Introduction: Diabetes or diabetes mellitus is a metabolic disorder in body when the body does not produce insulin, and produced insulin cannot function normally. The presence of various signs and symptoms of this disease makes it difficult for doctors to diagnose. Data mining allows analysis of patients’ clinical data for medical decision making. The aim of this study was to provide a model for increasing the accuracy of diabetes prediction. Method: In this study, the medical records of 1151 patients with diabetes were studied, with 19 features. Patients’ information were collected from the UCI standard database. Each patient has been followed for at least one year. Genetic Algorithm (GA) and the nearest neighbor algorithm were used to provide diabetes prediction model. Results: It was revealed that the prediction accuracy of the proposed model equals 0. 76. Also, for the methods of Naï ve Bayes, Multi-layer perceptron (MLP) neural network, and support vector machine (SVM), the prediction accuracy was 0. 62, 0. 65, and 0. 75, respectively. Conclusion: In predicting diabetes, the proposed model has the lowest error rate and the highest accuracy compared to the other models. Naï ve Bayes method has the highest error rate and the lowest accuracy.

Introduction: breast cancer is the most prevalent malignancy, and one of the most common types of cancer among women around the world that has showed a growing trend in recent years. There is always a probability of recurrence in patients who suffer from this disease. There are many factors that increase or decrease this probability. Data mining is one of the methods that can be used to predict or diagnose cancers. Recurrence detection of breast cancer is one of the most common applications of data mining. Method: In this retrospective study, data of 699 breast cancer patients with 14 characteristics were collected from patients' records of Jahad Daneshgahi University from 2012 to 2015 and used. From all, 458 patients (66%) did not have recurrence, while in 241 patients (34 %) recurrence was observed. In this study, through combining k nearest neighbor (KNN) and genetic algorithm (GA), a hybrid approach was proposed to predict recurrence of breast cancer. First, KNN was applied to predict recurrence of breast cancer and then, GA was used to reduce unnecessary independent variables to provide a more accurate model of accuracy. Results: The number of independent variables was 14 variables, which was reduced to 6 variables by genetic algorithm to make the prediction model more efficient. We used accuracy as the criterion to evaluate performance of the model, and it was obtained 77. 14% which is higher than the accuracy of alternative methods. Conclusion: In comparison to other alternative methods, the proposed method is more accurate.

In this paper, the Nearest Neighbor Algorithm has been applied to predict cavitation damage on dam spillways. In this research, based on flow velocity and cavitation index, five different damage levels from 'no cavitation damage' to 'major cavitation damage' have been determined.The hydraulic characteristics of flow over the Shahid Abbaspour dam spillway were calculated for different flow rates. Then, the Nearest Neighbor Algorithm has been applied to predict cavitation damage levels and locations on this dam spillway for different flow rates.Comparison of the model results with the observed damages occurred during past floods on this spillway structure, shows that this algorithm predict damage levels and locations appropriately.Finally, the efficiency and precision of the model results have been evaluated by some statistical coefficients. Appropriate values of the correlation coefficient (r=0.896), the Mean Absolute Error (MAE=0.101), the Root Mean Square Error (RMSE=0.108) and Efficiency of model (EF=0.813) confirm that the present model can be suitable and efficient.

Permeability is one of the most important petrophysical properties of hydrocarbon reservoirs. Estimating permeability is a challenge that petroleum engineers face, particularly in carbonate reservoirs, especially karst reservoirs, where data on core samples may be lacking. In this study, empirical relationships, regression analysis, artificial neural networks, and the nearest-neighbor algorithm, were employed to estimate permeability in depth intervals where core data were unavailable. The results obtained from these methods were compared with each other and with core measurements. Electrical facies provide intelligent models with the capability to estimate permeability with more details using conventional petrophysical logs. Furthermore, considering that electrical facies analysis is conducted for all wells in the field, the use of optimized intelligent models allows for the estimation of permeability in all wells, leading to more accurate results. Based on the results, artificial neural networks and the nearest-neighbor algorithm performed better compared to the other methods, with correlation coefficients of 2% and 5% higher, respectively, than the other approaches. To optimize the obtained results, permeability estimation using these two methods was incorporated into the framework of electrical facies modeling. Subsequently, the results of facies analysis were compared with the results of layered modeling. Ultimatly, among the two methods used, the nearest-neighbor algorithm, on average, provides a more suitable permeability estimation for the Fahliyan formation with a correlation coefficient of 66% compared to the artificial neural network method with a correlation coefficient of 57%. The proposed method in this study can be applied in heterogeneous carbonate reservoirs with well-defined heterogeneity in porosity distribution.

