Classification models of nondestructive acoustic response for predicting translucent mangosteens

Nattapong Swangmuang, Kasemsak Uthaichana, Nipon Theera-Umpon, Hideyuki Sawada

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

3 Citations (Scopus)

Abstract

Mangosteen export generates large revenue; however, translucent mangosteens, which contain undesirable internal condition, result in the shipment rejection and decrease the reliability of the export. This research investigates a novel non-destructive classification approach based on acoustic frequency response to detect mangosteens containing translucent fleshes. The set of uniform-distributed multi-frequency acoustic signal is generated and passed through each mangosteen under the test. The frequency responses, describing a feature space, for all mangosteens are computed via the discrete Fourier transform. To prevent intensive computation, a linear optimization is adopted to select relevant frequency contents, creating a compact classifying feature vector. To solve the classification problem, two proposed acoustic-based classification techniques are studied, namely linear classifier (LC), and non-linear classifier (NLC) based on an artificial neural network. Then the results from both classifiers are compared against the results from the conventional water-floating (WF) approach. Against the experimental data, it is found that the average flesh classification accuracy of good mangoteens achieved from the LC and the NLC are about 61% and 74% respectively, while the WF yields an accuracy of about 69%. It is evident that the acoustic-based approach possesses the convincing accuracy for solving the problem of export-grade translucent mangosteen classification. In addition, the paper shows that a mangosteen's physical density can possibly provide intuitive information for better classification performance in the future research study.

Original languageEnglish
Title of host publication2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012 - Phetchaburi, Thailand
Duration: 2012 May 162012 May 18

Other

Other2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012
CountryThailand
CityPhetchaburi
Period12/5/1612/5/18

Fingerprint

Acoustics
Classifiers
Frequency response
Discrete Fourier transforms
Water
Neural networks

Keywords

  • acoustic
  • acoutic signal processing applications
  • mangosteens
  • neural networks
  • non-destructive testing
  • pattern classification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Swangmuang, N., Uthaichana, K., Theera-Umpon, N., & Sawada, H. (2012). Classification models of nondestructive acoustic response for predicting translucent mangosteens. In 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012 [6254134] https://doi.org/10.1109/ECTICon.2012.6254134

Classification models of nondestructive acoustic response for predicting translucent mangosteens. / Swangmuang, Nattapong; Uthaichana, Kasemsak; Theera-Umpon, Nipon; Sawada, Hideyuki.

2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012. 2012. 6254134.

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

Swangmuang, N, Uthaichana, K, Theera-Umpon, N & Sawada, H 2012, Classification models of nondestructive acoustic response for predicting translucent mangosteens. in 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012., 6254134, 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012, Phetchaburi, Thailand, 12/5/16. https://doi.org/10.1109/ECTICon.2012.6254134
Swangmuang N, Uthaichana K, Theera-Umpon N, Sawada H. Classification models of nondestructive acoustic response for predicting translucent mangosteens. In 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012. 2012. 6254134 https://doi.org/10.1109/ECTICon.2012.6254134
Swangmuang, Nattapong ; Uthaichana, Kasemsak ; Theera-Umpon, Nipon ; Sawada, Hideyuki. / Classification models of nondestructive acoustic response for predicting translucent mangosteens. 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012. 2012.
@inproceedings{12e55e8a531e4b27805146278995b85e,
title = "Classification models of nondestructive acoustic response for predicting translucent mangosteens",
abstract = "Mangosteen export generates large revenue; however, translucent mangosteens, which contain undesirable internal condition, result in the shipment rejection and decrease the reliability of the export. This research investigates a novel non-destructive classification approach based on acoustic frequency response to detect mangosteens containing translucent fleshes. The set of uniform-distributed multi-frequency acoustic signal is generated and passed through each mangosteen under the test. The frequency responses, describing a feature space, for all mangosteens are computed via the discrete Fourier transform. To prevent intensive computation, a linear optimization is adopted to select relevant frequency contents, creating a compact classifying feature vector. To solve the classification problem, two proposed acoustic-based classification techniques are studied, namely linear classifier (LC), and non-linear classifier (NLC) based on an artificial neural network. Then the results from both classifiers are compared against the results from the conventional water-floating (WF) approach. Against the experimental data, it is found that the average flesh classification accuracy of good mangoteens achieved from the LC and the NLC are about 61{\%} and 74{\%} respectively, while the WF yields an accuracy of about 69{\%}. It is evident that the acoustic-based approach possesses the convincing accuracy for solving the problem of export-grade translucent mangosteen classification. In addition, the paper shows that a mangosteen's physical density can possibly provide intuitive information for better classification performance in the future research study.",
keywords = "acoustic, acoutic signal processing applications, mangosteens, neural networks, non-destructive testing, pattern classification",
author = "Nattapong Swangmuang and Kasemsak Uthaichana and Nipon Theera-Umpon and Hideyuki Sawada",
year = "2012",
doi = "10.1109/ECTICon.2012.6254134",
language = "English",
isbn = "9781467320245",
booktitle = "2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012",

