DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS
The paper deals with an actual problem of ensuring the control of foodstuff quality by means of machine learning methods. Existing analysis methods require special laboratory environment, significant time and depend on the qualification and some physiological characteristics of an expert while the s...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English Russian |
Published: |
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)
2014
|
Subjects: | |
Online Access: | https://doaj.org/article/9877800b028c46bbba0a72236405728d |
id |
ftdoajarticles:oai:doaj.org/article:9877800b028c46bbba0a72236405728d |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:9877800b028c46bbba0a72236405728d 2023-05-15T17:12:45+02:00 DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS A. P. Saenko V. M. Musalimov S. Lerm G. Linss 2014-01-01T00:00:00Z https://doaj.org/article/9877800b028c46bbba0a72236405728d EN RU eng rus Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) http://ntv.ifmo.ru/file/article/8401.pdf https://doaj.org/toc/2226-1494 https://doaj.org/toc/2500-0373 2226-1494 2500-0373 https://doaj.org/article/9877800b028c46bbba0a72236405728d Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki, Vol 14, Iss 1, Pp 93-98 (2014) machine learning bacteria detection Optics. Light QC350-467 Electronic computers. Computer science QA75.5-76.95 article 2014 ftdoajarticles 2022-12-31T05:29:19Z The paper deals with an actual problem of ensuring the control of foodstuff quality by means of machine learning methods. Existing analysis methods require special laboratory environment, significant time and depend on the qualification and some physiological characteristics of an expert while the suggested method gives the possibility to decrease significantly the costs due to automatization. The mobile analysis platform performing this method is based on the fluorescence microscopy. The problem of the object classification as either “bacterium” or “third-party artifact” was solved for the test data with some classification algorithms as support vector machine, random forest, decision tree C4.5, k-nearest neighbors, Bayes method. The analysis showed that the most effective algorithms are support vector machine and random forest. This research is performed on the Mechatronics Department of Saint Petersburg National Research University of Information Technologies, Mechanics and Optics and the Quality Assurance and Industrial Image Processing Department of Ilmenau University of Technology with the support of the program “Mikhail Lomonosov” of the Ministry of Education and Science of Russia and the German Academic Exchange Service. Article in Journal/Newspaper Mikhail Lomonosov Directory of Open Access Journals: DOAJ Articles |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English Russian |
topic |
machine learning bacteria detection Optics. Light QC350-467 Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
machine learning bacteria detection Optics. Light QC350-467 Electronic computers. Computer science QA75.5-76.95 A. P. Saenko V. M. Musalimov S. Lerm G. Linss DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS |
topic_facet |
machine learning bacteria detection Optics. Light QC350-467 Electronic computers. Computer science QA75.5-76.95 |
description |
The paper deals with an actual problem of ensuring the control of foodstuff quality by means of machine learning methods. Existing analysis methods require special laboratory environment, significant time and depend on the qualification and some physiological characteristics of an expert while the suggested method gives the possibility to decrease significantly the costs due to automatization. The mobile analysis platform performing this method is based on the fluorescence microscopy. The problem of the object classification as either “bacterium” or “third-party artifact” was solved for the test data with some classification algorithms as support vector machine, random forest, decision tree C4.5, k-nearest neighbors, Bayes method. The analysis showed that the most effective algorithms are support vector machine and random forest. This research is performed on the Mechatronics Department of Saint Petersburg National Research University of Information Technologies, Mechanics and Optics and the Quality Assurance and Industrial Image Processing Department of Ilmenau University of Technology with the support of the program “Mikhail Lomonosov” of the Ministry of Education and Science of Russia and the German Academic Exchange Service. |
format |
Article in Journal/Newspaper |
author |
A. P. Saenko V. M. Musalimov S. Lerm G. Linss |
author_facet |
A. P. Saenko V. M. Musalimov S. Lerm G. Linss |
author_sort |
A. P. Saenko |
title |
DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS |
title_short |
DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS |
title_full |
DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS |
title_fullStr |
DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS |
title_full_unstemmed |
DETECTION OF BACTERIA IN FOODSTUFF BY MACHINE LEARNING METHODS |
title_sort |
detection of bacteria in foodstuff by machine learning methods |
publisher |
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) |
publishDate |
2014 |
url |
https://doaj.org/article/9877800b028c46bbba0a72236405728d |
genre |
Mikhail Lomonosov |
genre_facet |
Mikhail Lomonosov |
op_source |
Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki, Vol 14, Iss 1, Pp 93-98 (2014) |
op_relation |
http://ntv.ifmo.ru/file/article/8401.pdf https://doaj.org/toc/2226-1494 https://doaj.org/toc/2500-0373 2226-1494 2500-0373 https://doaj.org/article/9877800b028c46bbba0a72236405728d |
_version_ |
1766069597533896704 |