• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• Journal of Computational Design and Engineering
• /
• v.1 no.3
• /
• pp.187-193
• /
• 2014

One of the hottest challenges in automotive industry is related to weight reduction in sheet metal forming processes, in order to produce a high quality metal part with minimal material cost. Stamping is the most widely used sheet metal forming process; but its implementation comes with several fabrication flaws such as springback and failure. A global and simple approach to circumvent these unwanted process drawbacks consists in optimizing the initial blank shape with innovative methods. The aim of this paper is to introduce an efficient methodology to deal with complex, computationally expensive multicriteria optimization problems. Our approach is based on the combination of methods to capture the Pareto Front, approximate criteria (to save computational costs) and global optimizers. To illustrate the efficiency, we consider the stamping of an industrial workpiece as test-case. Our approach is applied to the springback and failure criteria. To optimize these two criteria, a global optimization algorithm was chosen. It is the Simulated Annealing algorithm hybridized with the Simultaneous Perturbation Stochastic Approximation in order to gain in time and in precision. The multicriteria problems amounts to the capture of the Pareto Front associated to the two criteria. Normal Boundary Intersection and Normalized Normal Constraint Method are considered for generating a set of Pareto-optimal solutions with the characteristic of uniform distribution of front points. The computational results are compared to those obtained with the well-known Non-dominated Sorting Genetic Algorithm II. The results show that our proposed approach is efficient to deal with the multicriteria shape optimization of highly non-linear mechanical systems.

• Earthquakes and Structures
• /
• v.1 no.1
• /
• pp.109-127
• /
• 2010

This work aims at introducing structural sensitivity analysis capabilities into existing commercial finite element software codes for the purpose of mapping retrofit strategies for a broad group of structures including heritage-type buildings. More specifically, the first stage sensitivity analysis is implemented for the standard deterministic environment, followed by stochastic structural sensitivity analysis defined for the probabilistic environment in a subsequent, second phase. It is believed that this new generation of software that will be released by the industrial partner will address the needs of a rapidly developing specialty within the engineering design profession, namely commercial retrofit and rehabilitation activities. In congested urban areas, these activities are carried out in reference to a certain percentage of the contemporary building stock that can no longer be demolished to give room for new construction because of economical, historical or cultural reasons. Furthermore, such analysis tools are becoming essential in reference to a new generation of national codes that spell out in detail how retrofit strategies ought to be implemented. More specifically, our work focuses on identifying the minimum-cost intervention on a given structure undergoing retrofit. Finally, an additional factor that arises in earthquake-prone regions across the world is the random nature of seismic activity that further complicates the task of determining the dynamic overstress that is being induced in the building stock and the additional demands placed on the supporting structural system.

• Journal of Korea Water Resources Association
• /
• v.31 no.1
• /
• pp.59-69
• /
• 1998

A regression model with basin physiographic characteristics as independent variables was calibrated for regional flood frequency analysis. In case that high correlations existing among the independent variables the ridge regression has been known to have capability of overcoming the problems of multicollinearity. To optimize the ridge regression model the cost function including regularization parameter must be minimized. In this research the genetic algorithm was applied on this optimization problem. The genetic algorithm is a stochastic search method that mimic the metaphor of natural biological heredity. Using this method the regression model could have optimized and stable weights of variables.

• Structural Monitoring and Maintenance
• /
• v.6 no.3
• /
• pp.219-235
• /
• 2019

Scheduled inspections of common crossings are one of the main cost drivers of railway maintenance. Prognostics and health management (PHM) approach and modern monitoring means offer many possibilities in the optimization of inspections and maintenance. The present paper deals with data driven prognosis of the common crossing remaining useful life (RUL) that is based on an inertial monitoring system. The problem of scheduled inspections system for common crossings is outlined and analysed. The proposed analysis of inertial signals with the maximal overlap discrete wavelet packet transform (MODWPT) and Shannon entropy (SE) estimates enable to extract the spectral features. The relevant features for the acceleration components are selected with application of Lasso (Least absolute shrinkage and selection operator) regularization. The features are fused with time domain information about the longitudinal position of wheels impact and train velocities by multivariate regression. The fused structural health (SH) indicator has a significant correlation to the lifetime of crossing. The RUL prognosis is performed on the linear degradation stochastic model with recursive Bayesian update. Prognosis testing metrics show the promising results for common crossing inspection scheduling improvement.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.240-246
• /
• 2022

This paper introduces a container loading problem and proposes a theoretical approach that efficiently solves it. The problem is to determine a proper weight of products loaded on a container that is delivered by third party logistics (3PL) providers. When the company pre-loads products into a container, typically one or two days in advance of its delivery date, various truck weights of 3PL providers and unpredictability of the randomness make it difficult for the company to meet the total weight regulation. Such a randomness is mainly due to physical difference of trucks, fuel level, and personalized equipment/belongings, etc. This paper provides a theoretical methodology that uses historical shipping data to deal with the randomness. The problem is formulated as a stochastic optimization where the truck randomness is reflected by a theoretical distribution. The data analytics solution of the problem is derived, which can be easily applied in practice. Experiments using practical data reveal that the suggested approach results in a significant cost reduction, compared to a simple average heuristic method. This study provides new aspects of the container loading problem and the efficient solving approach, which can be widely applied in diverse industries using 3PL providers.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.757-764
• /
• 2017

