Intelligent Diagnosis of Alzheimer's Disease Based on Internet of Things Monitoring System and Deep Learning Classification Method

Abstract Alzheimer's disease is a syndrome with a decreased ability to a different classification. Alzheimer's disease (AD), memory, and learning affect the classification domain as cognitive-motor or executive function, which is the most common dementia. Death and expensive detection is high treatment and between the result of the count rate of patient care. Early detection of AD is considered very important to improve patients' quality of life and their families. The purpose of this article is to reduce the cost of accelerating related to the diagnosis. The o allow complete access is possible to introduce a new non-invasive early diagnosis method. The new AD screening tests' interaction is based on introducing new technology in the business system, and an immersive and advanced human-computer has been introduced to the Internet system. Four experiments, based on the large-scale screening, damage to the mechanism of classification domain, shows that can be used in the network design of the thing system. In the proposed test, mainly common goal, focusing on evaluating the recent related memory loss in the conversation and events, human and between the virtual world and the real machine; abnormal the ability to recognize, express, and understand diagnostic differences in language problems terms. IOT (IOT) has integrated hundreds of millions of smart devices that can communicate with a minimum of human intervention. It should be strengthened to secure methods to ensure the ecosystem of useful IOT. Machine Learning (ML) is proceeding significantly over the past few years; in some critical applications, machine intelligence is actually of the machine to the laboratory curiosity conversion. The ability to monitor the IOT devices and intelligence will provide an essential solution for new or zero-day attacks. Components and apparatus of the ML Hano IOT are, based on whether learning the IOT in the environment is an effective way to explore the "normal," "abnormal" behavior data.