• Industrial Engineering and Management Systems
• /
• v.8 no.1
• /
• pp.47-53
• /
• 2009

We define product line (or mix) selection problem as selecting a subset of potential product variants that can simultaneously minimize product proliferation and maintain market coverage. Selecting the most efficient product mix is a complex problem, which requires analyses of multiple criteria. This paper proposes a method based on Data Envelopment Analysis (DEA) for product line selection. Data Envelopment Analysis (DEA) is a linear programming based technique commonly used for measuring the relative performance of a group of decision making units with multiple inputs and outputs. Although DEA has been proved to be an effective evaluation tool in many fields, it has not been applied to solve the product line selection problem. In this study, we construct a five-step method that systematically adopts DEA to solve a product line selection problem. We then apply the proposed method to an existing line of staplers to provide quantitative evidence for managers to generate desirable decisions to maximize the company profits while also fulfilling market demands.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.5 no.4
• /
• pp.18-25
• /
• 1996

In this study, we have developed the stereolithography system that supports the development of a products. This paper presents the development of the stereolithography system. The system is composed of hardware, software and control part. The software converts a STL file to NC data and displays the monitoring figure in control part. The hardware part deals with structure of machine. The most important theme in this paper is LG-SLCAM software. This software can generate NC data and scanning condition data from a STL file semiautimatically. On the basis of three diensional shapes, it makes data for support structure from STL file. The effectiveness of using out stereolithography system is confirmed by processes of good development.

• Korean Journal of Computational Design and Engineering
• /
• v.11 no.6
• /
• pp.422-428
• /
• 2006

In this paper, an NC data optimization approach for enhancing 5-axis machining speed is presented. It is usual to use expensive commercial CAD/CAM programs for NC data of 5-axis machining, since it needs very large calculations for optimal tool positioning and orientation, tool path planning, and collision-free tool path generation. Since commercial CAD/CAM systems have similar functions and efficiency based on common algorithms of reliable theories, they do not have their own unique features for machining speed and efficiency. In other words, most commercial CAD/CAM systems consider only the characteristics of part geometry to be machined, which means that they generate almost the same NC data if the part to be machined is the same, even though different machines are used for the pin. A new approach is proposed for optimizing NC data of 5-axis machining, which is based on the characteristics of the machine to be operated. As a result, the speed of 5-axis machining can increase without losing machining accuracy and surface quality.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.4
• /
• pp.797-805
• /
• 2012

Many circular distributions are known to be not only asymmetric but also bimodal. Hidden truncation method of generating asymmetric distribution is applied to a bivariate circular distribution to generate an asymmetric circular distribution. While many other existing asymmetric circular distributions can only model an asymmetric data, this new circular model has great flexibility in terms of asymmetry and bi-modality. Some properties of the new model, such as the trigonometric moment generating function, and asymptotic inference about the truncation parameter are presented. Simulation and real data examples are provided at the end to demonstrate the utility of the novel distribution.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.3
• /
• pp.750-757
• /
• 1999

The protocol conformance testing is to check whether an implementation of a protocol conforms to its specification. And it is important to improve the interoperability of protocol and the efficiency of cost. In general, protocol is composed of the control flow representing observable behaviors and the data flow representing internally used variables. Until now, research for generation of test suite has been realized only consideration the control flow of protocol or separation control flow from data flow. Case of considering control flow, contents of test was simple and definite. Length of test was short. But it was of little application, and it didn't manage each kind errors in data flow. Therefore, we must generate test case that can manage control and data flow. So, anomaly of variable must be removed for efficient conformance testing. Therefore in this dissertation, we proposed algorithm which can remove anomaly of variable for efficient conformance testing. And it showed that anomaly of variable was got rid of applying this algorithm to real protocol.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2752-2763
• /
• 1999

On account of the text based mail system has it's limit to support multimedia applications, GUI based mail system platform was developed to control document flow and automatize information process. The existing mail systems's to transmit data must need additional functions to automate document flow control. The platform of document flow control is deeply related to EDMAS(Electronic document Management System), workflow, Electronic Banking, DMS(Document Management System) automation, so it needs an ability to control proper data and document correctly. To resolve this problems, we are need of browser and engine to design work flow and to control documents flow. In this paper, we develope a mail browser to design document flow by follow user's requirements. This system can generate executive script code for document flow, and we add the function of workflow and process management to automatize the document flow in this system, and then we implement this Data flow engine.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.38-41
• /
• 2003

There are many kinds of algorithms used for the purpose of data mining. But without the understanding the underlying principles in the algorithm, the result of the data mining cannot be interpreted correctly. In this paper, the principle of ID3 algorithm is explained for that purpose. In addition, the way how to generate good training examples from the relational database is treated, as well as how to convert continuous values into discrete values is considered to use the algorithm for the data mining of real world database.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.4
• /
• pp.375-381
• /
• 2014

Data mining is a process of discovering useful patterns or information from large amount of data. Decision tree is one of the data mining algorithms that can be used for both classification and prediction and has been widely used for various applications because of its flexibility and interpretability. Decision trees for classification generally generate a number of rules that belong to one of the predefined category and some rules may belong to the same category. In this case, it is necessary to determine the significance of each rule so as to provide the priority of the rule with users. The purpose of this paper is to propose a rule selection method in classification tree models that accommodate the umber of observation, accuracy, and effectiveness in each rule. Our experiments demonstrate that the proposed method produce better performance compared to other existing rule selection methods.

• Annual Conference of KIPS
• /
• 2014.11a
• /
• pp.849-852
• /
• 2014

Reverse engineering of gene regulatory network is a challenging task in computational biology. To detect a regulatory relationship among genes from time series data is called reverse engineering. Reverse engineering helps to discover the architecture of the underlying gene regulatory network. Besides, it insights into the disease process, biological process and drug discovery. There are many statistical approaches available for reverse engineering of gene regulatory network. In our paper, we propose pairwise mutual information for the reverse engineering of a gene regulatory network from time series data. Firstly, we create random boolean networks by the well-known $Erd{\ddot{o}}s-R{\acute{e}}nyi$ model. Secondly, we generate artificial time series data from that network. Then, we calculate pairwise mutual information for predicting the network. We implement of our system on java platform. To visualize the random boolean network graphically we use cytoscape plugins 2.8.0.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.82.3-82.3
• /
• 2019

In this study, we generate future full disk magnetograms in 12, 24, 36 and 48 hours advance from SDO/HMI images using deep learning. To perform this generation, we apply the convolutional generative adversarial network (cGAN) algorithm to a series of SDO/HMI magnetograms. We use SDO/HMI data from 2011 to 2016 for training four models. The models make AI-generated images for 2017 HMI data and compare them with the actual HMI magnetograms for evaluation. The AI-generated images by each model are very similar to the actual images. The average correlation coefficient between the two images for about 600 data sets are about 0.85 for four models. We are examining hundreds of active regions for more detail comparison. In the future we will use pix2pix HD and video2video translation networks for image prediction.