.

ISSN 2063-5346
For urgent queries please contact : +918130348310

LEVERAGING AN ADAPTIVE RANDOM FOREST ALGORITHM AND ENHANCED FEATURE EXTRACTION BATTERY (FEB) TECHNIQUE TO INCREASE THE STATISTICAL PRECISION OF SCHIZOPHRENIA PREDICTIVE ANALYSIS

Main Article Content

S.Harshavardhan naidu [1] , T.R. Dinesh kumar [2] , S.Siva saravanababu [3] , K. Stella [4] , J.R. Ghajendhiran [5] , H. Karthik kishore [6] , M. Ganesa moorthi
» doi: 10.31838/ecb/2023.12.s1-B.321

Abstract

The word "dementia" is applied to refer usually to a decrease in mental abilities, that may encompass diminished memory, challenges regarding speaking and listening, poor judgment, as well as shifts in character and conduct. This is an ongoing, incurable illness which primarily impacts elderly individuals. Disorders like cognitive impairment and memory loss condition have its potential to injure and exacerbate the brain. Dementia has no known cure, and there is no means to stop it. The signs of dementia have been found to show up to ten years prior to the illness actually reveals themselves. In order to take advantage of signs of dementia in the initial phases of dementia estimation, ML (machine learning) experts developed a variety of techniques. The research of algorithms as well as statistical models that enable systems to carry out particular tasks with no specific instructions is known as machine learning. The issue of risk assessment as well as early identification of AD has been determined, and our system's solution makes use of supervised learning algorithms for foreseeing dementia sooner. Additionally, it produces a summary that details the precision of the method that we utilized. In contrast to earlier studies that depended on warning signs for AD and utilized statistical tests for comparison or progressive screening using regression techniques, prompt identification of dementia is essential to provide avoidance or just delaying the progression of the disorder

Article Details