Machine Learning Algorithms to Detect Penetrations of PVDF

Yayu Zhai; Ping Song; Xiaoxiao Chen

doi:10.1109/ICSESS.2018.8663727

Machine Learning Algorithms to Detect Penetrations of PVDF

Yayu Zhai, Ping Song^*, Xiaoxiao Chen

^*Corresponding author for this work

School of Mechatronical Engineering

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Polyvinylidene fluoride (PVDF) has widely used in detecting the interplanetary dust. In the case of penetration and non-penetration, the output signals of the PVDF are quite different. Detecting whether particles penetrate PVDF is a crucial issue. We create a set of experimental equipment for collecting the signals from the PVDF. The equipment consists of particle emitter, shield, conditioning circuits and data acquisition equipment. 600 experiments are conducted. Among 200 experiments, the particles penetrate PVDF. We successfully distinguish penetration of PVDF using four machine learning algorithms: Anomaly Detection (AD), Artificial Neural Network (ANN), K-Nearest-Neighbors (KNN), and Support Vector Machines (SVM). We propose a unique evaluation criteria OP to evaluate the performance of four classifiers including their accuracy and computational time. The results show that ANN is the best machine learning algorithm for our problem, and AD is not suitable for our problem.

Original language	English
Title of host publication	ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science
Editors	Li Wenzheng, M. Surendra Prasad Babu
Publisher	IEEE Computer Society
Pages	644-648
Number of pages	5
ISBN (Electronic)	9781538665640
DOIs	https://doi.org/10.1109/ICSESS.2018.8663727
Publication status	Published - 2 Jul 2018
Event	9th IEEE International Conference on Software Engineering and Service Science, ICSESS 2018 - Beijing, China Duration: 23 Nov 2018 → 25 Nov 2018

Publication series

Name	Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
Volume	2018-November
ISSN (Print)	2327-0586
ISSN (Electronic)	2327-0594

Conference

Conference	9th IEEE International Conference on Software Engineering and Service Science, ICSESS 2018
Country/Territory	China
City	Beijing
Period	23/11/18 → 25/11/18

Keywords

PVDF
classification
feature extraction and reduction
machine learning algorithms

Access to Document

10.1109/ICSESS.2018.8663727

Cite this

Zhai, Y., Song, P., & Chen, X. (2018). Machine Learning Algorithms to Detect Penetrations of PVDF. In L. Wenzheng, & M. S. P. Babu (Eds.), ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science (pp. 644-648). Article 8663727 (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS; Vol. 2018-November). IEEE Computer Society. https://doi.org/10.1109/ICSESS.2018.8663727

Zhai, Yayu ; Song, Ping ; Chen, Xiaoxiao. / Machine Learning Algorithms to Detect Penetrations of PVDF. ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science. editor / Li Wenzheng ; M. Surendra Prasad Babu. IEEE Computer Society, 2018. pp. 644-648 (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS).

@inproceedings{1fcb2efb4ece4ea1a45c3bb22f8b10c0,

title = "Machine Learning Algorithms to Detect Penetrations of PVDF",

abstract = "Polyvinylidene fluoride (PVDF) has widely used in detecting the interplanetary dust. In the case of penetration and non-penetration, the output signals of the PVDF are quite different. Detecting whether particles penetrate PVDF is a crucial issue. We create a set of experimental equipment for collecting the signals from the PVDF. The equipment consists of particle emitter, shield, conditioning circuits and data acquisition equipment. 600 experiments are conducted. Among 200 experiments, the particles penetrate PVDF. We successfully distinguish penetration of PVDF using four machine learning algorithms: Anomaly Detection (AD), Artificial Neural Network (ANN), K-Nearest-Neighbors (KNN), and Support Vector Machines (SVM). We propose a unique evaluation criteria OP to evaluate the performance of four classifiers including their accuracy and computational time. The results show that ANN is the best machine learning algorithm for our problem, and AD is not suitable for our problem.",

keywords = "PVDF, classification, feature extraction and reduction, machine learning algorithms",

author = "Yayu Zhai and Ping Song and Xiaoxiao Chen",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 9th IEEE International Conference on Software Engineering and Service Science, ICSESS 2018 ; Conference date: 23-11-2018 Through 25-11-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/ICSESS.2018.8663727",

