Alzheimer is defined as the loss of mental functions such as thinking, memory, and reasoning that is severe enough to interfere with a person's daily functioning. The appearance of Alzheimer's Disease symptoms are resulted based on which part of the brain has a variety of infection or damage. Therefore, MRI is the best biomedical instrumentation to detect Alzheimer's Disease. For that reason, this paper proposes a novel method for detecting Alzheimer's Disease in MRI images using thresholding and morphology. In this paper, we analyzed 20 MRI images collected from OASIS brains database to detect the threshold that will allow our program to automatically detect Alzheimer's Disease existence in MRI images. Automatically Image Classification is one of the challenging problems of our recent era. So, we have implemented and tested our proposed technique and the end results have 98% accuracy.
Thresholding is one of the popular and fundamental techniques for conducting image segmentation. Many thresholding techniques have been proposed in the literature. Among them, the minimum cross entropy thresholding has been widely adopted. Most minimum cross entropy thresholding methods use Gaussian distribution as an ideal reference histogram for the images to be thresholded. Clearly, it is doubtful that any natural images would generate a histogram with such a distribution. In this paper, a new minimum cross entropy thresholding method using Gamma distribution is proposed, since it is more general than other distributions. The new entropy thresholding method using Gamma distribution is extended to multi-level thresholding. The experimental results manifest that the proposed method can derive multiple thresholds which are very close to the optimal ones. The convergence of the proposed method is analyzed mathematically and the results validate that the proposed method is efficient and is suited for different real time applications.
Although cloud computing is growing rapidly, a key challenge is to build confidence that the cloud can handle data securely. Data is migrated to the cloud after encryption. However, this data must be decrypted before carrying out any calculations; which can be considered as a security breach. Homomorphic encryption solved this problem by allowing different operations to be conducted on encrypted data and the result will come out encrypted as well. In this paper, we propose the application of Algebraic Homomorphic Encryption Scheme based on Fermat's Little Theorem on cloud computing for better security.
Embedded systems have become very popular in recent years, and that field is rapidly advancing especially in health monitoring technology. Therefore, we present in this paper an application for posture correction, utilizing microcontrollers and ultrasonic sensors. When a bad posture is detected, the user is noti?ed. Our system is designed specifically for computer users to prevent them from leaning too close to their computers' monitors.
Show abstract
Full Text
