Time Series Classification

163 papers with code • 29 benchmarks • 7 datasets

Time Series Classification is a general task that can be useful across many subject-matter domains and applications. The overall goal is to identify a time series as coming from one of possibly many sources or predefined groups, using labeled training data. That is, in this setting we conduct supervised learning, where the different time series sources are considered known.

Source: Nonlinear Time Series Classification Using Bispectrum-based Deep Convolutional Neural Networks


Use these libraries to find Time Series Classification models and implementations
4 papers
3 papers
3 papers
3 papers
See all 9 libraries.

Most implemented papers

Latent ODEs for Irregularly-Sampled Time Series

YuliaRubanova/latent_ode 8 Jul 2019

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs).

Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline

cauchyturing/UCR_Time_Series_Classification_Deep_Learning_Baseline 20 Nov 2016

We propose a simple but strong baseline for time series classification from scratch with deep neural networks.

LSTM Fully Convolutional Networks for Time Series Classification

houshd/LSTM-FCN 8 Sep 2017

We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification.

Multivariate LSTM-FCNs for Time Series Classification

houshd/MLSTM-FCN 14 Jan 2018

Over the past decade, multivariate time series classification has received great attention.

Recurrent Neural Networks for Multivariate Time Series with Missing Values

PeterChe1990/GRU-D 6 Jun 2016

Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values.

Deep learning for time series classification: a review

hfawaz/dl-4-tsc 12 Sep 2018

We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC.

LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection

chickenbestlover/RNN-Time-series-Anomaly-Detection 1 Jul 2016

Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine.

InceptionTime: Finding AlexNet for Time Series Classification

hfawaz/InceptionTime 11 Sep 2019

TSC is the area of machine learning tasked with the categorization (or labelling) of time series.

ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

angus924/rocket 29 Oct 2019

Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets.

Precision and Recall for Time Series

IntelLabs/TSAD-Evaluator NeurIPS 2018

Classical anomaly detection is principally concerned with point-based anomalies, those anomalies that occur at a single point in time.