Efforts to reduce the job burnout and psychological support for health care workers support motivation in order to provide better services to increase significantly. Thus, both personal productivity will be increased, and gain will be obtained in the institutional sense.

ÖzetGelişen toplum yapısı ile birlikte gerçek hayatta yaşanılan sorunlar ve olaylara bakış açıları da değişmektedir. İnsanlar sorunlarını sahip oldukları sözel ve sayısal verileri kullanarak çözmekte ve bunun için çeşitli yöntemlerden yararlanmaktadırlar. Matematiksel yöntemler insanlara kesinlik içeren durumlarda sorunların çözümlenmesinde sayısal verileri analiz ederek yardımcı olurken, belirsizlik içeren durumlarda yetersiz kalabilmektedir. Son yıllarda kalite değerlendirilmesi gibi belirsizlik içeren durumlarda ortaya çıkan problemlerin çözümünde sıklıkla kullanılan bulanık mantık, yapay zeka yöntemlerinden bir tanesidir. Klasik mantık teorisine göre daha esnek bir yapıya sahip olan bulanık mantık teorisi, olayları nesnelere "0" ve "1" arasında atadığı doğruluk dereceleri ile açıklamakta böylece sözel ve sayısal veriler arasında bir bağ oluşturmaktadır. Bu çalışmada, çiğ süt örneklerinin kalite sınıflarına ayrılmasını amaçlayan bulanık mantık tabanlı bir karar destek sistemi geliştirilmiştir. Sistemin girdileri çiğ süt örneklerine ilişkin toplam bakteri sayısı, somatik hücre sayısı ve protein miktarlarının ölçülen değerleridir. Tasarlanan bulanık sistemin çıktısı ise çiğ süt kalite değerlendirmesi şeklindedir. Yapılan analizin başarısını belirlemek amacıyla uzman kararları ile karşılaştırma yapılmış ve sistemin %80 değerinde başarılı olduğu görülmüştür. Sistemin modellenmesi Matlab (sürüm R2010b) programı kullanılarak yapılmıştır. Anahtar sözcükler: Bulanık mantık, Karar destek sistemi, Çiğ süt kalitesi Fuzzy Logic Approach in the Evaluation of Raw Milk Quality SummaryThe problems that faced with in real life and perspective of the events change with developing structure of society. The people in the face of problem use a variety of methods with their verbal and numerical data to find solution. Mathematical methods that including precision are sufficient in the analyses of numerical data while the modeling of verbal data may be insufficient in case of uncertainty. In recent years, fuzzy logic is one of the artificial intelligence methods that used in solution of the problems which are rosed from quality evaluation situations that consists of uncertainty cases. The fuzzy logic theory that has more flexible structure than the theory of classical logic, describe the events with degree of accuracy which is between "0" and "1" appointed to object. Fuzzy logic-based decision support system offers to people a more realistic and objective perspective in decision making. In this study, fuzzy logic base decision support system which aims to classify raw milk samples in quality has been developed. System inputs are; bacteria count for milk samples, somatic cell count and values for measured protein amounts. Designed fuzzy logic output is consist of raw milk quality value measurement; in order to calculate the success of the analysis, results have been compared to specialist's decisions and due to the comparison, it noticed that the system has 80% success rate. Modeling of the system has been made via Matlab (version R2...

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).

Abstract:Artificial neural network models (ANN's) are machine-learning systems, a type of artificial intelligence. They have been inspired by and developed along the working principles of the human brain and its nerve cells. ANN's are especially used in the modelling of nonlinear systems. With the information learned through repeated experience, similar to human learning, ANN's can provide classification, pattern recognition, optimisation and the realisation of forward-looking forecasts. Artificial neural network studies have been performed in animal husbandry in recent years. They have been used for the prediction of yield characteristics and classification, animal breeding, quality assessment, and disease diagnosis. In this study, classification of dairy cattle using artificial neural networks and cluster analysis are compared. Artificial neural networks models were determined to be more successful than cluster analysis.

In conclusion, our results do not support the hypothesis that the T102C and 1438 A/G polymorphisms in the 5-HT2A receptor gene are associated with schizophrenia, but further studies in a larger sample are needed.