Multivariate Time Series Information Bottleneck
Entropy, 2023 Time series (TS) and multiple time series (MTS) predictions have historically paved the way for distinct families of deep learning models. The temporal dimension, distinguished by its evolutionary sequential aspect, is usually modeled by decomposition ...
Denis Ullmann +2 more
doaj +3 more sources
Explicit Future Pattern-Enhanced Multivariate Time Series Forecasting [PDF]
EntropyMultivariate time series forecasting requires models to infer future values and how the temporal structure evolves beyond the observation boundary. A central challenge is to define this evolution as an intermediate prediction and connect it to value ...
Yaokang Li +4 more
doaj +2 more sources
Hyperbolic adaptive spatial-aware multivariate time series anomaly detection [PDF]
Nature CommunicationsExisting multivariate anomaly detection methods suffer from practical industrial limitations stemming from distribution assumptions, volatile data and scarce reliable anomaly labels.
Jiaxin Han +7 more
doaj +2 more sources
Pre-trained multi-scale RWKV-GCN for multivariate time series forecasting [PDF]
Scientific ReportsMultivariate time series forecasting faces two key challenges: capturing intra-series temporal dependencies and inter-series spatial dependencies. However, heterogeneous cross-scale correlations and noise from unrelated series may obscure temporal ...
Jianhua Hao, Fangai Liu, Weiwei Zhang
doaj +2 more sources
A multiscale model for multivariate time series forecasting [PDF]
Scientific ReportsTransformer based models for time-series forecasting have shown promising performance and during the past few years different Transformer variants have been proposed in time-series forecasting domain.
Vahid Naghashi +2 more
doaj +2 more sources
Multivariate Time Series Anomaly Detection Based on Inverted Transformer with Multivariate Memory Gate [PDF]
EntropyIn the industrial IoT, it is vital to detect anomalies in multivariate time series, yet it faces numerous challenges, including highly imbalanced datasets, complex and high-dimensional data, and large disparities across variables.
Yuan Ma +5 more
doaj +2 more sources
FreFilterTST: a dynamic channel graph sparsification approach to multivariate time series anomaly detection with frequency-domain restoration [PDF]
Scientific ReportsThe scope of time series anomaly detection is increasingly shifting from univariate to multivariate contexts, as a growing number of real-world problems can no longer be adequately addressed by analyzing individual variables in isolation.
Yi Wang, Jian Jie Zhang, Ming Yang Zhang
doaj +2 more sources
Multivariate epidemic count time series model.
PLoS ONE, 2023 An infectious disease spreads not only over a single population or community but also across multiple and heterogeneous communities. Moreover, its transmissibility varies over time because of various factors such as seasonality and epidemic control ...
Shinsuke Koyama
doaj +1 more source
Multivariate semi-blind deconvolution of fMRI time series
NeuroImage, 2021 Whole brain estimation of the haemodynamic response function (HRF) in functional magnetic resonance imaging (fMRI) is critical to get insight on the global status of the neurovascular coupling of an individual in healthy or pathological condition.
Hamza Cherkaoui +4 more
doaj +1 more source
Multivariate time series classification using kernel matrix
Electronics Letters, 2022 Multivariate time series (MTS) classification is a fundamental problem in time series mining, and the approach based on covariance matrix is an attractive way to solve the classification. In this study, it is noted that a traditional covariance matrix is
Jiancheng Sun +4 more
doaj +1 more source