ملف المستخدم
صورة الملف الشخصي

نور موفق جبر

إرسال رسالة

التخصص: هندسة حاسوب

الجامعة: جامعة الموصل

النقاط:

5
معامل الإنتاج البحثي

الخبرات العلمية

الأبحاث المنشورة

A CUSTOMIZED IOMT- CLOUD BASED HEALTHCARE SYSTEM FOR ANALYZING OF BRAIN SIGNALS VIA SUPERVISED MINING ALGORITHMS

المجلة: Journal of Engineering Science and Technology

سنة النشر: 20220

تاريخ النشر: 2022-02-28

The study of human-computer interaction has been transformed by Signal Analysis of the Brain (SAoB). The ability to analyze human brain activity opens new opportunities for SAoB study. A medical imaging tool known as ElectroEncephalography (EEG) is the most effective way for doctors to diagnose patients with brain disorders by examining the characteristics of their brain scans. The need for a cloud-based Internet of Medical Things (IoMT)-based healthcare system is critical case in order to make better decisions in SAoB. EEG data are used in this study to make predictions about EEG signal classification using prior knowledge. We used supervised mining methods to distinguish between two types of EEG (Normal and Abnormal). Reduction of dimensionality and extraction of a feature are implemented on the EEG dataset to obtain high-level features which assisted to increase the efficiency and accuracy of the supervised mining algorithms. To quickly identify signal analysis cases from EEG data, this work proposes eight supervised mining algorithms, namely Artificial Neural Network (ANN), K-Nearest Neighbor (K-NN), Decision Table (DT), Support Vector Machine (SVM), One Rule (OneR), Decision Stump (DS), Zero Rule (ZeroR), and Random Forest (RF). After choosing the important features, these eight algorithms were sorely tested in an experiment. On an EEG dataset. Seven of the eight algorithms tested yielded results with greater than 90% accuracy and the ANN algorithm is the best because it achieved 97% but its take longer time in implementing (42 second). Based on these findings, we believe that these seven algorithms provide excellent and precise EEG signal identification and processing. Additionally, this research proposes a personalized health care system based on IoMT-cloud based SAoB and studies EEG brain classification.

Enabling image optimisation and artificial intelligence technologies for better Internet of Things framework to predict COVID

المجلة: IET Networks

سنة النشر: 2022

تاريخ النشر: 2022-08-11

Abstract Sensor technology advancements have provided a viable solution to fight COVID and to develop healthcare systems based on Internet of Things (IoTs). In this study, image processing and Artificial Intelligence (AI) are used to improve the IoT framework. Computed Tomography (CT) image‐based forecasting of COVID disease is among the important activities in medicine for measuring the severity of variability in the human body. In COVID CT images, the optimal gamma correction value was optimised using the Whale Optimisation Algorithm (WOA). During the search for the optimal solution, WOA was found to be a highly efficient algorithm, which has the characteristics of high precision and fast convergence. Whale Optimisation Algorithm is used to find best gamma correction value to present detailed information about a lung CT image, Also, in this study, analysis of important AI techniques has been done, such as Support Vector Machine (SVM) and Deep‐Learning (Deep‐Learning (DL)) for COVID disease forecasting in terms of amount of data training and computational power. Many experiments have been implemented to investigate the optimisation: SVM and DL with WOA and without WOA are compared by using confusion matrix parameters. From the results, we find that the DL model outperforms the SVM with WOA and without WOA.