• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.410-421
• /
• 2016

In this paper, we propose a framework that attempts to incorporate landmarks into a segment-based Mandarin speech recognition system. In this method, landmarks provide boundary information and phonetic class information, and the information is used to direct the decoding process. To prove the validity of this method, two kinds of landmarks that can be reliably detected are used to direct the decoding process of a segment model (SM) based Mandarin LVCSR (large vocabulary continuous speech recognition) system. The results of our experiment show that about 30% decoding time can be saved without an obvious decrease in recognition accuracy. Thus, the potential of our method is demonstrated.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11c
• /
• pp.1677-1680
• /
• 2003

RUP(Rational Unified Process)의 Unified Process Model 에는 Use Case Model, Analysis Model, Design Model, Deployrnent Model, Implementation model, Test Model의 6가지 모델이 있다. 이 모델들은 다음단계의 모델에 대한 일관성 및 의존성을 가진다. 한 모델에서 발생되는 요소들은 전, 후 단계에서 다른 모델들과 Trace Dependencies 를 갖는다. 이러한 의존적인 관계들은 각각의 요소들 사이의 진행, 기록 관계를 나타낸다. 그러나 대부분의 시스템은 이러한 관계 및 의존성 없이 설계되어져 전체적인 일관성을 이루지 못 하였다. 본 논문에서는 이러한 관계를 유지 하면서 사용자의 요구사항에 일관성 있는 Use Case 모델을 설계하고자 한다. 따라서 본 논문에서는 대학 종합정보시스템 구축의 일부분인 구매관리 시스템을 분석하여 컴포넌트 시스템 모델을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.320-322
• /
• 2018

Data analysis is a process of generating useful information by evaluating real-world raw data for making better decisions in business development. In the freight transport logistics companies, the analysis of freight data is increasingly garnering considerable importance among the users for making better decisions regarding freight cost reductions. Consequently, in this study, we used R programming language to analyze the freight data that are collected from freight transport logistics company. Usually, the freight rate varies based on chosen day of the week. In here, we analyzed and visualized the results such as frequency of cost vs days, frequency of requested goods in ton vs days, frequency of order vs days, and frequency of order status vs days for the last one-year freight data. These analysis results are beneficial in the viewpoint of the users in ordering process.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.480-488
• /
• 2022

Images of tobacco retail licenses have complex unstructured characteristics, which is an urgent technical problem in the robot process automation of tobacco marketing. In this paper, a novel recognition approach using a double attention mechanism is presented to realize the automatic recognition and information extraction from such images. First, we utilized a DenseNet network to extract the license information from the input tobacco retail license data. Second, bi-directional long short-term memory was used for coding and decoding using a continuous decoder integrating dual attention to realize the recognition and information extraction of tobacco retail license images without segmentation. Finally, several performance experiments were conducted using a largescale dataset of tobacco retail licenses. The experimental results show that the proposed approach achieves a correction accuracy of 98.36% on the ZY-LQ dataset, outperforming most existing methods.

• Journal of Navigation and Port Research
• /
• v.32 no.4
• /
• pp.279-285
• /
• 2008

We have proposed modeling methods of mariners' standard behavior for collision avoidance by analyzing mariners' recognition process in a previous study. As a subsequent study, the aim of this study is to build a model of mariners' execution process which is one of six processes in the condition of collision avoidance. In this study, thus, the structure of mariners' information processing on the process of taking avoiding actions is described and the relation between mariners' behavior and necessary factors in the process is analyzed. And then we have built a model of mariners' standard behavior for execution process based on the characteristics of mariners in ship-handling, which are obtained from the international collaborative research on human factors. It is tried to define the contents of execution process based on the standard behavior of mariners for collision avoidance and to formulate information processing of mariners.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.341-345
• /
• 1996

We have developed the drawing and part information management system that could integrate drawing information with corresponding part information in design process. The modules developed include the drawing information management (DIM) and the part information management(PIM). DIM consist of processing drawing management, approved drawing management, disused drawing management, and drawing print management. PIM consist of new part management, option management, and part change management. Errors which may occur in the design process can be reduced by reference to part information directly. In addition, the number of parts can be reduced by minimizing the frequency of new parts generation through the systematic management.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.2
• /
• pp.75-80
• /
• 1998

Process information is known to have the continuous distribution in many manufacturing processes. Generalized p-chart has been developed for controlling processes by classifying the information characteristics into several groups. But it is improper to describe continuous processes with the classified process informal ion, which is based on the classical set concept. Fuzzy control chart, has been developed for the control of linguistic data, but it is also based on the dichotomous notion of classical set theory. In this paper, fuzzy sampling method is studied in order to process the uncertain data properly. The method is incorporated with the fuzzy control chart. Statistical characteristics of the fuzzy representative value are utilized to device the fuzzy-statistical control chart. The fuzzy-statistical control chart is compared with the generalized p-chart and both the sensitivity to the process information distribution change pared robustiness against the noise on the process information of the fuzzy-statistical control chart are shown to be superior.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.1
• /
• pp.111-118
• /
• 1998

The density of fabric is a very important parameter in many fabric production processes. However, in the textile fabrication factories, textile density measurement process has been done inefficiently by handicraft. Thus, exact textile density measurement process is necessary to fabricate high quality textile through weft straighten. In this paper, we propose an automatic textile density measurement system to measure textile density automatically and to improve fabrication efficiency. The proposed system uses cylindrical lens to optically scan the weftl information of the fabric as well as convex lens to enlarge the weft images. The proposed system improves textile quality and provides constant density value to the whole textile range in the high speed fabrication process.

• Journal of the Korea Safety Management & Science
• /
• v.23 no.3
• /
• pp.83-88
• /
• 2021

Recently, due to the aging of workers and the weakening of the labor base in the automobile industry, research on quality inspection methods through ICT(Information and Communication Technology) convergence is being actively conducted. A lot of research has already been done on the development of an automated system for quality inspection in the manufacturing process using image processing. However, there is a limit to detecting defects occurring in the automotive sunroof sealer application process, which is the subject of this study, only by image processing using a general camera. To solve this problem, this paper proposes a system construction method that collects image information using a infrared thermal imaging camera for the sunroof sealer application process and detects possible product defects based on the SVM(Support Vector Machine) algorithm. The proposed system construction method was actually tested and applied to auto parts makers equipped with the sunroof sealer application process, and as a result, the superiority, reliability, and field applicability of the proposed method were proven.