• 한국정보통신학회논문지
• /
• 제18권9호
• /
• pp.2087-2093
• /
• 2014

본 논문에서는 압축적으로 센싱된 희소 신호를 복원하기 위한 유전 알고리듬(GA)에 기반한 직교 정합 추구 방법(GAOMP)을 제안한다. 최근에 제안된 SP, CoSaMP, gOMP 등은 매 반복 단계에서 부적절한 atom을 제거하여 희소 신호의 복원 성능을 개선하였다. 그러나 support set이 국소 최저에 빠져 신호 복원에 실패하는 경우가 발생한다. 제안된 GAOMP는 유전 알고리듬의 중요 연산자인 변이를 통해 support set이 국소 최저를 벗어날 수 있도록 도와주어 희소 신호의 복원 성능을 향상시킨다. 모의 실험을 통해 GAOMP가 여러 OMP 기반 알고리듬과 $l_1$ 최적화보다 우수한 신호 복원 성능을 보임을 알 수 있다.

• Steel and Composite Structures
• /
• 제50권5호
• /
• pp.583-594
• /
• 2024

In this paper, a Guided Simulated Annealing (GSA) algorithm is presented to optimize 2D and 3D steel frames against Progressive Collapse. Considering the nature of structural optimization problems, a number of restrictions and improvements have been applied to the decision mechanisms of the algorithm without harming the randomness. With these improvements, the algorithm aims to focus relatively on the flawed variables of the analyzed frame. Besides that, it is intended to be more rational by instituting structural constraints on the sections to be selected as variables. In addition to the LRFD restrictions, the alternate path method with nonlinear dynamic procedure is used to assess the risk of progressive collapse, as specified in the US Department of Defense United Facilities Criteria (UFC) Design of Buildings to Resist Progressive Collapse. The entire optimization procedure was carried out on a C# software that supports parallel processing developed by the authors, and the frames were analyzed in SAP2000 using OAPI. Time history analyses of the removal scenarios are distributed to the processor cores in order to reduce computational time. The GSA produced 3% lighter structure weights than the SA (Simulated Annealing) and 4% lighter structure weights than the GA (Genetic Algorithm) for the 2D steel frame. For the 3D model, the GSA obtained 3% lighter results than the SA. Furthermore, it is clear that the UFC and LRFD requirements differ when the acceptance criteria are examined. It has been observed that the moment capacity of the entire frame is critical when designing according to UFC.

• 산업경영시스템학회지
• /
• 제40권2호
• /
• pp.92-98
• /
• 2017

Data clustering determines a group of patterns using similarity measure in a dataset and is one of the most important and difficult technique in data mining. Clustering can be formally considered as a particular kind of NP-hard grouping problem. K-means algorithm which is popular and efficient, is sensitive for initialization and has the possibility to be stuck in local optimum because of hill climbing clustering method. This method is also not computationally feasible in practice, especially for large datasets and large number of clusters. Therefore, we need a robust and efficient clustering algorithm to find the global optimum (not local optimum) especially when much data is collected from many IoT (Internet of Things) devices in these days. The objective of this paper is to propose new Hybrid Simulated Annealing (HSA) which is combined simulated annealing with K-means for non-hierarchical clustering of big data. Simulated annealing (SA) is useful for diversified search in large search space and K-means is useful for converged search in predetermined search space. Our proposed method can balance the intensification and diversification to find the global optimal solution in big data clustering. The performance of HSA is validated using Iris, Wine, Glass, and Vowel UCI machine learning repository datasets comparing to previous studies by experiment and analysis. Our proposed KSAK (K-means+SA+K-means) and SAK (SA+K-means) are better than KSA(K-means+SA), SA, and K-means in our simulations. Our method has significantly improved accuracy and efficiency to find the global optimal data clustering solution for complex, real time, and costly data mining process.

