599 Hits in 9.7 sec

Exploiting Patterns for Handling Incomplete Coevolving EEG Time Series

Ngoc Anh Nguyen Thi, Hyung-Jeong Yang, Sun-Hee Kim
2013 International Journal of Contents  
From these exploits, the proposed method successfully identifies a few hidden variables and discovers their dynamics to impute missing values.  ...  The proposed method aims to capture the optimal patterns based on two main characteristics in the coevolving EEG time series: namely, (i) dynamics via discovering temporal evolving behaviors, and (ii)  ...  the hidden dynamics in multiple EEG time series signals.  ... 
doi:10.5392/ijoc.2013.9.4.001 fatcat:74jo34altfe2jibxwqzs2zlfoq

SRI-EEG: State-Based Recurrent Imputation for EEG Artifact Correction

Yimeng Liu, Tobias Höllerer, Misha Sra
2022 Frontiers in Computational Neuroscience  
Our goal is to detect physiological artifacts in EEG signal and automatically replace the detected artifacts with imputed values to enable robust EEG sensing overall requiring significantly reduced manual  ...  While EEG signals can be beneficial for numerous types of interaction scenarios in the real world, high levels of noise limits their usage to strictly noise-controlled environments such as a research laboratory  ...  ACKNOWLEDGMENTS We would like to thank Barry Giesbrecht and Tom Bullock for providing and contextualizing the bike dataset and also Yi Ding for valuable discussions.  ... 
doi:10.3389/fncom.2022.803384 pmid:35669387 pmcid:PMC9163298 fatcat:cd2ttsm7tzaxnkdqitq6g7upcm

Cross-evidence for hypnotic susceptibility through nonlinear measures on EEGs of non-hypnotized subjects

Riccardo Chiarucci, Dario Madeo, Maria I. Loffredo, Eleonora Castellani, Enrica L. Santarcangelo, Chiara Mocenni
2014 Scientific Reports  
A satisfying classification obtained through quantitative measures is still missing, although it would be very useful for both diagnostic and clinical purposes.  ...  Indicators obtained through the application of these techniques to EEG signals of individuals in their ordinary state of consciousness allowed us to obtain a clear discrimination between subjects with  ...  The value of this exponent can discriminate between (short or long-range) correlated and uncorrelated time series.  ... 
doi:10.1038/srep05610 pmid:25002038 pmcid:PMC4085592 fatcat:d5ve42vegzfgdiuso3sj76qfry

Research on epileptic EEG recognition based on improved residual networks of 1-D CNN and indRNN

Mengnan Ma, Yinlin Cheng, Xiaoyan Wei, Ziyi Chen, Yi Zhou
2021 BMC Medical Informatics and Decision Making  
In recent years, automatic epilepsy diagnosis of EEG by deep learning had attracted more and more attention.  ...  The model can provide automatic detection capabilities for clinical epilepsy EEG detection. We hoped to provide a positive significance for the prediction of epileptic seizures EEG.  ...  And the authors thank the anonymous reviewers for their careful review and valuable comments. 1  ... 
doi:10.1186/s12911-021-01438-5 fatcat:qtspgkmen5bcnk3jy3rdvqr3pm

Generative Adversarial Networks for Spatio-temporal Data: A Survey [article]

Nan Gao, Hao Xue, Wei Shao, Sichen Zhao, Kyle Kai Qin, Arian Prabowo, Mohammad Saiedur Rahaman, Flora D. Salim
2021 arXiv   pre-print
Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation and time-series data imputation.  ...  In this paper, we have conducted a comprehensive review of the recent developments of GANs for spatio-temporal data.  ...  The missing values in time series make it hard for effective analysis [49] . One popular way to handle the missing values of time series is to impute the missing values to get the complete dataset.  ... 
arXiv:2008.08903v3 fatcat:pbhxbfgw65bodksjdmwazwo4dq

Real-Time Medical Electronic Data Mining Based Hierarchical Attention Mechanism

Yi Mao, Yun Li, Yixin Chen
2020 ICIC Express Letters  
time series.  ...  In this paper, we recur to hierarchical attention and encoder-to-decoder based model to automatically learn features from medical records of time series of vital sign, categorical features which include  ...  A large amount of information in a time series is hidden in its structure, not only in numerical values.  ... 
doi:10.24507/icicel.14.12.1155 fatcat:hqbycbrvknbltmihden2hgl6v4

Classification of Sparse Time Series via Supervised Matrix Factorization

Josif Grabocka, Alexandros Nanopoulos, Lars Schmidt-Thieme
Consecutively, numerous machine learning methods were modeled to treat missing values.  ...  We propose a novel principle for classifying time series, which in contrast to existing approaches, avoids reconstructing the missing segments in time series and operates solely on the observed ones.  ...  Specifically, missing segments are reconstructed by mimicking pattern structures from other time series, during the same time interval as the missing segment.  ... 
doi:10.1609/aaai.v26i1.8271 fatcat:ga5efhekifglth3cqyizd362su

Recognition of Patient Groups with Sleep Related Disorders using Bio-signal Processing and Deep Learning

Delaram Jarchi, Javier Andreu-Perez, Mehrin Kiani, Oldrich Vysata, Jiri Kuchynka, Ales Prochazka, Saeid Sanei
2020 Sensors  
Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders.  ...  In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders.  ...  This will produce a new time-series corresponding to instantaneous frequencies. For this new time-series, the sampling interval is fixed as 1/fs where fs is the sampling frequency.  ... 
doi:10.3390/s20092594 pmid:32370185 pmcid:PMC7248846 fatcat:65wcfavfujgz5eka7bhjfbiyyq

