Early diagnosis of COVID-19, the new coronavirus disease, is considered important for the treatment and control of this disease. The diagnosis of COVID-19 is based on two basic approaches of laboratory and chest radiography, and there has been a significant increase in studies performed in recent months by using chest computed tomography (CT) scans and artificial intelligence techniques. Classification of patient CT scans results in a serious loss of radiology professionals' valuable time. Considering the rapid increase in COVID-19 infections, in order to automate the analysis of CT scans and minimize this loss of time, in this paper a new method is proposed using BO (BO)-based MobilNetv2, ResNet-50 models, SVM and kNN machine learning algorithms. In this method, an accuracy of 99.37% was achieved with an average precision of 99.38%, 99.36% recall and 99.37% F-score on datasets containing COVID and non-COVID classes. When we examine the performance results of the proposed method, it is predicted that it can be used as a decision support mechanism with high classification success for the diagnosis of COVID-19 with CT scans.
Son yıllarda Bayesci yaklaşımların kullanımındaki esneklik Yapısal Eşitlik Modelleri (YEM)'de Monte Carlo Markov Zincir( MCMC) yöntemlerinin daha sık kullanılmasına neden olmuştur. MCMC yöntemlerinde çekilen örneklemler arasındaki otokorelasyon, sonsal dağılıma yakınsayıp yakınsamadığının belirlenmesi ve zincirin sonlandırılması önemli konular arasındadır. Bu çalışma kapsamında MCMC yöntemlerinden olan Gibbs Örneklemesi ile elde edilen bir Bayesci Yapısal Eşitlik Model sonuçlarına ait parametre tahmin değerleri kullanılmıştır. Bu parametre tahminleri için üretilen değerler başlangıç değerlerinin etkisinden kurtulabilmesi için yakma periyodu, bağımsızlığı içinde thin uygulamalarının iterasyonlar ve otokorelasyon üzerinde etkileri incelenmiştir. Çalışma sonunda yakma periyodu ve thin uygulamalarının etkili olduğu gösterilmiştir.
This study deals with radioactivity and heavy metal distribution and statistical analyses in the Bendimahi River Basin, which is within the Lake Van Closed Basin, Turkey. In order to identify the relationships between measured variables and to categorize soils and sediments collected at 15 sites on Bendimahi River, factor and cluster analysis have been applied. The data set is constituted of 9 radiological and physico-chemical variables, including gross alpha and gross beta activities and Pb, Zn, Cu, Cr, Cd, Co and Mn concentrations. Factor and cluster analysis were used to describe the relationship and similarity among data sets (variables) for the Bendimahi River. The convergence diagnostics such as trace plot and kernel density were applied to determine the convergence criteria to the data sets.
This research aimed to provide a greater insight into the relationship between feelings of satisfaction with the landscaping and the sense of place, particularly emphasizing on the planning and landscape design of post-disaster housing environments for the enhancement of the victims' and other residents' well-being on the case of Edremit TOKİ (Van) post-earthquake housing area which was built after the devastating earthquakes in 2011. Methodology The residents' satisfaction with various parts of landscaping in the housing area; their place identity, place attachment and place dependence characteristics as part of their sense of place; and the interrelations between these were examined through a questionnaire survey. The data collected from 235 locals were subjected to two types of factor analysis including both explanatory and structural equation modelling (SEM) in order to create a model. Conclusions According to the SEM results, the proposed model based on the hypothesis, which states that "there are positive relationship between the sense of place and satisfaction with landscaping," was not supported. In contrast, a negative relationship was found between the satisfaction with landscaping and sense of place. This suggests that when the respondents' sense of place has increased, it is likely that there might be lower satisfaction with the landscaping they have. Originality This study is original in two aspects; first being focused on the diverse dimensions of landscaping different from the studies mostly dealing with vegetation and visual quality; second being investigated the relationship amongst the satisfaction with landscaping, sense of place and the sub-components of these concepts in a post-earthquake residential area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.