• Management Science and Financial Engineering
• /
• v.3 no.2
• /
• pp.71-92
• /
• 1997

Developing FMS controllers has been a difficult problem largely because of the variety of the system configuration. The purpose of this paper is to develop a method of building an FMS controller. The controller consists of control module and execution module. A hierarchically layered structure of these modules is proposed. The control module generates abstract-level execution requested by identifying a set of activities that can be executed without creating any irregular state. The execution module transmits the requests to physical device controllers and reports back the completion of the requests to the control module. Both of these two modules use Petri Net-based models. In this paper, a controllable Petri Net model is automatically synthesized from declarative specifications provided by a user. An execution Petri Net model for the execution module is designed to ensure the consistency between the control module and the real target system. The controller operates in MMS on TCP/IP and UNIX environment.

• Journal of the Korea Society for Simulation
• /
• v.12 no.2
• /
• pp.13-24
• /
• 2003

In this study, we propose a scheduling analysis method of the Flexible management system using the transitive matrix. The Scheduling problem is a combination-optimization problem basically, and a complexity is increased exponentially for a size of the problem. To reduce an increase of a complexity, we define that the basic unit of concurrency (short BUC) is a set of control flows based on behavioral properties in the net. And we propose an algorithm to divide original system into some BUC. To sum up, we divide a petri net model of the Flexible management system Into the basic unit of concurrency through the division algorithm using the transitive matrix. Then we apply it to the division-scheduling algorithm to find an efficient scheduling. Finally, we verify its efficiency with an example.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.81-88
• /
• 2018

In this paper, we present some problems with the Groupware Messenger functionality based on dot net 2.0 and implement a new design structure to solve them. They include memory leakage, slow processing, and client window memory crash. These problems resulted in the inconvenience of using instant messaging and the inefficient handling of office tasks. Therefore, in this paper, instant messaging functionality is implemented according to a new design architecture. The new system upgrades dot net 4.5 for clients and deploys the new features based on MQTT for the messenger server. We verify that the memory leak problem and client window memory crash issues have been eliminated on the system with the new messenger functionality. We measure the amount of time it takes to bind data to a set of messages and evaluate the performance, compared to a given system. Through this comparative evaluation, we can see that the new system is more reliable and performing.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.7
• /
• pp.677-687
• /
• 1992

This paper presents a Fuzzy Pertri Net(FPN)model, which can be used to verify the validity and effectiveness of nervous system bebaviors. The similarities and differences between communication network and neural network are analyzed with respect to the representation and verification of the system behaviors. For the effective representation for the ambiguities of nervous system we combein fuzzy set theory to the PetriNet, and then design a new model, FPN, Also show that FPN is superior to the multiplayer perceptron model using computer simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.1
• /
• pp.15-23
• /
• 1995

In order to investigate the relation between the phytoplankton and the catch fluctuation of set net fishing grounds located in the coastal waters of Yeosu, phytoplankton observations on the fishing ground were carried out by the training ship of Yeosu, Fisheries University from April to November in 1990, and the data obtained were compared with the catch data from the joint market of yeosu fisheries cooperative society in 1990. The results obtained are summarized as follows: 1) The phytoplanktons were more appeared in summer than in spring or autumn and their quantity was much in the shore of Dolsan-do, and little in the offshore waters distributed in the shores of Sori-do and Sejon-do, Thus, the quantity of the planktons could be used for estimating the distribution of watermass. 2) The fishes caught by the set net were arranged in the order of catch amounts as follows: Spanish mackerel > Hair tail > Common mackerel > Sardine > Anchovy > Horse mackerel > Yellow tail. The catches of anchovy and Sardine were high in April to May and Hair tail. Horse mackerel and Common mackerel were caught from June to October. But Spanish mackerel were caught during the whole period of fishing. 3) The catches by set nets showed a correlation with the quantity of phytoplanktons. The planktons appeared most in the inner waters. influenced largely by the inflow of land waters in summer. and the catches were high in summer when the offshore water was distributed least. Therefore, the most important factor influencing the catches were regarded to be the productivity of food organism in inner water into which abundant nutrients were supplied by the inflow of land waters. That is, the fluctuation of catches by set nets seemed to be influenced mainly by the productivity of food organism.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.211-225
• /
• 2003

This paper aims at the design of collaborative architecture for business to business (B2B) applications based on Web service protocol. As different business processes should be interfaced in the B2B environment collaboration is important fur the success of B2B implementation. For the development tools, XML, Web services and ASP.NET were adopted Web services are emerging to provide a systematic and extensible framework for application-to-application interaction. The Web services framework is divided into three areas; communication protocols, service descriptions and Web discovery. Web services such as SOAP, WSDL and UDDI correspond to the three areas respectively. ASP.NET is utilized which corresponds to the component and service set located in the top layer of .NET. For the service of product category and product details, Web service architecture was implemented based upon the SQL server database.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.6
• /
• pp.44-51
• /
• 1999

The HMM-Net is a neural network architecture that implements the computation of output probabilities of a hidden Markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria of maximum likehood(ML) and minimization of mean squared error(MMSE) are used for learning HMM-Net classifiers. The criterion MMSE is better than ML when initial learning condition is well established. However Ml is more useful one when the condition is incomplete[3]. Therefore we propose an efficient learning method of HMM-Net classifiers using a hybrid criterion(ML/MMSE). In the method, we begin a learning with ML in order to get a stable start-point. After then, we continue the learning with MMSE to search an optimal or near-optimal solution. Experimental results for the isolated numeric digits from /0/ to /9/, a training and testing time-series pattern set, show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.17-24
• /
• 2019

The biggest problem in the AI field, which has become a hot topic in recent years, is how to deal with the lack of training data. Since manual data construction takes a lot of time and efforts, it is non-trivial for an individual to easily build the necessary data. On the other hand, automatic data construction needs to handle data quality issue. In this paper, we introduce a method to automatically extract the data required to develop Korean speech command recognizer from the web and to automatically select the data that can be used for training data. In particular, we propose a modified ResNet model that shows modest performance for the automatically constructed Korean speech command data. We conducted an experiment to show the applicability of the command set of the health and daily life domain. In a series of experiments using only automatically constructed data, the accuracy of the health domain was 89.5% in ResNet15 and 82% in ResNet8 in the daily lives domain, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.549-554
• /
• 2016

ConceptNet is a common sense knowledge base which is formed in a semantic graph whose nodes represent concepts and edges show relationships between concepts. As it is difficult to make knowledge base integrity, a knowledge base often suffers from incompleteness problem. Therefore the quality of reasoning performed over such knowledge bases is sometimes unreliable. This work presents neural tensor networks which can alleviate the problem of knowledge bases incompleteness by reasoning new assertions and adding them into ConceptNet. The neural tensor networks are trained with a collection of assertions extracted from ConceptNet. The input of the networks is two concepts, and the output is the confidence score, telling how possible the connection between two concepts is under a specified relationship. The neural tensor networks can expand the usefulness of ConceptNet by increasing the degree of nodes. The accuracy of the neural tensor networks is 87.7% on testing data set. Also the neural tensor networks can predict a new assertion which does not exist in ConceptNet with an accuracy 85.01%.