language = "English",

series = "Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS",

publisher = "IEEE Computer Society",

pages = "644--648",

editor = "Li Wenzheng and Babu, {M. Surendra Prasad}",

booktitle = "ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science",

address = "United States",

}

Zhai, Y, Song, P & Chen, X 2018, Machine Learning Algorithms to Detect Penetrations of PVDF. in L Wenzheng & MSP Babu (eds), ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science., 8663727, Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS, vol. 2018-November, IEEE Computer Society, pp. 644-648, 9th IEEE International Conference on Software Engineering and Service Science, ICSESS 2018, Beijing, China, 23/11/18. https://doi.org/10.1109/ICSESS.2018.8663727

Machine Learning Algorithms to Detect Penetrations of PVDF. / Zhai, Yayu; Song, Ping; Chen, Xiaoxiao.
ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science. ed. / Li Wenzheng; M. Surendra Prasad Babu. IEEE Computer Society, 2018. p. 644-648 8663727 (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS; Vol. 2018-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Machine Learning Algorithms to Detect Penetrations of PVDF

AU - Zhai, Yayu

AU - Song, Ping

AU - Chen, Xiaoxiao

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Polyvinylidene fluoride (PVDF) has widely used in detecting the interplanetary dust. In the case of penetration and non-penetration, the output signals of the PVDF are quite different. Detecting whether particles penetrate PVDF is a crucial issue. We create a set of experimental equipment for collecting the signals from the PVDF. The equipment consists of particle emitter, shield, conditioning circuits and data acquisition equipment. 600 experiments are conducted. Among 200 experiments, the particles penetrate PVDF. We successfully distinguish penetration of PVDF using four machine learning algorithms: Anomaly Detection (AD), Artificial Neural Network (ANN), K-Nearest-Neighbors (KNN), and Support Vector Machines (SVM). We propose a unique evaluation criteria OP to evaluate the performance of four classifiers including their accuracy and computational time. The results show that ANN is the best machine learning algorithm for our problem, and AD is not suitable for our problem.

AB - Polyvinylidene fluoride (PVDF) has widely used in detecting the interplanetary dust. In the case of penetration and non-penetration, the output signals of the PVDF are quite different. Detecting whether particles penetrate PVDF is a crucial issue. We create a set of experimental equipment for collecting the signals from the PVDF. The equipment consists of particle emitter, shield, conditioning circuits and data acquisition equipment. 600 experiments are conducted. Among 200 experiments, the particles penetrate PVDF. We successfully distinguish penetration of PVDF using four machine learning algorithms: Anomaly Detection (AD), Artificial Neural Network (ANN), K-Nearest-Neighbors (KNN), and Support Vector Machines (SVM). We propose a unique evaluation criteria OP to evaluate the performance of four classifiers including their accuracy and computational time. The results show that ANN is the best machine learning algorithm for our problem, and AD is not suitable for our problem.

KW - PVDF

KW - classification

KW - feature extraction and reduction

KW - machine learning algorithms

UR - http://www.scopus.com/inward/record.url?scp=85063629453&partnerID=8YFLogxK

U2 - 10.1109/ICSESS.2018.8663727

DO - 10.1109/ICSESS.2018.8663727

M3 - Conference contribution

AN - SCOPUS:85063629453

T3 - Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS

SP - 644

EP - 648

BT - ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science

A2 - Wenzheng, Li

A2 - Babu, M. Surendra Prasad

PB - IEEE Computer Society

T2 - 9th IEEE International Conference on Software Engineering and Service Science, ICSESS 2018

Y2 - 23 November 2018 through 25 November 2018

ER -

Zhai Y, Song P, Chen X. Machine Learning Algorithms to Detect Penetrations of PVDF. In Wenzheng L, Babu MSP, editors, ICSESS 2018 - Proceedings of 2018 IEEE 9th International Conference on Software Engineering and Service Science. IEEE Computer Society. 2018. p. 644-648. 8663727. (Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS). doi: 10.1109/ICSESS.2018.8663727

Machine Learning Algorithms to Detect Penetrations of PVDF

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this