• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.430-439
• /
• 2019

The CNN (convolutional neural network) based single degradation restoration method shows outstanding performance yet is tailored on solving a specific degradation type. In this paper, we present an algorithm of multi-degradation classification and restoration. We utilize the CNN based algorithm for solving image degradation classification problem using pre-trained Inception-v3 network. In addition, we use the existing CNN based algorithms for solving particular image degradation problems. We identity the restoration order of multi-degraded images empirically and compare with the non-reference image quality assessment score based on CNN. We use the restoration order to implement the algorithm. The experimental results show that the proposed algorithm can solve multi-degradation problem.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.06a
• /
• pp.56-59
• /
• 2000

한국어에서 복합명사는 명사간 결합이 자유롭고, 단위명사로 띄어쓰는 것을 원칙으로 하나 붙여써도 무방하다. 따라서, 정보검색분야, 기계번역분야에서 복합명사의 정확한 분해는 시스템의 성능에 많은 영향을 미치게 된다. 본 논문에서는 ETRI의 태깅된 코퍼스로부터 추출한 복합명사를 역방향 분해 알고리즘을 이용하여 단위명사로 분해한다. 분해되지 않은 3119개의 복합명사에 대해 실험한 결과 약 96.6%의 정확도를 얻었다. 또한, 미등록이나 접사에 대한 처리에도 비교적 정확한 결과를 얻을 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.70-72
• /
• 2005

데이터베이스 관리자는 효과적인 데이터베이스 관리를 위해 워크로드 특성을 잘 알아야 한다. 워크로드 특성은 데이터베이스 응용분야에 따라 다르며, 데이터베이스 환경에서 하나 이상의 응용 분야가 수행될 수 있다. 복합적인 데이터베이스 응용 분야 때문에, 관리자가 데이터베이스 시스템에서 발생하는 워크로드를 식별하기가 더욱 어려워졌다. 복합적인 데이터베이스 응용 분야의 효과적인 데이터베이스 관리를 수행하기 위해 워크로드를 식별할 수 있는 방법이 요구된다. 이를 위해, 본 연구는 TPC-C와 TPC-W 성능평가의 워크로드와 두 성능평가의 혼합된 워크로드들을 생성하여 워크로드 식별을 수행하였다. 워크로드 식별은 퍼지 k-NN 알고리즘을 수정하여 진행하였다. 수정된 k-NN 알고리즘은 혼합 비율에 따라 시험 워크로드 데이터와 훈련 워크로드 데이터간의 워크로드 식별 실험에 사용되었고, 분류를 위한 k-NN, 퍼지 k-NN, 분산 가중치 퍼지 k-NN 알고리즘의 결과와 비교되었다. 수정된 k-NN 알고리즘은 다른 알고리즘보다 k 인자에 따른 변동과 오차율이 감소하여 워크로드 식별에 더 적합함을 보였다. 본 논문의 결과는 복합된 데이터베이스 응용 분야의 특성을 보이는 데이터베이스 환경에서 워크로드 식별 정보를 창조하여 융통성 있는 튜닝 기법을 고려하는데 기여한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.18-19
• /
• 2018

본 논문에서는 실외 영상에서의 새로운 접근 방식의 복합 조명 알고리즘을 제안한다. 기존의 복합 조명 알고리즘들이 동시에 두 조명을 추정하는 것에 비해 제안 알고리즘은 먼저 단일 조명 기법을 적용하여 첫번째 광원의 색을 추정한 후에 각 영역에서 유사 패치 쌍을 찾아 두번째 광원의 색을 추정하는 방식이다. 일반적인 복합 조명 환경에서는 적용하기 힘들지만 환경을 실외로 제한하여 실외의 광원인 햇빛과 그늘 사이의 관계를 이용하여 효과적으로 유사 패치를 찾아 두 광원의 색을 추정한다. 따라서 실외 환경을 촬영하여 얻은 raw 파일 영상에 제안 알고리즘을 적용하여 효과적으로 광원들의 영향을 제거할 수 있다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.18 no.3
• /
• pp.227-243
• /
• 2005

This paper presents a hybrid control system combining lead rubber bearings and hydraulic actuators for seismic response control of a cable stayed bridge. Because multiple control devices are operating, a hybrid control system could improve the control performances. However, the overall system robustness may be impacted negatively by additional active control devices. Therefore, a secondary on-off type controller according to the responses of lead rubber bearings is combined with LQG algorithm to improve the controller robustness. Numerical simulation results show that control performances of the hybrid system controlled by an on off type LQG algorithm are improved compared to those of the passive and active control systems and are similar to those of performance oriented hybrid system controlled by a LQG algorithm with the similar peak and normed control forces. Furthermore, it is verified that the hybrid system with an on-off type LQG controller is more robust for stiffness matrix perturbation than conventional hybrid control of system, and there are no signs of instability in the overall system. The proposed control system also maintains the control performance under not only the design earthquakes but also the other earthquakes. Therefore, the hybrid control system using on-off type LQG algorithm could be proposed as an improved control strategy for seismically excited cable-stayed bridges containing many uncertainties.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.1
• /
• pp.137-147
• /
• 2013

