J.J. del Coz

The usefulness of artificial intelligence techniques to assess subjective quality of products in the food industry

In this paper we advocate the application of Artificial Intelligence techniques to quality assessment of food products. Machine Learning algorithms can help us to: (a) extract operative human knowledge from a set of examples; (b) conclude interpretable rules for classifying samples regardless of the non-linearity of the human behaviour or process; and (c) help us to ascertain the degree of influence of each objective attribute of the assessed food on the final decision of an expert. We illustrate these topics with an example of how it is possible to clone the behaviour of bovine carcass classifiers, leading to possible further industrial applications.

Artificial intelligence techniques point out differences in classification performance between light and standard bovine carcasses

The validity of the official SEUROP bovine carcass classification to grade light carcasses by means of three well reputed Artificial Intelligence algorithms has been tested to assess possible differences in the behavior of the classifiers in affecting the repeatability of grading. We used two training sets consisting of 65 and 162 examples respectively of light and standard carcass classifications, including up to 28 different attributes describing carcass conformation. We found that the behavior of the classifiers is different when they are dealing with a light or a standard carcass. Classifiers follow SEUROP rules more rigorously when they grade standard carcasses using attributes characterizing carcass profiles and muscular development. However, when they grade light carcasses, they include attributes characterizing body size or skeletal development. A reconsideration of the SEUROP classification system for light carcasses may be recommended to clarify and standardize this specific beef market in the European Union. In addition, since conformation of light and standard carcasses can be considered different traits, this could affect sire evaluation programs to improve carcass conformation scores from data from markets presenting a great variety of ages and weights of slaughtered animals.

Using artificial intelligence to design and implement a morphological assessment system in beef cattle

In this paper a methodology is developed to improve the design and implementation of a linear morphological system in beef cattle using artificial intelligence. The proposed process involves an iterative mechanism where type traits are successively defined and computationally represented using knowledge engineering methodologies, scored by a set of trained human experts and finally, analysed by means of four reputed machine learning algorithms. The results thus achieved serve as feed back to the next iteration in order to improve the accuracy and efficacy of the proposed assessment system. A sample of 260 conformation records of the Asturiana de los Valles beef cattle breed is shown to illustrate the methodology. Three sources of inconsistency were detected: (a) the existence of different interpretations of the trait’s definition, increasing the subjectivity of the assessment; (b) the narrow range of variation of some of the anatomical traits assessed; (c) the inclusion of some complex traits in the assessment system. In this sense, the reopening of the evaluated Asturiana de los Valles assessment system is recommended. In spite of the difficulty of collecting data from live animals, further implications of the artificial intelligence systems on morphological assessment are pointed out.

Identifying market segments in beef: Breed, slaughter weight and ageing time implications.

In this paper we propose a method to learn the reasons why groups of consumers prefer some beef products to others. We emphasise the role of groups since, from a practical point of view, they may represent market segments that demand different products. Our method starts representing peoples preferences in a metric space; there we are able to define a kernel based similarity function that allows a clustering algorithm to identify significant groups of consumers with homogeneous likes. Finally, in each cluster, we developed, with a support vector machine (SVM), a function that explains the preferences of those consumers grouped in the cluster. The method was applied to a real case of consumers of beef that tasted beef from seven Spanish breeds, slaughtered at two different weights and aged for three different ageing periods. Two different clusters of consumers were identified for acceptability and tenderness, but not for flavour. Those clusters ranked two very different breeds (Asturiana and Retinta) in opposite order. In acceptability, ageing period was appreciated in a different way. However, in tenderness most consumers preferred long ageing periods and heavier to lighter animals.

Intelligent control system for fluorescent lighting based on LonWorks technology

In this paper a new distributive control system for indoor fluorescent lighting based on LonWorks technology is presented. The system features the following elements: microprocessor-controlled fluorescent lamp electronic ballast, communication system using the power line as communication media and control software for Windows 95 environment. With this structure a low cost distributive control system for lighting applications has been achieved, allowing energy and maintenance saving and reliability increase of the fluorescent lighting systems.

