Performance of supervised classifiers for damage scoring of zebrafish neuromasts

Rohit C. Philip; Sree Ramya S.P. Malladi; Maki Niihori; Abraham Jacob; Jeffrey J Rodriguez

doi:10.1109/SSIAI.2018.8470377

Performance of supervised classifiers for damage scoring of zebrafish neuromasts

Rohit C. Philip, Sree Ramya S.P. Malladi, Maki Niihori, Abraham Jacob, Jeffrey J Rodriguez

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

Abstract

Supervised machine learning schemes are widely used to perform classification tasks. There is a wide variety of classifiers in use today, such as single- and multi-class support vector machines, k-nearest neighbors, decision trees, random forests, naive Bayes classifiers with or without kernel density estimation, linear discriminant analysis, quadratic discriminant analysis, and numerous neural network architectures. Our prior work used high-level shape, intensity, and texture features as predictors in a single-class support vector machine classifier to classify images of zebrafish neuromasts obtained using confocal microscopy into four discrete damage classes. Here, we analyze the performance of a multitude of supervised classifiers in terms of mean absolute error using these high-level features as predictors. In addition, we also analyze performance while using raw pixel data as predictors.

Original language	English (US)
Title of host publication	2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	113-116
Number of pages	4
ISBN (Electronic)	9781538665688
DOIs	https://doi.org/10.1109/SSIAI.2018.8470377
State	Published - Sep 21 2018
Event	2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Las Vegas, United States Duration: Apr 8 2018 → Apr 10 2018

Publication series

Name	Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume	2018-April

Other

Other	2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018
Country/Territory	United States
City	Las Vegas
Period	4/8/18 → 4/10/18

Keywords

Neural network
naive Bayes classifier
random forest
supervised learning
support vector machine

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/SSIAI.2018.8470377

Cite this

Philip, R. C., Malladi, S. R. S. P., Niihori, M., Jacob, A., & Rodriguez, J. J. (2018). Performance of supervised classifiers for damage scoring of zebrafish neuromasts. In 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings (pp. 113-116). [8470377] (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation; Vol. 2018-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSIAI.2018.8470377

Performance of supervised classifiers for damage scoring of zebrafish neuromasts. / Philip, Rohit C.; Malladi, Sree Ramya S.P.; Niihori, Maki; Jacob, Abraham; Rodriguez, Jeffrey J.

2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 113-116 8470377 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation; Vol. 2018-April).

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

Philip, RC, Malladi, SRSP, Niihori, M, Jacob, A & Rodriguez, JJ 2018, Performance of supervised classifiers for damage scoring of zebrafish neuromasts. in 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings., 8470377, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, vol. 2018-April, Institute of Electrical and Electronics Engineers Inc., pp. 113-116, 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018, Las Vegas, United States, 4/8/18. https://doi.org/10.1109/SSIAI.2018.8470377

Philip RC, Malladi SRSP, Niihori M, Jacob A, Rodriguez JJ. Performance of supervised classifiers for damage scoring of zebrafish neuromasts. In 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 113-116. 8470377. (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation). https://doi.org/10.1109/SSIAI.2018.8470377

Philip, Rohit C. ; Malladi, Sree Ramya S.P. ; Niihori, Maki ; Jacob, Abraham ; Rodriguez, Jeffrey J. / Performance of supervised classifiers for damage scoring of zebrafish neuromasts. 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 113-116 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation).

@inproceedings{8060f8f7704f458d8ddf556fe41029fe,

title = "Performance of supervised classifiers for damage scoring of zebrafish neuromasts",

abstract = "Supervised machine learning schemes are widely used to perform classification tasks. There is a wide variety of classifiers in use today, such as single- and multi-class support vector machines, k-nearest neighbors, decision trees, random forests, naive Bayes classifiers with or without kernel density estimation, linear discriminant analysis, quadratic discriminant analysis, and numerous neural network architectures. Our prior work used high-level shape, intensity, and texture features as predictors in a single-class support vector machine classifier to classify images of zebrafish neuromasts obtained using confocal microscopy into four discrete damage classes. Here, we analyze the performance of a multitude of supervised classifiers in terms of mean absolute error using these high-level features as predictors. In addition, we also analyze performance while using raw pixel data as predictors.",

keywords = "Neural network, naive Bayes classifier, random forest, supervised learning, support vector machine",

author = "Philip, {Rohit C.} and Malladi, {Sree Ramya S.P.} and Maki Niihori and Abraham Jacob and Rodriguez, {Jeffrey J}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 ; Conference date: 08-04-2018 Through 10-04-2018",

year = "2018",

month = sep,

day = "21",

doi = "10.1109/SSIAI.2018.8470377",

language = "English (US)",

series = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "113--116",

booktitle = "2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings",

}

TY - GEN

T1 - Performance of supervised classifiers for damage scoring of zebrafish neuromasts

AU - Philip, Rohit C.

AU - Malladi, Sree Ramya S.P.

AU - Niihori, Maki

AU - Jacob, Abraham

AU - Rodriguez, Jeffrey J

PY - 2018/9/21

Y1 - 2018/9/21

N2 - Supervised machine learning schemes are widely used to perform classification tasks. There is a wide variety of classifiers in use today, such as single- and multi-class support vector machines, k-nearest neighbors, decision trees, random forests, naive Bayes classifiers with or without kernel density estimation, linear discriminant analysis, quadratic discriminant analysis, and numerous neural network architectures. Our prior work used high-level shape, intensity, and texture features as predictors in a single-class support vector machine classifier to classify images of zebrafish neuromasts obtained using confocal microscopy into four discrete damage classes. Here, we analyze the performance of a multitude of supervised classifiers in terms of mean absolute error using these high-level features as predictors. In addition, we also analyze performance while using raw pixel data as predictors.

AB - Supervised machine learning schemes are widely used to perform classification tasks. There is a wide variety of classifiers in use today, such as single- and multi-class support vector machines, k-nearest neighbors, decision trees, random forests, naive Bayes classifiers with or without kernel density estimation, linear discriminant analysis, quadratic discriminant analysis, and numerous neural network architectures. Our prior work used high-level shape, intensity, and texture features as predictors in a single-class support vector machine classifier to classify images of zebrafish neuromasts obtained using confocal microscopy into four discrete damage classes. Here, we analyze the performance of a multitude of supervised classifiers in terms of mean absolute error using these high-level features as predictors. In addition, we also analyze performance while using raw pixel data as predictors.

KW - Neural network

KW - naive Bayes classifier

KW - random forest

KW - supervised learning

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85055470130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055470130&partnerID=8YFLogxK

U2 - 10.1109/SSIAI.2018.8470377

DO - 10.1109/SSIAI.2018.8470377

M3 - Conference contribution

AN - SCOPUS:85055470130

T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

SP - 113

EP - 116

BT - 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018

Y2 - 8 April 2018 through 10 April 2018

ER -

Performance of supervised classifiers for damage scoring of zebrafish neuromasts

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this