Louise Manha Peres

Storage time prediction of pork by Computational Intelligence

We use of CI for storage time prediction only by pH, CIELab and WHC parameters.Our approach has pork assessment by a non-destructive, fast, accurate analysis.We evaluate the pork aging, accurately, without the analysis of lipid oxidation.We test prediction by J48, Naive Bayes, kNN, RF, SVM, MLP and Fuzzy. In this paper, a storage time prediction of pork using Computational Intelligence (CI) model was reported. We investigated a solution based on traditional pork assessment towards a low time-cost parameters acquisition and high accurate CI models by selection of appropriate parameters. The models investigated were built by J48, Naive Bayes (NB), k-NN, Random Forest (RF), SVM, MLP and Fuzzy approaches. CI input were traditional quality parameters, including pH, water holding capacity (WHC), color and lipid oxidation extracted from 250 samples of 0, 7 and 14days of post mortem. Five parameters (pH, WHC, Lź, aź and bź) were found superior results to determine the storage time and corroborate with identification in minutes. Results showed RF (94.41%), 3-NN (93.57%), Fuzzy Chi (93.23%), Fuzzy W (92.35%), MLP (88.35%), J48 (83.64%), SVM (82.03%) and NB (78.26%) were modeled by the five parameters. One important observation is about the ease of 0-day identification, followed by 14-day and 7-day independently of CI approach. Result of this paper offers the potential of CI for implementation in real scenarios, inclusive for fraud detection and pork quality assessment based on a non-destructive, fast, accurate analysis of the storage time.

Fatty acid profile of beef from immunocastrated (BOPRIVA(®)) Nellore bulls.

Twenty Nellore bulls (ABW=357.7±9.65kg) were divided into 2 groups: intact and immunocastrated - Bopriva®. After the trial period, the cattle were slaughtered and carcass fat thickness was evaluated, ether extract and fatty acid composition of the longissimus thoracis analyses were performed, and the activity indices of relevant enzymes were calculated. The means were calculated and compared by Students t-test and Pearsons correlation coefficients (p<0.05). The immunocastrated group showed higher back fat thickness, ether extract, monounsaturated fatty acids (MUFAs), and activity index of Δ(9) desaturase C18 and lower polyunsaturated fatty acids (PUFAs) and n-6 fatty acids when compared to the intact group. The correlations between ether extract and the saturated and monounsaturated fatty acids were positive, and negative with polyunsaturated, n-3, n-6 and PUFA/SFA. Therefore, immunocastration may improve the fatty acid profile in the longissimus thoracis by increasing MUFAs, mainly oleic acid that is the most representative fatty acid in the meat and is considered beneficial to health.

Effect of low or high stress in pre-slaughter handling on pig carcass and meat quality

The objective of this study was to evaluate the consequences of low or high stress during pre-slaughter handling of pigs on their carcass and meat quality. Forty-four animals of a commercial lineage, with an average weight of 107.23±5.23 kg, were used. At lairage the animals were randomly divided into two groups, the least and the most stressed. At slaughter, during bleeding, blood samples were collected for later cortisol and lactate tests. Forty-five minutes after slaughter the initial pH of th carcasses was measured and samples of the semitendinosus muscle were collected for R-value calculation. After 24 hours of cooling, the final pH was measured, damage scores were assessed and samples of the longissimus dorsi muscle were collected to evaluate drip loss, liquid loss from defrosting and cooking, shear force, lipid oxidation, and color. The results were evaluated by analysis of variance and the means were compared by Tukey´s test. It was found that cortisol, lactate and R-value were lower and initial pH was higher for the least stressed animals, whereas the other parameters were not significantly affected. Thus, low stress in the pre-slaughter handling of pigs is effective in reducing stress and carcass damage, but has no effect on meat quality.

Effect of supplementing finishing pigs with different sources of chromium on performance and meat quality

The objective was to evaluate the dietary supplementation of different sources of chromium (inorganic: chromium sulfate and chelated: chromium-methionine) during the finishing period of pigs to obtain improvements in the animal performance, and carcass and meat quality. The statistical design was randomized blocks, where 44 barrows, with an initial weight 60.49±5.12 kg, were divided into four blocks (heavier, heavy, light and lighter) according to initial weight. The experimental diets were isoenergetic and isonutrient, except for the chromium level. The treatments were divided as follows: control (without chromium), control + 200 ppb of inorganic chromium (chromium sulfate), and control + 200 ppb of chelated chromium (chromium-methionine). In the performance measures, the stall was considered the experimental unit and in the blood parameters, carcass and meat evaluations each animal constituted the experimental unit. Animals were slaughtered when they reached the final average weight of 107.23±5.23 kg. Blood samples were collected and tested for blood parameters (cholesterol, triglycerides and glucose) as well as carcass quality (hot and cold weights, yield, loin-eye area, muscle depth and backfat thickness) and meat quality (initial and final pH, drip loss, color, chemical composition and lipid oxidation) parameters. Chromium-methionine supplementation provides a greater daily weight gain only compared with the animals that are not supplemented with chromium, because feed conversion is better as compared with the other treatments. After 24 hours of storage, the meat from pigs supplemented either with chromium-methionine or with chromium sulfate presents lower lipid oxidation than that from non-supplemented animals. However, after three days of storage, only chromim-methionine is effective in reducing lipid oxidation.

Fuzzy approach for classification of pork into quality grades: coping with unclassifiable samples

Abstract Meat classification methods are commonly based on quality parameters standardized by numeric ranges. However, some animal samples from different production chains do not match the current grades proposed. These unclassifiable samples are not capable to fit into a standard created by crisp range of values due to being infeasible toward its definition. An alternative to handle this kind of sample classification is the fuzzy logic, which could deal with uncertainty and ambiguity degree like human reasoning. In this work, we compare the traditional classification method and fuzzy approaches with the objective to handle the infeasible samples. This was compared to traditional pork standards using eleven real-life datasets with a total of 1798 samples described by pH, water holding capacity and/or L∗ value. The results demonstrated that traditional classification could not predict the unclassifiable samples. On the other hand, the fuzzy approaches improve significantly the number of classified samples. Performance of the fuzzy approaches were compared with several machine learning algorithms, but no significant statistical difference was observed. Finally, a real-life study case was explored, highlighting some advantages and further achievements of the fuzzy modeling.