universiy for their discussions and inspiration.  ... 
doi:10.3390/app112210906 fatcat:ybbhzfdesvhtdftdcfll7zrxmq

Alzheimer's Disease Diagnosis Based on Cognitive Methods in Virtual Environments and Emotions Analysis [article]

Juan Manuel Fernández Montenegro
2018 arXiv   pre-print
EEG features are based on quaternions in order to keep the correlation information between sensors, whereas, for facial expression recognition, a preprocessing method for motion magnification and descriptors  ...  Data from this dataset is used to introduce novel descriptors for Electroencephalogram (EEG) and facial images data.  ...  The F1 scores with ten fold cross-validation showed the superiority of deep learning approaches and the suitability of this method, as it outperforms the other deep learning approach, which is based on  ... 
arXiv:1810.10941v1 fatcat:lrqvy6gqkvhszkxffxbq5iyut4

Spatial-Temporal Recurrent Neural Network for Emotion Recognition

Tong Zhang, Wenming Zheng, Zhen Cui, Yuan Zong, Yang Li
2018 IEEE Transactions on Cybernetics  
According to their common characteristics of spatial-temporal volumes, in this paper we propose a novel deep learning framework named spatial-temporal recurrent neural network (STRNN) to unify the learning  ...  As external appearances of human emotions, electroencephalogram (EEG) signals and video face signals are widely used to track and analyze human's affective information.  ...  For instances, for EEG based emotion recognition, descriptors such as high order crossings [6] and differential entropy (DE) [7] are employed, and popular classifiers such as support vector machine  ... 
doi:10.1109/tcyb.2017.2788081 pmid:29994572 fatcat:dm5cy7whw5bj3o6jg5riefqxuq

IEEE Access Special Section Editorial: Biologically Inspired Image Processing Challenges and Future Directions

Jiachen Yang, Qinggang Meng, Maurizio Murroni, Shiqi Wang, Feng Shao
2020 IEEE Access  
In the article, ''Deep multi-level semantic hashing for cross-modal retrieval,'' by Ji et al., the authors propose a novel deep hashing framework based on multi-level semantic supervision for multi-label  ...  The article, ''Multivariate pattern analysis of EEG-based functional connectivity: A study on the identification of depression,'' by Peng et al., identifies the altered electroencephalography (EEG) resting-state  ... 
doi:10.1109/access.2020.3015372 fatcat:styxiguqlnaprclkiamogmjc24

A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances [article]

Yan Wang, Wei Song, Wei Tao, Antonio Liotta, Dawei Yang, Xinlei Li, Shuyong Gao, Yixuan Sun, Weifeng Ge, Wei Zhang, Wenqiang Zhang
2022 arXiv   pre-print
Physical-based affect recognition caters to more researchers due to multiple public databases.  ...  Affective computing is realized based on unimodal or multimodal data, primarily consisting of physical information (e.g., textual, audio, and visual data) and physiological signals (e.g., EEG and ECG signals  ...  Based on the difference of commonly used DL-based architectures for FER tasks, we divided deep FER into deep ConvNet learning for FER, deep ConvNet-RNN learning for FER, and deep adversarial learning for  ... 
arXiv:2203.06935v3 fatcat:h4t3omkzjvcejn2kpvxns7n2qe

Machine learning in nD signal processing

Jiuwen Cao, Chuan-Yu Chang
2017 Multidimensional systems and signal processing  
A brief description of the papers in each of the three groups is given in the following.  ...  video recognition and tracking, bioinformatics and medical data processing, array signal processing, and voice recognition, etc.  ...  Jin et al. study a cross-modal feature learning based face descriptor to reduce the cross-modal differences and develop a multi-task learning algorithm integrated with ELM.  ... 
doi:10.1007/s11045-017-0489-5 fatcat:uzkigeacz5b3vfehlm3ms7dgsm

Multimodal Approach for Emotion Recognition Based on Simulated Flight Experiments

Válber César Cavalcanti Roza, Octavian Adrian Postolache
2019 Sensors  
The emotion recognition is based on Artificial Neural Networks and Deep Learning techniques.  ...  The cardiac system based on Heart Rate (HR), Galvanic Skin Response (GSR) and Electroencephalography (EEG), were used to extract emotions, as well as the intensities of emotions detected from the pilot  ...  Cross Validation-Testing Recognition Models All the emotion recognition test were executed based on the methodology of Leave-One-Out Cross Validation (LOOCV).  ... 
doi:10.3390/s19245516 pmid:31847210 pmcid:PMC6960577 fatcat:vv6gaj3xibespcnbexa2csvq5i

Recognition of Human Emotion using Radial Basis Function Neural Networks with Inverse Fisher Transformed Physiological Signals

Abdultaofeek Abayomi, ICT and Society Research Group, Department of Information Technology, Durban University of Technology, Durban, 4001, SOUTH AFRICA, Oludayo O. Olugbara, Delene Heukelman, ICT and Society Research Group, Department of Information Technology, Durban University of Technology, Durban, 4001, SOUTH AFRICA, ICT and Society Research Group, Department of Information Technology, Durban University of Technology, Durban, 4001, SOUTH AFRICA
2021 International Journal of Integrated Engineering  
Emotion is a complex state of human mind influenced by body physiological changes and interdependent external events thus making an automatic recognition of emotional state a challenging task.  ...  The motivation for this study is therefore to discover a combination of emotion features and recognition method that will produce the best result in building an efficient emotion recognizer in an affective  ...  Acknowledgement The authors would like to thank the Research and Postgraduate Support Directorate, Durban University of Technology, Durban for supporting this research study.  ... 
doi:10.30880/ijie.2021.13.06.001 fatcat:2dxbdnbxn5hetpdhz5blnaux4u
« Previous Showing results 1 — 15 out of 1,359 results