• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.531-540
• /
• 2010

In this paper, we present a two-phase shallow semantic parsing method based on a maximum entropy model. The first phase is to recognize semantic arguments, i.e., argument identification. The second phase is to assign appropriate semantic roles to the recognized arguments, i.e., argument classification. Here, the performance of the first phase is crucial for the success of the entire system, because the second phase is performed on the regions recognized at the identification stage. In order to improve performances of the argument identification, we incorporate syntactic knowledge into its pre-processing step. More precisely, boundaries of the immediate clause and the upper clauses of a predicate obtained from clause identification are utilized for reducing the search space. Further, the distance on parse trees from the parent node of a predicate to the parent node of a parse constituent is exploited. Experimental results show that incorporation of syntactic knowledge and the separation of argument identification from the entire procedure enhance performances of the shallow semantic parsing system.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.145-154
• /
• 2022

Automatic Target Recognition (ATR) technology is emerging as a core technology of Future Combat Systems (FCS). Conventional ATR is performed based on IMINT (image information) collected from the SAR sensor, and various image-based deep learning models are used. However, with the development of IT and sensing technology, even though data/information related to ATR is expanding to HUMINT (human information) and SIGINT (signal information), ATR still contains image oriented IMINT data only is being used. In complex and diversified battlefield situations, it is difficult to guarantee high-level ATR accuracy and generalization performance with image data alone. Therefore, we propose a knowledge graph-based ATR method that can utilize image and text data simultaneously in this paper. The main idea of the knowledge graph and deep model-based ATR method is to convert the ATR image and text into graphs according to the characteristics of each data, align it to the knowledge graph, and connect the heterogeneous ATR data through the knowledge graph. In order to convert the ATR image into a graph, an object-tag graph consisting of object tags as nodes is generated from the image by using the pre-trained image object recognition model and the vocabulary of the knowledge graph. On the other hand, the ATR text uses the pre-trained language model, TF-IDF, co-occurrence word graph, and the vocabulary of knowledge graph to generate a word graph composed of nodes with key vocabulary for the ATR. The generated two types of graphs are connected to the knowledge graph using the entity alignment model for improvement of the ATR performance from images and texts. To prove the superiority of the proposed method, 227 documents from web documents and 61,714 RDF triples from dbpedia were collected, and comparison experiments were performed on precision, recall, and f1-score in a perspective of the entity alignment..

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.8
• /
• pp.1259-1268
• /
• 2002

One of the major goals suggested in distributed system is to improve the performance of the system through the load balancing of whole system. Load balancing among systems improves the rate of processor utilization and reduces the turnaround time of system. In this paper, we design the rule of decision-making and information interchange based on knowledge based mechanism which makes optimal load balancing by sharing the future load state information inferred from past and present information of each nodes. The result of performance evaluation shows that utilization of processors is balanced, the processing time is improved and reliability and availability of systems are enhanced. The proposed mechanism in this paper can be utilized in the design of load balancing algorithm in distributed operating systems.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1138-1146
• /
• 1996

Fuzzy logic ignores some informations in the reasoning process. Neural networks are powerful tools for the pattern processing. However, to model human knowledges, besides pattern processing capability, the logical reasoning capability is equally important. Another new neural network called neural logic network is able to do the logical reasoning. Because the fuzzy logical reasoning, we construct fuzzy inference net-work based on the neural logic network, extending the existing rule-inferencing network. And the traditional propagation rule is modified. For the search strategies to find out the belief value of a conclusion in the fuzzy inference network, we conduct a simulation to evaluate the search cost for searching sequentially and searching by means of priorities.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.109-111
• /
• 2003

클러스터 시스템의 성능 향상을 위해서는 컴퓨팅 자원을 효과적으로 사용하여야 한다. 과거에는 전체 시스템 자원을 효과적으로 사용하기 위해 각 노드들의 부하를 균등하게 하는 방향으로 연구가 진행되어 왔으나, 부하 분산 시스템이 작업의 자원 요구 형태를 고려하여 작업을 배치하는 경우 성능을 더욱 향상시킬 수 있다. 현재까지는 이런 자원 요구 형태에 대한 선행지식을 과거 작업 실행 기록에 기반하여 유추해내는 방법을 많이 사용하였으나 이 방법은 잘못된 예측을 가져와 실행시간을 증가시킬 수 있다. 본 논문에서는 이를 해결하기 위해 유효 작업수라 불리는 새로운 노드의 부하 측정 척도를 제시한다. 유효 작업수를 이용한 부하 분산 시스템은 작업의 자원 요구 사항을 알지 못하더라도 부하 분산 과정에서 작업이 잘못 배치되어 실행시간이 증가하는 경우를 방지한다. 성능분석 결과는 과거 자료에 의한 예측을 사용하는 기존 방법에 비해 전체 실행시간의 감소로 성능이 향상되었음을 보여준다.

