• 제목/요약/키워드: Spark Problem

검색결과 54건 처리시간 0.03초

Image-based Subway Security System by Histogram Projection Technology

  • Bai, Zhiguo;Jung, Sung-Hwan
    • 한국멀티미디어학회논문지
    • /
    • 제18권3호
    • /
    • pp.287-297
    • /
    • 2015
  • A railway security detection system is very important. There are many safety factors that directly affect the safe operation of trains. Security detection technology can be divided into passive and active approaches. In this paper, we will first survey the railway security systems and compare them. We will also propose a subway security detection system with computer vision technology, which can detect three kinds of problems: the spark problem, the obstacle problem, and the lost screw problem. The spark and obstacle detection methods are unique in our system. In our experiment using about 900 input test images, we obtained about a 99.8% performance in F- measure for the spark detection problem, and about 94.7% for the obstacle detection problem.

대규모 협동진화 차등진화 (Large Scale Cooperative Coevolution Differential Evolution)

  • 신성윤;탄쉬지에;신광성;이현창
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국정보통신학회 2022년도 춘계학술대회
    • /
    • pp.665-666
    • /
    • 2022
  • 미분 진화는 연속 최적화 문제에 대한 효율적인 알고리즘이다. 그러나 대규모 최적화 문제를 해결하기 위해 미분 진화를 적용하면 성능이 빠르게 저하되고 런타임이 기하급수적으로 증가한다. 이 문제를 극복하기 위해 Spark(SparkDECC라고 함)를 기반으로 하는 새로운 협력 공진화 미분 진화를 제안한다. 분할 정복 전략은 SparkDECC에서 사용된다.

  • PDF

Cooperative Coevolution Differential Evolution Based on Spark for Large-Scale Optimization Problems

  • Tan, Xujie;Lee, Hyun-Ae;Shin, Seong-Yoon
    • Journal of information and communication convergence engineering
    • /
    • 제19권3호
    • /
    • pp.155-160
    • /
    • 2021
  • Differential evolution is an efficient algorithm for solving continuous optimization problems. However, its performance deteriorates rapidly, and the runtime increases exponentially when differential evolution is applied for solving large-scale optimization problems. Hence, a novel cooperative coevolution differential evolution based on Spark (known as SparkDECC) is proposed. The divide-and-conquer strategy is used in SparkDECC. First, the large-scale problem is decomposed into several low-dimensional subproblems using the random grouping strategy. Subsequently, each subproblem can be addressed in a parallel manner by exploiting the parallel computation capability of the resilient distributed datasets model in Spark. Finally, the optimal solution of the entire problem is obtained using the cooperation mechanism. The experimental results on 13 high-benchmark functions show that the new algorithm performs well in terms of speedup and scalability. The effectiveness and applicability of the proposed algorithm are verified.

SparkR을 이용한 R 기반 빅데이터 분석의 분산 처리 (Distributed Processing of Big Data Analysis based on R using SparkR)

  • 류우석
    • 한국전자통신학회논문지
    • /
    • 제17권1호
    • /
    • pp.161-166
    • /
    • 2022
  • 본 논문에서는 데이터 분석 도구인 R을 이용하여 빅데이터 분석을 수행할 때 발생하는 문제점을 분석하고, 빅데이터의 분산 처리를 효과적으로 지원하는 스파크와 R을 연계한 SparkR을 이용한 분석의 유용성을 제시하고자 한다. 먼저, 대량의 데이터를 로딩하고 연산을 수행할 때 발생하는 R의 메모리 할당 문제점과 R과 비교한 SparkR의 특징 및 프로그래밍 환경을 분석한다. 그리고, 선형 회귀 분석을 각각의 환경에서 수행할 때의 실행 성능을 비교 분석한다. 분석 결과 SparkR을 통해 추가적인 언어 학습 없이도 R을 그대로 이용하여 데이터 분석에 활용할 수 있음을 보였으며, SparkR을 이용하여 R로 작성된 코드를 클러스터 내 노드 수의 증가에 따라 효과적으로 분산 처리할 수 있었다.

Distributed Indexing Methods for Moving Objects based on Spark Stream

  • Lee, Yunsou;Song, Seokil
    • International Journal of Contents
    • /
    • 제11권1호
    • /
    • pp.69-72
    • /
    • 2015
  • Generally, existing parallel main-memory spatial index structures to avoid the trade-off between query freshness and CPU cost uses light-weight locking techniques. However, still, the lock based methods have some limits such as thrashing which is a well-known problem in lock based methods. In this paper, we propose a distributed index structure for moving objects exploiting the parallelism in multiple machines. The proposed index is a lock free multi-version concurrency technique based on the D-Stream model of Spark Stream. The proposed method exploits the multiversion nature of D-Stream of Spark Streaming.

