scholarly journals F4: An All-Purpose Tool for Multivariate Time Series Classification

Mathematics ◽  
2021 ◽  
Vol 9 (23) ◽  
pp. 3051
Author(s):  
Ángel López-Oriona ◽  
José A. Vilar
Keyword(s):  
Time Series ◽  
Multivariate Time Series ◽  
Discrete Wavelet ◽  
Time Series Classification ◽  
East Anglia ◽  
Ecg Signals ◽  
Novel Approach ◽  
Cross Spectral Density ◽  
The University ◽  
Electrocardiogram Ecg

We propose Fast Forest of Flexible Features (F4), a novel approach for classifying multivariate time series, which is aimed to discriminate between underlying generating processes. This goal has barely been addressed in the literature. F4 consists of two steps. First, a set of features based on the quantile cross-spectral density and the maximum overlap discrete wavelet transform are extracted from each series. Second, a random forest is fed with the extracted features. An extensive simulation study shows that F4 outperforms some powerful classifiers in a wide variety of situations, including stationary and nonstationary series. The proposed method is also capable of successfully discriminating between electrocardiogram (ECG) signals of healthy subjects and those with myocardial infarction condition. Additionally, despite lacking shape-based information, F4 attains state-of-the-art results in some datasets of the University of East Anglia (UEA) multivariate time series classification archive.

scholarly journals A Novel Channel and Temporal-Wise Attention in Convolutional Networks for Multivariate Time Series Classification

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 212247-212257
Author(s):  
Xu Cheng ◽  
Peihua Han ◽  
Guoyuan Li ◽  
Shengyong Chen ◽  
Houxiang Zhang
Keyword(s):  
Time Series ◽  
Multivariate Time Series ◽  
Time Series Classification ◽  
Convolutional Networks

Information-based analysis of the coupling between brain and heart reactions to olfactory stimulation

2021 ◽  
pp. 1-11
Author(s):  
Najmeh Pakniyat ◽  
Mohammad Hossein Babini ◽  
Vladimir V. Kulish ◽  
Hamidreza Namazi
Keyword(s):  
Time Series ◽  
Biomedical Science ◽  
Strongly Correlated ◽  
Eeg Signals ◽  
Ecg Signals ◽  
Olfactory Stimuli ◽  
Electrocardiogram Ecg ◽  
First Time ◽  
Electroencephalogram Eeg ◽  
The Brain

BACKGROUND: Analysis of the heart activity is one of the important areas of research in biomedical science and engineering. For this purpose, scientists analyze the activity of the heart in various conditions. Since the brain controls the heart’s activity, a relationship should exist among their activities. OBJECTIVE: In this research, for the first time the coupling between heart and brain activities was analyzed by information-based analysis. METHODS: Considering Shannon entropy as the indicator of the information of a system, we recorded electroencephalogram (EEG) and electrocardiogram (ECG) signals of 13 participants (7 M, 6 F, 18–22 years old) in different external stimulations (using pineapple, banana, vanilla, and lemon flavors as olfactory stimuli) and evaluated how the information of EEG signals and R-R time series (as heart rate variability (HRV)) are linked. RESULTS: The results indicate that the changes in the information of the R-R time series and EEG signals are strongly correlated (ρ=-0.9566). CONCLUSION: We conclude that heart and brain activities are related.

scholarly journals Uncertainty quantification of the effects of biotic interactions on community dynamics from nonlinear time-series data

2018 ◽  
Vol 15 (147) ◽  
pp. 20180695 ◽  
Author(s):  
Simone Cenci ◽  
Serguei Saavedra
Keyword(s):  
Time Series ◽  
Community Dynamics ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Model Averaging ◽  
Biotic Interactions ◽  
Series Data ◽  
Time Intervals ◽  
Novel Approach ◽  
Data Generating Process

Biotic interactions are expected to play a major role in shaping the dynamics of ecological systems. Yet, quantifying the effects of biotic interactions has been challenging due to a lack of appropriate methods to extract accurate measurements of interaction parameters from experimental data. One of the main limitations of existing methods is that the parameters inferred from noisy, sparsely sampled, nonlinear data are seldom uniquely identifiable. That is, many different parameters can be compatible with the same dataset and can generalize to independent data equally well. Hence, it is difficult to justify conclusive assertions about the effect of biotic interactions without information about their associated uncertainty. Here, we develop an ensemble method based on model averaging to quantify the uncertainty associated with the effect of biotic interactions on community dynamics from non-equilibrium ecological time-series data. Our method is able to detect the most informative time intervals for each biotic interaction within a multivariate time series and can be easily adapted to different regression schemes. Overall, this novel approach can be used to associate a time-dependent uncertainty with the effect of biotic interactions. Moreover, because we quantify uncertainty with minimal assumptions about the data-generating process, our approach can be applied to any data for which interactions among variables strongly affect the overall dynamics of the system.

scholarly journals Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Prediction

2021 ◽  
Author(s):  
Fatemehalsadat Madaeni ◽  
Karem Chokmani ◽  
Rachid Lhissou ◽  
Saeid Homayuni ◽  
Yves Gauthier ◽  
...  
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Weather Forecasting ◽  
Multivariate Time Series ◽  
Water Levels ◽  
Time Series Classification ◽  
Ice Jams ◽  
Ice Jam ◽  
Learning Techniques ◽  
Long Short Term Memory

Abstract. In cold regions, ice-jam events result in severe flooding due to a rapid rise in water levels upstream of the jam. These floods threaten human safety and damage properties and infrastructures as the floods resulting from ice-jams are sudden. Hence, the ice-jam prediction tools can give an early warning to increase response time and minimize the possible corresponding damages. However, the ice-jam prediction has always been a challenging problem as there is no analytical method available for this purpose. Nonetheless, ice jams form when some hydro-meteorological conditions happen, a few hours to a few days before the event. The ice-jam prediction problem can be considered as a binary multivariate time-series classification. Deep learning techniques have been successfully applied for time-series classification in many fields such as finance, engineering, weather forecasting, and medicine. In this research, we successfully applied CNN, LSTM, and combined CN-LSTM networks for ice-jam prediction for all the rivers in Quebec. The results show that the CN-LSTM model yields the best results in the validation and generalization with F1 scores of 0.82 and 0.91, respectively. This demonstrates that CNN and LSTM models are complementary, and a combination of them further improves classification.

Time-Frequency Deep Metric Learning for Multivariate Time Series Classification

2021 ◽  
Author(s):  
Zhi Chen ◽  
Yongguo Liu ◽  
Jiajing Zhu ◽  
Yun Zhang ◽  
Rongjiang Jin ◽  
...  
Keyword(s):  
Time Series ◽  
Multivariate Time Series ◽  
Metric Learning ◽  
Time Series Classification ◽  
Time Frequency ◽  
Deep Metric Learning
Sign in / Sign up

Export Citation Format

Share Document