The RFID(Radio Frequency Identification) and the WSN(Wireless Sensor Network) have technical similarities and mutual effects, they have been recognized to be studied separately, and sufficient studies have not been conducted on the technical integration of the RFID and the WSN. Therefore, EPC global which realized the issue proposed the EPC(Electronic Produce Code) Sensor Network to efficiently integrate and interoperate the RFID and WSN technologies based on the international standard EPC global network. The proposed EPC Sensor Network technology uses the Complex Event Processing method in the middleware to integrate data occurring through the RFID and the WSN in a single environment and to interoperate the events based on the EPC global network. However, as the EPC Sensor Network technology continuously performs its operation even in the case that the minimum conditions are not to be met to find complex events in the middleware, its operation cost rises. Therefore, to address the problems of the existing system, we defined the minimum conditions of the complex events to detect unnecessary complex events in the middleware, and proposed an algorithm that can extract complex events only when the minimum conditions are to be met. To examine the minimum conditions, a index and a query index are used to extract complex events. To evaluate the performance of the proposed methods, In the case of the method of extracting complex events based on a bitmap index, we used the existing extraction method and NS2 simulation to evaluate its performance and thus to show its good performance in terms of the number of operation and the processing time for the complex events.

• Composites Research
• /
• v.34 no.1
• /
• pp.70-75
• /
• 2021

This paper presents a novel algorithm to reconstruct meso-scale representative volume elements (RVE), referring to experimentally observed features of Sheet Molding Compound (SMC) composites. Predicting anisotropic mechanical properties of SMC composites is challenging in the multiscale virtual test using finite element (FE) models. To this end, an SMC RVE modeler consisting of a series of image processing techniques, the novel reconstruction algorithm, and a FE mesh generator for the SMC composites are developed. First, micro-CT image processing is conducted to estimate probabilistic distributions of two critical features, such as fiber chip orientation and distribution that are highly related to mechanical performance. Second, a reconstruction algorithm for 3D fiber chip packing is developed in consideration of the overlapping effect between fiber chips. Third, the macro-scale behavior of the SMC is predicted by the multiscale analysis.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.3
• /
• pp.20-33
• /
• 2006

Because of rapid expansion of third party logistics, fierce competition in the transportation industry, and the diversification and globalization of transportation channels, an effective transportation planning by means of multimodal transport is badly needed. Accordingly, this study aims to suggest an optimal transport algorithm for the multimodal transport in the international logistics. As a solution for this problem, first of all, we have applied a pruning algorithm to simplify it, suggesting a heuristic algorithm for constrained shortest path problem to find out a feasible area with an effective time range, which has been applied to the Label Setting Algorithm, consequently leading to multiple Pareto optimal solutions. Also, in order to test the efficiency of the algorithm for constrained shortest path problem, this paper has applied it to the actual transportation path from Busan port of Korea to Rotterdam port of Netherlands.

• Composites Research
• /
• v.35 no.5
• /
• pp.334-339
• /
• 2022

This study suggests the prediction algorithm for transverse permeability, represented the flow resistance during the manufacturing process of composite, of unidirectional continuous fiber reinforced plastics. The cross-sectional shape of representative volume element (RVE) is considered to reflect fiber arrangement. The equivalent length is used as a factor to express the change of resin flow according to fiber arrangement. The permeability prediction algorithm is created by grafting the Electro-Hydraulic analogy and validity is confirmed. The code for permeability prediction was composed by means of MATLAB and Python, flow analysis was performed by using FLUENT. The algorithm was verified as the permeability results obtained through Algorithm and numerical analysis were almost identical to each other, and the calculation time was reduced around 1/450 compared to the numerical analysis.

• Journal of KIISE:Databases
• /
• v.27 no.4
• /
• pp.562-571
• /
• 2000

이미지 데이터는 텍스트 데이터와는 달리 다양한 색상과 모양, 질감과 같은 비정형적인 특징을 가진다. 따라서 이미지 데이터베이스는 텍스트 기반의 전통 데이터베이스와는 다른 모델링 방법과 질의, 검색 방법을 사용한. 특히, 내용 기반 이미지 검색에서의 검색 속도와 정확도를 향상시키기 위해서는 새로운 복합 질의문 계획 생성 기법이 필요하다. 본 논문에서는 이를 위해 먼저, 단일 조건을 갖는 시각 질의에 대한 처리 기법들을 토대로 여러 조건을 갖는 복합 질의를 처리하기 위한 복합 질의문 계획 생성기법인 SSCC(Similarity Search for Conjunction Combination Query) 알고리즘을 제안한다. SSCC는 이미지 데이터베이스 검색 시스템에서 복합 질의를 처리하기 위한 질의 최적화 과정에서 질의 수행 시간과 투플 I/O를 최소화하는 질의문 계획을 생성하기 위해 사용된다. SSCC 알고리즘은 복합질의를 단일 질의들로 준해하고 퍼지 집합 이론을 도입하여 단일 질의의 결과들을 통합한다. 논문에서 연구된 내용 기반 복합 질의문 계획 생성 기법은 특정 이미지 영역에 국한되지 않으며 다양한 종류의 시각 질의를 수행하기 위한 효율적인 질의문 계획 생성 기법으로 사용될 수 있다.