• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.121-130
• /
• 2024

As internet and communication technology (ICT) is improved exponentially, types and amount of available data also increase. Even though data analysis including statistics is significant to utilize this large amount of data, there are inevitable limits to process various and complex data in general way. Meanwhile, there are many attempts to apply machine learning (ML) in various fields to solve the problems according to the enhancement in computational performance and increase in demands for autonomous systems. Especially, data processing for the model input and designing the model to solve the objective function are critical to achieve the model performance. Data processing methods according to the type and property have been presented through many studies and the performance of ML highly varies depending on the methods. Nevertheless, there are difficulties in deciding which data processing method for data analysis since the types and characteristics of data have become more diverse. Specifically, multi-variate data processing is essential for solving non-linear problem based on ML. In this paper, we present a multi-variate tabular data processing scheme for ML-aided data analysis by using Titanic dataset from Kaggle including various kinds of data. We present the methods like input variable filtering applying statistical analysis and normalization according to the data property. In addition, we analyze the data structure using visualization. Lastly, we design an ML model and train the model by applying the proposed multi-variate data process. After that, we analyze the passenger's survival prediction performance of the trained model. We expect that the proposed multi-variate data processing and visualization can be extended to various environments for ML based analysis.

• Journal of Korean Association for Spatial Structures
• /
• v.4 no.2 s.12
• /
• pp.89-97
• /
• 2004

The objective of this study is the development of a scheme and discrete optimum design algorithm, which is based on the genetic algorithm. The algorithm can perform both scheme and size optimum designs of plane trusses. The developed Scheme genetic algorithm was implemented in a computer program. For the optimum design, the objective function is the weight of structures and the constraints are limits on loads and serviceability. The basic search method for the optimum design is the genetic algorithm. The algorithm is known to be very efficient for the discrete optimization. However, its application to the complicated structures has been limited because of the extreme time need for a number of structural analyses. This study solves the problem by introducing the size & scheme genetic algorithm operators into the genetic algorithm. The genetic process virtually takes no time. However, the evolutionary process requires a tremendous amount of time for a number of structural analyses. Therefore, the application of the genetic algorithm to the complicated structures is extremely difficult, if not impossible. The scheme genetic algorithm operators was introduced to overcome the problem and to complement the evolutionary process. It is very efficient in the approximate analyses and scheme and size optimization of plane trusses structures and considerably reduces structural analysis time. Scheme and size discrete optimum combined into the genetic algorithm is what makes the practical discrete optimum design of plane fusses structures possible. The efficiency and validity of the developed discrete optimum design algorithm was verified by applying the algorithm to various optimum design examples: plane pratt, howe and warren truss.

• Journal of Korea Water Resources Association
• /
• v.50 no.4
• /
• pp.241-252
• /
• 2017

This study aims to evaluate applicability of both online and offline parameter calibration techniques on rainfall-runoff modeling using a conceptual lumped hydrologic model. To achieve the goal, the storage function model was selected and then two different automatic calibration techniques: SCE-UA (offline method) and particle filter (online method) were applied to calibrate the optimal parameter sets for 9 rainfall events in the Cheoncheon catchment, upper area of the Yongdam multi-purpose dam. In order to assess reproducibility of hydrographs from the parameter sets of both techniques, the observed discharge of each event was divided into low flow (below average flow) and high flow (over average flow). The results show that the particle filter method, updating the parameters in real-time, provides more stable reproducibility than the SCE-UA method regardless of low and high flow. The optimal parameters estimated by SCE-UA are very sensitive to the selected objective functions used in this study: RMSE and HMLE. In particular, the parameter sets from RMSE and HMLE demonstrate superior goodness-of-fit values for high flow and low flow periods, respectively.

