Software and Systems Modeling - An ideal test is supposed to show not only the presence of bugs but also their absence. Based on the Fundamental Test Theory of Goodenough and Gerhart (IEEE Trans... 相似文献
One of the most important processes in the diagnosis of breast cancer, which is the leading mortality rate in women, is the detection of the mitosis stage at the cellular level. In literature, many studies have been proposed on the computer-aided diagnosis (CAD) system for detecting mitotic cells in breast cancer histopathological images. In this study, comparative evaluation of conventional and deep learning based feature extraction methods for automatic detection of mitosis in histopathological images are focused. While various handcrafted features are extracted with textural/spatial, statistical and shape-based methods in conventional approach, the convolutional neural network structure proposed on the deep learning approach aims to create an architecture that extracts the features of small cellular structures such as mitotic cells. Mitosis detection/counting is an important process that helps us assess how aggressive or malignant the cancer’s spread is. In the proposed study, approximately 180,000 non-mitotic and 748 mitotic cells are extracted for the evaluations. It is obvious that the classification stage cannot be performed properly due to the imbalanced numbers of mitotic and non-mitotic cells extracted from histopathological images. Hence, the random under-sampling boosting (RUSBoost) method is exploited to overcome this problem. The proposed framework is tested on mitosis detection in breast cancer histopathological images dataset provided from the International Conference on Pattern Recognition (ICPR) 2014 contest. In the results obtained with the deep learning approach, 79.42% recall, 96.78% precision and 86.97% F-measure values are achieved more successfully than handcrafted methods. A client/server-based framework has also been developed as a secondary decision support system for use by pathologists in hospitals. Thus, it is aimed that pathologists will be able to detect mitotic cells in various histopathological images more easily through necessary interfaces.
The effects of thermal cycles on the impact fatigue properties of unidirectional carbon fibre reinforced polyetherimide (PEI)
matrix composites were investigated. During the thermal cycles, samples were immersed into boiling water (100 °C) and subsequently
to ice water (0 °C), 50, 200 and 500 times. The changes in viscoelastic properties of the composites were investigated by
means of dynamic mechanical thermal analyzer (DMTA). At the second step, thermal cycled composites were subjected to repeated
impact loadings, with different impact energies. Instrumented impact test results were presented as a function of force, energy,
deformation during the experiments. The scanning electron microscope (SEM) studies were done in order to understand the morphology
of fractured samples after impact fatigue loading. The number of thermal cycles and applied impact energy of the hammer are
found to have a great importance on the fracture morphology of repeatedly impacted material, as expected. 相似文献
Particle–particle and bubble–particle-interactions in flotation systems are governed by physico-chemical and hydrodynamic conditions of pulp. Shape factor and roughness of particles significantly affect these interactions, and hence both grade and recovery in flotation. Although many studies have been conducted to understand morphological features of particles, the underlying mechanism of their effect on flotation recovery have not been clearly shown. Towards this aim, acombination of grinding and abrasion processes was applied to mimic grinding in terms of shape and roughness in order to get their corresponding flotation recoveries at different collector levels. For this purpose, glass beads representing smooth spherical particles of –150+106 µm in size along with ground and abraded glass particles of different shapes and roughness were used to evaluate the flotation efficiency of these particles in the absence and presence of amine collector. The dependence of the shape and roughness on the flotation recoveries at different hydrophobicities as monitored by different amine collector concentrations is demonstrated. Finally, the results are discussed to see if morphology ofparticles can be tuned through grinding to achieve maximum flotation efficiencies. 相似文献
Due to its high hydrogen density and extensive experience base, ammonia (NH3) has been gaining special attention as a potential green energy carrier. This study focuses on premixed ammonia–hydrogen–air flames under standard temperature and pressure conditions using an inert silicon-carbide (SiC) porous block as a practical and effective medium for flame stabilization. Combustion experiments conducted using a lab scale burner resulted in stable combustion and high combustion efficiencies at very high ammonia concentration levels over a wide range of equivalence ratios. Noticeable power output densities have also been achieved. Preliminary results of NOx emission measurements indicate NOx concentrations as low as 35 ppm under rich conditions. The remarkable capability of this specific burner to operate efficiently and cleanly at high ammonia concentration levels, which can easily be achieved by partial cracking of NH3, is believed to be a key accomplishment in the development of ammonia fired power generation systems. 相似文献