Challenges of large-class-number classification (LCNC): A novel ensemble strategy (ES) and its application to discriminating the geographical origins of 25 green teas

Fu, Hai; Yin, Qiao Bo; Xu, Lu; Goodarzi, Mohammad; Yang, Tian Ming; Li, Gang Feng; FengQiao,; She, Yuan Bin

doi:10.1016/j.chemolab.2016.06.018

Cited by 17 publications

(10 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e highest total accuracy was acquired by ES-PLSDA with the value of 0.9377, while the total accuracies of OVO-PLSDA, OVR-PLSDA, and PLSDAsoftmax were 0.8494, 0.6468, and 0.9299, respectively. ES pattern recognition thus achieved improved performance in large-class-number classification [50].…”

Section: Geographical Originsmentioning

confidence: 98%

The Quality Control of Tea by Near-Infrared Reflectance (NIR) Spectroscopy and Chemometrics

Zhu

Wen

et al. 2019

Journal of Spectroscopy

View full text Add to dashboard Cite

Tea is known to be one of the most popular beverages enjoyed by two-thirds of the world’s population. Concern of variability in tea quality is increasing among consumers. It is of great significance to control quality for commercialized tea products. As a rapid, noninvasive, and nondestructive instrumental technique with simplicity in sample preparation, near-infrared reflectance (NIR) spectroscopy has been proved to be one of the most advanced and efficient tools for the control quality of tea products in recent years. In this article, we review the most recent advances and applications of NIR spectroscopy and chemometrics for the quality control of tea, including the measurement of chemical compositions, the evaluation of sensory attributes, the identification of categories and varieties, and the discrimination of geographical origins. Besides, challenges and future trends of tea quality control by NIR spectroscopy are also presented.

show abstract

Section: Geographical Originsmentioning

confidence: 98%

The Quality Control of Tea by Near-Infrared Reflectance (NIR) Spectroscopy and Chemometrics

Zhu

Wen

et al. 2019

Journal of Spectroscopy

View full text Add to dashboard Cite

show abstract

“…The final accuracy for the calibration set and the validation set was 98.43 and 96.84%, respectively. Fu et al (85) proposed PLS-DA-softmax with Gaussian kernel transformation, which obtained the accuracy of 92.99% for classifying tea from 25 regions. Besides, the proposed ensemble strategy (ES)-PLS-DA achieved the highest accuracy of 93.77%.…”

Section: Beveragementioning

confidence: 99%

Application of Visible/Infrared Spectroscopy and Hyperspectral Imaging With Machine Learning Techniques for Identifying Food Varieties and Geographical Origins

Liu

Zhu

et al. 2021

Front. Nutr.

View full text Add to dashboard Cite

Food quality and safety are strongly related to human health. Food quality varies with variety and geographical origin, and food fraud is becoming a threat to domestic and global markets. Visible/infrared spectroscopy and hyperspectral imaging techniques, as rapid and non-destructive analytical methods, have been widely utilized to trace food varieties and geographical origins. In this review, we outline recent research progress on identifying food varieties and geographical origins using visible/infrared spectroscopy and hyperspectral imaging with the help of machine learning techniques. The applications of visible, near-infrared, and mid-infrared spectroscopy as well as hyperspectral imaging techniques on crop food, beverage, fruits, nuts, meat, oil, and some other kinds of food are reviewed. Furthermore, existing challenges and prospects are discussed. In general, the existing machine learning techniques contribute to satisfactory classification results. Follow-up researches of food varieties and geographical origins traceability and development of real-time detection equipment are still in demand.

show abstract

“…Partial least squares discriminant analysis (PLSDA) was used to develop two-class classification models [44][45][46][47]. To tackle the multiclass problems in this work, two chemometrics strategies, one-versus-rest (OVR) and one-versusone (OVO), were performed and compared to develop a set of binary PLSDA classifiers [48,49].…”

Section: Chemometrics Data Analysismentioning

confidence: 99%

Classification of Different Blueberry Cultivars by Analysis of Physical Factors, Chemical and Nutritional Ingredients, and Antioxidant Capacities

Shi

Yan

et al. 2020

Journal of Food Quality

Self Cite

View full text Add to dashboard Cite

Blueberry fruits of different cultivars are featured with different quality indices. In this work, three types of quality factors, including 6 physical parameters, 12 chemical and nutritional components, and 3 antioxidant indices, were measured to compare and classify blueberry fruits from 12 different cultivars in China. Using the autoscaled data of quality factors, unsupervised principal component analysis was performed for exploratory analysis of intercultivar differences and the influences of quality factors. A supervised classification method, partial least squares discriminant analysis (PLSDA), was combined with the global particle swarm optimization algorithm (PSO) and two multiclass strategies, one-versus-rest (OVR) and one-versus-one (OVO), to select discriminative quality factors and develop classification models of the 12 cultivars. As a result, OVO-PLSDA with 8 quality factors could achieve the classification accuracy of 0.915. This study will provide new insights into the quality variations and key factors among different blueberry cultivars.

show abstract

Challenges of large-class-number classification (LCNC): A novel ensemble strategy (ES) and its application to discriminating the geographical origins of 25 green teas

Cited by 17 publications

References 48 publications

The Quality Control of Tea by Near-Infrared Reflectance (NIR) Spectroscopy and Chemometrics

The Quality Control of Tea by Near-Infrared Reflectance (NIR) Spectroscopy and Chemometrics

Application of Visible/Infrared Spectroscopy and Hyperspectral Imaging With Machine Learning Techniques for Identifying Food Varieties and Geographical Origins

Classification of Different Blueberry Cultivars by Analysis of Physical Factors, Chemical and Nutritional Ingredients, and Antioxidant Capacities

Contact Info

Product

Resources

About