Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images
This paper proposes a framework to perform the sensor classification by using multivariate time series sensors data as inputs. The framework encodes multivariate time series data into two-dimensional colored images, and concatenate the images into one bigger image for classification through a Convol...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/1/168 |
id |
doaj-0f3066ac89d74bb9b31c4de4fe169fb1 |
---|---|
record_format |
Article |
spelling |
doaj-0f3066ac89d74bb9b31c4de4fe169fb12020-11-25T02:19:36ZengMDPI AGSensors1424-82202019-12-0120116810.3390/s20010168s20010168Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored ImagesChao-Lung Yang0Zhi-Xuan Chen1Chen-Yi Yang2Department of Industrial Management, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Industrial Management, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Industrial Management, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanThis paper proposes a framework to perform the sensor classification by using multivariate time series sensors data as inputs. The framework encodes multivariate time series data into two-dimensional colored images, and concatenate the images into one bigger image for classification through a Convolutional Neural Network (ConvNet). This study applied three transformation methods to encode time series into images: Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), and Markov Transition Field (MTF). Two open multivariate datasets were used to evaluate the impact of using different transformation methods, the sequences of concatenating images, and the complexity of ConvNet architectures on classification accuracy. The results show that the selection of transformation methods and the sequence of concatenation do not affect the prediction outcome significantly. Surprisingly, the simple structure of ConvNet is sufficient enough for classification as it performed equally well with the complex structure of VGGNet. The results were also compared with other classification methods and found that the proposed framework outperformed other methods in terms of classification accuracy.https://www.mdpi.com/1424-8220/20/1/168time series classificationmultivariate time seriesimage concatenationconvolutional neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chao-Lung Yang Zhi-Xuan Chen Chen-Yi Yang |
spellingShingle |
Chao-Lung Yang Zhi-Xuan Chen Chen-Yi Yang Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images Sensors time series classification multivariate time series image concatenation convolutional neural network |
author_facet |
Chao-Lung Yang Zhi-Xuan Chen Chen-Yi Yang |
author_sort |
Chao-Lung Yang |
title |
Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images |
title_short |
Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images |
title_full |
Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images |
title_fullStr |
Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images |
title_full_unstemmed |
Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images |
title_sort |
sensor classification using convolutional neural network by encoding multivariate time series as two-dimensional colored images |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-12-01 |
description |
This paper proposes a framework to perform the sensor classification by using multivariate time series sensors data as inputs. The framework encodes multivariate time series data into two-dimensional colored images, and concatenate the images into one bigger image for classification through a Convolutional Neural Network (ConvNet). This study applied three transformation methods to encode time series into images: Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), and Markov Transition Field (MTF). Two open multivariate datasets were used to evaluate the impact of using different transformation methods, the sequences of concatenating images, and the complexity of ConvNet architectures on classification accuracy. The results show that the selection of transformation methods and the sequence of concatenation do not affect the prediction outcome significantly. Surprisingly, the simple structure of ConvNet is sufficient enough for classification as it performed equally well with the complex structure of VGGNet. The results were also compared with other classification methods and found that the proposed framework outperformed other methods in terms of classification accuracy. |
topic |
time series classification multivariate time series image concatenation convolutional neural network |
url |
https://www.mdpi.com/1424-8220/20/1/168 |
work_keys_str_mv |
AT chaolungyang sensorclassificationusingconvolutionalneuralnetworkbyencodingmultivariatetimeseriesastwodimensionalcoloredimages AT zhixuanchen sensorclassificationusingconvolutionalneuralnetworkbyencodingmultivariatetimeseriesastwodimensionalcoloredimages AT chenyiyang sensorclassificationusingconvolutionalneuralnetworkbyencodingmultivariatetimeseriesastwodimensionalcoloredimages |
_version_ |
1724875638399041536 |