Web access prediction based on parallel deep learning

  • Togtokh, Gantur;Kim, Kyung-Chang
    • 한국컴퓨터정보학회논문지
    • /
    • 제24권11호
    • /
    • pp.51-59
    • /
    • 2019
  • 웹에서 정보 접근에 대한 폭발적인 주문으로 웹 사용자의 다음 접근 페이지를 예측하는 필요성이 대두되었다. 웹 접근 예측을 위해 마코브(markov) 모델, 딥 신경망, 벡터 머신, 퍼지 추론 모델 등 많은 모델이 제안되었다. 신경망 모델에 기반한 딥러닝 기법에서 대규모 웹 사용 데이터에 대한 학습 시간이 엄청 길어진다. 이 문제를 해결하기 위하여 딥 신경망 모델에서는 학습을 여러 컴퓨터에 동시에, 즉 병렬로 학습시킨다. 본 논문에서는 먼저 스파크 클러스터에서 다층 Perceptron 모델을 학습 시킬 때 중요한 데이터 분할, shuffling, 압축, locality와 관련된 기본 파라미터들이 얼마만큼 영향을 미치는지 살펴보았다. 그 다음 웹 접근 예측을 위해 다층 Perceptron 모델을 학습 시킬 때 성능을 높이기 위하여 이들 스파크 파라미터들을 튜닝 하였다. 실험을 통하여 논문에서 제안한 스파크 파라미터 튜닝을 통한 웹 접근 예측 모델이 파라미터 튜닝을 하지 않았을 경우와 비교하여 웹 접근 예측에 대한 정확성과 성능 향상의 효과를 보였다.

저압 배전선로의 누전 및 배선용 차단기의 오동작 방지를 위한 고속형 전기안전 보호장치 (Electric Safety Protection Device of High Speed for Incapable Operation of ELB and MCCB Using the Low Voltage Distribution Line)

  • 곽동걸;정도영
    • 전기학회논문지
    • /
    • 제56권11호
    • /
    • pp.1925-1929
    • /
    • 2007
  • This paper is studied on a novel Electric Safety Protection Device (ESPD) of high speed for incapable operation of Earth Leakage Circuit Breaker (ELB) and Molded_case Circuit Breaker (MCCB) using the low voltage distribution line. The major causes of electrical fire are classified to short circuit fault, overload fault, electric leakage and electric contact failure. The occurrence factor of the fire is electric arc or spark accompanied with electrical faults. Residual Current Protective Device (RCD), that is ELB and MCCB, of high sensitivity type used at low voltage wiring cuts off earth leakage and overload, but the RCD can't cut off electric arc or spark to be a major factor of electrical fire. As the RCDs which are applied low voltage distribution panel are prescribed to rated breaking time about 30[ms] (KS C 4613), the RCDs can't perceive to the periodic electric arc or spark of more short wavelength level. To be improved on such problem, this research development is proposed to a novel ESPD of high speed to trip of distribution line on electric arc or spark due to electrical fire. Some experimental results of the proposed ESPD are confirmed to the validity of the analytical results.

스파크 플라즈마 소결공정의 전산모사(1부 : 수식화) (Computer aided simulation of spark plasma sintering process (Part 1 : formulation))

  • 금영탁;전종훈
    • 한국결정성장학회지
    • /
    • 제16권1호
    • /
    • pp.38-42
    • /
    • 2006
  • 본 1부 연구에서는 스파크 플라스마 열에 의한 그린 세라믹의 소결에서 열전달 및 가압력으로 인한 상대밀도의 변화를 유한요소법(FEM)으로 해석하고 그 결과에 따른 입자성장을 몬테카를로법(MCM)을 이용하여 전산모사하는 방법을 제시하기 위하여 SPS의 FEH 해석과 MCM 해석의 이론적 배경을 기술한다.

k-NN Join Based on LSH in Big Data Environment

  • Ji, Jiaqi;Chung, Yeongjee
    • Journal of information and communication convergence engineering
    • /
    • 제16권2호
    • /
    • pp.99-105
    • /
    • 2018
  • k-Nearest neighbor join (k-NN Join) is a computationally intensive algorithm that is designed to find k-nearest neighbors from a dataset S for every object in another dataset R. Most related studies on k-NN Join are based on single-computer operations. As the data dimensions and data volume increase, running the k-NN Join algorithm on a single computer cannot generate results quickly. To solve this scalability problem, we introduce the locality-sensitive hashing (LSH) k-NN Join algorithm implemented in Spark, an approach for high-dimensional big data. LSH is used to map similar data onto the same bucket, which can reduce the data search scope. In order to achieve parallel implementation of the algorithm on multiple computers, the Spark framework is used to accelerate the computation of distances between objects in a cluster. Results show that our proposed approach is fast and accurate for high-dimensional and big data.

접속·접촉불량 사고에 의한 전기화재 방지용 보호장치에 관한 연구 (A Study on Protection Device for Electrical Fire Prevention on Joint/Contact Badness Faults)

  • 최정규;곽동걸;이승철;이봉섭;박영직
    • 전력전자학회:학술대회논문집
    • /
    • 전력전자학회 2014년도 전력전자학술대회 논문집
    • /
    • pp.5-6
    • /
    • 2014
  • According to 2013 fire statistical yearbook in the National Emergency Management Agency, the main cause of an electrical fire are classified to short circuit fault, overload fault, electric leakage, partial disconnection, and joint/contact badness. The occurrence factor of fire is electric arc or spark accompanied with electrical faults. Residual Current Protective Devices(RCDs) of high sensitivity type used at single phase (220V) cut off earth leakage and overload but the RCDs can not cut off electric arc or spark to be a main cause of electrical fire. To be improved on such problem, this thesis is proposed to a auxiliary control device for RCD cut off electric arc or spark.

  • PDF