Alzheimer’s Disease Detection Using Ensemble of Classifiers

Alzheimer’s disease is a major intellectual deficit that makes it impossible for a person to carry out daily tasks. Finding the people with Alzheimer’s and mild cognitive impairment is a difficult task. In order to arrange healthy, mildly cognitively impaired patients at the model stage itself using multimodal features. This paper will consider the presentation of cutting-edge Dynamic Ensemble Selection of Classifier computations. The review’s data came from the Alzheimer’s Disease Neuroimaging Initiative Dataset. For the purpose of expectation, the patients’ clinical imaging, cerebrospinal fluid, cognitive test, and socioeconomic data are taken into consideration at the routine appointments. The demonstration of the most recent dynamic En-semble of Classifier Selection calculations is reviewed with the aid of these highlights in terms of Accuracy, Specificity and Sensitivity. Calculations for the Classifier Selection use the pool of machine learning classifiers that are used the most frequently as a contribution. Additionally, the display of the machine learning classifiers without using the computations for the Selection of Classifiers is also examined. Classifier selection calculations performed on the majority of the classifier pool to identify individuals with moderate cognitive impairment, Alzheimer’s disease, and hearing loss have expanded presentation metrics including balanced classification accuracy, sensitivity, and specificity.