• ETRI Journal
• /
• 제27권5호
• /
• pp.533-538
• /
• 2005

We developed a pipelined scheduling technique of functional hardware and software modules for platform-based system-on-a-chip (SoC) designs. It is based on a modified list scheduling algorithm. We used the pipelined scheduling technique for a performance analysis of an MPEG4 video encoder application. Then, we applied it for architecture exploration to achieve a better performance. In our experiments, the modified SoC platform with 6 pipelines for the 32-bit dual layer architecture shows a 118% improvement in performance compared to the given basic SoC platform with 4 pipelines for the 16-bit single-layer architecture.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권2호
• /
• pp.835-838
• /
• 2016

Background: Lung cancer remains one of the most common cancers in the world, both in terms of new cases (about 13% of total per year) and deaths (nearly one cancer death in five), because of the high case fatality. Errors in lung cancer type or malignant growth determination lead to degraded treatment efficacy, because anticancer strategy depends on tumor morphology. Materials and Methods: We have made an attempt to evaluate effectiveness of machine learning algorithms in the task of lung cancer classification based on gene expression levels. We processed four publicly available data sets. The Dana-Farber Cancer Institute data set contains 203 samples and the task was to classify four cancer types and sound tissue samples. With the University of Michigan data set of 96 samples, the task was to execute a binary classification of adenocarcinoma and non-neoplastic tissues. The University of Toronto data set contains 39 samples and the task was to detect recurrence, while with the Brigham and Women's Hospital data set of 181 samples it was to make a binary classification of malignant pleural mesothelioma and adenocarcinoma. We used the k-nearest neighbor algorithm (k=1, k=5, k=10), naive Bayes classifier with assumption of both a normal distribution of attributes and a distribution through histograms, support vector machine and C4.5 decision tree. Effectiveness of machine learning algorithms was evaluated with the Matthews correlation coefficient. Results: The support vector machine method showed best results among data sets from the Dana-Farber Cancer Institute and Brigham and Women's Hospital. All algorithms with the exception of the C4.5 decision tree showed maximum potential effectiveness in the University of Michigan data set. However, the C4.5 decision tree showed best results for the University of Toronto data set. Conclusions: Machine learning algorithms can be used for lung cancer morphology classification and similar tasks based on gene expression level evaluation.

• 대한안전경영과학회지
• /
• 제7권5호
• /
• pp.1-8
• /
• 2005

The consequences of rapid industrial advancement, diversified types of business and unexpected industrial accidents have caused a lot of damage to many unspecified persons both in a human way and a material way Although various previous studies have been analyzed to prevent industrial accidents, these studies only provide managerial and educational policies using frequency analysis and comparative analysis based on data from past industrial accidents. The main objective of this study is to find an optimal algorithm for data analysis of industrial accidents and this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. Enterprise Miner of SAS and AnswerTree of SPSS will be used to evaluate the validity of the results of the four algorithms. The sample for this work chosen from 19,574 data related to construction industries during three years ($2002\sim2004$) in Korea.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2011년도 추계학술대회
• /
• pp.301-302
• /
• 2011

본 논문에서는 리튬 폴리머 배터리($LiFePO_4/C$)의 개방전압(OCV;open-circuit voltage) 히스테리시스 특성을 이용한 확장 칼만 필터(EKF;extended Kalman filter) 기반 state-of-charge(SOC) 추정방법을 소개한다. 배터리 등가회로의 중요 요소인 OCV 모델링을 위해 충전 및 방전 각각의 OCV 히스테리시스 특성을 고려하였고 더불어 OCV-SOC 관계의 SOC 간격을 10%에서 5%로 조정하여 EKF 기반 SOC 추정알고리즘의 성능이 향상되었다. 축소된 하이브리드 자동차용 전류프로파일을 적용했을 때 SOC 추정이 잘 이루어지지 않는 영역은 EKF의 측정방정식에 노이즈 모델 및 데이터 리젝션(data rejection)을 구축하였다. 제안된 방법을 이용하여 SOC 추정결과 전류적산법 대비 5%이내의 SOC 추정에러를 만족하였다.

