Data mining derived from food analyses using non-invasive/non-destructive analytical techniques; determination of food authenticity, quality &amp; safety in tandem with computer science disciplines

Ropodi, Athina; Panagou, Efstathios Ζ.; Nychas, George‐John E.

doi:10.1016/j.tifs.2016.01.011

Cited by 151 publications

(107 citation statements)

References 79 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…There have been many published methods for detection of food contamination utilizing traditional machine learning algorithms (Bisgin et al., ; Ropodi, Panagou, & Nychas, ; Ravikanth, Jayas, White, Fields, & Sun, ). There are potential possibilities for deep learning to replace the traditional machine learning method to achieve better detection results for food contamination in different food production procedures.…”

Section: Food Contaminationmentioning

confidence: 99%

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

388

166

View full text Add to dashboard Cite

Deep learning has been proved to be an advanced technology for big data analysis with a large number of successful cases in image processing, speech recognition, object detection, and so on. Recently, it has also been introduced in food science and engineering. To our knowledge, this review is the first in the food domain. In this paper, we provided a brief introduction of deep learning and detailedly described the structure of some popular architectures of deep neural networks and the approaches for training a model. We surveyed dozens of articles that used deep learning as the data analysis tool to solve the problems and challenges in food domain, including food recognition, calories estimation, quality detection of fruits, vegetables, meat and aquatic products, food supply chain, and food contamination. The specific problems, the datasets, the preprocessing methods, the networks and frameworks used, the performance achieved, and the comparison with other popular solutions of each research were investigated. We also analyzed the potential of deep learning to be used as an advanced data mining tool in food sensory and consume researches. The result of our survey indicates that deep learning outperforms other methods such as manual feature extractors, conventional machine learning algorithms, and deep learning as a promising tool in food quality and safety inspection. The encouraging results in classification and regression problems achieved by deep learning will attract more research efforts to apply deep learning into the field of food in the future.

show abstract

Section: Food Contaminationmentioning

confidence: 99%

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

388

166

View full text Add to dashboard Cite

show abstract

“…The best region selection for freshness evaluations was based on the results of the developed PLS models. Smaller models were also developed by selecting the most influential wavelengths using the I-PLS forward algorithm of interval selection [39]. This algorithm selects a subset of variables for building the PLS model, which will give a similar prediction compared to using all the variables.…”

Section: Methodsmentioning

confidence: 99%

Predicting Gilthead Sea Bream (Sparus aurata) Freshness by a Novel Combined Technique of 3D Imaging and SW-NIR Spectral Analysis

Ivorra

Verdú

Sanchez

et al. 2016

Sensors

View full text Add to dashboard Cite

A technique that combines the spatial resolution of a 3D structured-light (SL) imaging system with the spectral analysis of a hyperspectral short-wave near infrared system was developed for freshness predictions of gilthead sea bream on the first storage days (Days 0–6). This novel approach allows the hyperspectral analysis of very specific fish areas, which provides more information for freshness estimations. The SL system obtains a 3D reconstruction of fish, and an automatic method locates gilthead’s pupils and irises. Once these regions are positioned, the hyperspectral camera acquires spectral information and a multivariate statistical study is done. The best region is the pupil with an R2 of 0.92 and an RMSE of 0.651 for predictions. We conclude that the combination of 3D technology with the hyperspectral analysis offers plenty of potential and is a very promising technique to non destructively predict gilthead freshness.

show abstract

“…Sample number of Class I was a little small, which may not represent generality. SPA is just one among plenty of feature selection methods [20] , leaving the effectiveness of other selected wavelengths questionable. Similarly, more classifiers shall be introduced into the model to test the effectivity and universality.…”

Section: Classification Of Sprouting Potato Eyesmentioning

confidence: 99%

Precautionary analysis of sprouting potato eyes using hyperspectral imaging technology

Gao

Rao

et al. 2018

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Sprouted potatoes are not allowed for healthy diet. A good knowledge of the sprouting stage of potatoes can help manage the storage conditions and guide market distribution, thus enabling the quality assurance of potatoes on table. This article presented an intelligent method for precautionary analysis of potato eyes based on hyperspectral imaging technique. Potential potato eyes were classified into two categories according to the time gap to the sprouting date, i.e. by-sprouting and pre-sprouting potato eyes, representing eyes about to sprout and eyes that will take a while to sprout. Features used for classification were extracted by two methods, including successive projections algorithm (SPA) and a newly-developed sine fit algorithm (SFA). Then classifiers of fisher discriminant analysis (FDA) and least square support vector machine (LSSVM) were utilized for classification of potential sprouting potato eyes. Results showed that FDA was more effective than LSSVM in classifying pre-sprouting and by-sprouting potato eyes, and SFA performed well in FDA classifier with the recognition accuracy of 95.3% for prediction set. It is concluded that hyperspectral imaging has the potential for predicting the sprouting stages of potato eyes.

show abstract

Data mining derived from food analyses using non-invasive/non-destructive analytical techniques; determination of food authenticity, quality & safety in tandem with computer science disciplines

Cited by 151 publications

References 79 publications

Application of Deep Learning in Food: A Review

Application of Deep Learning in Food: A Review

Predicting Gilthead Sea Bream (Sparus aurata) Freshness by a Novel Combined Technique of 3D Imaging and SW-NIR Spectral Analysis

Precautionary analysis of sprouting potato eyes using hyperspectral imaging technology

Contact Info

Product

Resources

About