Diabetes is one of the increasing chronic diseases, affecting millions of people around the earth. Diabetes diagnosis, its prediction, proper cure, and management are compulsory. Machine learning-based prediction techniques for diabetes data analysis can help in the early detection and prediction of the disease and its consequences such as hypo/hyperglycemia. In this paper, we explored the diabetes dataset collected from the medical records of one thousand Iraqi patients. We applied three classifiers, the multilayer perceptron, the KNN and the Random Forest. We involved two experiments: the first experiment used all 12 features of the dataset. The Random Forest outperforms others with 98.8% accuracy. The second experiment used only five attributes of the training process. The results of the second experiment showed improvement in the performance of the KNN and the Multilayer Perceptron. The results of the second experiment showed a slight decrease in the performance of the Random Forest with 97.5 % accuracy.
Background: The influence of glucose metabolism is seen in many infectious diseases, making diabetic patients more vulnerable to sepsis and other serious sequelae of bacterial invasion such as UTI and vaginitis.Patients and method: sixty two patients (women) were suffering from GUTIs consulting Al-Elwya hospital from November- 2009 to March -2010. Two samples were taken from those patients (urine samples and vaginal swabs); these samples were cultured on Blood, Chocolate, and MacConkey's agar for isolation of bacteria.Results: The study group consists of sixty two women suffering from (GUTI), their ages range from 18-55 years. Thirty eight of them were diabetic women and twenty four of them were non- diabetic women. Twenty t
... Show MoreThe purpose of this paper is to model and forecast the white oil during the period (2012-2019) using volatility GARCH-class. After showing that squared returns of white oil have a significant long memory in the volatility, the return series based on fractional GARCH models are estimated and forecasted for the mean and volatility by quasi maximum likelihood QML as a traditional method. While the competition includes machine learning approaches using Support Vector Regression (SVR). Results showed that the best appropriate model among many other models to forecast the volatility, depending on the lowest value of Akaike information criterion and Schwartz information criterion, also the parameters must be significant. In addition, the residuals
... Show MoreThe issue of penalized regression model has received considerable critical attention to variable selection. It plays an essential role in dealing with high dimensional data. Arctangent denoted by the Atan penalty has been used in both estimation and variable selection as an efficient method recently. However, the Atan penalty is very sensitive to outliers in response to variables or heavy-tailed error distribution. While the least absolute deviation is a good method to get robustness in regression estimation. The specific objective of this research is to propose a robust Atan estimator from combining these two ideas at once. Simulation experiments and real data applications show that the proposed LAD-Atan estimator
... Show MoreCompression is the reduction in size of data in order to save space or transmission time. For data transmission, compression can be performed on just the data content or on the entire transmission unit (including header data) depending on a number of factors. In this study, we considered the application of an audio compression method by using text coding where audio compression represented via convert audio file to text file for reducing the time to data transfer by communication channel. Approach: we proposed two coding methods are applied to optimizing the solution by using CFG. Results: we test our application by using 4-bit coding algorithm the results of this method show not satisfy then we proposed a new approach to compress audio fil
... Show MoreThe issue of penalized regression model has received considerable critical attention to variable selection. It plays an essential role in dealing with high dimensional data. Arctangent denoted by the Atan penalty has been used in both estimation and variable selection as an efficient method recently. However, the Atan penalty is very sensitive to outliers in response to variables or heavy-tailed error distribution. While the least absolute deviation is a good method to get robustness in regression estimation. The specific objective of this research is to propose a robust Atan estimator from combining these two ideas at once. Simulation experiments and real data applications show that the p
... Show MoreAt the level of both individuals and companies, Wireless Sensor Networks (WSNs) get a wide range of applications and uses. Sensors are used in a wide range of industries, including agriculture, transportation, health, and many more. Many technologies, such as wireless communication protocols, the Internet of Things, cloud computing, mobile computing, and other emerging technologies, are connected to the usage of sensors. In many circumstances, this contact necessitates the transmission of crucial data, necessitating the need to protect that data from potential threats. However, as the WSN components often have constrained computation and power capabilities, protecting the communication in WSNs comes at a significant performance pena
... Show MoreTransit agencies constantly need information about system operations and passengers to support their regular scheduling and operation planning processes. The lack of these processes and cultural motivations to use public transportations contributes enormously to the reliance on the private cars rather than public transportation, resulting in traffic congestions. The traffic congestions occur mainly during peak hours and the accidents happening as a result of road accidents and construction works. This study investigates the effects of weekday and weekend travel variability on peak hours of the passenger flow distribution on bus lines, which can effectively reflect the degree of traffic congestion. A study of passen
... Show MoreThe performance in the 110-meter hurdles at the sprint hurdles event is determined by several physical and physiological qualities. Nonetheless, relatively little attention has been paid to the predictability of such factors in determining race performance. This study seeks to fill this gap by establishing the most critical physical and physiological characteristics affecting elite hurdlers’ performance and creating a statistical model that predicts race times from the identified measurable characteristics. The study utilized a descriptive research design in-volving six elite male hurdlers, all of whom completed a battery of standardized physical and functional tests to assess their explosive lower-body strength, agility, reaction
... Show MoreCloud computing is the new technological trend for future generations. It represents a new way to use IT resources more efficiently. Cloud computing is one of the most technological models for developing and exploiting infrastructure resources in the world. Under the cloud, the user no longer needs to look for major financing to purchase infrastructure equipment as companies, especially small and medium-sized ones, can get the equipment as a service, rather than buying it as a product. The idea of cloud computing dates back to the sixties of the last century, but this idea did not come into actual application until the beginning of the third millennium, at the hands of technology companies such as Apple, Hp, IBM, which had
... Show MoreComputational Thinking (CT) is very useful in the process of solving everyday problems for undergraduates. In terms of content, computational thinking involves solving problems, studying data patterns, deconstructing problems using algorithms and procedures, doing simulations, computer modeling, and reasoning about abstract things. However, there is a lack of studies dealing with it and its skills that can be developed and utilized in the field of information and technology used in learning and teaching. The descriptive research method was used, and a test research tool was prepared to measure the level of (CT) consisting of (24) items of the type of multiple-choice to measure the level of "CT". The research study group consists of
... Show More