• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.169-172
• /
• 1995

In optmizing cutting condition for face milling operation, tool wear is an important maching factor. For the purpose of establishing the relationship between various maching factor and tool wear, cutting tests have been performed. As a result, hardness and chemical composition of workpiece material, chemical compositition and grain size of cutting tool and cutting speed have been selected as machining factor. In addition, relationship between feed rate and workpiece hardness has been observed. Prior to utilizing cutting condition recommended by 'Machining Data Hardbook(MDH)' as a Knowledge base, an analysis for the validity has been provided. Based on this analysis, tool life criteria applied by MDH has been modifiied. Finaly, using MDH recommended data for neural network trainning, we can compensate the result form the trained neural network for optimizing cutting condition for some given workpice and cutting tool.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.2
• /
• pp.209-216
• /
• 1997

A feature is well known as a medium to integrate CAD, CAPP and CAM systems. For a part drawing including both simple geometry and compound geometry, a process plan such as the selection of process, machine tool, cutting tool etc. normally needs simple geometry data and non-geometry data of the feature as the input. However, a extended process plan such as the generation of process sequence, operation sequence, jig & fixture, NC program etc. necessarily needs the compound geometry data as well as the simple geometry data and non-geometry data. In this paper, we propose a feature data model according to the result of analyzing necessary data, including the compound geometry data, the simple geometry data and the non-geometry data. Also, an example of the feature data model in milling process planning is described.

• International journal of advanced smart convergence
• /
• v.5 no.1
• /
• pp.30-33
• /
• 2016

With the advent of big data, data mining is more increasingly utilized in various decision-making fields by extracting hidden and meaningful information from large amounts of data. Even as exponential increase of the request of unrevealing the hidden meaning behind data, it becomes more and more important to decide to select which data mining algorithm and how to use it. There are several mainly used data mining algorithms in biology and clinics highlighted; Logistic regression, Neural networks, Supportvector machine, and variety of statistical techniques. In this paper it is attempted to compare the classification performance of an exemplary algorithm J48 and REPTree of ML algorithms. It is confirmed that more accurate classification algorithm is provided by the performance comparison results. More accurate prediction is possible with the algorithm for the goal of experiment. Based on this, it is expected to be relatively difficult visually detailed classification and distinction.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.217-226
• /
• 2002

In this paper, we derive noninformative priors for the ratio of failure rates in exponential model. A class of priors is found by matching the coverage probabilities of one-sided Baysian credible interval with the corresponding frequentist coverage probabilities. And we prove that the noninformative prior matches the alternative coverage probabilities and is a HPD matching prior up to the second order. Finally, we provide simulated freqentist coverage probabilities under the derived noninformative prior for small samples.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.6_3
• /
• pp.1197-1204
• /
• 2023

Ti-alloy, a high-strength alloy material among the materials used in aircraft that are trending toward lighter weight, is classified as a difficult-to-cut material that requires a lot of energy for cutting. Cutting in a high-temperature environment is considered one means of making this possible, and various studies have been conducted on it. In particular, research on LAM (Laser Assisted Machining (LAM)), which utilizes laser heating of the cutting area, is being actively conducted. Before processing of the milling cutter begins, the temperature is raised locally by the laser irradiated through the laser head carrier, and the resistance during milling is reduced. Therefore, in this paper, in order to derive such conditions, we performed heat transfer analysis according to transfer conditions and compared it with actually applied test data to use it to establish appropriate processing conditions.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_3
• /
• pp.1127-1133
• /
• 2022

Recently, the use of aircraft structures using Ti alloy (Ti-6Al-4V), a lightweight high-strength alloy material, is rapidly increasing due to the weight reduction of aircraft. However, high-strength materials such as Ti alloys require high energy for cutting and are classified as difficult-to-cut materials. Also, research on Laser Assisted Machining (hereinafter referred to as LAM), a cutting processing technology that utilizes improved machinability, is being actively researched. Therefore, in this paper, in order to confirm the proper temperature distribution using a laser, the finite element method is used to determine the temperature distribution according to the calorific value condition to derive the appropriate condition, and the thermal load generated at this time is used as a structural analysis. It is intended to be used as basic data for LAM processing conditions by measuring the amount of residual stress and thermal deformation caused by heat.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.471-475
• /
• 2008

Microarray technology in biological science enables molecular level observations and analyses on the biological phenomina by allowing to measure the RNA expression profiles in cells. Microarray data analysis is applied in various purposes such as identifying significant genes which react to drug treatment, understanding the genome scale phenomina. In drug response experiments, the microarray-based gene expression analysis could provide meaningful information. It is sometimes needed to identify the genes which shows different expression behavior for treatment group and normal group each other. When the normal group shows the medium level expression, it is not easy to discriminate the group just by expression level comparison. This paper proposes a method which selects group-wise representative values for each gene and sets the value range of the groups in order to filter out the genes with specific pattern. It also shows some experiment results.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.1
• /
• pp.120-130
• /
• 1993

Generally, the machinability of materials that have a good mechanical properties is poor. For materials having a high strength, high toughness, high strength in high temperature and wear resistance, it is difficult to remove a chip from work materials. These properties are well shown in a Nickel, so this metal is used in machine materials, semi-conductor industry, metal mold and optical fields etc. But it is limitted in use because of high cost and poor machinability. In this study, the cutting of pure Nickel was conducted to examine wear of CBN, poly crystal diamond (PCD) and single crystal diamond (SCD) tools. From the result, the CBN tool is superior to poly crystal diamond tools or single crystal diamond tools in terms of tool wear and tool wear is predictable from experimental data base.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.1-10
• /
• 2018

This study is to seek to find the importance of next digital marketing factors by using AHP method and analyze comparison between an advertising expert and a non-advertising expert. In results, the relative importance ranking is as follows; combination (0.26), transformation (0.259), optimization (0.243), and technology (0.238). The relative importance ranking of sub-factors is as follows: artificial intelligence and maching learning (0.086), big data (0.085), and contents curation (0.060). While the relative importance of combination and optimization for an advertising expert is higher than for non-advertising expert, the relative importance of transformation and technology for non-advertising is higher than for an advertising expert. This study provides managerial implication to build digital strategy based on these result.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.62-73
• /
• 2022

Researches on the prediction of domestic apartment sales price have been continuously conducted, but it is not easy to accurately predict apartment prices because various characteristics are compounded. Prior to predicting apartment sales price, the analysis of major factors, influencing on sale prices, is of paramount importance to improve the accuracy of sales price. Therefore, this study aims to analyze what are the factors that affect the apartment sales price in Gwangju, which is currently showing a steady increase rate. With 6 years of Gwangju apartment transaction price and various social factor data, several maching learning techniques such as multiple regression analysis, random forest, and deep artificial neural network algorithms are applied to identify major factors in each model. The performances of each model are compared with RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and R² (coefficient of determination). The experiment shows that several factors such as 'contract year', 'applicable area', 'certificate of deposit', 'mortgage rate', 'leading index', 'producer price index', 'coincident composite index' are analyzed as main factors, affecting the sales price.