TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Time Series Classification	ArabicDigits	MALSTM-FCN	Accuracy	0.99	# 4
Time Series Classification	AUSLAN	MALSTM-FCN	Accuracy	0.96	# 5
Time Series Classification	CharacterTrajectories	MALSTM-FCN	Accuracy	1	# 1
Time Series Classification	CMUsubject16	MALSTM-FCN	Accuracy	1	# 1
Time Series Classification	DigitShapes	MALSTM-FCN	Accuracy	1	# 1
Time Series Classification	ECG	MALSTM-FCN	Accuracy	0.86	# 1
Time Series Classification	JapaneseVowels	MALSTM-FCN	Accuracy	0.99	# 1
Time Series Classification	KickvsPunch	MALSTM-FCN	Accuracy	1	# 1
Time Series Classification	Libras	MALSTM-FCN	Accuracy	0.97	# 1
Time Series Classification	LP1	MALSTM-FCN	Accuracy	0.82	# 1
Time Series Classification	LP2	MALSTM-FCN	Accuracy	0.77	# 1
Time Series Classification	LP3	MALSTM-FCN	Accuracy	0.73	# 1
Time Series Classification	LP4	MALSTM-FCN	Accuracy	0.93	# 1
Time Series Classification	LP5	MALSTM-FCN	Accuracy	0.67	# 1
Time Series Classification	NetFlow	MALSTM-FCN	Accuracy	0.95	# 2
Time Series Classification	pendigits	MALSTM-FCN	Accuracy	0.97	# 1
Time Series Classification	SHAPES	MALSTM-FCN	Accuracy	1	# 1
Time Series Classification	UWave	MALSTM-FCN	Accuracy	0.98	# 1
Time Series Classification	Wafer	MALSTM-FCN	Accuracy	0.99	# 2
Time Series Classification	WalkvsRun	MALSTM-FCN	Accuracy	1	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on)](https://paperswithcode.com/sota/time-series-classification-on?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-cmusubject16)](https://paperswithcode.com/sota/time-series-classification-on-cmusubject16?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-digitshapes)](https://paperswithcode.com/sota/time-series-classification-on-digitshapes?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-ecg)](https://paperswithcode.com/sota/time-series-classification-on-ecg?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-japanesevowels)](https://paperswithcode.com/sota/time-series-classification-on-japanesevowels?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-kickvspunch)](https://paperswithcode.com/sota/time-series-classification-on-kickvspunch?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-libras)](https://paperswithcode.com/sota/time-series-classification-on-libras?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-lp1)](https://paperswithcode.com/sota/time-series-classification-on-lp1?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-lp2)](https://paperswithcode.com/sota/time-series-classification-on-lp2?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-lp3)](https://paperswithcode.com/sota/time-series-classification-on-lp3?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-lp4)](https://paperswithcode.com/sota/time-series-classification-on-lp4?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-lp5)](https://paperswithcode.com/sota/time-series-classification-on-lp5?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-pendigits-1)](https://paperswithcode.com/sota/time-series-classification-on-pendigits-1?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-shapes)](https://paperswithcode.com/sota/time-series-classification-on-shapes?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-uwave)](https://paperswithcode.com/sota/time-series-classification-on-uwave?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-walkvsrun)](https://paperswithcode.com/sota/time-series-classification-on-walkvsrun?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-netflow)](https://paperswithcode.com/sota/time-series-classification-on-netflow?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-wafer)](https://paperswithcode.com/sota/time-series-classification-on-wafer?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-arabicdigits)](https://paperswithcode.com/sota/time-series-classification-on-arabicdigits?p=multivariate-lstm-fcns-for-time-series)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multivariate-lstm-fcns-for-time-series/time-series-classification-on-auslan)](https://paperswithcode.com/sota/time-series-classification-on-auslan?p=multivariate-lstm-fcns-for-time-series)`

Multivariate LSTM-FCNs for Time Series Classification

14 Jan 2018 · Fazle Karim, Somshubra Majumdar, Houshang Darabi, Samuel Harford ·

Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems.

PDF Abstract

Code

Add Remove Mark official

houshd/MLSTM-FCN official

timeseriesAI/tsai

2,887

titu1994/LSTM-FCN

626

titu1994/MLSTM-FCN

395

houshd/LSTM-FCN

122

See all 8 implementations

Tasks

Add Remove

Action Recognition

Activity Recognition

General Classification

Temporal Action Localization

Time Series

Time Series Classification

Datasets

SHAPES

PenDigits

Results from the Paper

Edit

Ranked #1 on Time Series Classification on pendigits

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Time Series Classification	ArabicDigits	MALSTM-FCN	Accuracy	0.99	# 4	Compare
Time Series Classification	AUSLAN	MALSTM-FCN	Accuracy	0.96	# 5	Compare
Time Series Classification	CharacterTrajectories	MALSTM-FCN	Accuracy	1	# 1	Compare
Time Series Classification	CMUsubject16	MALSTM-FCN	Accuracy	1	# 1	Compare
Time Series Classification	DigitShapes	MALSTM-FCN	Accuracy	1	# 1	Compare
Time Series Classification	ECG	MALSTM-FCN	Accuracy	0.86	# 1	Compare
Time Series Classification	JapaneseVowels	MALSTM-FCN	Accuracy	0.99	# 1	Compare
Time Series Classification	KickvsPunch	MALSTM-FCN	Accuracy	1	# 1	Compare
Time Series Classification	Libras	MALSTM-FCN	Accuracy	0.97	# 1	Compare
Time Series Classification	LP1	MALSTM-FCN	Accuracy	0.82	# 1	Compare
Time Series Classification	LP2	MALSTM-FCN	Accuracy	0.77	# 1	Compare
Time Series Classification	LP3	MALSTM-FCN	Accuracy	0.73	# 1	Compare
Time Series Classification	LP4	MALSTM-FCN	Accuracy	0.93	# 1	Compare
Time Series Classification	LP5	MALSTM-FCN	Accuracy	0.67	# 1	Compare
Time Series Classification	NetFlow	MALSTM-FCN	Accuracy	0.95	# 2	Compare
Time Series Classification	pendigits	MALSTM-FCN	Accuracy	0.97	# 1	Compare
Time Series Classification	SHAPES	MALSTM-FCN	Accuracy	1	# 1	Compare
Time Series Classification	UWave	MALSTM-FCN	Accuracy	0.98	# 1	Compare
Time Series Classification	Wafer	MALSTM-FCN	Accuracy	0.99	# 2	Compare
Time Series Classification	WalkvsRun	MALSTM-FCN	Accuracy	1	# 1	Compare

Methods

Add Remove

Average Pooling • Convolution • Dense Connections • ReLU • Sigmoid Activation • Squeeze-and-Excitation Block

Edit Social Preview

Multivariate LSTM-FCNs for Time Series Classification

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove