• 한국안전학회지
• /
• 제32권1호
• /
• pp.115-120
• /
• 2017

The aim of this study is to develop construction safety and health management cost prediction model using support vector machine (SVM). To this end, theoretical concept of SVM is investigated to formulate the cost prediction model. Input and output variables have been selected by analyzing the balancing accounts for the completed construction project. In order to train and validate the proposed prediction model, 150 data sets have been gathered from field. Effects of SVM parameters on prediction accuracy are analyzed and from which the optimal parameter values have been determined. The prediction performance tests are conducted to confirm the applicability of the proposed model. Based on the results, it is concluded that the proposed SVM model can effectively be used to predict the construction safety and health management cost.

• 소음진동
• /
• 제8권4호
• /
• pp.670-682
• /
• 1998

Ball type automatic balancer is used to reduce the vibration caused by unbalance of rotor. In this study, A analytic modeling of a front loaded washing machine with ball type automatic balancer has been suggested theoretically and ADAMS has been used to analyze the dynamic characteristics of automatic balancer. It is found from simulation and experimental results that the automatic balancer suppress the steady state vibration of washing machine effectively. The test results match with the simulation results of ADAMS, thereby the dynamic model of ADAMS can be used as virtual prototype to predict the vibration characteristics which could be changed by the modification of design variableand can reduce the design cycle sharphy. To maximize the balancing effect of automatic balancer, the friction between balls and race and the deviation between geometric center and rotation center of drum need to be minimized and the optimum design for the stiffness of flange shaft and the angular acceleration of drum should be achieved.

• 한국컴퓨터정보학회논문지
• /
• 제21권2호
• /
• pp.97-103
• /
• 2016

This paper deals with the cycle time minimization problem that determines the productivity in printed circuit board (PCB) with n components using the m placement machines. This is known as production cycle time determination problem (PCTDP). The polynomial time algorithm to be obtain the optimal solution has been unknown yet, therefore this hard problem classified by NP-complete. This paper gets the initial assignment result with the machine has minimum unit placement time per each component firstly. Then, the balancing process with reallocation from overhead machine to underhead machine. Finally, we perform the swap optimization and get the optimal solution of cycle time $T^*$ within O(mn) computational complexity. For experimental data, the proposed algorithm can be obtain the same result as integer programming+branch-and-bound (IP+B&B) and B&B.

• International journal of advanced smart convergence
• /
• 제7권3호
• /
• pp.15-22
• /
• 2018

Nowadays multiple control methods are used in robot control systems. A model, predictor or error estimator is often used as feedback controller to control a robot. While robots have become more and more intensive with algorithms capable to acquiring independent knowledge from raw data. This paper represents experimental results of real time machine learning control that does not require explicit knowledge about the plant. The controller can be applied on a broad range of tasks with different dynamic characteristics. We tested our controller on the balancing problem of a single propeller pendulum. Experimental results show that the use of a supervised machine learning algorithm in a single propeller pendulum allows the stable swing of a given angle.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1997년도 추계학술대회논문집; 한국과학기술회관; 6 Nov. 1997
• /
• pp.119-131
• /
• 1997

Ball type automatic balancer is used to reduce the vibration caused by unbalance of rotor. In this study, A analytic modeling of a front loaded washing machine with ball type automatic balancer has been suggested theoretically and ADAMS has been used to analyze the dynamic characteristics of automatic balancer. It is found from simulation and experimental results that the automatic balancer suppress the steady state vibration of the washing machine effectively. The test results match well with the simulation results of ADAMS, thereby the dynamic model of ADAMS can be used as virtual prototype to predict the vibration characteristics which could be changed by the modification of design variable and can reduce the design cycle sharply. To maximize the balancing effect of automatic balancer, the friction between balls and race and the deviation between geometric center and rotation center of drum need to be minimized and the optimum design for the stiffness of flange shaft and the angular acceleration of drum should be achieved.

• 한국컴퓨터그래픽스학회논문지
• /
• 제1권2호
• /
• pp.213-225
• /
• 1995

3 차원 볼륨 데이터를 시각화(visualization)하기 위해서는 많은 계산 량과 메모리 량을 필요로 한다. 단일컴퓨터에서 순차 알고리즘을 이용하여 데이터를 시각화하고 분석하는 것은 실시간 응용 프로그램에는 부적합하다. 기존의 병렬 볼륨 렌더링에서의 데이터 분할 방법은 대부분 정적 로드 밸런싱(static load balancing)에 기반하고 있다. 동적 로드 밸런싱에 기반한 기존의 방법들은 불륨 데이터의 정규성(regularity)을 이용할 수 없다는 단점이 있다. 본 연구에서는 3 차원 볼륨 데이터에 대하여 로컬 태스크 큐(local task queue) 기법에 기반한 새로운 로드밸런싱 알고리즘을 제안한다. 제안한 방법은 계산에 참여할 노드(node)들을 PVM(parallel virtual machine)의 동적 프로세스 그룹(dynamic process group: DPG)을 이용하여 정적으로 그룹화(grouping)한다. 각각의 DPG들은 로컬 태스크 큐를 기반으로 단위 서브-블록에 대하여 동적 로드 밸런싱을 수행한다. 최적화된 레이 캐스팅 알고리즘들을 분산 환경에 새롭게 적용함으로써 로드 밸런싱으로 생길 수 있는 오버 헤드를 최소화하였다.

• 한국정보과학회논문지:시스템및이론
• /
• 제35권12호
• /
• pp.568-575
• /
• 2008

서버 가상화 기술에 의한 서버 통합은 효율적인 자원 사용에 따른 비용적인 장점이 있다. 그러나 하나의 물리적 장치에 여러 개의 서버가 가상머신으로 함께 동작함으로써 더욱 복잡한 부하특성을 가지게 되었다. 따라서 이를 해결하기 위한 효율적인 자원관리 방법이 요구된다. 이러한 문제에 대한 해결방법으로 제안된 것이 가상머신 이동(live migration)[1,2]을 이용한 가상머신 동적 재배치 기법이다[3,4]. 본 논문은 가상머신 동적 재배치 알고리즘에 있어서 각 자원요소(CPU, network I/O, memory)들의 활용률을 다차원 공간상에서 분석하여 조율함으로써 서버통합의 자원 효율성을 증가시키는 방법(Server consolidation optimizing algorithm)을 제안하고 있다. 실험을 위해서 여러 대의 통합서버와 수많은 서비스를 생성하여야 하는 어려움이 있기 때문에 본 논문에서는 기업환경에서의 서버 가상화 프로젝트 경험을 바탕으로 서버의 부하변화와 유사한 패턴의 모니터링 데이타들을 정의하여 수치적인 시뮬레이션을 통해 sandpiper[3]와 SCOA 알고리즘의 부하 균형에 대한 효율성을 비교하였다.

• 한국정밀공학회지
• /
• 제29권2호
• /
• pp.156-160
• /
• 2012

Recently, the demands of the large scale machine tools gradually increase to machine the large parts, such as large scale crankshaft, yaw and pitch bearings for the wind power generator and the vehicle or aircraft components. But the high technology is necessary in order to develop the huge machine tools. Furthermore, the global market of it has been monopolized by a few companies. So, we need to develop the large scale machine tools and study its core technology to rush into the increasing market. In this study, we carried out the researches for the important core technology of a multi-tasking, machine tool; a large scale 5-axis machine tool of gantry type for multi-task machining. This study is focused on the design of large size gantry type multi-axis machine. In the case of large size of machine the cross rail deflection in the X-axis is significant. To reduce the deflection due to the eccentric spindle head, a special hollow type design in the cross rail with outside ram is adapted in this study. Also, the Zig-Zag motion in the Y-axis is inevitable with the gantry geometry, which is by the un-balancing, different motion at the left and the right columns moving. We tried to reduce the influence of Zig-Zag motion using FEM with different loading conditions at the left and the right side column.

• 한국콘텐츠학회논문지
• /
• 제16권7호
• /
• pp.667-680
• /
• 2016

하둡 맵리듀스와 같은 분산 컴퓨팅 플랫폼이 개발됨에 따라, 기존 단일 컴퓨터 상에서 수행되는 질의 처리 기법을 분산 컴퓨팅 환경에서 효율적으로 수행하는 것이 필요하다. 특히, 주어진 두 데이터 집합에서 유사도가 높은 모든 데이터 쌍을 탐색하는 유사 조인 질의를 분산 컴퓨팅 환경에서 수행하려는 연구가 있어 왔다. 그러나 분산 병렬 환경에서의 기존 유사 조인 질의처리 기법은 데이터 전송 비용만을 고려하기 때문에 클러스터 간에 비균등 연산 부하 분산의 문제점이 존재한다. 본 논문에서는 분산 컴퓨팅 환경에서 효율적인 유사 조인 처리를 위한 행렬 기반 부하 분산 알고리즘을 제안한다. 제안하는 알고리즘은 클러스터의 균등 부하 분산을 위해 행렬을 이용하여 예상되는 연산 부하를 측정하고 이에 따라 파티션을 생성한다. 아울러, 클러스터에서 질의 처리에 사용되지 않는 데이터를 필터링함으로서 연산 부하를 감소시킨다. 마지막으로 성능 평가를 통해 제안하는 알고리즘이 기존 기법에 비해 질의 처리 성능 측면에서 우수함을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.3093-3115
• /
• 2020

Network anomaly detection system plays an essential role in detecting network anomaly and ensuring network security. Anomaly detection system based machine learning has become an increasingly popular solution. However, due to the unbalance and high-dimension characteristics of network traffic, the existing methods unable to achieve the excellent performance of high accuracy and low false alarm rate. To address this problem, a new network anomaly detection method based on data balancing and recursive feature addition is proposed. Firstly, data balancing algorithm based on improved KNN outlier detection is designed to select part respective data on each category. Combination optimization about parameters of improved KNN outlier detection is implemented by genetic algorithm. Next, recursive feature addition algorithm based on correlation analysis is proposed to select effective features, in which a cross contingency test is utilized to analyze correlation and obtain a features subset with a strong correlation. Then, random forests model is as the classification model to detection anomaly. Finally, the proposed algorithm is evaluated on benchmark datasets KDD Cup 1999 and UNSW_NB15. The result illustrates the proposed strategies enhance accuracy and recall, and decrease the false alarm rate. Compared with other algorithms, this algorithm still achieves significant effects, especially recall in the small category.