• 한국가스학회지
• /
• 제19권1호
• /
• pp.28-37
• /
• 2015

본 연구에서는 고속의 연산이 가능한 인공신경망 시뮬레이터와 SA 알고리즘을 결합하여 지능형 생산정 위치 최적화 전산 모델을 개발하였다. 기존의 사용하는 상용시뮬레이터의 경우 현장 규모의 저류 전산 시뮬레이션을 수행시 시간이 많이 소모되므로 이를 해결하기 위하여 이 모델에서는 인공신경망을 사용하여 짧은 시간내에 시뮬레이션을 수행할 수 있도록 하였다. 이렇게 얻은 결과를 주관적인 경험에 의거하지 않고 자동으로 최적의 생산정 위치를 선정할 수 있도록 최적화기법인 SA 알고리즘을 적용하였다. 개발된 모델을 사용하여 얻은 결과를 기존 사용 시뮬레이터와 비교하여 예측성능이 양호함을 검증할 수 있었으며, 연산속도 또한 향상됨을 확인하였다. 특히 SA 최적화 알고리즘의 제어변수인 초기온도와 냉각률에 대한 민감도분석을 실시하여 각각에 대한 최적값을 산출하였으며, 이를 통해 개발한 모델의 연산성능을 향상시킬 수 있었다. 마지막으로 개발된 모델을 사용하여 생산정 위치 최적화를 수행한 결과, 생산성이 우수한 지역을 선정하여 최적의 생산정 위치를 도출하였다.

• 전자공학회논문지
• /
• 제51권3호
• /
• pp.75-81
• /
• 2014

디지털 영상의 배포에서, 저작권 침해자에 의해 영상이 불법으로 위 변조되어 유통되는 심각한 문제가 대두되어 있다. 이러한 문제를 해결하기 위하여, 본 논문에서는 위 변조된 디지털 영상의 에지 에너지 정보를 이용한 영상 포렌식 판정 알고리즘을 제안한다. 제안된 알고리즘은 SA (Streaking Artifacts)와 SPAM (Subtractive Pixel Adjacency Matrix)을 이용하여, 원 영상의 JPEG 압축률 (QF=90, 70, 50, 30)에 따른 에지정보와 질의영상의 에지정보를 추출하고, 이를 각각 비교하여 위 변조 여부를 판정한다. 원 영상과 질의영상의 에지정보 매칭은 JPEG 압축률 조합의 임계치 (TCJCR : Threshold by Combination of JPEG Compression Ratios)에 따라 이루어진다. 실험을 통하여, TP (True Positive)와 FN (False Negative)은 87.2%와 13.8%이며, 산출된 최소평균 판정 에러는 0.1349이다. 그리고 제안된 알고리즘의 성능평가에서 민감도 (Sensitivity)와 1-특이도(1-Specificity)의 AUROC (Area Under Receiver Operating Characteristic) 커브 면적은 0.9388로 'Excellent(A)' 등급임을 확인하였다.

• 제어로봇시스템학회논문지
• /
• 제8권5호
• /
• pp.425-433
• /
• 2002

After the removal of SA (Selective Availability), horizontal accuracy of 25m(2dRMS) is easily obtained using GPS (Global Positioning System). In this paper, the error characteristics without SA are analyzed and a navigation algorithm concerns this error characteristics is proposed to further improve the accuracy. The proposed method utilizes the relationship between elevation angle and errors that are remained after ionospheric and troposheric delay compensation. The relationship is derived from real measurements and used as a weighting matrix of weighted least squares estimator. Furthermore, a RAIM (Receiver Autonomous Integrity Monitoring) technique is included to remove abnormal measurements affected by multi-path or low SNR (Signal-to-Noise Ratio). It is shown that using the proposed method, more than 4 times accurate result, which is comparable with DGPS (Differential GPS), can be obtained from experiments with real data. Besides accuracy and reliability, the proposed method reduces large jumps in position and maintains better performance than a method using mask angle to completely remove satellites below this mask angle. Thus it is expected that the proposed method can be efficiently applied to land navigation where some satellites are blocked by building or forest.

