Prognosis of Relocation Disease in Animals using Aggregation Method with Optimization Techniques

In the most cutting-edge setting, health data is processed by machine learning algorithms, which are used to forecast illnesses. Dementia, especially Alzheimer's disease, is a leading cause of diminished quality of life in the elderly. Early diagnosis by medical professionals increases the likelihood of reducing the aggressiveness of the disease. In this study, we develop a new uncertainty-based clustering model to handle the centroid selection ambiguity and the issue of noisy instances and outliers that lower the efficiency of prediction models. This work employs an uncertainty-based optimization technique to handle the unknown pattern of Alzheimer Disease (AD) patients, since it is relatively tough to handle unknown patterns with unsupervised learning algorithms. Converting the instances in the AD dataset to the membership value of the dependent variable allows for an accurate determination of whether they belong as AD patterns or non-AD patterns. This proposed study takes a migration-based optimization method to animal migration, where the best instances are chosen as centroids and fresh instances are evaluated for clustering; this minimizes outliers throughout the clustering process by using comparable patterns. To make sure, we check the fitness values of each instance; the ones with the highest values are called centroids. To control the unknowns when dealing with outliers, the fuzzy Euclidean distance is employed. By comparing it to current state-of-the-art clustering methods, the OASIS dataset simulation results show that the proposed uncertainty-based Animal Migration optimization method (UAMO) performs better.