Multivariate Time Series Data

Multivariate time series data analysis focuses on understanding and extracting insights from data involving multiple variables measured over time, aiming to improve prediction, anomaly detection, and classification accuracy. Current research emphasizes advanced preprocessing techniques to handle missing data and class imbalance, alongside the application of deep learning models like recurrent neural networks (RNNs), transformers, variational autoencoders (VAEs), and graph neural networks (GNNs), often integrated with contrastive learning or generative adversarial networks (GANs). These advancements are crucial for diverse applications, including space weather forecasting, industrial process monitoring, and financial modeling, where accurate predictions and timely anomaly detection are critical for risk mitigation and improved decision-making.

Papers

February 27, 2023

A Self-Supervised Learning-based Approach to Clustering Multivariate Time-Series Data with Missing Values (SLAC-Time): An Application to TBI Phenotyping
Hamid Ghaderi, Brandon Foreman, Amin Nayebi, Sindhu Tipirneni, Chandan K. Reddy, Vignesh Subbian
Self Supervised Time Matter Learning Based Approach Multivariate Time Series Data Traumatic Brain Injury

February 17, 2023

DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data
Lingrui Yu
Anomaly Detection Multivariate Time Series Data

November 11, 2022

Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction
Thanh Trung Huynh, Minh Hieu Nguyen, Thanh Tam Nguyen, Phi Le Nguyen, Matthias Weidlich, Quoc Viet Hung Nguyen, Karl Aberer
Multivariate Time Series Data Stock Movement Prediction Stock Market Data Numerical Integration Order Dynamic Intrinsic Dynamic

September 22, 2022

STING: Self-attention based Time-series Imputation Networks using GAN
Eunkyu Oh, Taehun Kim, Yunhu Ji, Sushil Khyalia
Self Attention GAN Model Multivariate Time Series Imputation Method Multivariate Time Series Data Imputation Accuracy Signal Imputation

September 9, 2022

Autoencoder Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm
Jonas Köhne, Lars Henning, Clemens Gühmann
Recurrent Neural Network Multivariate Time Series Data Time Series Clustering Iterative Neural Network Time Series Subsequence Transient Imaging Data

August 31, 2022

Learning Multiscale Non-stationary Causal Structures
Gabriele D'Acunto, Gianmarco De Francisci Morales, Paolo Bajardi, Francesco Bonchi
Causal Graph Causal Effect Causal Structure Multivariate Time Series Data Causal Theory

May 20, 2022

Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder
Susumu Naito, Yasunori Taguchi, Kouta Nakata, Yuichi Kato
Anomaly Detection Multivariate Time Series Multivariate Time Series Data Dimensional Signal

May 9, 2022

Deep Federated Anomaly Detection for Multivariate Time Series Data
Wei Zhu, Dongjin Song, Yuncong Chen, Wei Cheng, Bo Zong, Takehiko Mizoguchi, Cristian Lumezanu, Haifeng Chen, Jiebo Luo
Anomaly Detection Unsupervised Anomaly Detection Multivariate Time Series Data State of the Art Anomaly Time Series Representation

April 23, 2022

Dimension Reduction for time series with Variational AutoEncoders
William Todo, Beatrice Laurent, Jean-Michel Loubes, Merwann Selmani
Time Series Variational Autoencoders Dimensionality Reduction Dimension Reduction Multivariate Time Series Data

February 26, 2022

Regularized Bilinear Discriminant Analysis for Multivariate Time Series Data
Jianhua Zhao, Haiye Liang, Shulan Li, Zhiji Yang, Zhen Wang
Model Selection Multivariate Time Series Data Discriminant Analysis Multivariate Time Series Classification Multilinear Discriminant Analysis

February 25, 2022

Long-Term Missing Value Imputation for Time Series Data Using Deep Neural Networks
Jangho Park, Juliane Muller, Bhavna Arora, Boris Faybishenko, Gilberto Pastorello, Charuleka Varadharajan, Reetik Sahu, Deborah Agarwal
Deep Neural Network Multi Layer Long Term Time Series Data Filling Gap Multivariate Time Series Data Time Series Imputation Missing Value Imputation

February 8, 2022

Contrastive predictive coding for Anomaly Detection in Multi-variate Time Series Data
Theivendiram Pranavan, Terence Sim, Arulmurugan Ambikapathi, Savitha Ramasamy
Anomaly Detection Time Series Latent Representation Multivariate Time Series Data Time Series Representation Learning Contrastive Predictive Coding

January 18, 2022

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data
Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Deep Learning Anomaly Detection Multivariate Time Series Data Deep Transformer Efficient Anomaly Detection

November 26, 2021

Correlation Based Feature Subset Selection for Multivariate Time-Series Data
Bahavathy Kathirgamanathan, Padraig Cunningham
Multivariate Time Series Data Feature Subset

Multivariate Time Series Data

Papers

A Self-Supervised Learning-based Approach to Clustering Multivariate Time-Series Data with Missing Values (SLAC-Time): An Application to TBI Phenotyping

DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data

Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction

STING: Self-attention based Time-series Imputation Networks using GAN

Autoencoder Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm

Learning Multiscale Non-stationary Causal Structures

Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder

Deep Federated Anomaly Detection for Multivariate Time Series Data

Dimension Reduction for time series with Variational AutoEncoders

Regularized Bilinear Discriminant Analysis for Multivariate Time Series Data

Long-Term Missing Value Imputation for Time Series Data Using Deep Neural Networks

Contrastive predictive coding for Anomaly Detection in Multi-variate Time Series Data

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

Correlation Based Feature Subset Selection for Multivariate Time-Series Data