• 대한원격탐사학회지
• /
• 제18권3호
• /
• pp.147-153
• /
• 2002

The real-time reception and recording of down-link mission data from a satellite requires the highest reliability because the data lost in receiving process cannot be recovered. The data receiving and recording system has moved from a set of dedicated hardware and software components to commercial-off-the-shelf (COTS) components in order to reduce the system cost as well as to upgrade the system easily for handling other satellite data. The use of COTS hardware and middleware components prevents the system developer from correcting or modifying the internal operations of the COTS components, and hence, instant performance degradation of the COTS components which affects the reliable data acquisition must be covered by a software algorithm. This paper introduces the instant performance problem of a COTS data recording device which leads to the data loss in the real-time data reception and recording process. As a result, the requirement of the modification of the conventional data read/write technique is issued. In order to overcome the data loss problem due to the use of COTS components and the conventional software technique, a new algorithm called a software buffering technique is proposed. The experiments show that the application of the proposed technique results in reliable real-time reception and recording of high speed serial data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4372-4394
• /
• 2020

The distribution of popular videos incurs a large amount of traffic at the base stations (BS) of networks. Device-to-multi-device (D2MD) communication has emerged an efficient radio access technology for offloading BS traffic in recent years. However, traditional studies have focused on synchronous user requests whereas asynchronous user requests are more common. Hence, offloading BS traffic in case of asynchronous user requests while considering their time-varying characteristics and the quality of experience (QoE) of video request users (VRUs) is a pressing problem. This paper uses social stability (SS) and video loading duration (VLD)-tolerant property to group VRUs and seed users (SUs) to offload BS traffic. We define the average amount of data transmission (AADT) to measure the network's capacity for offloading BS traffic. Based on this, we formulate a time-varying bipartite graph matching optimization problem. We decouple the problem into two subproblems which can be solved separately in terms of time and space. Then, we propose the socially aware D2MD user selection (SA-D2MD-S) algorithm based on finite horizon optimal stopping theory, and propose the SA-D2MD user matching (SA-D2MD-M) algorithm to solve the two subproblems. The results of simulations show that our algorithms outperform prevalent algorithms.

• 대한전자공학회논문지SD
• /
• 제45권2호
• /
• pp.93-100
• /
• 2008

본 논문에서는 NoC 기반 SoC의 테스트 시간을 감소시키기 위하여 NoC를 TAM으로 재활용하는 구조를 바탕으로 하는 새로운 형태의 스케줄링 알고리즘을 제안한다. 제안한 방식에서는 기존 연구된 NoC 테스트 플랫폼을 사용하여 스케줄링 문제를 rectangle packing 문제로 변환하고 이를 simulated annealing(SA) 기법을 적용하여 향상된 스케줄링 결과를 유도한다. ITC'02 벤치회로를 이용한 실험 결과 제안한 방법이 기존 방법에 비해 최대 2.8%까지 테스트 시간을 줄일 수 있음을 확인하였다.

• 전자공학회논문지A
• /
• 제33A권7호
• /
• pp.65-75
• /
• 1996

The probability distributio function (pdf) of transmitted symbols should be asymmectric for recovering the received data in the 3rd order blind equalizer system. In this paper, we hav edesigned the blind equalizer using symmetric-asymmetric (SA) and asymmetric-symmetric (AS) transforms for less computational complexities and robustness in the noisy environments. The method of SA and AS transform was peformed using natural logarithmic operation. This paper proves that the proposed in this paper can be performed as real time operation. This paper proves that the compression factor k has no effet on transmitted symbols. Also 3rd order equalization method proposed in this paper can be performed as real time operation. As a result of computer simulatio, the computational complexity of proposed algorithm is reduced to be an half of 4th order method and MSE is enhanced as 10dB at the case of 4-PAM and 15dB at the case of 8-PAM respectivley. Conclusively, we have found that 3rd order blind equalizer can be implemented when the pdf of transmitter is asymmetric.