In this paper, we propose a improved Markov Random Field (MRF) segmentation model, which integrates region, priori knowledge and boundary information of the image, for segmenting left ventricle (LV) boundary from cardiac MR image. The proposed model incorporates geometry shape boundary information, and improves the objective function of traditional MRF model. Furthermore, Chaotic Simulated Annealing (CSA) algorithm is introduced to solve the MRF model for the first time. Since CSA algorithm introduces chaos ergodicity mechanism, it can take advantage of Chaos Algorithm (COA) and Simulated Annealing (SA) algorithm in the search process. CSA algorithm can not only avoid the limitations of mathematical optimization methods, but also greatly enhance the speed of global optimization. Experiments on clinical cardiac MR images show that the improved MRF model has high performance on segmenting LV boundary. The evaluation results illustrate that this model is robust, accurate and efficient, especially for the weak boundary and concave region .
The fuel booster pump is one of the most vulnerable physical assets in an operating engine due to the harsh environmental and operational conditions. However, because of its high structural complexity and extreme operational conditions, the reliability design of the fuel booster pump becomes especially difficult, particularly by means of experiments. Thus, to overcome such a problem, advanced simulation techniques have become adequate solutions for the reliability assessment and analysis of a fuel booster pump at the design stage. In this paper, by considering the effects of the uncertainties of multiple design parameters, fatigue life distributions of the four key components (which are the sealing bolt, spline shaft, graphite ring, and inducer, respectively) in a fuel booster pump were first predicted by PoF-based reliability simulations. Then, through further sensitivity analysis on each key component, the design parameters most sensitive to the component mean fatigue life were detected from a total of 25 candidate parameters. These parameters include the “nominal diameter” and “preload” for the sealing bolt, “major and minor diameters of the small spline” for the spline shaft, “inside diameter” for the graphite ring, and “fuel pressure on the blade front surface” for the inducer, respectively. These sensitivity results were found to be in good agreement with the results from the qualitative cause analysis on each key component.
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.