Minimum Variance Extreme Learning Machine for human action recognition

Alexandros Iosifidis; Anastasios Tefas; Ioannis Pitas

doi:10.1109/ICASSP.2014.6854640

Minimum Variance Extreme Learning Machine for human action recognition

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

Department of Electrical & Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

31 Citations (Scopus)

324 Downloads (Pure)

Abstract

Layer Feedforward Neural networks training. Based on the observation that the learning process of such networks can be considered to be a non-linear mapping of the training data to a high-dimensional feature space, followed by a data projection process to a low-dimensional space where classification is performed by a linear classifier, we extend the Extreme Learning Machine (ELM) algorithm in order to exploit the training data dispersion in its optimization process. The proposed Minimum Variance Extreme Learning Machine classifier is evaluated in human action recognition, where we compare its performance with that of other ELM-based classifiers, as well as the kernel Support Vector Machine classifier.

Original language	English
Title of host publication	2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)
Subtitle of host publication	Proceedings of a meeting held 4-9 May 2014, Florence, Italy
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	5427-5431
Number of pages	5
ISBN (Electronic)	9781479928927
ISBN (Print)	9781479928941
DOIs	https://doi.org/10.1109/ICASSP.2014.6854640
Publication status	Published - Sept 2014
Event	2014 IEEE International Conference on Acoustics, Speech and Signal Processing - Florence, Italy Duration: 4 May 2014 → 9 May 2014

Publication series

Name	Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	1520-6149

Conference

Conference	2014 IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	ICASSP '14
Country/Territory	Italy
City	Florence
Period	4/05/14 → 9/05/14

Keywords

Single-hidden Layer Feedforward Neural networks
Extreme Learning Machine
Human Action Recognition
Classification

Access to Document

10.1109/ICASSP.2014.6854640

Ioannis Pitas - Minimum variance extreme learning machine for human action recognition - 2014
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6854640. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 593 KB

Handle.net

Persistent link

Cite this

Iosifidis, A., Tefas, A., & Pitas, I. (2014). Minimum Variance Extreme Learning Machine for human action recognition. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014): Proceedings of a meeting held 4-9 May 2014, Florence, Italy (pp. 5427-5431). (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2014.6854640

Iosifidis, Alexandros ; Tefas, Anastasios ; Pitas, Ioannis. / Minimum Variance Extreme Learning Machine for human action recognition. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014): Proceedings of a meeting held 4-9 May 2014, Florence, Italy. Institute of Electrical and Electronics Engineers (IEEE), 2014. pp. 5427-5431 (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).

@inproceedings{9880f79b7460421b93cc25a42040699d,

title = "Minimum Variance Extreme Learning Machine for human action recognition",

abstract = "Layer Feedforward Neural networks training. Based on the observation that the learning process of such networks can be considered to be a non-linear mapping of the training data to a high-dimensional feature space, followed by a data projection process to a low-dimensional space where classification is performed by a linear classifier, we extend the Extreme Learning Machine (ELM) algorithm in order to exploit the training data dispersion in its optimization process. The proposed Minimum Variance Extreme Learning Machine classifier is evaluated in human action recognition, where we compare its performance with that of other ELM-based classifiers, as well as the kernel Support Vector Machine classifier.",

keywords = "Single-hidden Layer Feedforward Neural networks, Extreme Learning Machine, Human Action Recognition, Classification",

author = "Alexandros Iosifidis and Anastasios Tefas and Ioannis Pitas",

year = "2014",

month = sep,

doi = "10.1109/ICASSP.2014.6854640",

language = "English",

isbn = "9781479928941",

series = "Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "5427--5431",

booktitle = "2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)",

address = "United States",

note = "2014 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '14 ; Conference date: 04-05-2014 Through 09-05-2014",

}

Iosifidis, A, Tefas, A & Pitas, I 2014, Minimum Variance Extreme Learning Machine for human action recognition. in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014): Proceedings of a meeting held 4-9 May 2014, Florence, Italy. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers (IEEE), pp. 5427-5431, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, 4/05/14. https://doi.org/10.1109/ICASSP.2014.6854640

Minimum Variance Extreme Learning Machine for human action recognition. / Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis.
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014): Proceedings of a meeting held 4-9 May 2014, Florence, Italy. Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 5427-5431 (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Minimum Variance Extreme Learning Machine for human action recognition

AU - Iosifidis, Alexandros

AU - Tefas, Anastasios

AU - Pitas, Ioannis

PY - 2014/9

Y1 - 2014/9

N2 - Layer Feedforward Neural networks training. Based on the observation that the learning process of such networks can be considered to be a non-linear mapping of the training data to a high-dimensional feature space, followed by a data projection process to a low-dimensional space where classification is performed by a linear classifier, we extend the Extreme Learning Machine (ELM) algorithm in order to exploit the training data dispersion in its optimization process. The proposed Minimum Variance Extreme Learning Machine classifier is evaluated in human action recognition, where we compare its performance with that of other ELM-based classifiers, as well as the kernel Support Vector Machine classifier.

AB - Layer Feedforward Neural networks training. Based on the observation that the learning process of such networks can be considered to be a non-linear mapping of the training data to a high-dimensional feature space, followed by a data projection process to a low-dimensional space where classification is performed by a linear classifier, we extend the Extreme Learning Machine (ELM) algorithm in order to exploit the training data dispersion in its optimization process. The proposed Minimum Variance Extreme Learning Machine classifier is evaluated in human action recognition, where we compare its performance with that of other ELM-based classifiers, as well as the kernel Support Vector Machine classifier.

KW - Single-hidden Layer Feedforward Neural networks

KW - Extreme Learning Machine

KW - Human Action Recognition

KW - Classification

U2 - 10.1109/ICASSP.2014.6854640

DO - 10.1109/ICASSP.2014.6854640

M3 - Conference Contribution (Conference Proceeding)

SN - 9781479928941

T3 - Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

SP - 5427

EP - 5431

BT - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 4 May 2014 through 9 May 2014

ER -

Iosifidis A, Tefas A, Pitas I. Minimum Variance Extreme Learning Machine for human action recognition. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014): Proceedings of a meeting held 4-9 May 2014, Florence, Italy. Institute of Electrical and Electronics Engineers (IEEE). 2014. p. 5427-5431. (Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). doi: 10.1109/ICASSP.2014.6854640

Minimum Variance Extreme Learning Machine for human action recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this