Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning
Sericulture is the process of cultivating silkworms for the production of silk. High-quality production of silk without mixing with low quality is a great challenge faced in the silk production centers. One of the possibilities to overcome this issue is by separating male and female cocoons before e...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2022-01-01
|
Series: | Artificial Intelligence in Agriculture |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2589721722000083 |
_version_ | 1798006074526138368 |
---|---|
author | Sania Thomas Jyothi Thomas |
author_facet | Sania Thomas Jyothi Thomas |
author_sort | Sania Thomas |
collection | DOAJ |
description | Sericulture is the process of cultivating silkworms for the production of silk. High-quality production of silk without mixing with low quality is a great challenge faced in the silk production centers. One of the possibilities to overcome this issue is by separating male and female cocoons before extracting silk fibers from the cocoons as male cocoon silk fibers are finer than females. This study proposes a method for the classification of male and female cocoons with the help of X-ray images without destructing the cocoon. The study used popular single hybrid varieties FC1 and FC2 mulberry silkworm cocoons. The shape features of the pupa are considered for the classification process and were obtained without cutting the cocoon. A novel point interpolation method is used for the computation of the width and height of the cocoon. Different dimensionality reduction methods are employed to enhance the performance of the model. The preprocessed features are fed to the powerful ensemble learning method AdaBoost and used logistic regression as the base learner. This model attained a mean accuracy of 96.3% for FC1 and FC2 in cross-validation and 95.3% in FC1 and 95.1% in FC2 for external validation. |
first_indexed | 2024-04-11T12:49:10Z |
format | Article |
id | doaj.art-fe0bdbf08c0e44148baaf3d08f1b3946 |
institution | Directory Open Access Journal |
issn | 2589-7217 |
language | English |
last_indexed | 2024-04-11T12:49:10Z |
publishDate | 2022-01-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Artificial Intelligence in Agriculture |
spelling | doaj.art-fe0bdbf08c0e44148baaf3d08f1b39462022-12-22T04:23:15ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172022-01-016100110Non-destructive silkworm pupa gender classification with X-ray images using ensemble learningSania Thomas0Jyothi Thomas1Corresponding author.; Department of Computer Science and Engineering, Christ (Deemed to be University), Bangalore, IndiaDepartment of Computer Science and Engineering, Christ (Deemed to be University), Bangalore, IndiaSericulture is the process of cultivating silkworms for the production of silk. High-quality production of silk without mixing with low quality is a great challenge faced in the silk production centers. One of the possibilities to overcome this issue is by separating male and female cocoons before extracting silk fibers from the cocoons as male cocoon silk fibers are finer than females. This study proposes a method for the classification of male and female cocoons with the help of X-ray images without destructing the cocoon. The study used popular single hybrid varieties FC1 and FC2 mulberry silkworm cocoons. The shape features of the pupa are considered for the classification process and were obtained without cutting the cocoon. A novel point interpolation method is used for the computation of the width and height of the cocoon. Different dimensionality reduction methods are employed to enhance the performance of the model. The preprocessed features are fed to the powerful ensemble learning method AdaBoost and used logistic regression as the base learner. This model attained a mean accuracy of 96.3% for FC1 and FC2 in cross-validation and 95.3% in FC1 and 95.1% in FC2 for external validation.http://www.sciencedirect.com/science/article/pii/S2589721722000083SericultureGender classificationStratified k-fold cross-validationMachine learningAdaBoost |
spellingShingle | Sania Thomas Jyothi Thomas Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning Artificial Intelligence in Agriculture Sericulture Gender classification Stratified k-fold cross-validation Machine learning AdaBoost |
title | Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning |
title_full | Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning |
title_fullStr | Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning |
title_full_unstemmed | Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning |
title_short | Non-destructive silkworm pupa gender classification with X-ray images using ensemble learning |
title_sort | non destructive silkworm pupa gender classification with x ray images using ensemble learning |
topic | Sericulture Gender classification Stratified k-fold cross-validation Machine learning AdaBoost |
url | http://www.sciencedirect.com/science/article/pii/S2589721722000083 |
work_keys_str_mv | AT saniathomas nondestructivesilkwormpupagenderclassificationwithxrayimagesusingensemblelearning AT jyothithomas nondestructivesilkwormpupagenderclassificationwithxrayimagesusingensemblelearning |