Sparse representation for time-series classification

Soheil Bahrampour, Nasser M. Nasrabadi, Asok Ray

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter studies the problem of time-series classification and presents an overview of recent developments in the area of feature extraction and information fusion. In particular, a recently proposed feature extraction algorithm, namely symbolic dynamic filtering (SDF), is reviewed. The SDF algorithm generates low-dimensional feature vectors using proba- bilistic finite state automata that are well-suited for discriminative tasks. The chapter also presents the recent developments in the area of sparse- representation-based algorithms for multimodal classification. This in- cludes the joint sparse representation that enforces collaboration across all the modalities as well as the tree-structured sparsity that provides a exible framework for fusion of modalities at multiple granularities. Fur- thermore, unsupervised and supervised dictionary learning algorithms are reviewed. The performance of the algorithms are evaluated on a set of field data that consist of passive infrared and seismic sensors.

Original languageEnglish (US)
Title of host publicationPattern Recognition and Big Data
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages199-215
Number of pages17
ISBN (Electronic)9789813144552
ISBN (Print)9789813144545
DOIs
StatePublished - Dec 15 2016

Fingerprint

Time series
Feature extraction
Information fusion
Finite automata
Glossaries
Learning algorithms
Infrared radiation
Sensors

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Bahrampour, S., Nasrabadi, N. M., & Ray, A. (2016). Sparse representation for time-series classification. In Pattern Recognition and Big Data (pp. 199-215). World Scientific Publishing Co. Pte Ltd. https://doi.org/10.1142/9789813144552_0007
Bahrampour, Soheil ; Nasrabadi, Nasser M. ; Ray, Asok. / Sparse representation for time-series classification. Pattern Recognition and Big Data. World Scientific Publishing Co. Pte Ltd, 2016. pp. 199-215
@inbook{7165675a61ab48dda43c7921c6522d18,
title = "Sparse representation for time-series classification",
abstract = "This chapter studies the problem of time-series classification and presents an overview of recent developments in the area of feature extraction and information fusion. In particular, a recently proposed feature extraction algorithm, namely symbolic dynamic filtering (SDF), is reviewed. The SDF algorithm generates low-dimensional feature vectors using proba- bilistic finite state automata that are well-suited for discriminative tasks. The chapter also presents the recent developments in the area of sparse- representation-based algorithms for multimodal classification. This in- cludes the joint sparse representation that enforces collaboration across all the modalities as well as the tree-structured sparsity that provides a exible framework for fusion of modalities at multiple granularities. Fur- thermore, unsupervised and supervised dictionary learning algorithms are reviewed. The performance of the algorithms are evaluated on a set of field data that consist of passive infrared and seismic sensors.",
author = "Soheil Bahrampour and Nasrabadi, {Nasser M.} and Asok Ray",
year = "2016",
month = "12",
day = "15",
doi = "10.1142/9789813144552_0007",
language = "English (US)",
isbn = "9789813144545",
pages = "199--215",
booktitle = "Pattern Recognition and Big Data",
publisher = "World Scientific Publishing Co. Pte Ltd",
address = "Singapore",

}

Bahrampour, S, Nasrabadi, NM & Ray, A 2016, Sparse representation for time-series classification. in Pattern Recognition and Big Data. World Scientific Publishing Co. Pte Ltd, pp. 199-215. https://doi.org/10.1142/9789813144552_0007

Sparse representation for time-series classification. / Bahrampour, Soheil; Nasrabadi, Nasser M.; Ray, Asok.

Pattern Recognition and Big Data. World Scientific Publishing Co. Pte Ltd, 2016. p. 199-215.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Sparse representation for time-series classification

AU - Bahrampour, Soheil

AU - Nasrabadi, Nasser M.

AU - Ray, Asok

PY - 2016/12/15

Y1 - 2016/12/15

N2 - This chapter studies the problem of time-series classification and presents an overview of recent developments in the area of feature extraction and information fusion. In particular, a recently proposed feature extraction algorithm, namely symbolic dynamic filtering (SDF), is reviewed. The SDF algorithm generates low-dimensional feature vectors using proba- bilistic finite state automata that are well-suited for discriminative tasks. The chapter also presents the recent developments in the area of sparse- representation-based algorithms for multimodal classification. This in- cludes the joint sparse representation that enforces collaboration across all the modalities as well as the tree-structured sparsity that provides a exible framework for fusion of modalities at multiple granularities. Fur- thermore, unsupervised and supervised dictionary learning algorithms are reviewed. The performance of the algorithms are evaluated on a set of field data that consist of passive infrared and seismic sensors.

AB - This chapter studies the problem of time-series classification and presents an overview of recent developments in the area of feature extraction and information fusion. In particular, a recently proposed feature extraction algorithm, namely symbolic dynamic filtering (SDF), is reviewed. The SDF algorithm generates low-dimensional feature vectors using proba- bilistic finite state automata that are well-suited for discriminative tasks. The chapter also presents the recent developments in the area of sparse- representation-based algorithms for multimodal classification. This in- cludes the joint sparse representation that enforces collaboration across all the modalities as well as the tree-structured sparsity that provides a exible framework for fusion of modalities at multiple granularities. Fur- thermore, unsupervised and supervised dictionary learning algorithms are reviewed. The performance of the algorithms are evaluated on a set of field data that consist of passive infrared and seismic sensors.

UR - http://www.scopus.com/inward/record.url?scp=85059464911&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059464911&partnerID=8YFLogxK

U2 - 10.1142/9789813144552_0007

DO - 10.1142/9789813144552_0007

M3 - Chapter

AN - SCOPUS:85059464911

SN - 9789813144545

SP - 199

EP - 215

BT - Pattern Recognition and Big Data

PB - World Scientific Publishing Co. Pte Ltd

ER -

Bahrampour S, Nasrabadi NM, Ray A. Sparse representation for time-series classification. In Pattern Recognition and Big Data. World Scientific Publishing Co. Pte Ltd. 2016. p. 199-215 https://doi.org/10.1142/9789813144552_0007