Rommel M. Barbosa

Classification of geographic origin of rice by data mining and inductively coupled plasma mass spectrometry

We used data mining with ICP-MS to evaluate origin of rice.An accuracy above 93% was obtained with SVM and RF algorithms.Our method can be used for authentication purposes of other food. Rice is one of the most consumed cereals in the world and the main food product in the diet of the Brazilian population. Brazil itself is among the ten largest producers of rice, and most of the harvest comes from the South and Midwest regions. This paper presents a data mining study of samples of rice obtained from producers in Goias (Midwest region) and Rio Grande do Sul (South region), and builds classification models capable of predicting the geographical origin of a rice sample based on its chemical components. We use three popular classification techniques, support vector machines, random forests and neural networks, along with the F-score formula which measures the relative importance of the input variables. We achieved very good performances for the SVM, RF and MLP models with 93.66%, 93.83% and 90% prediction accuracy, respectively, on the 10-fold cross validation. The F-score shows that Cd(cadmium), Rb(rubidium), Mg(magnesium) and K(potassium) are the four most relevant components for prediction.

A simple and practical control of the authenticity of organic sugarcane samples based on the use of machine-learning algorithms and trace elements determination by inductively coupled plasma mass spectrometry.

A practical and easy control of the authenticity of organic sugarcane samples based on the use of machine-learning algorithms and trace elements determination by inductively coupled plasma mass spectrometry is proposed. Reference ranges for 32 chemical elements in 22 samples of sugarcane (13 organic and 9 non organic) were established and then two algorithms, Naive Bayes (NB) and Random Forest (RF), were evaluated to classify the samples. Accurate results (>90%) were obtained when using all variables (i.e., 32 elements). However, accuracy was improved (95.4% for NB) when only eight minerals (Rb, U, Al, Sr, Dy, Nb, Ta, Mo), chosen by a feature selection algorithm, were employed. Thus, the use of a fingerprint based on trace element levels associated with classification machine learning algorithms may be used as a simple alternative for authenticity evaluation of organic sugarcane samples.

Determination of trace elements in bovine semen samples by inductively coupled plasma mass spectrometry and data mining techniques for identification of bovine class

The reproductive performance of cattle may be influenced by several factors, but mineral imbalances are crucial in terms of direct effects on reproduction. Several studies have shown that elements such as calcium, copper, iron, magnesium, selenium, and zinc are essential for reproduction and can prevent oxidative stress. However, toxic elements such as lead, nickel, and arsenic can have adverse effects on reproduction. In this paper, we applied a simple and fast method of multi-element analysis to bovine semen samples from Zebu and European classes used in reproduction programs and artificial insemination. Samples were analyzed by inductively coupled plasma spectrometry (ICP-MS) using aqueous medium calibration and the samples were diluted in a proportion of 1:50 in a solution containing 0.01% (vol/vol) Triton X-100 and 0.5% (vol/vol) nitric acid. Rhodium, iridium, and yttrium were used as the internal standards for ICP-MS analysis. To develop a reliable method of tracing the class of bovine semen, we used data mining techniques that make it possible to classify unknown samples after checking the differentiation of known-class samples. Based on the determination of 15 elements in 41 samples of bovine semen, 3 machine-learning tools for classification were applied to determine cattle class. Our results demonstrate the potential of support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF) chemometric tools to identify cattle class. Moreover, the selection tools made it possible to reduce the number of chemical elements needed from 15 to just 8.

Comparative study of data mining techniques for the authentication of organic grape juice based on ICP-MS analysis

We used data mining with ICP-MS to classify grape juice.An accuracy above 89% was obtained with SVM.Our method can be used for authentication purposes of other foods. Authenticity is a substantial matter and a current concern of the organic food industry. Organic foods are appreciated by customers because of their benefits to health and friendliness to the environment. However, currently, the most common way for customers to confirm that the organic food they are buying are organic is by certificates and label information, which can be fraudulent. Furthermore, it is interesting to gain insight into organic food composition and visualize which mineral components are fundamental in the differentiation of organic from conventional food. This work addresses these problems using data mining concepts and techniques in a comparative study of organic and conventional food focusing on grape juice, but the proposed methodology can be adapted and employed for analysis of other types of organic food. This article presents a data mining analysis of the elemental composition of 37 grape juice samples collected from different locations in Brazil. The elemental composition of grape juice samples was determined by inductively-coupled plasma-mass spectrometry (ICP-MS). Forty-four elements were determined in the two types of samples, namely organic and conventional grape juice. Special effort was devoted to selecting the variables (elements) that best described each type of grape juice. Predictive models based on support vector machines, neural networks and decision trees were developed to successfully differentiate organic from conventional grape juice samples. We found that, according to the F-score, Chi-square and Random Forest Importance variable selection measures, the components Na, Sn, P, K, Sm and Nd are among the most important variables in the differentiation of organic and conventional grape juice samples. Particularly, the components Na, Sn and K received first, second or third position according to at least two methods. On the other hand, all variable selection methods considered indicated that Ag, Zn, Cr, Be and Pd were among the least important variables for the differentiation of organic and conventional grape juices. SVM yielded an accuracy of 89.18%, both CART and MLP achieved an accuracy of 86.48%.

