In situ cocoa beans quality grading by near-infrared-chemodyes systems

Kutsanedzie, Felix Y.H.; Chen, Quansheng; Sun, Hao; Cheng, Wu

doi:10.1039/c7ay01751k

Cited by 26 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, in the present study, it was aimed to distinguish 3 different types of high-quality cocoa beans. Slightly better classification performances were obtained compared to those reported by Kutsanedzie et al, for the classification of cocoa beans from 3 quality grades (fully fermented, partially fermented and nonfermented) using an E-nose coupled with LDA, SVM or k-NN models (accuracies from 89 to 94%) [9]. The overall results reported in the present study allowed verifying that the E-nose, comprising MOS gas sensors and a moisture-temperature sensor, coupled with suitable supervised classification models (SVM or MLP-ANN) can be used as a practical device to correctly discriminating cocoa bean samples according to their quality grades, being possible to infer that fine dark cocoa bean < 20% and fine dark cocoa bean > 60% possessed different aroma fingerprints even though they belong to the same cocoa class, i.e., fine cocoa beans.…”

Section: Resultsmentioning

confidence: 58%

“…For example, cocoa bean's fermentation index has been predicted based on hyperspectral imaging [4] or based on colour analysis [6]. Near-Infrared (NIR) spectroscopy or Fourier Transform Near-Infrared (FT-NIR) spectroscopy, coupled with multivariate statistical tools, have been used as non-destructive techniques, to assess cocoa bean geographical origin or quality grades [2,[7][8][9]. A NIR spectroscopy-electronic tongue integrated approach was accurately used for classifying cocoa bean varieties [10,11].…”

Section: Introductionmentioning

confidence: 99%

“…So, some studies reported the use of E-noses for cocoa bean analysis. The quality of cocoa beans could be accurately assessed using different E-nose devices coupled with chemometric tools, such as extreme machine learning (ELM), support vector machine (SVM), linear discriminant analysis (LDA), knearest neighbours (k-NN) and artificial neural networks (ANN), with accuracy rates of 89% to 95% [9,28]. On the other hand, cocoa beans degree of roasting could also be assessed coupling an Enose (MOS sensors) with ANN model, with a predictive accuracy of 94.4%, similar to that of a GC-MS (95.8%) [5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Electronic Nose Coupled with Linear and Nonlinear Supervised Learning Methods for Rapid Discriminating Quality Grades of Superior Java Cocoa Beans

Hidayat¹,

Rusman²,

Julian³

et al. 2019

IJIES

View full text Add to dashboard Cite

An electronic nose (E-nose), comprising eight metal oxide semiconductor (MOS) gas sensors and a moisture-temperature sensor, was used for classifying three quality grades of superior java cocoa beans, namely fine cocoa dark bean < 20%, fine cocoa dark bean > 60%, and bulk cocoa bean that is a harder task compared to the discrimination of high versus low-quality cocoa beans. The E-nose signals were pre-processed using the maximum value method. The capability for discriminating the quality grade of the cocoa beans was checked by applying multivariate statistical tools, namely, linear discriminant analysis (LDA), support vector machine (SVM) and artificial neural networks (ANN). For this, the experimental dataset was split into two subsets, one for training (i.e., establishing the classification models) and the other for external-validation purposes. Furthermore, hyperparameter optimization and K-fold cross-validation variant were implemented during the model training procedure to select the best classification models and to avoid over-fitting issues. The best predictive classification performance was obtained with the E-nose-MLP-ANN procedure, which allowed 99% of correct classifications (overall accuracy) for the training dataset and 95% of correct classifications (overall accuracy) for the external-validation dataset. The satisfactory results clearly demonstrated that the E-nose could be applied as a quality control tool in the cocoa industry, requiring minimum and simple sample preparation.

show abstract

Section: Resultsmentioning

confidence: 58%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Electronic Nose Coupled with Linear and Nonlinear Supervised Learning Methods for Rapid Discriminating Quality Grades of Superior Java Cocoa Beans

Hidayat¹,

Rusman²,

Julian³

et al. 2019

IJIES

View full text Add to dashboard Cite

show abstract

“…The optimum value of K that has the lowest error rate is used for the calibration process. This algorithm has been used for several studies, such as quality grading of cocoa beans (Kutsanedzi et al, 2017), tea classification based on mould effect (Xin et al, 2019), etc. The present study used the algorithm in predicting the long-term effect of working capital management on firm performance, for both financial and non-financial distress firms of the two leading economies of West Africa (Nigeria and Ghana) in the economic recession period 2012–2016.…”

Section: Literature Reviewmentioning

confidence: 99%

Combination of Ant Colony Optimization and K-nearest Neighbours: The Influence of Working Capital Management on Corporate Performance

