scholarly journals Prediction of epileptic seizures based on multivariate multiscale modified-distribution entropy

2021 ◽  
Vol 7 ◽  
pp. e744
Author(s):  
Si Thu Aung ◽  
Yodchanan Wongsawat
Keyword(s):  
Time Series ◽  
Data Analysis ◽  
Performance Measures ◽  
Multiple Scales ◽  
Multivariate Time Series ◽  
World Population ◽  
Prediction System ◽  
Seizure Prediction ◽  
Feature Extraction Method ◽  
Wide Range

Epilepsy is a common neurological disease that affects a wide range of the world population and is not limited by age. Moreover, seizures can occur anytime and anywhere because of the sudden abnormal discharge of brain neurons, leading to malfunction. The seizures of approximately 30% of epilepsy patients cannot be treated with medicines or surgery; hence these patients would benefit from a seizure prediction system to live normal lives. Thus, a system that can predict a seizure before its onset could improve not only these patients’ social lives but also their safety. Numerous seizure prediction methods have already been proposed, but the performance measures of these methods are still inadequate for a complete prediction system. Here, a seizure prediction system is proposed by exploring the advantages of multivariate entropy, which can reflect the complexity of multivariate time series over multiple scales (frequencies), called multivariate multiscale modified-distribution entropy (MM-mDistEn), with an artificial neural network (ANN). The phase-space reconstruction and estimation of the probability density between vectors provide hidden complex information. The multivariate time series property of MM-mDistEn provides more understandable information within the multichannel data and makes it possible to predict of epilepsy. Moreover, the proposed method was tested with two different analyses: simulation data analysis proves that the proposed method has strong consistency over the different parameter selections, and the results from experimental data analysis showed that the proposed entropy combined with an ANN obtains performance measures of 98.66% accuracy, 91.82% sensitivity, 99.11% specificity, and 0.84 area under the curve (AUC) value. In addition, the seizure alarm system was applied as a postprocessing step for prediction purposes, and a false alarm rate of 0.014 per hour and an average prediction time of 26.73 min before seizure onset were achieved by the proposed method. Thus, the proposed entropy as a feature extraction method combined with an ANN can predict the ictal state of epilepsy, and the results show great potential for all epilepsy patients.

Empirical analysis of time series using feature selection algorithms

2021 ◽  
Author(s):  
Mikhail Kanevski
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Feature Selection ◽  
Dimensional Space ◽  
Multivariate Time Series ◽  
Feature Space ◽  
Real Data ◽  
Theoretical Concepts ◽  
Wide Range ◽  
Linear And Nonlinear

<p>Nowadays a wide range of methods and tools to study and forecast time series is available. An important problem in forecasting concerns embedding of time series, i.e. construction of a high dimensional space where forecasting problem is considered as a regression task. There are several basic linear and nonlinear approaches of constructing such space by defining an optimal delay vector using different theoretical concepts. Another way is to consider this space as an input feature space – IFS, and to apply machine learning feature selection (FS) algorithms to optimize IFS according to the problem under study (analysis, modelling or forecasting). Such approach is an empirical one: it is based on data and depends on the FS algorithms applied. In machine learning features are generally classified as relevant, redundant and irrelevant. It gives a reach possibility to perform advanced multivariate time series exploration and development of interpretable predictive models.</p><p>Therefore, in the present research different FS algorithms are used to analyze fundamental properties of time series from empirical point of view. Linear and nonlinear simulated time series are studied in detail to understand the advantages and drawbacks of the proposed approach. Real data case studies deal with air pollution and wind speed times series. Preliminary results are quite promising and more research is in progress.</p>

scholarly journals StreamStory: Exploring Multivariate Time Series on Multiple Scales

2019 ◽  
Vol 25 (4) ◽  
pp. 1788-1802 ◽  
Author(s):  
Luka Stopar ◽  
Primoz Skraba ◽  
Marko Grobelnik ◽  
Dunja Mladenic
Keyword(s):  
Time Series ◽  
Multiple Scales ◽  
Multivariate Time Series

scholarly journals Time-Aware Multi-Scale RNNs for Time Series Modeling

2021 ◽  
Author(s):  
Zipeng Chen ◽  
Qianli Ma ◽  
Zhenxi Lin
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Multiple Scales ◽  
Multivariate Time Series ◽  
Human Motion ◽  
Series Data ◽  
Time Step ◽  
Multi Scale ◽  
Important Time ◽  
Time Aware