The use of decision trees and naïve Bayes algorithms and trace element patterns for controlling the authenticity of free-range-pastured hens' eggs.

This article aims to evaluate 2 machine learning algorithms, decision trees and naïve Bayes (NB), for egg classification (free-range eggs compared with battery eggs). The database used for the study consisted of 15 chemical elements (As, Ba, Cd, Co, Cs, Cu, Fe, Mg, Mn, Mo, Pb, Se, Sr, V, and Zn) determined in 52 eggs samples (20 free-range and 32 battery eggs) by inductively coupled plasma mass spectrometry. Our results demonstrated that decision trees and NB associated with the mineral contents of eggs provide a high level of accuracy (above 80% and 90%, respectively) for classification between free-range and battery eggs and can be used as an alternative method for adulteration evaluation.

The Use of Support Vector Machine to Analyze Food Security in a Region of Brazil

ABSTRACT The application of Support Vector Machine (SVM) to classify food security in a northeast region in Brazil is explored. This type of application represents a novel use of the SVM in addressing contemporary social science questions. The results demonstrate an accuracy > 75% and a recall of 84% for classifying households that are food insecure. The variables identified by the model are consistent with contemporary theories of food security and vulnerability. The successful application of SVM in this instance and the growing availability of large-scale social science datasets suggest that data mining techniques will have a larger role to play in answering critical social science questions in the future.

Classification of Cabernet Sauvignon from Two Different Countries in South America by Chemical Compounds and Support Vector Machines

ABSTRACT A simple approach is proposed for the classification of Cabernet Sauvignon wines from two different countries in South America (Brazil and Chile). The strategy combines the wines’ functionality, designed as antioxidant activity (DPPH and ORAC), total polyphenols (TP), total anthocyanins (TA), and color, with a data mining technique known as support vector machines (SVM). The original dataset has 16 wine samples from Brazil and 113 from Chile. Algorithms were used to balance the dataset. Using resampling algorithms, we extended the Brazilian wines to 32 samples and reduced the Chilean wines to 32. With the proposed methodology, it was possible to classify the origin of the wine with an accuracy of 89% when using the 20 original elements. An accuracy of 83% was found using only 5 elements (L, DPPH, delph-3-acetylglu, peon-3-(coum)glu, and pet-3-acetylglu). Our methodology can be used for origin certification of other wines.

Establishing chemical profiling for ecstasy tablets based on trace element levels and support vector machine

Ecstasy is an amphetamine-type substance that belongs to a popular group of illicit drugs known as “club drugs” whose consumption is rising in Brazil. The effects caused by this substance in the human organism are mainly psychological, including hallucinations, euphoria and other stimulant effects. The distribution of this drug is illegal, and effective strategies are required in order to detain its growth. One possible way to obtain useful information on ecstasy trafficking routes, sources of supply, clandestine laboratories and synthetic protocols is by its chemical components. In this paper, we present a data mining and predictive analysis for ecstasy tablets seized in two cities of São Paulo state (Brazil), Campinas and Ribeirão Preto, based on their chemical profile. We use the concentrations of 25 elements determined in the ecstasy samples by ICP-MS as our descriptive variables. We develop classification models based on support vector machines capable of predicting in which of the two cities an arbitrary ecstasy sample was most likely to have been seized. Our best model achieved a 81.59% prediction accuracy. The F-score measure shows that Se, Mo and Mg are the most significant elements that differentiate the samples from the two cities, and they alone are capable of yielding an SVM model which achieved the highest prediction accuracy.

Recent applications of multivariate data analysis methods in the authentication of rice and the most analyzed parameters: A review

ABSTRACT Rice is one of the most important staple foods around the world. Authentication of rice is one of the most addressed concerns in the present literature, which includes recognition of its geographical origin and variety, certification of organic rice and many other issues. Good results have been achieved by multivariate data analysis and data mining techniques when combined with specific parameters for ascertaining authenticity and many other useful characteristics of rice, such as quality, yield and others. This paper brings a review of the recent research projects on discrimination and authentication of rice using multivariate data analysis and data mining techniques. We found that data obtained from image processing, molecular and atomic spectroscopy, elemental fingerprinting, genetic markers, molecular content and others are promising sources of information regarding geographical origin, variety and other aspects of rice, being widely used combined with multivariate data analysis techniques. Principal component analysis and linear discriminant analysis are the preferred methods, but several other data classification techniques such as support vector machines, artificial neural networks and others are also frequently present in some studies and show high performance for discrimination of rice.

Characterization of Z m -well-covered graphs for some classes of graphs

Abstract A graph G is a Z m -well-covered graph if |I 1 |≡|I 2 |( mod m ) for all maximal independent sets I 1 and I 2 in V(G) [3]. The recognition problem of Z m -well-covered graphs is a Co-NP-Complete problem. We give a characterization of Z m -well-covered graphs for chordal, simplicial and circular arc graphs.