• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.10
• /
• pp.487-492
• /
• 2017

Clustering is a technique which is used to measure similarities between data in big data analysis and data mining field. Among various clustering methods, k-Modes algorithm is representatively used for categorical data. To increase the performance of iterative-centric tasks such as k-Modes, a distributed and concurrent framework Spark has been received great attention recently because it overcomes the limitation of Hadoop. Spark provides an environment that can process large amount of data in main memory using the concept of abstract objects called RDD. Spark provides Mllib, a dedicated library for machine learning, but Mllib only includes k-means that can process only continuous data, so there is a limitation that categorical data processing is impossible. In this paper, we design RDD for k-Modes algorithm for categorical data clustering in spark environment and implement an algorithm that can operate effectively. Experiments show that the proposed algorithm increases linearly in the spark environment.

• Journal of KIISE
• /
• v.42 no.3
• /
• pp.307-319
• /
• 2015

Current ontology studies use the Hadoop distributed storage framework to perform map-reduce algorithm-based reasoning for scalable ontologies. In this paper, however, we propose a novel approach for scalable Web Ontology Language (OWL) Horst Lite ontology reasoning, based on distributed cluster memories. Rule-based reasoning, which is frequently used for scalable ontologies, iteratively executes triple-format ontology rules, until the inferred data no longer exists. Therefore, when the scalable ontology reasoning is performed on computer hard drives, the ontology reasoner suffers from performance limitations. In order to overcome this drawback, we propose an approach that loads the ontologies into distributed cluster memories, using Spark (a memory-based distributed computing framework), which executes the ontology reasoning. In order to implement an appropriate OWL Horst Lite ontology reasoning system on Spark, our method divides the scalable ontologies into blocks, loads each block into the cluster nodes, and subsequently handles the data in the distributed memories. We used the Lehigh University Benchmark, which is used to evaluate ontology inference and search speed, to experimentally evaluate the methods suggested in this paper, which we applied to LUBM8000 (1.1 billion triples, 155 gigabytes). When compared with WebPIE, a representative mapreduce algorithm-based scalable ontology reasoner, the proposed approach showed a throughput improvement of 320% (62k/s) over WebPIE (19k/s).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.94-96
• /
• 2017

최근 빅 데이터를 이용한 시스템들이 여러 분야에서 활발히 이용되기 시작하면서 대표적인 빅 데이터 저장 및 처리 플랫폼인 하둡(Hadoop)의 기술적 단점을 보완할 수 있는 분산 시스템 플랫폼 스파크(Apache Spark)가 등장하였다. 본 플랫폼을 바탕으로 슬레이브 노드들에게 작업을 분산하여 대용량 연산을 수행한다. 하지만 요구하는 성능을 내기 위해 어느 정도 규모의 슬레이브 노드가 필요한지, 각각의 컴퓨팅 능력은 얼마나 필요한지를 예측하는데 어려움이 있다. 본 논문에서는 스파크에서 원하는 성능을 내기 위해 어떤 조건을 충족해야 하는지, 현재 환경에서는 어느 정도 성능을 낼 수 있는지 실험을 통해 모델을 만들어 예측한다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.119-126
• /
• 2024

The volume of genomic data is constantly increasing in various modern industries and research fields. This growth presents new challenges and opportunities in terms of the quantity and diversity of genetic data. In this paper, we propose a distributed cloud system for integrating and managing large-scale gene databases. By introducing a distributed data storage and processing system based on the Hadoop Distributed File System (HDFS), various formats and sizes of genomic data can be efficiently integrated. Furthermore, by leveraging Spark on YARN, efficient management of distributed cloud computing tasks and optimal resource allocation are achieved. This establishes a foundation for the rapid processing and analysis of large-scale genomic data. Additionally, by utilizing BigQuery ML, machine learning models are developed to support genetic search and prediction, enabling researchers to more effectively utilize data. It is expected that this will contribute to driving innovative advancements in genetic research and applications.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.17-24
• /
• 2018

Today, we are living in the era of data and information. With the advent of Internet of Things (IoT), the popularity of social networking sites, and the development of mobile devices, a large amount of data is being produced in diverse areas. The collection of such data generated in various area is called big data. As the importance of big data grows, there has been a growing need to share big data containing information regarding an individual entity. As big data contains sensitive information about individuals, directly releasing it for public use may violate existing privacy requirements. Thus, privacy-preserving data publishing (PPDP) has been actively studied to share big data containing personal information for public use, while preserving the privacy of the individual. K-anonymity, which is the most popular method in the area of PPDP, transforms each record in a table such that at least k records have the same values for the given quasi-identifier attributes, and thus each record is indistinguishable from other records in the same class. As the size of big data continuously getting larger, there is a growing demand for the method which can efficiently anonymize vast amount of dta. Thus, in this paper, we develop an efficient k-anonymity method by using Spark distributed framework. Experimental results show that, through the developed method, significant gains in processing time can be achieved.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.149-158
• /
• 2017

