Alzheimer's disease is a type of dementia that is well known and responsible for affecting the lives of the elderly. It is defined by the gradual loss of structure and function of neurons in the brain leading to m...
详细信息
Alzheimer's disease is a type of dementia that is well known and responsible for affecting the lives of the elderly. It is defined by the gradual loss of structure and function of neurons in the brain leading to memory, thinking and other activities. This is the most crucial step since a patient's quality of life and the disease's progression may both be improved with an early diagnosis. Nevertheless, existing diagnostic tests rarely diagnose the disease in its preliminary stage, and this has a significant impact on the course of the illness. The more conventional assessment techniques that involve neuroimaging and cognitive ability standardized tests are usually unable to pick up early stage alterations. To address these limitations, we have developed a new Hybrid AI Model, which combines both the conventional machine learning techniques, namely SVM, Naive Bayes, Cat boost, and XGBoost and Stacked DL model. This combination uses the advantages of the proposed models to enhance the diagnostic sensitivity based on the early AD biomarkers. The MRI data was obtained from Kaggle and the proposed Stacked DL Model achieved an accuracy93%, an f1-score94, and a specificity99%. The Voting classifier (ML models) outperformed the other models with an accuracy94.22%, an f1-score94%, and a specificity99%. proving the proposed model superior to the prior state of the art. The implications for clinical care contained in this model are vast. SPECT imaging with PIB is a very accurate means of identifying very early signs of AD that needs to be treated after prevent further deterioration, lessening the patient's discomfort and saving money for the healthcare industry in the long run. Because the failures of this approach have been widely identified in early stage detection, it can, therefore, be greatly beneficial to lower the social and economic implications of AD. The Hybrid AI Model therefore offers a potential solution to the problem of developing better, more efficient approache
Spam emails have become an increasing difficulty for the entire web-users. These unsolicited messages waste the resources of network unnecessarily. Customarily, machine learning techniques are adopted for filtering em...
详细信息
Spam emails have become an increasing difficulty for the entire web-users. These unsolicited messages waste the resources of network unnecessarily. Customarily, machine learning techniques are adopted for filtering email spams. This article examines the capabilities of the extreme learning machine (ELM) and supportvectormachine (SVM) for the classification of spam emails with the class level (d). The ELM method is an efficient model based on single layer feed-forward neural network, which can choose weights from hidden layers, randomly. supportvectormachine is a strong statistical learning theory used frequently for classification. The performance of ELM has been compared with SVM. The comparative study examines accuracy, precision, recall, false positive and true positive. Moreover, a sensitivity analysis has been performed by ELM and SVM for spam email classification.
In this paper, experimental results from the face contour classification tests are shown. The presented approach is dedicated to a face recognition algorithm based on the Active Shape Model method. The results were ob...
详细信息
ISBN:
(纸本)9789898111692
In this paper, experimental results from the face contour classification tests are shown. The presented approach is dedicated to a face recognition algorithm based on the Active Shape Model method. The results were obtained from experiments carried out on the set of 3300 images taken from 100 persons. Automatically fitted contours (as 194 ordered face contour points vector, where the contour consisted of eight components) were classified by Nearest Neighbourhood Classifier and supportvectormachines classifier, after feature space decomposition, carried out by the Linear Discriminant Analysis method. Feature subspace size reduction and classification sensitivity analysis for boundary case testing set are presented.
暂无评论