Health Information Technology (HIT) provides many opportunities for transforming and improving health care systems. HIT enhances the quality of health care delivery, reduces medical errors, increases patient safety, facilitates care coordination, monitors the updated data over time, improves clinical outcomes, and strengthens the interaction between patients and health care providers. Living in modern large cities has a significant negative impact on people's health, for instance, the increased risk of chronic diseases such as diabetes. According to the rising morbidity in the last decade, the number of patients with diabetes worldwide will exceed 642 million in 2040, meaning that one in every ten adults will be affected. All the previous research on diabetes mellitus indicates that early diagnoses can reduce death rates and overcome many problems. In this regard, machine learning (ML) techniques show promising results in using medical data to predict diabetes at an early stage to save people's lives. In this paper, we propose an intelligent health care system based on ML methods as a real-time monitoring system to detect diabetes mellitus and examine other health issues such as food and drug allergies of patients. The proposed system uses five machine learning methods: K-Nearest Neighbors, Naïve Bayes, Logistic Regression, Random Forest, and Support Vector Machine (SVM). The system selects the best classification method with high accuracy to optimize the diagnosis of patients with diabetes. The experimental results show that in the proposed system, the SVM classifier has the highest accuracy of 83%.
The electrical load is affected by the weather conditions in many countries as well as in Iraq. The weather-sensitive electrical load is, usually, divided into two components, a weather-sensitive component, and a weather-insensitive component. The research provides a method for separating the weather-sensitive electrical load into five components. and aims to prove the efficiency of the five-component load Forecasting model. The artificial neural network was used to predict the weather-sensitive electrical load using the MATLAB R17a software. Weather data and loads were used for one year for Mosul City. The performance of the artificial neural network was evaluated using the mean squared error and the mean absolute percentage error. The results indicate the accuracy of the prediction model used, MAPE equal to 0.0402.
Hybrid electric vehicles have received considerable attention because of their ability to improve fuel consumption compared to conventional vehicles. In this paper, a series-parallel hybrid electric vehicle is used because they combine the advantages of the other two configurations. In this paper, the control unit for a series-parallel hybrid electric vehicle is implemented using a Nonlinear Model Predictive Control (NMPC) strategy. The NMPC strategy needs to create a vehicle energy management optimization problem, which consists of the cost function and its constraints. The cost function describes the required control objectives, which are to improve fuel consumption and obtain a good dynamic response to the required speed while maintaining a stable value of the state of charge (SOC) for batteries. While the cost function is subject to the physical constraints and the mathematical prediction model that evaluate vehicle's behavior based on the current vehicle measurements. The optimization problem is solved at each sampling step using the (SQP) algorithm to obtain the optimum operating points of the vehicle's energy converters, which are represented by the torque of the vehicle components.