---

In this paper, the urinary infection, that is a common symptom of the decline of the immune system, is discussed based on the well-known algorithms in machine learning, such as Bayesian networks in both Markov and tree structures. A large scale sampling has been executed to evaluate the performance of Bayesian network algorithm. A number of 4052 samples wereobtained from the database of the Takestan Department of Health, a center affiliated to Qazvin University of Medical Sciences. According to the goals of the study and using the expert opinion of the laboratory and urologist, 15 variables were selected. The database included both urine analysis and culture tests. The results indicated 99.7% accuracy of the diagnosis for the training data, (75% of total data), and 99.8% accuracy of the diagnosis for testing data (25% of total data). Based on the Bayesian network model, the important covariates influencing the Urinary infection have been proved to be the increase of bacteria and the decrease of white blood cells in different age groups. The results of this study can be used in the context of machine learning and intelligent systems for rapid diagnosis of the disease and the treatment of people suspected of suffering from it.
 

---

In recent years, the use of machine learning methods in various fields of agriculture is increasing, and these methods provide us with very good information for predicting and checking different levels of performance in plants. In the current research, according to the results of the preliminary experiment carried out previously with specific levels of salinity stress and fertilization (salinity stress levels of zero, 75 and 150 mM sodium chloride and fertilization levels of zero and 3 grams per liter of silica) which were previously carried out and using the nonlinear regression model (NLR) and Python programming language, the morphological and physiological traits of the fenugreek medicinal plant at the newly defined levels of salinity stress and silica fertilization (salinity of up to 300 mM level and silica fertilization in two levels of 1 and 2 grams per liter) were predicted without conducting practical tests and based on the levels of salinity and initial fertilization. The non-linear regression model is a widely used algorithm in data analysis where the relationship between variables is non-linear and can create meaningful relationships between variables using non-linear functions. The results showed that the positive effect of silica on the amount of chlorophyll fluorescence (Fv/Fm) can be seen from zero to 180 mM salinity level and the amount of greenness index (SPAD) from zero to 100 mM salinity level. It seems that according to the results of the present research, it is possible to use machine learning to investigate and analyze the morphological and physiological characteristics of the fenugreek medicinal plant at other defined levels of salinity stress and other defined silica fertilization with no need conduct a practical experiment.