Abstract:
Medical imaging has been used extensively in research on AD. However, the acquisition of medical image data is difficult, time intensive, and ineffective because expensive diagnosis tools and radiologist experts. To reduce the above-mentioned challenges, this paper suggests a novel technique for the diagnosis of AD using an intelligent health informatics system designed based on EEG signals captured by 16 antennas put on the patient's head. The EEG signals data is collected with the help of different electrodes (antenna) put on the head of people of different ages. A brain computing interface (BCI) is used for the collection of the EEG data which consists of a helmet of 16 antennas. The microprocessor then transmits the EEG signal data to the computer system. After that feature selection techniques, such as mRMR and reliefF are applied to remove irrelevant, noisy, and redundant features. Further, several machine learning and deep learning algorithms are utilized as learners. Several performance metrics, including accuracy, sensitivity, specificity, f1measure, MCC, and ROC curve, are utilized to examine the performance of all the classifiers used in this study in order to demonstrate the efficiency and effectiveness of the proposed computational framework. After utilizing feature selection techniques, the classification accuracy of Fuzzy-SVM with the relief feature selection methodology. The experimental results prove the efficiency and significance of the proposed computational framework. Alzheimer's disease (AD) is an illness of the human brain, which is considered one of the most hazardous diseases. Medical Physicians utilize physical and neurological exams, blood tests, mental status, neurophysiological testing, and brain imaging.
Page(s):
1-1
DOI:
DOI not available
Published:
Journal: Second International Conference on Computing Technologies, Tools and Applications (ICTAPP-24), June 4-6,2024 (Abstract Book), Volume: 0, Issue: 0, Year: 2024