As the reduction of greenhouse gases(GHGs) emission has become a global issue, the microgrid markets are growing rapidly. With the sudden changes in the market, Korean government suggested a new business model called 'Self-Sufficient Energy Islands'. Its main concern is a stand-alone microgrid composed of Distributed Energy Resources(DERs) such as Renewable Energy Sources(RESs), Energy Storage System(ESS) and Fuel Cell, in order to minimize the emission of GHGs. According to these trend, this paper is written to propose an optimal sizing method of DERs in a stand-alone microgrid by using Genetic Algorithm(GA), one of the representative stochastic methods. It is to minimize the net present cost with the variables, size of RESs and ESS. In the process for optimization, the sunless days are considered as additional constraints. Through the case study analysis, the size of DERs installed in a microgrid system has been computed using the proposed method in MATLAB. And the result of MATLAB is compared with that of HOMER(Hybrid Optimization of Multiple Energy Resources), a well-known energy modeling software.

• Journal of Korean Society of Transportation
• /
• v.26 no.5
• /
• pp.175-184
• /
• 2008

Uncertainties are unavoidable in engineering applications. In this paper we propose an alpha reliable multi-variable network design problem under demand uncertainty. In order to decide the optimal capacity enhancement, three performance measures based on 3E(Efficiency, Equity, and Environmental) are considered. The objective is to minimize the total budget required to satisfy alpha reliability constraint of total travel time, equity ratio, and total emission, while considering the route choice behavior of network users. The problem is formulated as the chance-constrained model for application of alpha confidence level and solved as a lexicographic optimization problem to consider the multi-variable. A simulation-based genetic algorithm procedure is developed to solve this complex network design problem(NDP). A simple numerical example ispresented to illustrate the features of the proposed NDP model.

• Korean Chemical Engineering Research
• /
• v.58 no.3
• /
• pp.396-407
• /
• 2020

As fossil fuels are depleted worldwide, alternative resources is required to replace fossil fuels, and biofuels are in the spotlight as alternative resources. Biofuels are produced from biomass, which is a renewable resource to produce biofuels or bio-chemicals. Especially, in order to substitute fossil fuels, the research focusing the biofuel (biodiesel) production based on CO₂ and biomass achieves more attention recently. To produce biomass-based biodiesel, the development of a supply chain network is required considering the amounts of feedstocks (ex, CO₂ and water) required producing biodiesel, potential locations and capacities of bio-refineries, and transportations of biodiesel produced at biorefineries to demand cities. Although many studies of the biomass-based biodiesel supply chain network are performed, there are few types of research handled the uncertainty in CO₂ supply which influences the optimal strategies of microalgae-based biodiesel production. Because CO₂, which is used in the production of microalgae-based biodiesel as one of important resources, is captured from the off-gases emitted in power plants, the uncertainty in CO₂ supply from power plants has big impacts on the optimal configuration of the biodiesel supply chain network. Therefore, in this study, to handle those issues, we develop the two-stage stochastic model to determine the optimal strategies of the biodiesel supply chain network considering the uncertainty in CO₂ supply. The goal of the proposed model is to minimize the expected total cost of the biodiesel supply chain network considering the uncertain CO₂ supply as well as satisfy diesel demands at each city. This model conducted a case study satisfying 10% diesel demand in the Republic of Korea. The overall cost of the stochastic model (US$ 12.9/gallon·y) is slightly higher (23%) than that of the deterministic model (US$ 10.5/gallon·y). Fluctuations in CO₂ supply (stochastic model) had a significant impact on the optimal strategies of the biodiesel supply network.

• Korean Chemical Engineering Research
• /
• v.52 no.4
• /
• pp.467-474
• /
• 2014

Preliminary design in chemical process furnishes economic feasibility through calculation of both mass balance and energy balance and makes it possible to produce a desired product under the given conditions. Through this design stage, the process possesses unchangeable characteristics, since the materials, reactions, unit configuration, and operating conditions were determined. Unique characteristics could be very economic, but it also implies various potential risk factors as well. Therefore, it becomes extremely important to design process considering both economics and safety by integrating process simulation and quantitative risk analysis during preliminary design stage. The target of this study is LNG liquefaction process. By the simulation using Aspen HYSYS and quantitative risk analysis, the design variables of the process were determined in the way to minimize the inherent explosion risks and operating cost. Instead of the optimization tool of Aspen HYSYS, the optimization was performed by using stochastic optimization algorithm (Covariance Matrix Adaptation-Evolution Strategy, CMA-ES) which was implemented through automation between Aspen HYSYS and Matlab. The research obtained that the important variable to enhance inherent safety was the operation pressure of mixed refrigerant. The inherent risk was able to be reduced about 4~18% by increasing the operating cost about 0.5~10%. As the operating cost increases, the absolute value of risk was decreased as expected, but cost-effectiveness of risk reduction had decreased. Integration of process simulation and quantitative risk analysis made it possible to design inherently safe process, and it is expected to be useful in designing the less risky process since risk factors in the process can be numerically monitored during preliminary process design stage.