• Journal of Korean Society of Environmental Engineers
• /
• v.38 no.6
• /
• pp.334-342
• /
• 2016

Conventional eco-design has been implemented based only on the environmental aspects of a product. Key components of a product identified from the analysis of the environmental aspects have been the target for improvement in the conventional eco-design. The use of eco-design index (EDI) considering both the environmental and economic aspects, and utility value (UV) of a product can be envisaged as an alternative way of implementing and assessing the eco-design. The objective of this study was to propose the logic of the EDI and apply it to the components for performing printing function of the multi-function printer. The EDI was formulated by quantifying the UV, life cycle environmental impact (LCE) and life cycle cost (LCC) of the components of a product, here components of the printer. Of the eight components investigated, roller was identified as the best performing consumable in both the environmental and economic aspects. However, its UV was the lowest among the eight. The EDI of the roller was mere $4^{th}$ in ranking out of the eight. Transfer belt ranked $8^{th}$ and $5^{th}$ in the environmental and economic aspects, respectively, while $2^{nd}$ in the utility value with its EDI ranked $3^{rd}$. This indicates that not only the environmental aspects but also economic and utility value aspects should be considered when identifying the key components for improvement in the eco-design.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.13 no.2
• /
• pp.73-84
• /
• 1993

In this research, configuration design optimization of plane truss structure has been tested by using decomposition technique. In the first level, the problem of transferring the nonlinear programming problem to linear programming problem has been effectively solved and the number of the structural analysis necessary for doing the sensitivity analysis can be decreased by developing stress constraint into member stress approximation according to the design space approach which has been proved to be efficient to the sensitivity analysis. And the weight function has been adopted as cost function in order to minimize structures. For the design constraint, allowable stress, buckling stress, displacement constraint under multi-condition and upper and lower constraints of the design variable are considered. In the second level, the nodal point coordinates of the truss structure are used as coordinating variable and the objective function has been taken as the weight function. By treating the nodal point coordinates as design variable, unconstrained optimal design problems are easy to solve. The decomposition method which optimize the section areas in the first level and optimize configuration variables in the second level was applied to the plane truss structures. The numerical comparisons with results which are obtained from numerical test for several truss structures with various shapes and any design criteria show that convergence rate is very fast regardless of constraint types and configuration of truss structures. And the optimal configuration of the truss structures obtained in this study is almost the identical one from other results. The total weight couldbe decreased by 5.4% - 15.4% when optimal configuration was accomplished, though there is some difference.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.320-326
• /
• 2017

Multistage deep-drawing technology is used widely in the production of mobile phone battery cases to improve productivity and economy. To ensure adequate capacity and rigidity, such cases are fabricated as a rectangular cup with a high slender ratio. The multistage deep-drawing of a rectangular cup entails a high slender ratio, and the heights of the product sides may be non-uniform because of the complicated deformation mechanisms. This causes problems in product assembly that affects the surface quality of the case. This study examined a blank shape that minimizes the height variations of the product to resolve the aforementioned problems. Optimization design and analysis were performed to identify the shape that yields the least variation. The long and short sides of an oval blank were set as the design variables. The objective function was set to yield the lowest height difference, and the thickness reduction rate of the product was set to the target range. In addition, the height of the final shape was set as a constraint. The height difference was minimized successfully using the optimized design. The design process of the initial blank for all rectangular shapes can be automated in the future.

• Journal of Korea Soil Environment Society
• /
• v.3 no.2
• /
• pp.127-145
• /
• 1998

Unlike water or air quality standards that have been established by legislation using potential human health impact as the primary criterion, soil quality depends on the soils primary function and its relevant environmental factors, which is much more site- and soil specific. A properly characterized soil quality assessment system should serve as an indicator of the soil capacity to produce safe and nutritious food, to enhance human and animal health, and to overcome degrative processes. For our proposed example, a high quality soil with regard to maintaining an adequate soil productivity as a food production resources must accommodate soil and water properties, food chain, sustainability and utilization, environment, and profitability, that (i) facilitate water transfer and absorption, (ii) sustain plant growth, (iii) resist physical degradation of soil, (iv) produce a safe food resources, (v) cost-effective agricultural management. Possible soil quality indicators are identified at several levels within the framework for each of these functions. Each indicator is assigned a priority or weight that reflects its relative importance using a multi-objective approach based on principles of systems to be considered. To do this, individual scoring system is differentiated by the several levels from low to very high category or point scoring ranging from 0 to 10, And then weights are multiplied and products are summed to provide an overall soil quality rating based on several physical and chemical indicators. Tlne framework and procedure in developing the soil quality assessment are determined by using information collected from an alternative and conventional farm practices in the regions. The use of an expanded framework for assessing effects of other processes, management practices, or policy issues on soil quality is also considered. To develop one possible form for a soil quality index, we should permit coupling the soil characteristics with assessment system based on soil properties and incoming and resident chemicals. The purpose of this paper is to discuss approaches to defining and assessing soil quality and to suggest the factors to be considered.

