Filters








16,647 Hits in 5.9 sec

Combined head phantom and neural mass model validation of effective connectivity measures

Steven M Peterson, Daniel P Ferris
2019 Journal of Neural Engineering  
While many connectivity estimators are available, the efficacy of these measures has not been rigorously validated in real-world scenarios.  ...  Due to its high temporal resolution, electroencephalography (EEG) has become a promising tool for quantifying cortical dynamics and effective connectivity in a mobile setting.  ...  Acknowledgments We would like to thank Jean Vettel and Manuel Vindiola at the Army Research Lab for providing the neural mass model and assisting with its implementation.  ... 
doi:10.1088/1741-2552/aaf60e pmid:30523864 pmcid:PMC6448772 fatcat:6j3wdyrbl5egpmtlcnxyrarrne

Mapping distinct timescales of functional interactions among brain networks

Mali Sundaresan, Arshed Nabeel, Devarajan Sridharan
2019 Advances in Neural Information Processing Systems  
Due to the slow sampling rate of fMRI, it is widely held that GC produces spurious and unreliable estimates of functional connectivity when applied to fMRI data.  ...  resonance imaging (fMRI) data.  ...  We would like to thank Hritik Jain for help with data analysis.  ... 
pmid:31285649 pmcid:PMC6614036 fatcat:hgzscu353vdfhkxyqbfnkos7bm

Pruning neural network for architecture optimization applied to near-infrared reflectance spectroscopic measurements. Determination of the nitrogen content in wheat leaves

Cesar Mello, Ronei J. Poppi, João Carlos de Andrade, Heitor Cantarella
1999 The Analyst  
This network pruning procedure was applied for estimating the nitrogen contents in wheat leaves, using near-infrared diffuse reflectance spectroscopy.  ...  Although the comparison was performed for one data set, the pruning procedure has the advantage of introducing an automatic architecture optimization, which is cumbersome when performed by the other neural  ...  Collins for critically reading the manuscript.  ... 
doi:10.1039/a905570c fatcat:ew5lagyt75af7jqtq6tvb7nx44

Learning-based AC-OPF Solvers on Realistic Network and Realistic Loads [article]

Tsun Ho Aaron Cheung, Min Zhou, Minghua Chen
2022 arXiv   pre-print
Trained on samples with bus loads generated from a fitted multivariate normal distribution, our learning-based AC-OPF solver achieves 0.13% cost optimality gap, 99.73% feasibility rate, and 38.62 times  ...  Feasibility-optimized end-to-end deep neural network models are trained and tested on the constructed dataset.  ...  It is a problem faced daily by power companies that, if solved reliably in near real-time, could result in tremendous savings in operation costs.  ... 
arXiv:2205.09452v1 fatcat:yo2pqguscrbqdnpvvqf5t3i5jy

A state-space model for dynamic functional connectivity

Sourish Chakravarty, Zachary D. Threlkeld, Yelena G. Bodien, Brian L. Edlow, Emery N. Brown
2019 2019 53rd Asilomar Conference on Signals, Systems, and Computers  
Dynamic functional connectivity (DFC) analysis involves measuring correlated neural activity over time across multiple brain regions.  ...  To address this issue, we propose a multivariate stochastic volatility model for estimating DFC inspired by recent work in econometrics research.  ...  Therefore, DFC analysis involves estimating a time-series of pairwise correlations from multivariate neural data.  ... 
doi:10.1109/ieeeconf44664.2019.9048807 pmid:32801606 pmcid:PMC7425228 fatcat:imb33si7wrfc5itmbnisauhio4

Multi-Connection Pattern Analysis: Decoding the Representational Content of Neural Communication [article]

Yuanning Li, Robert Mark Richardson, Avniel Singh Ghuman
2016 bioRxiv   pre-print
The lack of multivariate methods for decoding the representational content of interregional neural communication has left it difficult to know what information is represented in distributed brain circuit  ...  Here we present Multi-Connection Pattern Analysis (MCPA), which works by learning mappings between the activity patterns of the populations as a factor of the information being processed.  ...  Acknowledgements We would like to thank the patient for participating in the iEEG experiments, and Dr. R. Mark Richardson, Michael Ward and the epilepsy monitoring unit staff, Cheryl Plummer,  ... 
doi:10.1101/046441 fatcat:me3v7ymza5h2blvhbzzkcbtciq

BSMART: A Matlab/C toolbox for analysis of multichannel neural time series

Jie Cui, Lei Xu, Steven L. Bressler, Mingzhou Ding, Hualou Liang
2008 Neural Networks  
We have developed a Matlab/C toolbox, Brain-SMART (System for Multivariate AutoRegressive Time series, or BSMART), for spectral analysis of continuous neural time series data recorded simultaneously from  ...  Available functions include time series data importing/exporting, preprocessing (normalization and trend removal), AutoRegressive (AR) modeling (multivariate/bivariate model estimation and validation),  ...  Richard Nakamura of the National Institute of Mental Health for providing the sample data set of event-related LFP time series used in BSMART.  ... 
doi:10.1016/j.neunet.2008.05.007 pmid:18599267 pmcid:PMC2585694 fatcat:zjgggt7cafajvje334w7lmif4y

Using Neural Networks for Simulating and Predicting Core-End Temperatures in Electrical Generators: Power Uprate Application

