- You are here:
-
-
All publications
- Imbalanced data problem in food processing analysis
All publications from your selection
Imbalanced data problem in food processing analysis
Authors: Adegbenjo, A., M. Ngadi
Identifier: CSBE15038
Download file:
Published in: CSBE-SCGAB Technical Conferences » AGM Edmonton 2015
Download RAW file:
DOI:
Description: Imbalanced data situation exists in most fields of endeavours like the biomedical, surveillance and security industries, management/finance and the Agricultural sectors. The problem has been identified as a major bottleneck in machine learning/data mining and is becoming a serious issue of concern in the Food processing applications. The problem occurs when we have availability of certain class of data that are more than the other in a population. Due to the fact that rare cases occur infrequently, classification rules that detect small groups tends to be scarce and samples belonging to small classes are largely misclassified than those of prevalent classes. Most existing machine learning algorithms including but not limited to the K-means, decision trees, and support vector machine (SVM) are not very optimal in handling imbalanced data having been trained to achieve overall accuracy to which smaller class data contributes little. Consequently, models developed from analysis of such data are very prone to rejection and non-adoptability in the real industrial and commercial settings. This presentation seeks to highlight the reality of this problem in the Food processing sector and proposes possible ways of handling the problem before further analysis and model development. Imbalanced data in food processing applications need to be treated as such right from the laboratory. Rightly and successfully analysing imbalanced data from food processing application researches will improve accuracy of results and model developments. This will consequently enhance acceptability and adoptability of innovations/inventions.
Keywords: food processing, imbalanced data, machine learning
Résumé:
Mots-clés:
Citation: Adegbenjo, A., M. Ngadi. 2015. Imbalanced data problem in food processing analysis. CSBE/SCGAB 2015 Annual Conference, Edmonton, AB, 5-8 July 2015.
Volume:
Issue:
Pages -
Contributor:
Date: 2015-07-05
Technical field: Bioprocess Systems Engineering
Conference name: CSBE/SCGAB 2015 Annual Conference, Edmonton, AB, 5-8 July 2015.
Session name: Poster
Other information:
Type: Text.Article
Format:
Publication type: Poster
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
DOI:
Description: Imbalanced data situation exists in most fields of endeavours like the biomedical, surveillance and security industries, management/finance and the Agricultural sectors. The problem has been identified as a major bottleneck in machine learning/data mining and is becoming a serious issue of concern in the Food processing applications. The problem occurs when we have availability of certain class of data that are more than the other in a population. Due to the fact that rare cases occur infrequently, classification rules that detect small groups tends to be scarce and samples belonging to small classes are largely misclassified than those of prevalent classes. Most existing machine learning algorithms including but not limited to the K-means, decision trees, and support vector machine (SVM) are not very optimal in handling imbalanced data having been trained to achieve overall accuracy to which smaller class data contributes little. Consequently, models developed from analysis of such data are very prone to rejection and non-adoptability in the real industrial and commercial settings. This presentation seeks to highlight the reality of this problem in the Food processing sector and proposes possible ways of handling the problem before further analysis and model development. Imbalanced data in food processing applications need to be treated as such right from the laboratory. Rightly and successfully analysing imbalanced data from food processing application researches will improve accuracy of results and model developments. This will consequently enhance acceptability and adoptability of innovations/inventions.
Keywords: food processing, imbalanced data, machine learning
Résumé:
Mots-clés:
Citation: Adegbenjo, A., M. Ngadi. 2015. Imbalanced data problem in food processing analysis. CSBE/SCGAB 2015 Annual Conference, Edmonton, AB, 5-8 July 2015.
Volume:
Issue:
Pages -
Contributor:
Date: 2015-07-05
Technical field: Bioprocess Systems Engineering
Conference name: CSBE/SCGAB 2015 Annual Conference, Edmonton, AB, 5-8 July 2015.
Session name: Poster
Other information:
Type: Text.Article
Format:
Publication type: Poster
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
©
2024
CSBE-SCGAB