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1217-1228
• /
• 2005

Recently, since DNA computing has been widely studied for various applications, DNA sequence design which is the most basic and important step for DNA computing has been highlighted. In previous works, DNA sequence design has been formulated as a multi-objective optimization task, and solved by elitist non-dominated sorting genetic algorithm (NSGA-II). However, NSGA-II needed lots of computational time. Therefore, we use an $\varepsilon$- multiobjective evolutionarv algorithm ($\varepsilon$-MOEA) to overcome the drawbacks of NSGA-II in this paper. To compare the performance of two algorithms in detail, we apply both algorithms to the DTLZ2 benchmark function. $\varepsilon$-MOEA outperformed NSGA-II in both convergence and diversity, $70\%$ and $73\%$ respectively. Especially, $\varepsilon$-MOEA finds optimal solutions using small computational time. Based on these results, we redesign the DNA sequences generated by the previous DNA sequence design tools and the DNA sequences for the 7-travelling salesman problem (TSP). The experimental results show that $\varepsilon$-MOEA outperforms the most cases. Especially, for 7-TSP, $\varepsilon$-MOEA achieves the comparative results two tines faster while finding $22\%$ improved diversity and $92\%$ improved convergence in final solutions using the same time.

• Journal of the Korean Institute of Gas
• /
• v.24 no.4
• /
• pp.62-72
• /
• 2020

This study presents a methodology of history matching to evaluate the productivity of shale gas reservoir with high reliability and predict future production rate in the Horn-River basin, Canada. Sensitivity analysis was performed to analyze the effect of physical properties of shale gas reservoir on productivity. Based on the results, reservoir properties were classified into 4 cases and history matching were performed considering the classified 4 cases as objective function. The blind test was conducted using additional field production data for 3 years after the history matching period. The error of gas production rate in Case 1(all reservoir parameters), Case 2(influenced parameters for productivity), Case 3(controllable parameters), and Case 4(uncontrollable parameters) were 7.67%, 7.13%, 17.54%, and 10.04%, respectively. This means that it seems to be effective to consider all reservoir parameters in early period for 4 years but Case 2 which considered influenced parameters for productivity shows the highest reliability in predicting future production. The estimated ultimate recovery (EUR) of production well predicted using the Case 2 model was estimated to be 17.24 Bcf by December 2030 and the recovery factor compared to original gas in place (OGIP) was 32.2%.

• Journal of Oriental Neuropsychiatry
• /
• v.32 no.2
• /
• pp.81-93
• /
• 2021

Objectives: Mild cognitive impairment (MCI) is condition of cognitive decline shown in transition from normal aging to dementia. Hominis placenta pharmacopuncture (HPP) is a treatment that combines effects of medication and acupuncture by injecting Hominis placenta into acupoints. The objective of this study was to evaluate the efficacy and safety of HPP for MCI. Methods: This was a randomized, double-blind, placebo-controlled, two-center clinical trial. Eligible patients were randomly allocated to either the HPP group or the placebo group. HPP or saline as placebo was administered to participants for eight weeks. Changes in symptoms were observed. The primary outcome was difference in mean change of Korean Version of the Montreal Cognitive Assessment (MoCA-K) score between the HPP group and the placebo group. Cognitive function, overall status of mood and sleep, and quality of life (QoL) were also assessed. Safety assessment and economic analysis were then conducted. Results: Thirty participants were enrolled. One participant in the placebo group dropped out. The score of MoCA-K increased after treatment. Its mean change was smaller in the HPP group than in the control group. HPP ameliorated Global Deterioration Scale and Korean Dementia Rating Scale subtests for attention, organization, and memory compared to the placebo. However, none of them was significantly different between the two groups. Mood, sleep, and QoL all improved more in the HPP group than in the placebo group, although differences between the two groups were not statistically significant. There was no adverse event probably related to the drug. HPP treatment needed KRW 345,000 more than the placebo group in improving Geriatric Quality of Life scale-Dementia score by one point for one year. Conclusions: Although HPP treatment did not significantly improve cognition, it changed behavioral and psychological symptoms in MCI.