A semi-dependent decomposition approach to learn hierarchical classifiers

In hierarchical classification, classes are arranged in a hierarchy represented by a tree or a forest, and each example is labeled with a set of classes located on paths from roots to leaves or internal nodes. In other words, both multiple and partial paths are allowed. A straightforward approach to learn a hierarchical classifier, usually used as a baseline method, consists in learning one binary classifier for each node of the hierarchy; the hierarchical classifier is then obtained using a top-down evaluation procedure. The main drawback of this naive approach is that these binary classifiers are constructed independently, when it is clear that there are dependencies between them that are motivated by the hierarchy and the evaluation procedure employed. In this paper, we present a new decomposition method in which each node classifier is built taking into account other classifiers, its descendants, and the loss function used to measure the goodness of hierarchical classifiers. Following a bottom-up learning strategy, the idea is to optimize the loss function at every subtree assuming that all classifiers are known except the one at the root. Experimental results show that the proposed approach has accuracies comparable to state-of-the-art hierarchical algorithms and is better than the naive baseline method described above. Moreover, the benefits of our proposal include the possibility of parallel implementations, as well as the use of all available well-known techniques to tune binary classification SVMs.

On the prediction of Hodgkin lymphoma treatment response

PurposeThe cure rate in Hodgkin lymphoma is high, but the response along with treatment is still unpredictable and highly variable among patients. Detecting those patients who do not respond to treatment at early stages could bring improvements in their treatment. This research tries to identify the main biological prognostic variables currently gathered at diagnosis and design a simple machine learning methodology to help physicians improve the treatment response assessment.MethodsWe carried out a retrospective analysis of the response to treatment of a cohort of 263 Caucasians who were diagnosed with Hodgkin lymphoma in Asturias (Spain). For that purpose, we used a list of 35 clinical and biological variables that are currently measured at diagnosis before any treatment begins. To establish the list of most discriminatory prognostic variables for treatment response, we designed a machine learning approach based on two different feature selection methods (Fisher’s ratio and maximum percentile distance) and backwards recursive feature elimination using a nearest-neighbor classifier (k-NN). The weights of the k-NN classifier were optimized using different terms of the confusion matrix (true- and false-positive rates) to minimize risk in the decisions.Results and conclusionsWe found that the optimum strategy to predict treatment response in Hodgkin lymphoma consists in solving two different binary classification problems, discriminating first if the patient is in progressive disease; if not, then discerning among complete and partial remission. Serum ferritin turned to be the most discriminatory variable in predicting treatment response, followed by alanine aminotransferase and alkaline phosphatase. The importance of these prognostic variables suggests a close relationship between inflammation, iron overload, liver damage and the extension of the disease.

Learning data structure from classes: A case study applied to population genetics

In most cases, the main goal of machine learning and data mining applications is to obtain good classifiers. However, final users, for instance researchers in other fields, sometimes prefer to infer new knowledge about their domain that may be useful to confirm or reject their hypotheses. This paper presents a learning method that works along these lines, in addition to reporting three interesting applications in the field of population genetics in which the aim is to discover relationships between species or breeds according to their genotypes. The proposed method has two steps: first it builds a hierarchical clustering of the set of classes and then a hierarchical classifier is learned. Both models can be analyzed by experts to extract useful information about their domain. In addition, we propose a new method for learning the hierarchical classifier. By means of a voting scheme employing pairwise binary models constrained by the hierarchical structure, the proposed classifier is computationally more efficient than previous approaches while improving on their performance.

Implementation of an elastic-viscoplastic ductile model for the numerical simulation of the ductile crack growth in notched tensile and Charpy impact tests

A mathematical algorithm which integrates the constitutive equations for the ductile fracture process in viscoplastic materials is described. The algorithm has been implemented in the finite-element commercial code ABAQUS by means of a constitutive USER subroutine. Based on the computational cell methodology proposed by Xia and Shih, the R-curves for pre-cracked Charpy specimens under different dynamic load conditions are obtained. In all cases it is observed that the mathematical algorithm is able to reproduce the increase in the material resistance to ductile tearing as the impact speed increases.