Search

Pelvis fracture detection is vital for diagnosing patients and making treatment decisions for traumatic pelvis injuries. Computer-aided diagnostic approaches have recently become popular for assisting doctors in disease diagnosis, making their conclusions more trustworthy and error-free. Inspecting X-ray images with fractures needs a lot of time from experienced physicians. However, there is a lack of inexperienced radiologists in many hospitals to deal with these images. Therefore, this study presents an accurate computer-aided-diagnosing system based on deep learning for detecting pelvis fractures. In this research, we construct an explainable artificial intelligence (XAI) framework for pelvis fracture classification. We used a dataset containing 876 X-ray images (472 pelvis fractures and 404 normal images) to train the model. The obtained results are 98.5%, 98.5%, 98.5%, and 98.5% for accuracy, sensitivity, specificity, and precision.

Multi-group diffusion depletion 3D code TRITON was used to calculate the power density profile for a 2775 MW PWR core. TRITON was run for different control rod axial positions at full power: (a) all the control rods are outside the core and (b) control rod group D position at 220 cm with length 213 cm in core. Depending on the axial power density shape, a suitable function was chosen to fit the power density. This function was used to evaluate the temperature distribution in the core. A MATLAB script was used to predict the temperature distribution. The maximum temperatures for the coolant, clad and fuel centre were determined for each control rod position. The maximum temperature locations, when all the control rods were outside the core, were found to exist in assembly (F6), and the vicinity of the centre of the core in assemblies that are burnable absorber free. When control rod group D was inserted in the core in steps, a significant number of high temperatures were found on the same axial position or became closer to the centre of the core.

The Particle Swarm Optimization (PSO) algorithm is used to optimize the design of shell-and-tube heat exchangers and determine the optimal feasible solutions so as to eliminate trial-and-error during the design process. The design formulation takes into account the area and the total annual cost of heat exchangers as two objective functions together with operating as well as geometrical constraints. The Nonlinear Constrained Single Objective Particle Swarm Optimization (NCSOPSO) algorithm is used to minimize and find the optimal feasible solution for each of the nonlinear constrained objective functions alone, respectively. Then, a novel Nonlinear Constrained Multobjective Particle Swarm Optimization (NCMOPSO) algorithm is used to minimize and find the Pareto optimal solutions for both of the nonlinear constrained objective functions together. The experimental results show that the two algorithms are very efficient, fast and can find the accurate optimal feasible solutions of the shell and tube heat exchangers design optimization problem.

In this paper, the Particle Swarm Optimization (PSO) algorithm is modified to deal with Multiobjective Optimization Problems (MOPs). A mathematical model for predicting the dynamic response of the H. B. Robinson nuclear power plant, which represents an Initial Value Problem (IVP) of Ordinary Differential Equations (ODEs), is solved using Runge-Kutta formula. The resulted data values are represented as a system of nonlinear algebraic equations by interpolation schemes for data fitting. This system of fitted nonlinear algebraic equations represents a nonlinear multiobjective optimization problem. A Multiobjective Particle Swarm Optimizer (MOPSO) which is based on the Pareto optimality concept is developed and applied to maximize the above mentioned problem. Results show that MOPSO efficiently cope with the problem and finds multiple Pareto optimal solutions.

Summary Potassium uptake as affected by the presence of divalent and other ions was studied from KCl solutions to which other salts were added. The study also includes the effect of the initial Ca-content of roots on the uptake of K+ from KCl and KCl + CaCl2 solutions. The effect of time on K-uptake from electrolyte mixtures containing Mg-ions was also included. The experimental results seem to fit well a model of K+-uptake based on diffusion of ions in mixed electrolytes.

The mid-filmR process has been developed to combine the photolithographic capability of thin film technology and the low cost, non-vacuum processing of thick film technology. In this paper, we present results on the characterization of mid-film gold for multilayer applications. The effects of various processing parameters on the properties of the conductor were investigated to establish optimum processing conditions on alumina and dielectric-coated alumina substrates. The use of a resin thickness in the range from 5 μm to 15 μm and firing temperatures from 750℃ to 1000℃ produced conductor lines with sheet resistances less than 4 mΩ/□, and with adhesion strengths capable of with-standing a pull force of 2.3 Kg exerted on a 2.03 mm × 1.03 mm area. The conductor lines exhibited stable resistances upon several firings at 920℃. The ultrasonic bondability of 25 μm (1 mil) aluminum wire to the mid-film gold was observed to withstand pull forces of 7.3 ± 1.5 g before breaking the bond. In addition, it was confirmed that the resolution limit of the mid-film conductor is 50 μm for line widths and spaces. Furthermore, the prototype fabrication of a multilayer memory package has been successfully demonstrated using a combination of both mid-film and thick film processes. The finished packages were free of electrical shorts and conductor discontinuities and the resistance of the mid-film conductor lines was well within the required design specifications.

Competing Interests: The author declares no competing financial interest.