Coleman

2020

Management and Labour Studies

View full text Add to dashboard Cite

Purpose: This study looked at the influence of working capital management on firm performance using both accounting measure (ROE) and market measure (Tobin’s q) of firms listed in Nigeria and Ghana. Design/methodology/approach: The study used ant colony optimization (ACO) and k-nearest neighbours (KNN) in establishing the long-term effect of working capital management on corporate performance. Data were extracted from annual financial reports of non-financial companies listed on the Nigeria and Ghana stock exchanges for the recession period 2012–2016, with a total observation of 510. Findings: ACO was applied to determine the working capital management variables that influence corporate performance, and KNN predicted its longitudinal influence, which, in our view, has not been deeply researched. It was discovered that non-financial firms in the period of economic crises manage the account receivables and payables, as well as cash conversion cycles, maintaining optimum working capital for efficient operational activities. It is therefore assumed that these firms are exposed to external and other sources of finance, which enables them to increase investment in working capital, preventing the risk of low production hindering firms from settling debt, as well as customers, leading to the collapse of many firms in this region and accounting for an increase in the unemployment rate. Research limitations/implications: This study will inform corporate management and policymakers on the effect of economic crises on the performance of firms in the management of working capital to achieve desirable accounting and market performance. The ability of a firm to manage working capital during boom and recession periods enhances maximization of shareholders’ wealth. Originality/value: This study will alert policymakers to the urgency in setting up appropriate policies to address pertinent issues regarding longitudinal influence of economic crises on firm continuity and value. JEL Code: M4

show abstract

“…It is fast, requires little or no sample preparation, has low operating cost, and is environmentally friendly [ 12 ]. In other studies, the NIR spectroscopy has been used for the quantification of moisture content, nitrogen, and fat of cocoa powder [ 13 ], prediction of procyanidins in cocoa [ 14 ], differentiation of Ghana cocoa beans and cocoa bean varieties [ 15 , 16 ], verification of cocoa powder authenticity [ 17 ], classification and determination of chemical quality parameters [ 18 – 20 ], and estimation of cocoa bean parameters [ 21 ]. A critical study of recent applications of the use of NIR spectroscopic technique in the cocoa bean industry showed that it has also been applied in the rapid detection of cocoa bean adulterations and fraud [ 22 , 23 ] and quality control of commercial cocoa beans [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Differentiation of Organic Cocoa Beans and Conventional Ones by Using Handheld NIR Spectroscopy and Multivariate Classification Techniques

Anyidoho

Teye

Agbemafle

2021

International Journal of Food Science

View full text Add to dashboard Cite

The global market for organic cocoa beans continues to show sturdy growth. A low-cost handheld NIR spectrometer (900-1700 nm) combined with multivariate classification algorithms was used for rapid differentiation analysis of organic cocoa beans’ integrity. In this research, organic and conventionally cultivated cocoa beans were collected from different locations in Ghana and scanned nondestructively with a handheld spectrometer. Different preprocessing treatments were employed. Principal component analysis (PCA) and classification analysis, RF (random forest), KNN ( K -nearest neighbours), LDA (linear discriminant analysis), and PLS-DA (partial least squares-discriminant analysis) were performed comparatively to build classification models. The performance of the models was evaluated by accuracy, specificity, sensitivity, and efficiency. Second derivative preprocessing together with PLS-DA algorithm was superior to the rest of the algorithms with a classification accuracy of 100.00% in both the calibration set and prediction set. Second derivative algorithm was found to be the best preprocessing tool. The identification rates for the calibration set and prediction set were 96.15% and 98.08%, respectively, for RF, 91.35% and 92.31% for KNN, and 90.38% and 98.08% for LDA. Generally, the results showed that a handheld NIR spectrometer coupled with an appropriate multivariate algorithm could be used in situ for the differentiation of organic cocoa beans from conventional ones to ensure food integrity along the cocoa bean value chain.

show abstract

In situ cocoa beans quality grading by near-infrared-chemodyes systems

Abstract: Cocoa beans were quality graded innovatively using a near-infrared chemo-dyes system as aroma sensor to capture and detect their volatiles.

Cited by 26 publications

References 34 publications

Electronic Nose Coupled with Linear and Nonlinear Supervised Learning Methods for Rapid Discriminating Quality Grades of Superior Java Cocoa Beans

Electronic Nose Coupled with Linear and Nonlinear Supervised Learning Methods for Rapid Discriminating Quality Grades of Superior Java Cocoa Beans

Combination of Ant Colony Optimization and K-nearest Neighbours: The Influence of Working Capital Management on Corporate Performance

Differentiation of Organic Cocoa Beans and Conventional Ones by Using Handheld NIR Spectroscopy and Multivariate Classification Techniques

Contact Info

Product

Resources

About