• Title/Summary/Keyword: 순차적 배치 데이터

Search Result 12, Processing Time 0.034 seconds

Classification of large-scale data and data batch stream with forward stagewise algorithm (전진적 단계 알고리즘을 이용한 대용량 데이터와 순차적 배치 데이터의 분류)

  • Yoon, Young Joo
    • Journal of the Korean Data and Information Science Society
    • /
    • v.25 no.6
    • /
    • pp.1283-1291
    • /
    • 2014
  • In this paper, we propose forward stagewise algorithm when data are very large or coming in batches sequentially over time. In this situation, ordinary boosting algorithm for large scale data and data batch stream may be greedy and have worse performance with class noise situations. To overcome those and apply to large scale data or data batch stream, we modify the forward stagewise algorithm. This algorithm has better results for both large scale data and data batch stream with or without concept drift on simulated data and real data sets than boosting algorithms.

Process-level integration method for performance improvement of large scaled batch data processing in EAI environment (EAI에서 대용량 배치 데이터의 통합 성능 향상을 위한 Process-level 방식)

  • Kim Yonghee;Kwon Juhum
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2004.11a
    • /
    • pp.19-22
    • /
    • 2004
  • 분산 시스템 환경에서 여러 시스템에 정보를 전송하기 위한 방법으로 최근 EAI 의 DB Trigger 및 Redo Log 등을 이용한 실시간 데이터 통합 방식을 적용해 왔다. 그러나 기업에서 순차적인 배치 프로세스들을 통해 처리하는 대량의 데이터에 대해 기존의 EAI 의 데이터 통합 방식을 사용할 경우 모든 변경 건수에 대해 이벤트가 발생하여 Source 시스템의 부하 및 통합 성능상의 문제점이 있다. 본 논문에서는 순차적인 배치 프로세스들을 EAI 의 프로세스 레벨 통합을 적용하여 최종 변경된 데이터에 대해서만 통합하도록 하여 통합 처리 시간을 단축할 수 있는 방법을 제시하고자 한다.

  • PDF

Mining Sequential Patterns Using Multi-level Linear Location Tree (단계 선형 배치 트리를 이용한 순차 패턴 추출)

  • 최현화;이동하;이전영
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2003.10b
    • /
    • pp.70-72
    • /
    • 2003
  • 대용량 데이터베이스로부터 순차 패턴을 발견하는 문제는 지식 발견 또는 데이터 마이닝(Data Mining) 분야에서 주요한 패턴 추출 문제이다. 순차 패턴은 추출 기법에 있어 연관 규칙의 Apriori 알고리즘과 비슷한 방식을 사용하며 그 과정에서 시퀀스는 해쉬 트리 구조를 통해 다루어 진다. 이러한 해쉬 트리 구조는 항목들의 정렬과 데이터 시퀀스의 지역성을 무시한 저장 구조로 단순 검색을 통한 다수의 복잡한 포인터 연산수행을 기반으로 한다. 본 논문에서는 이러한 해쉬 트리 구조의 단정을 보완한 다단게 선형 배치 트리(MLLT, Multi-level Linear Location Tree)를 제안하고, 다단계 선형 배치 트리를 이용한 효율적인 마이닝 메소드(MLLT-Join)를 소개한다.

  • PDF

Efficient Placement Scheme of Continuous Media in Multimedia Database (멀티미디어 데이터베이스에서 연속매체의 효율적인 배치기법)

  • Kim, Keun-Hyung;park, Seog
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 1999.10a
    • /
    • pp.9-11
    • /
    • 1999
  • 멀티미디어 DBMS는 연속매체를 서비스할 때 동시에 보다 많은 사용자들에게 일정한 서비스 품질을 유지하면서 서비스를 제공할 수 있어야 한다. 이를 위하여 멀티미디어 DBMS를 위한 저장시스템은 보다 큰 디스크 대역폭을 지원해야 하므로 디스크 배열의 구조를 갖는 것이 바람직하다. 디스크 배열 환경에서 다수의 연속매체를 병행적으로 서비스할 때 요구 데이터를 순차접근에 의하여 검색할 수 있으면 디스크 대역폭을 탐색시간 등으로 소모하지 않으므로 고속 디스크 대역폭을 유지할 수 있다. 또한, 디스크 접근시 디스브 부하 균형을 유지할 수 있으면 자원 활용율이 높은 고성능의 저장 시스템이 될 수 있다. 본 논문에서는 연속매체들을 순차접근에 의해서 처리하면서 디스크 부하 균형을 유지할 수 있는 데이터 배치 기법을 제안한다. 제안한 데이터 배치기법에 의한 성능평가는 모의 실험 전용틀인 AweSim 2.0을 사용하였다.

  • PDF

Opponent Move Prediction of a Real-time Strategy Game Using a Multi-label Classification Based on Machine Learning (기계학습 기반 다중 레이블 분류를 이용한 실시간 전략 게임에서의 상대 행동 예측)

  • Shin, Seung-Soo;Cho, Dong-Hee;Kim, Yong-Hyuk
    • Journal of the Korea Convergence Society
    • /
    • v.11 no.10
    • /
    • pp.45-51
    • /
    • 2020
  • Recently, many games provide data related to the users' game play, and there have been a few studies that predict opponent move by combining machine learning methods. This study predicts opponent move using match data of a real-time strategy game named ClashRoyale and a multi-label classification based on machine learning. In the initial experiment, binary card properties, binary card coordinates, and normalized time information are input, and card type and card coordinates are predicted using random forest and multi-layer perceptron. Subsequently, experiments were conducted sequentially using the next three data preprocessing methods. First, some property information of the input data were transformed. Next, input data were converted to nested form considering the consecutive card input system. Finally, input data were predicted by dividing into the early and the latter according to the normalized time information. As a result, the best preprocessing step was shown about 2.6% improvement in card type and about 1.8% improvement in card coordinates when nested data divided into the early.