Introduction: The timely diagnosis and prediction of diseases are among the main issues in medical sciences. The use of decision-making systems to discover the underlying knowledge in the disease information package and patient records is one of the most effective ways of diagnosing and preventing disease. This study aimed to design a medical decision system that can detect hepatitis. Materials & Methods: This study was conducted based on a descriptive-analytic design. Its dataset contains 155 records with 19 features in the University of California-Irvine machine learning database. This study utilized the Binary Artificial Algae Algorithm (BAAA) for Feature Selection (FS). Moreover, K-Nearest Neighbor (KNN) was used to classify hepatitis into two healthy and unhealthy classes. In total, 80% of the data was employed for training, and the remaining (20%) was used for testing. Furthermore, Precision, Recall, F-measure, and Accuracy were utilized to evaluate the model. Findings: According to the results, the accuracy of the proposed model was estimated at 96. 45%. After selecting the features with the BAAA, the percentage of the accuracy reached 98. 36% in the best situation. In the proposed model with 300 repetitions, the Precision, Recall, F-Measure, and error rate were 96. 23%, 96. 74%, 96. 48%, and 3. 55%, respectively. Discussion & Conclusions: Hepatitis is one of the most common diseases among females and males. A timely diagnosis of this disease not only reduces the costs but also increases the chance of successful treatment. In this study, the disease was diagnosed using the hybrid method, and a high accuracy level was obtained in disease diagnosis by FS.

Introduction: Diabetes is a disease, which is caused by the cessation of insulin production or the dysfunction of the body. Early detection of diabetic foot ulcers thermal images of the sole of the foot is one of the new methods of diagnosing diabetic foot ulcers. Material and Method: In this paper, by optimizing the nearest neighbor algorithm, early detection of diabetic foot ulcers is performed by comparing the thermal similarity of the left and right soles of the feet. And the condition of the possibility of foot ulcer is diagnosed. In the proposed solution, by removing additional areas and creating a temperature image of the soles of the feet, using image matching techniques and then extracting statistical features such as standard distribution, percentage of dissimilar pixels and average temperature of the soles of the feet, early diagnosis of the wound condition is attempted. Results: To evaluate the proposed method, 74 images of gray surfaces were used, in which the image of the left and right soles of the feet is specified in the image, and along with the images, there is a file in which the class of each image is specified. The information file also contains the minimum and maximum temperatures in the image to create a thermal image. Therefore, the above problem is a 3-class classification problem in which 75% of the images are used for training and 25% for testing. We have used thermal images by crossvalidation method, which we have achieved with a total accuracy of 85. 14%. Conclusion: Many researches have been done in recent years, most of which have been qualitatively examining the quality of thermal images. In this research, a method based on the use of optimization algorithm using MATLAB software and computer aided diagnostics has been performed. Based on the designed objective functions and the constraints considered in the diagnostic design, we were able to take a step, towards early diagnosis of the ulcer. As sometimes a diabetic patient as possible,Inflammation and change in tissue temperature and cannot diagnose this change in temperature, can be used the proposed methods to eliminate this lack of diagnosis In this study, it has been shown that among the images that the algorithm has been able to run on, the symptoms of inflammation and subcutaneous heat and rising tissue temperature have been obtained correctly and accurately to prevent and follow the early diagnosis of such ulcers.

Introduction: Diabetes is a disease, which is caused by the cessation of insulin production or the dysfunction of the body. Early detection of diabetic foot ulcers thermal images of the sole of the foot is one of the new methods of diagnosing diabetic foot ulcers. Method: In this paper, by optimizing the nearest neighbor algorithm, early detection of diabetic foot ulcers is performed by comparing the thermal similarity of the left and right soles of the feet. And the condition of the possibility of foot ulcer is diagnosed. In the proposed solution, by removing additional areas and creating a temperature image of the soles of the feet, using image matching techniques and then extracting statistical features such as standard distribution, percentage of dissimilar pixels and average temperature of the soles of the feet, early diagnosis of the wound condition is attempted. Results: To evaluate the proposed method, 74 images of gray surfaces were used, in which the image of the left and right soles of the feet is specified in the image, and along with the images, there is a file in which the class of each image is specified. The information file also contains the minimum and maximum temperatures in the image to create a thermal image. Therefore, the above problem is a 3-class classification problem in which 75% of the images are used for training and 25% for testing. We have used thermal images by cross-validation method, which we have achieved with a total accuracy of 85. 14%. Conclusion: Many researches have been done in recent years, most of which have been qualitatively examining the quality of thermal images. In this research, a method based on the use of optimization algorithm using MATLAB software and computer aided diagnostics has been performed. Based on the designed objective functions and the constraints considered in the diagnostic design, we were able to take a step, towards early diagnosis of the ulcer. As sometimes a diabetic patient as possible,Inflammation and change in tissue temperature and cannot diagnose this change in temperature, can be used the proposed methods to eliminate this lack of diagnosis In this study, it has been shown that among the images that the algorithm has been able to run on, the symptoms of inflammation and subcutaneous heat and rising tissue temperature have been obtained correctly and accurately to prevent and follow the early diagnosis of such ulcers.