• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.83-92
• /
• 2020

Recently, many companies and organizations are interested in predictive process monitoring for the efficient operation of business process models. Traditional process monitoring focused on the elapsed execution state of a particular process instance. On the other hand, predictive process monitoring focuses on predicting the future execution status of a particular process instance. In this paper, we implement the function of the business process remaining time prediction, which is one of the predictive process monitoring functions. In order to effectively model the remaining time, normalization by activity is proposed and applied to the predictive model by taking into account the difference in the distribution of time feature values according to the properties of each activity. In order to demonstrate the superiority of the predictive performance of the proposed model in this paper, it is compared with previous studies through event log data of actual companies provided by 4TU.Centre for Research Data.

• Journal of Broadcast Engineering
• /
• v.26 no.7
• /
• pp.868-876
• /
• 2021

Deploying deep neural network model training performs remarkable performance in the fields of Object detection and Instance segmentation. To train these models, features are first extracted from the input image using a backbone network. The extracted features can be reused by various tasks. Research has been actively conducted to serve various tasks by using these learned features. In this process, standardization discussions about encoding, decoding, and transmission methods are proceeding actively. In this scenario, it is necessary to analyze the response characteristics of features against various distortions that may occur in the data transmission or data compression process. In this paper, experiment was conducted to inject various distortions into the feature in the object recognition task. And analyze the mAP (mean Average Precision) metric between the predicted value output from the neural network and the target value as the intensity of various distortions was increased. Experiments have shown that features are more robust to distortion than images. And this points out that using the feature as transmission means can prevent the loss of information against the various distortions during data transmission and compression process.

• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.77-84
• /
• 2019

Workflow management system is a system that manages the workflow model which defines the process of work in reality. We can define the workflow process by sequencing jobs which is performed by the performers. Using the workflow management system, we can also analyze the flow of the process and revise it more efficiently. Many researches are focused on how to make the workflow process model more efficiently and manage it more easily. Recently, many researches use the workflow log files which are the execution history of the workflow process model performed by the workflow management system. Ourresearch group has many interests in making useful knowledge from the workflow event logs. In this paper we use XES log files because there are many data using this format. This papersuggests what are the cardinalities of the temporal workcases and how to get them from the workflow event logs. Cardinalities of the temporal workcases are the occurrence pattern of critical elements in the workflow process. We discover instance cardinalities, activity cardinalities and organizational resource cardinalities from several XES-based workflow event logs and visualize them. The instance cardinality defines the occurrence of the workflow process instances, the activity cardinality defines the occurrence of the activities and the organizational cardinality defines the occurrence of the organizational resources. From them, we expect to get many useful knowledge such as a patterns of the control flow of the process, frequently executed events, frequently working performer and etc. In further, we even expect to predict the original process model by only using the workflow event logs.

• The Journal of the Korean dental association
• /
• v.17 no.1 s.116
• /
• pp.25-28
• /
• 1979

An instance of difficulty in mouth opening as around 2mm due to impingement of fractured coronoid process and zygomatic arch in 30-year-old man who had met with a traffic accident was observed and surgical operation was done. After removal of the fractured coronoid process and elevation of the depressed malunited zygomatic arch, the patient could open mouth by now about 30mm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.97.1-97
• /
• 2001

One of the main problems to constitute control method on biologically oriented wastewater purification processes, e.g. activated sludge process, sequential batch reactor, rotating bio-disk contactor, etc. is that it is hard to control the target component directly. For instance, while biochemical oxygen demand, suspended solids, and chemical oxygen demand are the key components to check the process performance, one may not control them directly since they are the results of microbial activities related to numerous physiochemical factors. Therefore controllers for bioprocess should be designed to make favorable condition for microorganisms´ living, e.g. dissolved oxygen level favorable, mixed liquor suspended solids concentration suitable ...

• Journal of KIISE:Software and Applications
• /
• v.37 no.5
• /
• pp.363-369
• /
• 2010

Demonstration-based learning has the advantage that a user can easily teach his/her robot new task knowledge just by demonstrating directly how to perform the task. However, many previous demonstration-based learning techniques used a kind of attribute-value vector model to represent their state spaces and policies. Due to the limitation of this model, they suffered from both low efficiency of the learning process and low reusability of the learned policy. In this paper, we present a new demonstration-based learning method, in which the relational model is adopted in place of the attribute-value model. Applying the relational instance-based learning to the training examples extracted from the records of the user demonstrations, the method derives a relational instance-based policy which can be easily utilized for other similar tasks in the same domain. A relational policy maps a context, represented as a pair of (state, goal), to a corresponding action to be executed. In this paper, we give a detail explanation of our demonstration-based relational policy learning method, and then analyze the effectiveness of our learning method through some experiments using a robot simulator.

• 한국경영정보학회:학술대회논문집
• /
• 2008.06a
• /
• pp.216-221
• /
• 2008

기업 업무활동의 글로벌화가 가속화 되어감에 따라 글로벌 요인을 반영한 통합 시스템의 구비가 절실하게 요구되고 있는 시점이다. 많은 기업들이 프로세스 경쟁력 강화를 위해 ERP 시스템을 구축해오고 있다. 기존의 ERP 시스템은 단위 사업장 중심의 프로세스 및 시스템 운영을 근간으로 하고 있기 때문에 글로벌 비즈니스 프로세스 및 시스템 운영에 대한 고려가 부족하다. 성공적인 글로벌 ERP의 통합을 위해서는 글로벌 표준화와 글로벌 IT 요건을 고려한 체계적인 구축방법론이 필요하다. 하지만 국내외를 막론하고 체계적으로 정리된 글로벌 ERP 구축 방법론은 제시가 부족한 실정이다. 본 논문에서는 글로벌 비즈니스의 효율적인 실행을 위한 표준 설계, 글로벌 IT 요건을 고려한 ERP 구축, 글로벌 시스템운영을 위한 관리방안을 포괄한 통합적인 접근법으로 효과적인 글로벌 ERP 구축을 위한 가이드 라인을 제시하였다.

• Journal of Advanced Navigation Technology
• /
• v.18 no.1
• /
• pp.74-77
• /
• 2014

This paper suggested an error control for multi-channel running on machine to machine environment. This system is suitable for recovering software fault for multimedia CSCW(Computer Supported Cooperative Works) based on machine to machine environment. It is necessary for the system to be protected by reactivity of media service instance instead of breaking process of session. This paper explains a performance analysis of an error recovery system of M2M based computing collaboration environment using rule-based DEVS modeling and simulation techniques.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.12-18
• /
• 2020

In semiconductor manufacturing, defect detection is critical to maintain high yield. Currently, computer vision systems used in semiconductor photo lithography still have adopt to digital image processing algorithm, which often occur inspection faults due to sensitivity to external environment. Thus, we intend to handle this problem by means of using Mask R-CNN instead of digital image processing algorithm. Additionally, Mask R-CNN can be trained with image dataset pre-processed by means of the specific designed digital image filter to extract the enhanced feature map of Convolutional Neural Network (CNN). Our approach converged advantage of digital image processing and instance segmentation with deep learning yields more efficient semiconductor photo lithography inspection system than conventional system.

• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.71-76
• /
• 2010

This research proposed the method for application of SCORM in U-learning system. That is, I proposed the API broker to connect between U-learning and API Instance of RTE that is existing SCORM based learning object interface environment. The API broker operated handling process using request port and response port between SCORM and U-learning server. For efficient operation in each service, this system has learning contents service buffer in API broker.