Dergiler / Bitlis Eren Üniversitesi Fen Bilimleri Dergisi / 2019 / Cilt: 8 - Sayı: 4
Comparison of heat gain values obtained for building structures with real and constant properties
- Sayfa
- 1518–1532
- DOI
- —
Özet
The magnitude of energy consumption due to heating and cooling of buildings has led to the demand for increasing the thermal performance of building structures. Many investigations are presented in literature arguing to find the effect of each thermophysical property on the thermal characteristics of building components, while the properties have been assumed as independent of each other. In this context, this paper focuses on the effect of each property on heat gain value utilizing relationships between the measurement values of thermophysical properties of building structures. In previous study, 102 new wall samples were produced, their thermophysical properties were tested and expressions among these properties are obtained. In this study, the heat gain values through the structures are computed using solution of transient heat transfer problem by using both the obtained expressions between the thermophysical properties and assumptions proposed from the literature. Results obtained for varying and constant thermophysical properties have been compared with those values presented in literature. The results show that the assumptions are not realistic in a significant number of cases. Moreover, if one of the thermophysical properties of a material is known, heat gain values can be calculated easily for the selected wall or roof types.
Abstract
Otitis media (OM) is a medical concept representing a range of inflammatory middle ear disorders. OM is one of the most common diseases worldwide, especially in childhood. In clinical practice, the diagnosis of OM is carried out by examining the images of the middle ear obtained via the otoscope device by specialists. The subjective examination leads to arise the variabilities among observers. At the same time, the use of computer-aided systems in this area is not common enough. Failure to diagnose OM disorders in a timely manner leads to the progression of the diseases, the emergence of hearing, speech, and cognitive disorders. To overcome all these disadvantages, an integrated diagnostic system based on the pretrained deep convolutional neural networks is proposed for the diagnosis of OM in this study. Experimental studies were carried out on 898 otoscope images, representing five different classes, collected from volunteer patients admitted to Özel Van Akdamar Hospital. As a result, the proposed model achieved 82.16% classification success. With the end-to-end learning and high sensitivity provided by the proposed model based on convolutional neural networks, OM diagnosis can be realized objectively and physicians' decision-making process can be supported using this system. The proposed method has produced promising results in these respects.