Big data have been presenting us with exciting opportunities and challenges in economic development. For instance, in the agriculture sector, mixing up of various agricultural data (e.g., weather data, soil data, etc.), and subsequently analyzing these data deliver valuable and helpful information to farmers and agribusinesses. However, massive data in agriculture are generated in every minute through multiple kinds of devices and services such as sensors and agricultural web markets. It leads to the challenges of big data problem including data collection, data storage, and data analysis. Although some systems have been proposed to address this problem, they are still restricted either in the type of data, the type of storage, or the size of data they can handle. In this paper, we propose a novel design of a platform for collecting and analyzing agricultural big data. The proposed platform supports (1) multiple methods of collecting data from various data sources using Flume and MapReduce; (2) multiple choices of data storage including HDFS, HBase, and Hive; and (3) big data analysis modules with Spark and Hadoop.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.575-580
• /
• 2018

This paper discusses system for real-time monitoring of patient waiting time in hospitals based on open-source platform. It is necessary to make use of open-source projects to develop a high-performance stream processing system, which analyzes and processes stream data in real time, with less cost. The Hadoop ecosystem is a well-known big data processing platform consisting of numerous open-source subprojects. This paper first defines several requirements for the monitoring system, and selects a few projects from the Hadoop ecosystem that are suited to meet the requirements. Then, the paper proposes system architecture and a detailed module design using Apache Spark, Apache Kafka, and so on. The proposed system can reduce development costs by using open-source projects and by acquiring data from legacy hospital information system. High-performance and fault-tolerance of the system can also be achieved through distributed processing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.17-28
• /
• 2017

Recently, a study on data has been actively conducted because the value of the data has become more useful. Web crawler that is program of data collection recently spotlighted because it can take advantage of the various fields. Web crawler can be defined as a tool to analyze the web pages and collects the URL by traversing the web server in an automated manner. For the treatment of Big-data, distributed Web crawler is widely used which is based on the Hadoop MapReduce. But, it is difficult to use and has constraints on the performance. Apache spark that is the In-memory computing platform is an alternative to MapReduce. The search engine which is one of the main purposes of web crawler displays the information you search by keyword gathered by web crawler. If search engines implement a spark-based web crawler instead of traditional MapReduce-based web crawler, it would be a more rapid data collection.

• Journal of Multimedia Information System
• /
• v.7 no.2
• /
• pp.125-136
• /
• 2020

Nowadays, cloud computing is becoming more popular among companies. However, the characteristics of cloud computing such as a virtualized environment, constantly changing, possible to modify easily and multi-tenancy with a distributed nature, it is difficult to perform attack detection with traditional tools. This work proposes a solution which aims to collect traffic packets data by using Flume and filter them with Spark Streaming so it is possible to only consider suspicious data related to HTTP Slow Rate Denial-of-Service attacks and reduce the data that will be stored in Hadoop Distributed File System for analysis with the FP-Growth algorithm. With the proposed system, we also aim to address the difficulties in attack detection in cloud environment, facilitating the data collection, reducing detection time and enabling an almost real-time attack detection.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.539-541
• /
• 2016

최근 빅데이터 분석을 위해 아파치 하둡(Apache Hadoop) 기반 에코시스템(Ecosystern)이 다양하게 활용되고 있다. 본 논문에서는 수집된 로그 데이터를 가공하여 데이터베이스에 로드하는 과정을 효율적으로 처리하기 위한 성능 평가를 수행한다. 이를 기반으로 텍스트 파일의 로그 데이터를 자바 코드로 개발된 프로그램에서 JDBC를 이용하여 오라클(Oracle) 데이터베이스에 삽입(Insert)하는 과정의 성능을 개선하기 위한 방안을 제안한다. 대용량 로그 파일의 효율적인 처리를 위해 하둡 에코시스템을 이용하여 처리 속도를 개선하고, 최근 인메모리(In-Mernory) 처리 방식으로 빠른 처리 속도로 인해 각광받고 있는 아파치 스파크(Apache Spark)를 이용한 처리와의 성능 평가를 수행한다. 이 연구를 통해 최적의 로그데이터 처리 시스템의 구축 방안을 제안한다.