Identification of egg’s freshness using NIR and support vector data description

Zhao, Jing; Hao, Lin; Chen, Quansheng; Huang, Xingyi; Sun, Zongbao; Fang, Zhou

doi:10.1016/j.jfoodeng.2010.01.018

Cited by 76 publications

(41 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A predictive model of Haugh unit was obtained with determination coefficient R 2 of 0.676. Zhao et al (2010) employed support vector data description (SVDD) to solve the problem with imbalance training samples (the number of fresh eggs is much larger than that of un-fresh ones) in the process of building egg freshness measurement model by NIR spectroscopy, the identification rates of fresh eggs and un-fresh eggs were both 93.3% in prediction set.…”

Section: Introductionmentioning

confidence: 99%

Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis

Hao

Zhao

Sun

et al. 2011

Innovative Food Science & Emerging Technologies

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis

Hao

Zhao

Sun

et al. 2011

Innovative Food Science & Emerging Technologies

Self Cite

View full text Add to dashboard Cite

“…Los autores reportaron un desempeño sobre el 95% del método del clasificador, aunque no comparan sus resultados con otros métodos de balanceo ni otros métodos de clasificación diferentes a la SVDD. Por su lado, en [71] los autores usan imágenes infrarrojas y una SVDD para determinar la calidad y la frescura de huevos. En su trabajo, los autores reportan que comparado con diferentes algoritmos de clasificación para dos o más clases, como SVM y KNN, la SVDD obtuvo los mejores resultados.…”

Section: Sivas Con Técnicas De Clasificación De Una Claseunclassified

A Survey on Class Imbalance Learning on Automatic Visual Inspection

Mera

Branch

2014

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

The supervised machine learning has been showing very useful for the automatic visual inspection task. However, little has been considered about use traditional machine learning techniques on a domain where the classes are imbalanced. This problem corresponds to dealing with the situation where one class outnumbers the other. Traditional machine learning algorithms trained with imbalance datasets can be biased towards the majority class, thus producing poor predictive accuracy over the minority class. In this paper, we present different approaches to address the class imbalance problem and how these approaches have been used in the context of automatic visual inspection. The literature shows there are few works that consider the class imbalance problem on automatic visual inspection task and it shows that the one class classification technique is the most used.

show abstract

“…Giunchi et al reported non-destructive freshness assessment of shell eggs by means of FT-NIR and partial least square regression (PLS) [3]. A predictive model of Haugh unit was obtained with determination coefficient R2 of 0.676. employed support vector data description (SVDD) to solve the problem with imbalance training samples in egg freshness measurement by NIR spectroscopy, the identification rates of fresh eggs and unfresh eggs were both 93.3% in prediction set [4]. employed NIR spectroscopy combined with multivariate calibration model qualitative and quantitative analyze freshness of eggs [5].…”

Section: Introductionmentioning

confidence: 99%

Effective Variables Selection in Eggs Freshness Graphically Oriented Local Multivariate Analysis using NIR Spectroscopy

Hao¹,

Zhao²,

Sun³

et al. 2015

Proceedings of the International Conference on Chemical, Material and Food Engineering

Self Cite

View full text Add to dashboard Cite

Abstract-In multi-component spectral analysis, informative variables selection is important to get satisfied performance. The present research intends to establish relationship between eggs freshness and NIR spectroscopy, and build a compact and robust calibration model. Graphically-oriented local multivariate calibration modeling procedures were used comparatively to select efficient spectral variables in comparison to the full-spectrum model. Three kinds of methods, which were spectral interval selection, effective coefficient variables selection and genetic algorithm, were used for variable selection. Successive projections algorithm (SPA) showed its superior ability in reducing the complexity of model building. A satisfactory result was achieved while only 8 variables were used. Meanwhile, the optimal performance was obtained with genetic algorithm synergy interval partial leastsquare (GA-siPLS) by using 9 PCs and 42 variables selected, which resulted in root mean square error value of prediction (RMSEP) value of 3.29. This work indicates that it is feasible to identify egg freshness using NIR spectroscopy combined with graphically-oriented local multivariate analysis, and using variables methods is important to reduce he complexity of model building with fewer spectral variables and improve performance of calibration model.

show abstract

Identification of egg’s freshness using NIR and support vector data description

Cited by 76 publications

References 32 publications

Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis

Freshness measurement of eggs using near infrared (NIR) spectroscopy and multivariate data analysis

A Survey on Class Imbalance Learning on Automatic Visual Inspection

Effective Variables Selection in Eggs Freshness Graphically Oriented Local Multivariate Analysis using NIR Spectroscopy

Contact Info

Product

Resources

About