Object classification with convolution neural network based on the time-frequency representation of their echo

Mariia Dmitrieva, Matias Valdenegro Toro, Keith Brown, Gary Heald, David Lane

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents classification of spherical objects with different physical properties. The classification is based on the energy distribution in wideband pulses that have been scattered from objects. The echo is represented in Time-Frequency Domain (TFD), using Short Time Fourier Transform (STFT) with different window lengths, and is fed into a Convolution Neural Network (CNN) for classification. The results for different window lengths are analysed to study the influence of time and frequency resolution in classification. The CNN performs the best results with accuracy of (98.44 ± 0.8)% over 5 object classes trained on grayscale TFD images with 0.1 ms window length of STFT. The CNN is compared with a Multilayer Perceptron classifier, Support Vector Machine, and Gradient Boosting.

Original languageEnglish
Title of host publication2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
PublisherIEEE
ISBN (Electronic)9781509063413
DOIs
Publication statusPublished - 7 Dec 2017
Event2017 IEEE 27th International Workshop on Machine Learning for Signal Processing - Tokyo, Japan
Duration: 25 Sep 201728 Sep 2017

Conference

Conference2017 IEEE 27th International Workshop on Machine Learning for Signal Processing
Abbreviated titleMLSP 2017
CountryJapan
CityTokyo
Period25/09/1728/09/17

Fingerprint

Convolution
Neural networks
Fourier transforms
Multilayer neural networks
Support vector machines
Classifiers
Physical properties

Keywords

  • Convolution neural networks
  • Object classification
  • Time-frequency representation
  • Wideband pulses

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Cite this

Dmitrieva, M., Valdenegro Toro, M., Brown, K., Heald, G., & Lane, D. (2017). Object classification with convolution neural network based on the time-frequency representation of their echo. In 2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) [8168134] IEEE. https://doi.org/10.1109/MLSP.2017.8168134
Dmitrieva, Mariia ; Valdenegro Toro, Matias ; Brown, Keith ; Heald, Gary ; Lane, David. / Object classification with convolution neural network based on the time-frequency representation of their echo. 2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2017.
@inproceedings{a16bcf70550d46f68fd3f4a1cd517edc,
title = "Object classification with convolution neural network based on the time-frequency representation of their echo",
abstract = "This paper presents classification of spherical objects with different physical properties. The classification is based on the energy distribution in wideband pulses that have been scattered from objects. The echo is represented in Time-Frequency Domain (TFD), using Short Time Fourier Transform (STFT) with different window lengths, and is fed into a Convolution Neural Network (CNN) for classification. The results for different window lengths are analysed to study the influence of time and frequency resolution in classification. The CNN performs the best results with accuracy of (98.44 ± 0.8){\%} over 5 object classes trained on grayscale TFD images with 0.1 ms window length of STFT. The CNN is compared with a Multilayer Perceptron classifier, Support Vector Machine, and Gradient Boosting.",
keywords = "Convolution neural networks, Object classification, Time-frequency representation, Wideband pulses",
author = "Mariia Dmitrieva and {Valdenegro Toro}, Matias and Keith Brown and Gary Heald and David Lane",
year = "2017",
month = "12",
day = "7",
doi = "10.1109/MLSP.2017.8168134",
language = "English",
booktitle = "2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)",
publisher = "IEEE",
address = "United States",

}

Dmitrieva, M, Valdenegro Toro, M, Brown, K, Heald, G & Lane, D 2017, Object classification with convolution neural network based on the time-frequency representation of their echo. in 2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)., 8168134, IEEE, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing, Tokyo, Japan, 25/09/17. https://doi.org/10.1109/MLSP.2017.8168134

Object classification with convolution neural network based on the time-frequency representation of their echo. / Dmitrieva, Mariia; Valdenegro Toro, Matias; Brown, Keith; Heald, Gary; Lane, David.

2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2017. 8168134.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Object classification with convolution neural network based on the time-frequency representation of their echo

AU - Dmitrieva, Mariia

AU - Valdenegro Toro, Matias

AU - Brown, Keith

AU - Heald, Gary

AU - Lane, David

PY - 2017/12/7

Y1 - 2017/12/7

N2 - This paper presents classification of spherical objects with different physical properties. The classification is based on the energy distribution in wideband pulses that have been scattered from objects. The echo is represented in Time-Frequency Domain (TFD), using Short Time Fourier Transform (STFT) with different window lengths, and is fed into a Convolution Neural Network (CNN) for classification. The results for different window lengths are analysed to study the influence of time and frequency resolution in classification. The CNN performs the best results with accuracy of (98.44 ± 0.8)% over 5 object classes trained on grayscale TFD images with 0.1 ms window length of STFT. The CNN is compared with a Multilayer Perceptron classifier, Support Vector Machine, and Gradient Boosting.

AB - This paper presents classification of spherical objects with different physical properties. The classification is based on the energy distribution in wideband pulses that have been scattered from objects. The echo is represented in Time-Frequency Domain (TFD), using Short Time Fourier Transform (STFT) with different window lengths, and is fed into a Convolution Neural Network (CNN) for classification. The results for different window lengths are analysed to study the influence of time and frequency resolution in classification. The CNN performs the best results with accuracy of (98.44 ± 0.8)% over 5 object classes trained on grayscale TFD images with 0.1 ms window length of STFT. The CNN is compared with a Multilayer Perceptron classifier, Support Vector Machine, and Gradient Boosting.

KW - Convolution neural networks

KW - Object classification

KW - Time-frequency representation

KW - Wideband pulses

UR - http://www.scopus.com/inward/record.url?scp=85042296264&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2017.8168134

DO - 10.1109/MLSP.2017.8168134

M3 - Conference contribution

BT - 2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

PB - IEEE

ER -

Dmitrieva M, Valdenegro Toro M, Brown K, Heald G, Lane D. Object classification with convolution neural network based on the time-frequency representation of their echo. In 2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE. 2017. 8168134 https://doi.org/10.1109/MLSP.2017.8168134