Learning brain dynamics for decoding and predicting individual differences

Joyneel Misra, Srinivas Govinda Surampudi, Manasij Venkatesh, Chirag Limbachia, Joseph Jaja, Luiz Pessoa, Daniele Marinazzo
2021 PLoS Computational Biology  
The model was also able to learn individual differences in measures of fluid intelligence and verbal IQ at levels comparable to that of existing techniques.  ...  Our approach provides a framework for visualizing, analyzing, and discovering dynamic spatially distributed brain representations during naturalistic conditions.  ...  The permutation-based test draws from ideas used in the MEG/EEG field to evaluate if two time series differ in time [52] . Specifically, our method was as follows.  ... 
doi:10.1371/journal.pcbi.1008943 pmid:34478442 pmcid:PMC8445454 fatcat:nxt75mv6xzbwfnjaq72wsmxlpa

Learning brain dynamics for decoding and predicting individual differences [article]

Luiz Pessoa, Chirag Limbachia, Joyneel Misra, Srinivas Govinda Surampudi, Manasij Venkatesh, Joseph Jaja
2021 bioRxiv   pre-print
The model was also able to learn individual differences in measures of fluid intelligence and verbal IQ at levels comparable or better than existing techniques.  ...  We believe our approach provides a powerful framework for visualizing, analyzing, and discovering dynamic spatially distributed brain representations during naturalistic conditions.  ...  test draws from ideas used in the MEG/EEG field to evaluate if 267 two time series differ in time [40] .  ... 
doi:10.1101/2021.03.27.437315 fatcat:iapz4oqy75awpl3tgvfcxb4zfq

Bio-Signal Complexity Analysis in Epileptic Seizure Monitoring: A Topic Review

Zhenning Mei, Xian Zhao, Hongyu Chen, Wei Chen
2018 Sensors  
By delving into the complexity in electrophysiological signals and neuroimaging, new insights have emerged.  ...  Despite the promising results about epileptic seizure detection and prediction through offline analysis, we are still lacking robust, tried-and-true real-time applications.  ...  time series in different resolution levels.  ... 
doi:10.3390/s18061720 pmid:29861451 pmcid:PMC6022076 fatcat:owwowgqp7za5ll5ph5lrpiysma

DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series prediction [article]

Yeqi Liu, Chuanyang Gong, Ling Yang, Yingyi Chen
2019 arXiv   pre-print
RNN (DSTP-RNN) and DSTP-RNN-2 respectively for long-term time series prediction.  ...  Attention-based recurrent neural networks (RNN) can effectively represent the dynamic spatio-temporal relationships between exogenous series and target series, but it only performs well in one-step time  ...  In fact, the supervised dataset reconstruction based on target series is the key to use traditional machine learning method for time series prediction, which reflects the effect of past information of  ... 
arXiv:1904.07464v1 fatcat:enelhyel2vf3paq2klqxzqetpi

Applying Deep Learning to Individual and Community Health Monitoring Data: A Survey

Zhen-Jie Yao, Jie Bi, Yi-Xin Chen
2018 International Journal of Automation and Computing  
Nowadays, application of deep learning to solve the problems in healthcare is a hot research direction. This paper introduces the application of deep learning in healthcare extensively.  ...  In the recent years, deep learning models have addressed many problems in various fields. Meanwhile, technology development has spawned the big data in healthcare rapidly.  ...  It takes two representations of missing patterns and effectively incor-porates them into a deep model architecture so that it not only captures the long-term temporal dependencies in time series, but also  ... 
doi:10.1007/s11633-018-1136-9 fatcat:drp2ixw3dvb5thxxnuzl4vjqsu

Priority-based transformations of stimulus representation in visual working memory

Quan Wan, Jorge A. Menendez, Bradley R. Postle, Tim Buschman
2022 PLoS Computational Biology  
To acquire independent evidence for such a priority-based representational transformation, and to explore underlying mechanisms, we trained recurrent neural networks (RNNs) with a long short-term memory  ...  This type of transformation could allow for retention of unprioritized information in WM while preventing it from interfering with concurrent behavior.  ...  Yuri Saalmann, Joseph Austerweil, Timothy Rogers, Jacqueline Fulvio, Qing Yu and Mohsen Afrasiabi for helpful discussion and critical feedback.  ... 
doi:10.1371/journal.pcbi.1009062 pmid:35653404 pmcid:PMC9197029 fatcat:dcnqnnm7pfeyvdkzv42brjoaim

Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset [article]

Desmond C. Ong, Zhengxuan Wu, Tan Zhi-Xuan, Marianne Reddan, Isabella Kahhale, Alison Mattek, Jamil Zaki
2019 arXiv   pre-print
We end by discussing the implications for future research in time-series affective computing.  ...  Modeling dynamic emotional stimuli requires solving the twin challenges of time-series modeling and of collecting high-quality time-series datasets.  ...  This work was supported in part by the A*STAR Human-Centric Artificial Intelligence Programme (SERC SSF Project No.  ... 
arXiv:1912.05008v1 fatcat:g5tmrhdluvf57nru6mkqrevfjy
« Previous Showing results 1 — 15 out of 599 results