Sequence-Based Travel Route Recommendation Systems Using Deep Learning - A Case of Jeju Island - (딥러닝을 이용한 시퀀스 기반의 여행경로 추천시스템 -제주도 사례-)

  • Lee, Hee Jun;Lee, Won Sok;Choi, In Hyeok;Lee, Choong Kwon
    • Smart Media Journal
    • /
    • v.9 no.1
    • /
    • pp.45-50
    • /
    • 2020
  • With the development of deep learning, studies using artificial neural networks based on deep learning in recommendation systems are being actively conducted. Especially, the recommendation system based on RNN (Recurrent Neural Network) shows good performance because it considers the sequential characteristics of data. This study proposes a travel route recommendation system using GRU(Gated Recurrent Unit) and Session-based Parallel Mini-batch which are RNN-based algorithm. This study improved the recommendation performance through an ensemble of top1 and bpr(Bayesian personalized ranking) error functions. In addition, it was confirmed that the RNN-based recommendation system considering the sequential characteristics in the data makes a recommendation reflecting the meaning of the travel destination inherent in the travel route.

Incremental Linear Discriminant Analysis for Streaming Data Using the Minimum Squared Error Solution (스트리밍 데이터에 대한 최소제곱오차해를 통한 점층적 선형 판별 분석 기법)

  • Lee, Gyeong-Hoon;Park, Cheong Hee
    • Journal of KIISE
    • /
    • v.45 no.1
    • /
    • pp.69-75
    • /
    • 2018
  • In the streaming data where data samples arrive sequentially in time, it is difficult to apply the dimension reduction method based on batch learning. Therefore an incremental dimension reduction method for the application to streaming data has been studied. In this paper, we propose an incremental linear discriminant analysis method using the least squared error solution. Instead of computing scatter matrices directly, the proposed method incrementally updates the projective direction for dimension reduction by using the information of a new incoming sample. The experimental results demonstrate that the proposed method is more efficient compared with previously proposed incremental dimension reduction methods.

A Design of a Distributed Computing Problem Solving Environment for Dietary Data Analysis (식이 데이터 분석을 위한 분산 컴퓨팅 문제풀이환경 설계)

  • Choi, Jieun;Ahn, Younsun;Kim, Yoonhee
    • Journal of KIISE
    • /
    • v.42 no.7
    • /
    • pp.834-839
    • /
    • 2015
  • Recently, wellness has become an issue related to improvements in personal health and quality of life. Data that are accumulated daily, such as meals and momentum records, in addition to body measurement information such as body weight, BMI and blood pressure have been used to analyze the personal health data of an individual. Therefore, it has become possible to prevent potential disease and to analyze dietary or exercise patterns. In terms of food and nutrition, analyses are performed to evaluate the health status of an individual using dietary data. However, it is very difficult to process the large amount of dietary data. An analysis of dietary data includes four steps, and each step contains a series of iterative tasks that are executed over a long time. This paper proposes a problem solving environment that automates dietary data analysis, and the proposed framework increases the speed with which an experiment can be conducted.

Design of a Vido Storage Server that Maximizes Concurrent Streams and Minimizes Initial Latency (사용자 수 증대와 초기 대기시간 감소를 위한 비디오 저장 서버의 설계)

  • Ma, Pyeong-Su;Jo, Chang-Sik;Jin, Yun-Suk;Sin, Gyu-Sang
    • The Transactions of the Korea Information Processing Society
    • /
    • v.6 no.10
    • /
    • pp.2608-2617
    • /
    • 1999
  • One of the most important functionality that commercial video storage servers should provide is to maximize the number of concurrent streams and to minimize the initial latency of new requests. In this paper, we propose a data placement scheme whose disk read unit size can be twice large than that of conventional striping methods. The proposed scheme can significantly increase the number of concurrent streams, since the ratio of rotational latency time is decreased and the disks are effectively utilized. The disk scheduling scheme we propose guarantees constant initial latency time. We also propose a procedural design method for a storage server by introducing the concept of allowed initial latency. The comparison with previous research shows that the proposed scheme provides better performance.

  • PDF

Integration of flash memory for effective Weather monitoring system (재해예방 모니터링 시스템의 효율적인 데이터 전송을 위한 플래시 메모리의 활용)

  • Yoo, Jae-Ho;Lee, Seung-Chul;Kwon, Tae-Ha;Chung, Wan-Young
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2010.05a
    • /
    • pp.223-225
    • /
    • 2010
  • In order to minimize the casualties and damages from natural disasters, local terrain and weather phenomena need to be constantly monitored. Various weather monitoring systems are designed to collect and monitor the weather information for disaster prevention. Nowadays, wireless sensor networks have been widely used to transmit the weather information and collected by the base station at a regular interval. In this paper, disaster prevention monitoring system for efficient data transfer of weather information such as temperature, humidity and illumination are designed. Weather information is able to burst the data transmission based on storage of flash memory. Telosb sensor node are used in the research; programmed by nesC language used by TinyOS.

  • PDF