In this study, the impact of data preprocessing on the prediction of 305-day milk yield using neural networks were investigated with regard to the effect of different normalization techniques. Eight normalization techniques “Z-Score, Min-Max, D-Min-Max, Median, Sigmoid, Decimal Scaling, Median and MAD, TanhEstimators" and five different back propagation algorithms “Levenberg-Marquardt (LM), Bayesian Regularization (BR), Scaled Conjugate Gradient (SCG), Conjugate Gradient Back propagation with Powell-Beale Restarts (CGB) and Brayde Fletcher Gold Farlo Shanno Quasi Newton Back propagation (BFG)” were examined and tested comparatively for the analysis. Neural network architecture was optimized and tested with several experiments. Results of the analysis show that applying different normalization techniques affect the performance and the distribution of outputs influences the learning process of the neural network. The magnitude of the effects varied with the type of back propagation algorithms, activation functions, and network's architectural structure. According to the results of the analysis, the most successful performance value in the 305-day milk yield estimation was obtained by using the neural network structured by using the Decimal Scaling normalization technique with the Bayesian Regulation algorithm (R2Adj = 0.8181, RMSE= 0.0068, MAPE= 160.42 for test set; R2Adj =0.8141, RMSE= 0.0067, MAPE= 114.12 for validation set).
17 February 2020 in Tropical Animal Health and Production
Introduction In various applications in poultry breeding and feeding, the dependent variable can vary with time. Time-varying data can be represented by non-linear functions and usually have a curvilinear structure. In models developed under nonlinear
4 October 2022 in Turkish Journal of Agriculture - Food Science and Technology
Climate change is one of the biggest global environmental problems faced by mankind in recent times. Therefore, determining the knowledge and awareness levels of individuals on this issue is very important in terms of contributing to the solutions to be developed in the fight against climate change at the local level. In this study, it is aimed to determine the approaches, consciousness and awareness levels of Kırşehir Ahi Evran University students and local people about climate change in Kırşehir. The main material of the research consisted of primary data obtained from 250 face-to-face surveys applied to students and the public. Related literatures are also secondary data. The survey questions include questions about the individual characteristics of the person (gender, age, education level, job), climate change awareness level, and the effects of climate change on agriculture and water resources. The obtained data were analyzed using SPSS 26.0 statistical package program. In the evaluation of the data, descriptive statistics, frequency tables and graphical representations were used. As a result of the analyzes performed using the Kruskall-Wallis test, it is seen that there are statistically significant differences between the education groups in the variables of climate change awareness level and climate change risk perception level (P0.05), and there was a statistically significant difference between the occupational group averages in the climate change risk perception level (P
Path Analizi, süt sığırcılığı başta olmak üzere hayvancılık alanında yaygın kullanılan yöntemler arasındadır. Modelde bulunan bağımlı ve bağımsız değişkenlerin birbirleri üzerinde doğrudan ve dolaylı etkilerinin hesaplanmasında kullanılan bu yöntem araştırmacılara oldukça ayrıntılı yorumlama imkânı sunmaktadır. Bu çalışmada, 1007 baş Holstein ırkı süt sığırına ilişkin laktasyon sayısı, buzağılama mevsimi, kuru dönem, servis periyodu ve tohumlama sayısı değişkenlerinin 305-gün süt verimi üzerine doğrudan ve dolaylı etkileri Path analizi ile araştırılmıştır. Çalışmanın analizleri IBM SPSS 26.0 ve IBM SPSS AMOS 21 programı ile gerçekleştirilmiştir. Laktasyon sırası (-0.061) ve buzağılama mevsimi (0.027) değişkenlerinin 305-gün süt verimi üzerine doğrudan etkilerinin istatistiksel açıdan anlamlı olmadığı görülmektedir (p>0.05). Kuru dönem (-0.354), servis periyodu (-0.505) ve tohumlama sayısı (0.386) değişkenlerinin 305-gün süt verimi üzerine doğrudan etkilerinin istatistiksel açıdan anlamlı olduğu tespit edilmiştir (p