Cocoa bean and cocoa bean products quality evaluation by NIR spectroscopy and chemometrics: A review

Teye, Ernest; Anyidoho, Elliot K.; Agbemafle, Robert; Sam-Amoah, Livingstone K.; Elliott, Chris

doi:10.1016/j.infrared.2019.103127

Cited by 47 publications

(16 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But different from our common sense that nonlinear models generally performed better than linear models, nonlinear model MLP achieved lower accuracy than linear model LDA in this study [41,[45][46]. Thus, many models need to be tried to determine which is the optimal one if we use traditional multivariate analysis methods [45][46][47][48]. Conversely, deep models will generally achieve satisfactory results if the training data is sufficient and the structure is properly designed.…”

Section: Identification Results Analysis On Source Datasetcontrasting

confidence: 61%

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Liu

Bao

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Varieties identification of crop seeds is significant for breeders to screen out seeds with specific traits and for market regulators to detect seeds purity. Hyperspectral imaging technology provides a fast and non-destructive means for varieties identification. And deep learning algorithm is suitable for effective analysis of redundant spectral data. However, deep learning algorithms have serious big data dependency, while collecting high-quality large-scale samples was high-cost in many cases. This made it difficult to build an accurate identification model. This study aimed to explore a rapid and accurate method for varieties identification of different crop seeds under sample-limited condition based on hyperspectral imaging and deep transfer learning.Results: Three deep neural networks with typical structures were designed based on a samples-rich Pea dataset. Obtained the highest accuracy of 99.57 %, VGG-MODEL was transferred to classify four target datasets (Rice, Oat, Wheat, Cotton) with limited samples. The accuracies of deep transferred model achieved 95 %, 99 %, 80.8 %, and 83.86 % on the four datasets, respectively. Using training sets with different sizes, deep transferred model could always obtain higher performance than other traditional methods. Visualization of training process and classification results confirmed the portability of common features of seed spectra and provided an interpreted method for rapid and accurate varieties identification of crop seeds.Conclusions: This study combined hyperspectral imaging and deep transfer learning to identify varieties of different crop seeds, which was proved to be efficient under sample-limited condition. This facilitated crop variety screening process under the scenario of sample scarcity. It also provided a new idea for the detection of other qualities of crop seeds based on hyperspectral imaging under sample-limited condition.

show abstract

Section: Identification Results Analysis On Source Datasetcontrasting

confidence: 61%

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Liu

Bao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Noteworthy, near‐infrared spectroscopy has been extensively applied for the rapid nondestructive authentication and geographical classification of cocoa beans 114–117 . Recently, a combined near‐infrared hyperspectral imaging and chemometric method has been developed for the discrimination of cocoa hybrids 118 .…”

Section: Authentication and Geographical Differentiation Of Qualitymentioning

confidence: 99%

Quality differentiation of cocoa beans: implications for geographical indications

Hernandez

Granados²

2021

J Sci Food Agric

View full text Add to dashboard Cite

Geographical indications may stimulate collective actions of governance for quality control, trade and marketing as well as innovation based on the use of local resources and regional biodiversity. Cocoa production, however, dominated by small family agriculture in tropical regions, has rarely made use of such strategies. This review is aimed at understanding major research interests and emerging technologies helpful for the origin differentiation of cocoa quality. Results from literature search and cited references of publications on cocoa research were imported into VOSviewer for data analysis, which aided in visualizing major research hotpots. Co‐occurrence analysis yielded major research clusters which guided the discussion of this review. Observed was a consensus recognizing cocoa quality resulting from the interaction of genotype, fermentation variables and geographical origin. A classic view of cocoa genetics based on the dichotomy of ‘fine versus bulk’ has been reexamined by a broader perspective of human selection and cocoa genotype evolution. This new approach to cocoa genetic diversity, together with the understanding of complex microbiome interactions through fermentation, as well as quality reproducibility challenged by geographical conditions, have demonstrated the importance of terroir in the production of special attributes. Cocoa growing communities around the tropics have been clearly enabled by new omics and chemometrics to systematize producing conditions and practices in the designation of specifications for the differentiation of origin quality. © 2021 Society of Chemical Industry

show abstract

“…Good quality cocoa beans will result in good quality products (Owosu 2010) considering that optimal results are obtained from fully fermented cocoa beans as the raw material. Teye et al (2019) underlined the variability in the quality of cocoa beans from different countries due to the differences in the main processing techniques, particularly fermentation and drying.…”

Section: Number Of Beans Per 100 Gramsmentioning

confidence: 99%

Evaluation of yield and pest and disease resistance of cocoa clones in Kolaka District, Southeast Sulawesi, Indonesia

et al. 2020

View full text Add to dashboard Cite

Abstract. Rubiyo, Dewi YA, Imran, Salim A, Baharudin, Indrawanto C, Ratule MT. 2020. Evaluation of yield and pest and disease resistance of cocoa clones in Kolaka District, Southeast Sulawesi, Indonesia. Biodiversitas 21: 5698-5607. Cocoa is one of the main plantation commodities in Indonesia. It is an important source of foreign exchange and employment. Currently, Indonesian cocoa production and productivity, including in Southeast Sulawesi, are declining due to pests and diseases. In addition, there is a lack of high-quality and high-yielding clones. This study aimed to evaluate the quality of cocoa clones and resistance to cocoa pod borer (CPB) and cocoa pod rot (CPR) disease caused by the fungus Phytophthora palmivora. The study tested 12 cocoa clones, which included four high-yielding clones. The research location was in Lambandia Subdistrict, Kolaka District, Southeast Sulawesi Province, Indonesia. Clonal planting material was propagated by grafting in 2010. The study used a randomized block design and the treatments consisted of 20 plants of each cocoa clone with three replications. The clones were evaluated from 2018 to 2019. The observed variables included resistance to CPB and CPR. The results of the study based on the quality component showed that the clones MT, M04, and M01 had the highest average weight per one dry bean of 1.55 g, 1.64 g, and 1.24 g, respectively. Beans produced by clones MT, M01, and M04 had an average fat content of 53.36%, 52.72%, and 50.76%, respectively. Observations of the average number of pods with CPR showed that the lowest rate of attack (about 6%) was in BAL 209 and PT. Ladongi clones, with attack intensities of 20% and 18%, respectively; therefore, these clones were classified as resistant to CPR. Evaluation of the level of resistance to attack by CPB pests found two resistant clones, PT. Ladongi and Sulawesi 2, with light levels of attack on beans.

show abstract

Cocoa bean and cocoa bean products quality evaluation by NIR spectroscopy and chemometrics: A review

Cited by 47 publications

References 52 publications

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Quality differentiation of cocoa beans: implications for geographical indications

Evaluation of yield and pest and disease resistance of cocoa clones in Kolaka District, Southeast Sulawesi, Indonesia

Contact Info

Product

Resources

About