Multi-scale information is crucial for modeling time series. Although most existing methods consider multiple scales in the time-series data, they assume all kinds of scales are equally important for each sample, making them unable to capture the dynamic temporal patterns of time series. To this end, we propose Time-Aware Multi-Scale Recurrent Neural Networks (TAMS-RNNs), which disentangle representations of different scales and adaptively select the most important scale for each sample at each time step. First, the hidden state of the RNN is disentangled into multiple independently updated small hidden states, which use different update frequencies to model time-series multi-scale information. Then, at each time step, the temporal context information is used to modulate the features of different scales, selecting the most important time-series scale. Therefore, the proposed model can capture the multi-scale information for each time series at each time step adaptively. Extensive experiments demonstrate that the model outperforms state-of-the-art methods on multivariate time series classification and human motion prediction tasks. Furthermore, visualized analysis on music genre recognition verifies the effectiveness of the model.

Multivariate Time Series Data Mining in Ship Monitoring Database

2017 ◽  
Vol 139 (6) ◽  
Author(s):  
Afshin Abbasi Hoseini ◽  
Sverre Steen
Keyword(s):  
Data Mining ◽  
Time Series ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Principal Component ◽  
Series Data ◽  
Specific Information ◽  
Self Organizing Map ◽  
Time Series Data Mining ◽  
Wide Range

A framework is presented for data mining in multivariate time series collected over hours of ship operation to extract vessel states from the data. The measurements made by a ship monitoring system lead to a collection of time-organized in-service data. Usually, these time series datasets are big, complicated, and highly dimensional. The purpose of time-series data mining is to bridge the gap between a massive database and meaningful information hidden behind the data. An important aspect of the framework proposed is selecting relevant variables, eliminating unnecessary information or noises, and extracting the essential features of the problem so that the vessel behavior can be identified reliably. Principal component analysis (PCA) is employed to address the issues of multicollinearity in the data and dimensionality reduction. The data mining approach itself is established on unsupervised data clustering using self-organizing map (SOM) and k-means, and k-nearest neighbors search (k-NNS) for searching and recovering specific information from the database. As a case study, the results are based on onboard monitoring data of the Norwegian University of Science and Technology (NTNU) research vessel, “Gunnerus.” The scope of this work is limited to detecting ship maneuvers. However, it is extendable to a wide range of smart marine applications. As illustrated in the results, this approach is effective in identifying the prior unknown states of the ship with acceptable accuracy.

The Oxford Handbook of Functional Data Analysis

2018 ◽  
Keyword(s):  
Time Series ◽  
Data Analysis ◽  
Functional Data Analysis ◽  
Functional Data ◽  
Principal Component ◽  
Regression Modeling ◽  
Functional Principal Component Analysis ◽  
Functional Regression ◽  
Vector Integration ◽  
Wide Range

This handbook presents the state-of-the-art of the statistics dealing with functional data analysis. With contributions from international experts in the field, it discusses a wide range of the most important statistical topics (classification, inference, factor-based analysis, regression modeling, resampling methods, time series, random processes) while also taking into account practical, methodological, and theoretical aspects of the problems. The book is organised into three sections. Part I deals with regression modeling and covers various statistical methods for functional data such as linear/nonparametric functional regression, varying coefficient models, and linear/nonparametric functional processes (i.e. functional time series). Part II considers related benchmark methods/tools for functional data analysis, including curve registration methods for preprocessing functional data, functional principal component analysis, and resampling/bootstrap methods. Finally, Part III examines some of the fundamental mathematical aspects of the infinite-dimensional setting, with a focus on the stochastic background and operatorial statistics: vector-valued function integration, spectral and random measures linked to stationary processes, operator geometry, vector integration and stochastic integration in Banach spaces, and operatorial statistics linked to quantum statistics.

Sign in / Sign up

Export Citation Format

Share Document