Прегледај по Аутор "Pezo, Lato"

Сада се приказује 1 - 3 од 3
  • Сличица
    Ставка
    Effect of Atmospheric Cold Plasma Treatments on Reduction of Alternaria Toxins Content in Wheat Flour
    (MDPI, 2019) Janić Hajnal, Elizabet; Vukić, Milan; Pezo, Lato; Orčić, Dejan; Puač, Nevena; Škoro, Nikola; Milidrag, Ardea; Šoronja Simović, Dragana
    Beside Fusarium toxins, Alternaria toxins are among the most commonly found mycotoxins in wheat and wheat products. Currently, investigations of possibilities of reduction of Alternaria toxins in the wheat-processing chain are limited. Therefore, the aim of this study was to explore the potency of cold atmospheric plasma treatments, as a new non-thermal approach, for reduction of alternariol (AOH), alternariol monomethyl ether (AME) and tentoxin (TEN) content in spiked white wheat flour samples. Samples were treated with plasma generated in the air during 30 s to 180 s, with an increment step of 30 s, and at four varying distances from the cold plasma source (6 mm, 21 mm, 36 mm and 51 mm). The reduction of the Alternaria toxins content in samples after treatment was monitored by high performance liquid chromatography coupled to tandem mass spectrometry (LC-MS/MS). The maximum reduction of the examined Alternaria toxins was obtained by treatment performed at 6 mm distance from the plasma source, lasting 180 s, resulting in reductions of 60.6%, 73.8% and 54.5% for AOH, AME and TEN, respectively. According to the obtained experimental results, five empirical models in the form of the second-order polynomials were developed for the prediction of AOH, AME and TEN reduction, as well as the temperature and the moisture content of the wheat flour, that gave a good fit to experimental data and were able to predict the response variables successfully. The developed second-order polynomial models showed high coefficients of determination for prediction of experimental results (between 0.918 and 0.961).
  • Сличица
    Ставка
    Predicting Road Traffic Accidents—Artificial Neural Network Approach
    (MDPI, 2023) Gatarić, Dragan; Ruškić, Nenad; Aleksić, Branko; Ðurić, Tihomir; Pezo, Lato; Lončar, Biljana; Pezo, Milada
    Road traffic accidents are a significant public health issue, accounting for almost 1.3 million deaths worldwide annually, with millions more experiencing non-fatal injuries. A variety of subjective and objective factors contribute to the occurrence of traffic accidents, making it difficult to predict and prevent them on new road sections. Artificial neural networks (ANN) have demonstrated their effectiveness in predicting traffic accidents using limited data sets. This study presents two ANN models to predict traffic accidents on common roads in the Republic of Serbia and the Republic of Srpska (Bosnia and Herzegovina) using objective factors that can be easily determined, such as road length, terrain type, road width, average daily traffic volume, and speed limit. The models predict the number of traffic accidents, as well as the severity of their consequences, including fatalities, injuries and property damage. The developed optimal neural network models showed good generalization capabilities for the collected data foresee, and could be used to accurately predict the observed outputs, based on the input parameters. The highest values of r2 for developed models ANN1 and ANN2 were 0.986, 0.988, and 0.977, and 0.990, 0.969, and 0.990, accordingly, for training, testing and validation cycles. Identifying the most influential factors can assist in improving road safety and reducing the number of accidents. Overall, this research highlights the potential of ANN in predicting traffic accidents and supporting decision-making in transportation planning.
  • Сличица
    Ставка
    The prediction of lean meat and subcutaneous fat with skin content in pork cuts on the carcass meatness and weight
    (Springer, 2019) Tomović, Vladimir; Pezo, Lato; Jokanović, Marija; Tomović, Mila; Šojić, Branislav; Škaljac, Snežana; Vujadinović, Dragan; Ivić, Maja; Djekić, Ilija; Tomašević, Igor
    Early post-mortem, objective and non-destructive prediction of tissue distribution in the major pork cuts is a challenge for the meat industry. Mathematical models to predict pig carcass composition using total lean meat percentage and carcass weight were evaluated in this study. The data were obtained from 455 cold pig carcasses which were dissected according to the EU reference method; total lean meat percentage and carcass weight ranged from 42.45 to 69.21% and from 23.26 to 55.22 kg, respectively. Developed empirical models gave a reasonable fit to the experimental data and successfully predicted the carcass composition and tissue distribution in primal cuts. The second order polynomial models showed high coefficients of determination for prediction of experimental results (between 0.612 and 0.929), while the artificial neural network (ANN) model, based on the Broyden–Fletcher–Goldfarb–Shanno iterative algorithm, showed better prediction capabilities (overall r2 was 0.889). The newly developed software, based on ANN model is easy, fast, cheap and with sufficient precision for application in the meat industry.