An Extreme Learning Machine based Approach to Detect the Alzheimer's Disease

Alzheimer's Disease (AD) is a gradually escalating brain disorder that affects the brain cells and neurotransmitters. It affects certain brain activities such as memory and behavior and causes dementia in the elderly at an end stage. There is currently no cure for the disease but the availability of treatment at an initial stage can help in delaying the progression of the disease. There are major issues in diagnosing the disease by the use of conventional algorithms. One of them is the availability of a huge number of plausible feature representations. Conventional machine learning algorithms are known to have low training speed. In order to overcome this, we have applied Extreme Learning Machine algorithms on the Open Access Series of Imaging Studies (OASIS) dataset. We have also discussed the preprocessing filter, segmentation method applied along with the features extracted on these MRI scans.