User talk:Abdulkareemmradhiit59
Heart disease classification using optimized Machine learning algorithms
[edit]Early detection of heart disease is exceptionally critical to saving the lives of human beings. Heart attack is one of the primary causes of high death rates throughout the world, due to the lack of human and logistical resources in addition to the high costs of diagnosing heart diseases, which play a key role in the healthcare sector, this model is suggested. In the field of cardiology, patient data plays an essential role in the healthcare system. This paper presents a proposed model that aims to identify the optimal machine learning algorithm that can predict heart attacks with high accuracy in the early stages. The concepts of machine learning are used for training and testing the model based on the patient's data for effective decision-making. The proposed model consists of three stages: the first stage is patient data collection and processing, and the second stage is data training and testing using machine learning algorithms (Random Forest, Support Vector Machines, K-Nearest Neighbor, and Decision Tree) that show The best classification (94.958 percent) is with the Random Forest algorithm and the third stage is optimizing the classification results using one of the hyperparameters optimization techniques, random search, that shows The best accuracy was (95.4 percent) obtained also with RF. Abdulkareemmradhiit59 (talk) 20:38, 24 September 2024 (UTC)
Optimization of energy consumption and thermal comfort for intelligent building management system using genetic algorithm
[edit]Am Radhi and et al. Design, simulate, and evaluate the performance of an optimized model for the heating, ventilation, and air conditioning (HVAC) systems using an intelligent control algorithm. Fanger’s comfort method and genetic algorithms were used to obtain the optimal and initial values. The heat transmission coefficient between internal and external environments was determined depending on several inputs and factors acquired via supervisory control and data acquisition (SCADA) system sensors. The main feature of the real-time model is the prediction of the internal building environment, in order to control the HVAC system for the indoor environment and to utilize the optimum power consumed depending on the optimized air temperature value. The predicted air temperature value and predictive mean vote (PMV) value were applied using an intelligent algorithm to obtain an optimal comfort level of the air temperature. The optimized air temperature value can be used in an HVAC system controller to ensure that the temperature indoors can reach a specific value after a known period of time. The use of genetic algorithms (GE) ensures that the used power is well below its peak value and maintains the comfort of the user’s environment. Abdulkareemmradhiit59 (talk) 20:54, 24 September 2024 (UTC)
Machine Learning Prediction of Brain Stroke at an Early Stage
[edit]AM Radhi and et. al. Present that the healthcare sector has traditionally been an early adopter of technological progress, gaining significant advantages, particularly in machine learning applications such as disease prediction. One of the most important diseases is stroke. Early detection of a brain stroke is exceptionally critical to saving human lives. A brain stroke is a condition that happens when the blood flow to the brain is disturbed or reduced, leading brain cells to die and resulting in impairment or death. Furthermore, the World Health Organization (WHO) classifies brain stroke as the world's second-deadliest disease. Brain stroke is still an essential factor in the healthcare sector. Controlling the risk of a brain stroke is important for the survival of patients. In this context, machine learning is used in various health-related fields, especially "brain stroke." To that end, an automated model for recognizing and providing helpful information for brain stroke prediction was created. It can predict brain strokes with high accuracy in the early stages. The proposed model aims to examine the patient for effective decision-making. This research study employed a freely accessible dataset and a mix of machine learning methods such as random forest, logistic regression, and decision trees. Furthermore, the Synthetic Minority Over Sampling Technique (SMOTE) was implemented to handle unbalanced data. The result shows a high accuracy of 99% in predicting a brain stroke. Abdulkareemmradhiit59 (talk) 21:00, 24 September 2024 (UTC)