• Information Systems Review
• /
• v.13 no.2
• /
• pp.1-16
• /
• 2011

Recently, many companies have started to manage and support CoPs formally at the organizational level because of strategic usability of CoP. These companies are also seeking ways to motivate CoP members to actively participate in their groups. Accordingly, this paper proposes one way of increasing CoP activities by rearranging CoP members. In practice, active CoP members often lead their groups. Therefore, rearranging members can, eventually, be one method to motivate more individuals to participate in CoP activities. This paper first suggests a new approach in order to improve knowledge sharing activities at the organizational level based on rearranging members of current CoPs. Second, a mathematical model is presented which maximizes total BLS (Balanced Level Score) of company A with several constraints. Then a real world problem is changed to a popular problem, VRP to solve this problem. Third, the solution program was developed to find a meaningful solution.

• Journal of the Korea Knowledge Information Technology Society
• /
• v.13 no.5
• /
• pp.607-614
• /
• 2018

Oryeong-san is a prescription widely used for diseases where water is stagnant because it has the effect of circulating the water in the body and releasing it into the urine. In order to investigate the mechanisms of oryeong-san, we in this paper construct and analysis the compound-target network of medicinal materials constituting oryeong-san based on a systems pharmacology approach. First, the targets related to the 475 chemical compounds of oryeong-san were searched in the STITCH database, and the search results for the interactions between compounds and targets were downloaded as XML files. The compound-target network of oryeong-san is visualized and explored using Gephi 0.8.2, which is an open-source software for graphs and networks. In the network, nodes are compounds and targets, and edges are interactions between the nodes. The edge is weighted according to the reliability of the interaction. In order to analysis the compound-target network, it is clustered using MCL algorithm, which is able to cluster the weighted network. A total of 130 clusters were created, and the number of nodes in the cluster with the largest number of nodes was 32. In the clustered network, it was revealed that the active compounds of medicinal materials were associated with the targets for regulating the blood pressure in the kidney. In the future, we will clarify the mechanisms of oryeong-san by linking the information on disease databases and the network of this research.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.8
• /
• pp.1102-1108
• /
• 2020

Mobile edge computing is a technology that can prepare for a new era of cloud computing and compensate for shortcomings by processing data near the edge of the network where data is generated rather than centralized data processing. It is possible to realize a low-latency/high-speed computing service by locating computing power to the edge and analyzing data, rather than in a data center far from computing and processing data. In this article, we develop a virtual mobile edge computing testbed environment where the cloud and edge nodes divide computing tasks from mobile terminals using the EdgeCloudSim simulator. Performance of offloading techniques for distribution of computing tasks from mobile terminals between the central cloud and mobile edge computing nodes is evaluated and analyzed under the virtual mobile edge computing environment. By providing a virtual mobile edge computing environment and offloading capabilities, we intend to provide prior knowledge to industry engineers for building mobile edge computing nodes that collaborate with the cloud.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.15 no.2
• /
• pp.27-48
• /
• 2004

Research and development projects in Research and development projects in Korea are ineffectively conducted due to the lack of a system for effectively planning, conducting and disseminating the result of the research projects. In this study, we have designed a framework for system that can be used in the planning and managing stage of National R & D information to guarantee standardization and extendability of the information. A national R & D technology information portal system for managing the distributed national R & D information on a single database is suggested based on this framework for the construction of a more effective information support system and the dissemination of national R & D information between researchers.

• Journal of Internet Computing and Services
• /
• v.14 no.4
• /
• pp.53-62
• /
• 2013

In cloud robotics, the model to share information efficiently is still a research challenge. This paper presents an information sharing model for cloud-enabled robots to collaborate and share intelligence. To provide the efficient message dissemination, an adaptive group communication based on multi-agent is proposed. The proposed algorithm uses a weight function for the link nodes to determine the significant links. The performance evaluation showed that the proposed algorithm produced minimal message overhead and was faster to answer queries because of the significant links compared to traditional group communication methods.