Improving Efficiency in Prediction of Dementia Using Deep Learning Technique

Deep learning algorithms are thought to be effective tools for diagnosing cerebrovascular disorders.On the one hand, memory loss, impaired reasoning, behavioral changes, and impaired ability to do daily chores are all hallmarks of dementia.Our goal in developing this deep learning model was to be able to predict when Alzheimer's disease will manifest in its early stages.The mono objective and multi objective classification and feature selection processes used evolutionary algorithms to aid in the natural selection process.Common algorithms that are used in this proposed work is the convolutional neural network (CNN).To counteract the variables that cause dementia, the proposed method combines information from written descriptions of the condition with pictures of both healthy and diseased brains.Neuroimaging research have shown that deep learning algorithm CNN are effective at differentiating between dementia and a healthy ageing brain with 98% accuracy.A sort of artificial intelligence that mimics the brain is known as neural networks.They can spot patterns, learn new ones, and forecast the future using data.