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

doi:10.1109/MLSP.2017.8168134

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 proceeding › Conference contribution

11 Citations (Scopus)

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 language	English
Title of host publication	2017 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
Publisher	IEEE
ISBN (Electronic)	9781509063413
DOIs	https://doi.org/10.1109/MLSP.2017.8168134
Publication status	Published - 7 Dec 2017
Event	2017 IEEE 27th International Workshop on Machine Learning for Signal Processing - Tokyo, Japan Duration: 25 Sept 2017 → 28 Sept 2017

Conference

Conference	2017 IEEE 27th International Workshop on Machine Learning for Signal Processing
Abbreviated title	MLSP 2017
Country/Territory	Japan
City	Tokyo
Period	25/09/17 → 28/09/17

Keywords

Convolution neural networks
Object classification
Time-frequency representation
Wideband pulses

ASJC Scopus subject areas

Human-Computer Interaction
Signal Processing

Access to Document

10.1109/MLSP.2017.8168134

Cite this

@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 = dec,

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",

note = "2017 IEEE 27th International Workshop on Machine Learning for Signal Processing, MLSP 2017 ; Conference date: 25-09-2017 Through 28-09-2017",

}

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

Research output: Chapter in Book/Report/Conference proceeding › Conference 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

AN - SCOPUS:85042296264

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

PB - IEEE

T2 - 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing

Y2 - 25 September 2017 through 28 September 2017

ER -

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

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this