}

TY - GEN

T1 - Classification models of nondestructive acoustic response for predicting translucent mangosteens

AU - Swangmuang, Nattapong

AU - Uthaichana, Kasemsak

AU - Theera-Umpon, Nipon

AU - Sawada, Hideyuki

PY - 2012

Y1 - 2012

N2 - Mangosteen export generates large revenue; however, translucent mangosteens, which contain undesirable internal condition, result in the shipment rejection and decrease the reliability of the export. This research investigates a novel non-destructive classification approach based on acoustic frequency response to detect mangosteens containing translucent fleshes. The set of uniform-distributed multi-frequency acoustic signal is generated and passed through each mangosteen under the test. The frequency responses, describing a feature space, for all mangosteens are computed via the discrete Fourier transform. To prevent intensive computation, a linear optimization is adopted to select relevant frequency contents, creating a compact classifying feature vector. To solve the classification problem, two proposed acoustic-based classification techniques are studied, namely linear classifier (LC), and non-linear classifier (NLC) based on an artificial neural network. Then the results from both classifiers are compared against the results from the conventional water-floating (WF) approach. Against the experimental data, it is found that the average flesh classification accuracy of good mangoteens achieved from the LC and the NLC are about 61% and 74% respectively, while the WF yields an accuracy of about 69%. It is evident that the acoustic-based approach possesses the convincing accuracy for solving the problem of export-grade translucent mangosteen classification. In addition, the paper shows that a mangosteen's physical density can possibly provide intuitive information for better classification performance in the future research study.

AB - Mangosteen export generates large revenue; however, translucent mangosteens, which contain undesirable internal condition, result in the shipment rejection and decrease the reliability of the export. This research investigates a novel non-destructive classification approach based on acoustic frequency response to detect mangosteens containing translucent fleshes. The set of uniform-distributed multi-frequency acoustic signal is generated and passed through each mangosteen under the test. The frequency responses, describing a feature space, for all mangosteens are computed via the discrete Fourier transform. To prevent intensive computation, a linear optimization is adopted to select relevant frequency contents, creating a compact classifying feature vector. To solve the classification problem, two proposed acoustic-based classification techniques are studied, namely linear classifier (LC), and non-linear classifier (NLC) based on an artificial neural network. Then the results from both classifiers are compared against the results from the conventional water-floating (WF) approach. Against the experimental data, it is found that the average flesh classification accuracy of good mangoteens achieved from the LC and the NLC are about 61% and 74% respectively, while the WF yields an accuracy of about 69%. It is evident that the acoustic-based approach possesses the convincing accuracy for solving the problem of export-grade translucent mangosteen classification. In addition, the paper shows that a mangosteen's physical density can possibly provide intuitive information for better classification performance in the future research study.

KW - acoustic

KW - acoutic signal processing applications

KW - mangosteens

KW - neural networks

KW - non-destructive testing

KW - pattern classification

UR - http://www.scopus.com/inward/record.url?scp=84866760875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866760875&partnerID=8YFLogxK

U2 - 10.1109/ECTICon.2012.6254134

DO - 10.1109/ECTICon.2012.6254134

M3 - Conference contribution

AN - SCOPUS:84866760875

SN - 9781467320245

BT - 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012

ER -