Carlos J. Gavilán Moreno
2015 World Journal of Engineering and Technology  
The model was successfully applied to estimate temperatures associated to 108% power and used to extrapolate temperature values for a power uprate to 113.48%.  ...  The mathematical model developed was based on an artificial intelligence technique, more specifically neural networks.  ...  that neural network temperature output values match real values.  ... 
doi:10.4236/wjet.2015.31001 fatcat:od4wk7wexjazxa6xti2rnkgou4

Similarity representation of pattern-information fMRI

ShaoWei Xue, XuChu Weng, Sheng He, DianWen Li
2013 Chinese Science Bulletin  
Representational similarity analysis (RSA) is a rapidly developing multivariate platform to investigate the structure of neural activities.  ...  This review summarizes dissimilarity/similarity definition of RSA, introduces how to derive the dissimilarity structure in neural response pattern, and carry out connectivity analysis based on RSA platform  ...  in the GLM model; then the estimated coefficient of GLM (beta value) for each predictor and each voxel is obtained and forms the basis for computation of the representational dissimilarities.  ... 
doi:10.1007/s11434-013-5743-0 fatcat:af6oc4nmnjftrapukernlxkv6u

Analysis of Time Series Prediction using Recurrent Neural Networks

Gaurav Yadav, Richa Vasuja
2019 International Journal of Computer Applications  
can provide the vital help and safety or the advancement for the change, though the future is uncertain but people must know their future as near it could be to the future.  ...  Based on the research this paper contains analytical data of recurrent neural network and its use with time series alongside the experimental data analysis of weather forecast and financial forecast data  ...  ARIMA was feeded with same parameters and feature spaces as LSTM and GRU for same collected rendered data to predict the values for Bitcoin which found to have RMSE of 255.90 and had training time of 0.6169  ... 
doi:10.5120/ijca2019918732 fatcat:u2ighcayznegbcjty42d4j7mle

Efficient estimation of neural weights by polynomial approximation

G. Ritter
1999 IEEE Transactions on Information Theory  
It has been known for some years that the uniformdensity problem for forward neural networks has a positive answer: Any real-valued, continuous function on a compact subset of R R R d can be uniformly  ...  This theorem, in turn, is a consequence of a close relationship between neural networks of nearly exponential type and multivariate algebraic and exponential polynomials.  ...  ACKNOWLEDGMENT The author thanks Herr Christoph Pesch for his help with the SNNS and a referee for pointing out [2] and [8] and a weakness of Algorithm 4.1 that led to the formulation of Algorithm  ... 
doi:10.1109/18.771153 fatcat:tvp5brxe2fcepdbennkblomyfe

A Hybrid Model of Bidirectional Long-Short Term Memory and CNN for Multivariate Time Series Classification of Remote Sensing Data

Sawsan Morkos Gharghory
2021 Journal of Computer Science  
The proposed Conv-BiLSTM is carried out for classifying the land cover multivariate time series of Landsat 8 satellite images.  ...  The traditional modeling classifiers are complicated patterns and are incompetent to capture the dependencies of multivariate time series data.  ...  band of twenty three time series data for different classes of land cover.  ... 
doi:10.3844/jcssp.2021.789.802 fatcat:7ck4p675xfbx5iqjmwlrxl2ome

A state-space model for dynamic functional connectivity [article]

Sourish Chakravarty, Zachary D. Threlkeld, Yelena G. Bodien, Brian L. Edlow, Emery N. Brown
2019 arXiv   pre-print
Dynamic functional connectivity (DFC) analysis involves measuring correlated neural activity over time across multiple brain regions.  ...  To address this issue, we propose a multivariate stochastic volatility model for estimating DFC inspired by recent work in econometrics research.  ...  Therefore, DFC analysis involves estimating a time-series of pairwise correlations from multivariate neural data.  ... 
arXiv:1912.05595v1 fatcat:mn6gtnhduffqpd7wrfesgvvipu

Deep Learning Framework for Physical Internet Hubs Inbound Containers Forecasting

El-Sayed Orabi Helmi, Osama Emam, Mohamed Abdel-Salam
2022 International Journal of Advanced Computer Science and Applications  
Second, the framework uses convolutional neural network (CNN) and recurrent neural network (RNN) as training networks for the historical time series data in two techniques.  ...  The proposed framework uses univariate and multivariate time series analysis to explore the maximum forecasting outcomes.  ...  Multivariate analysis is more suitable for real life applications because of its high conclusion accuracy.  ... 
doi:10.14569/ijacsa.2022.0130327 fatcat:tms2jmmwt5gdjmxrqdwdsj2fl4

Torus graphs for multivariate phase coupling analysis

Natalie Klein, Josue Orellana, Scott L. Brincat, Earl K. Miller, Robert E. Kass
2020 Annals of Applied Statistics  
Torus graphs thus unify multivariate analysis of circular data and present fertile territory for future research.  ...  For such vectors we present here a class of graphical models, which we call torus graphs, based on the full exponential family with pairwise interactions.  ...  The authors thank the reviewers for their valuable feedback. Robert E. Kass, N. Klein and J.  ... 
doi:10.1214/19-aoas1300 fatcat:m6wgyiktm5h7fjihhukkverq3a
« Previous Showing results 1 — 15 out of 16,647 results