• Journal of Electrical Engineering and Technology
• /
• 제5권4호
• /
• pp.597-605
• /
• 2010

This paper presents a contribution to parameter identification of a non-linear system using a new strategy to improve the genetic algorithm (GA) method. Since cost function plays an important role in GA-based parameter identification, we propose to improve the simple version of GA, where weights of the cost function are not taken as constant values, but varying along the procedure of parameter identification. This modified version of GA is applied to the induction motor (IM) as an example of nonlinear system. The GA cost function is the weighted sum of stator current and rotor speed errors between the plant and the model of induction motor. Simulation results show that the identification method based on improved GA is feasible and gives high precision.

• 한국통신학회논문지
• /
• 제33권10B호
• /
• pp.845-854
• /
• 2008

센서 네트워크에서의 센서 노드는 특성상 제한된 에너지를 가지고 있어 다양한 네트워크 환경을 갖는 유비쿼터스 컴퓨팅 환경에서 그 활용 범위가 제한되는 문제를 가지고 있다. 본 논문에서는 센서 네트워크의 효율적 에너지 관리를 위한 클러스터링 알고리즘을 제안하였다. 제안한 알고리즘은 기존의 LEACH-C 알고리즘이 고려하지 않은 또 다른 에너지 소비 요소인 센싱 파워를 제어함으로써 에너지 효율을 개선하며, 다양한 네트워크 환경에 적용 가능한 특징을 갖는다. 제안한 알고리즘은 IEEE 802.15.4 기반의 ZigBee 기술과 더불어 다양한 네트워크 환경을 갖는 유비쿼터스 컴퓨팅 환경에 적용하여 기존 알고리즘 보다 에너지 효율적 측면에서 우수한 성능을 보여주는데, 작게는 센서 노드의 생존 시간과 크게는 센서 네트워크의 생존 시간 향상을 가져오는 것을 알 수 있으며, 빠르게 변화하는 네트워크 환경에 센서 네트워크 기술의 활용 범위를 보다 확대 할 수 있을 것이다.

• 한국정보처리학회논문지
• /
• 제5권1호
• /
• pp.202-214
• /
• 1998

명령어 수준에서 병렬성(Instruction-Level Parallelism, ILP)을 추출하는 것은 슈퍼스칼라 및 VLIW프로세서들의 성능 개선을 위한 효과적인 메커니즘이다. 이를 위하여 여러 가지 소프트웨어 기법들이 응용될 수 있다. 이들 기법 중 조건실행(predicated execution)은 명령어의 조건으로 참조되는 부울 소스 오퍼랜드의 값을 기본으로 명령어 조건적 실행 여부를 참조하여 분기명령을 제거함으로서 여러 기본 블록의 명령들을 하나의 기본블록으로 구성하여 ILP를 증가시키는 기법이다. 본 논문은 조건실행을 지원하는 ILP프로세서들의 성능개선을 위하여 기본 블록을 넘어선 광역 조건실행 지원 스케쥴링 알고리듬(global predicate-sensitive scheduling algorithm)을 제안한다. 또한 C 컴파일러와 시뮬레이터를 개발하고 다양한 벤치마크 프로그램에 대하여 제안된 알고리듬의 성능을 측정하고 타당성을 확인한다. 1, 2, 4이슈실행에 대한 성능 측정 결과, 평균 20%의 성능 개선이 확인되었다.

• 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.

• Journal of the Korean Data and Information Science Society
• /
• 제16권2호
• /
• pp.195-205
• /
• 2005

In decision tree analysis, C4.5 and CART algorithm have some problems of computational complexity and bias on variable selection. But QUEST algorithm solves these problems by dividing the step of variable selection and split point selection. When input variables are continuous, QUEST algorithm uses ANOVA F-test under the assumption of normality and homogeneity of variances. In this paper, we investigate the influence of violation of normality assumption and effect of the transformation of variables in the QUEST algorithm. In the simulation study, we obtained the empirical powers of variable selection and the empirical bias of variable selection after transformation of variables having various type of underlying distributions.

• 반도체디스플레이기술학회지
• /
• 제14권4호
• /
• pp.30-37
• /
• 2015

This research aims to develop Look Ahead position interpolation algorithm for small size CNC machine controlled by PC based controller. Look Ahead scheme can process a bundle of CNC's linear interpolation commands simultaneously, which reduces acceleration and deceleration time within single linear interpolation command. The algorithm is derived as simple analytical form which can be adapted to PC based CNC system by C language programming. The performance of the algorithm was verified by tail stock machining G codes experimentally. The average traverse speed of the CNC machine was increased by 27.5% and the total traverse time also reduced by 27.2% with the Look Ahead scheme.