• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.535-544
• /
• 2018

As the spread of mobile devices equipped with various sensors and high-quality wireless network communications functionsexpands, the amount of spatio-temporal data generated from mobile devices in various service fields is rapidly increasing. In conventional research into processing a large amount of real-time spatio-temporal streams, it is very difficult to apply a Hadoop-based spatial big data system, designed to be a batch processing platform, to a real-time service for spatio-temporal data streams. This paper extends the MapReduce online framework to support real-time query processing for continuous-input, spatio-temporal data streams, and proposes a load management method to distribute overloads for efficient query processing. The proposed scheme shows a dynamic load balancing method for the nodes based on the inflow rate and the load factor of the input data based on the space partition. Experiments show that it is possible to support efficient query processing by distributing the spatial data stream in the corresponding area to the shared resources when load management in a specific area is required.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.9
• /
• pp.1731-1737
• /
• 2017

K Nearest Neighbor Join (KNN Join) is a simple yet effective method in machine learning. It is widely used in small dataset of the past time. As the number of data increases, it is infeasible to run this model on an actual application by a single machine due to memory and time restrictions. Nowadays a popular batch process model called MapReduce which can run on a cluster with a large number of computers is widely used for large-scale data processing. Hadoop is a framework to implement MapReduce, but its performance can be further improved by a new framework named Spark. In the present study, we will provide a KNN Join implement based on Spark. With the advantage of its in-memory calculation capability, it will be faster and more effective than Hadoop. In our experiments, we study the influence of different factors on running time and demonstrate robustness and efficiency of our approach.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.376-377
• /
• 2016

Performance of Hadoop, which is a distributed data processing framework for big data analysis, is affected by several characteristics of each node in distributed cluster such as processing power and network bandwidth. This paper analyzes previous approaches for heterogeneous hadoop clusters, and presents several requirements for distributed node clustering in small-and-medium sized hospitals by considering computing environments of the hospitals.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.191-193
• /
• 2016

본 논문에서는 SSD 저장장치를 포함하는 하둡의 Iterative Processing에 대한 성능 분석 결과를 소개한다. 하둡은 맵 리듀스 병렬 프로그래밍 모델을 통해 Batch Processing에 특화된 구조를 가지고 있는 프레임 워크이다. 이는 병렬/분산 환경에서 큰 성능향상을 보장하지만, 반복 작업을 수행하는 Iterative Processing에 대하여는 성능이 낮아지는 문제가 존재하고 있다. 이에 본 논문에서는 점차 낮아지는 가격으로 인해 하둡시스템에 적용 가능성이 타진되는 SSD를 통해 반복 작업의 성능이슈를 해결할 수 있는지 확인하고, SSD를 통한 성능향상의 요소가 존재하는지 알아보고자 실험을 진행하였다. 실험에서는 Batch Processing인 word count와 Iterative Processing인 Page Rank 알고리즘을 MapReduce로 구현하고 데이터 크기에 따른 성능 향상도를 측정하였고, SSD 추가와 같은 하드웨어적인 성능을 통한 하둡의 반복 작업은 큰 효율을 기대하기가 어렵다는 결론을 보였다.

• KIISE Transactions on Computing Practices
• /
• v.20 no.12
• /
• pp.615-622
• /
• 2014

The Korean film market has rapidly achieved an international scale, and this has led to a need for decision-making based on analytical methods that are more precise and appropriate. In this modern era, a highly advanced information environment can provide an overwhelming amount of data that is generated in real time, and this data must be properly handled and analyzed in order to extract useful information. In particular, the preprocessing of large data, which is the most time-consuming step, should be done in a reasonable amount of time. In this paper, we investigated a big data preprocessing method for predicting movie box office success. We analyzed the movie data characteristics for specialized preprocessing methods, and used the Hadoop MapReduce framework. The experimental results showed that the preprocessing methods using big data techniques are more effective than existing methods.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.820-826
• /
• 2016

There is a growing requirement for big data processing which extracts valuable information from a large amount of data. The Hadoop system employs the MapReduce framework to process big data. However, MapReduce has limitations such as inflexible and slow data processing. To overcome these drawbacks, SQL query processing techniques known as SQL-on-Hadoop were developed. Apache Tajo, one of the SQL-on-Hadoop techniques, was developed by a Korean development group. External merge sort is one of the heavily used algorithms in Tajo for query processing. The performance of external merge sort in Tajo is influenced by two parameters, sort buffer size and fanout. In this paper, we analyzed the performance of external merge sort in Tajo with various sort buffer sizes and fanouts. In addition, we figured out that there are two major causes of differences in the performance of external merge sort: CPU cache misses which increase as the sort buffer size grows; and the number of merge passes determined by fanout.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.479-482
• /
• 2014

Nowadays open-source hadoop systems have been using widely to efficiently manage a fast-growing big data. Hadoop systems consist of distributed file processing system called HDFS (Hadoop Distributed File System) and distributed parallel processing system called MapReduce. The MapReduce reads and processes big data from HDFS and then processed results are written in HDFS again by the MapReduce. Such a processing method has different system structure respectively according to hadoop version. Therefore, this paper shows analysis results for performance of hadoop systems. For this, we devise a way which monitors hadoop systems and measure occurrence frequency of processes, threads, and variables generated in hadoop system itself using the devised way. So, by using the measured results as analysis indicator, we help the indicator predict inner performance of hadoop systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.236-239
• /
• 2021

With the growth of AI technology, the scale of Knowledge Graphs continues to be expanded. Knowledge Graphs are mainly expressed as RDF representations that consist of connected triples. Many RDF storages compress and transform RDF triples into the condensed IDs. However, if we try to transform a large scale of RDF triples, it occurs the high processing time and memory overhead because it needs to search the large ID mapping table. In this paper, we propose the method of converting RDF triples using Hash-based ID mapping tables with MapReduce, which is the software framework with a parallel, distributed algorithm. Our proposed method not only transforms RDF triples into Integer-based IDs, but also improves the conversion speed and memory overhead. As a result of our experiment with the proposed method for LUBM, the size of the dataset is reduced by about 3.8 times and the conversion time was spent about 106 seconds.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.944-946
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. We modified the existing Support vector machine algorithm to fit into the distributed hadoop architecture system for localization of a sensor node. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.691-693
• /
• 2015

SQL on Hadoop 기술은 하둡 분산 파일 시스템에 저장된 데이터를 대상으로 SQL을 이용하여 사용자의 질의를 처리하는 기술이다. 기존의 Hadoop 시스템이 맵리듀스의 한계와 기존 시스템의 호환성으로 인해 RDBMS와 병행사용이 불가피하다는 단점을 SQL을 이용해 극복하고자 하는 것이다. 본 논문에서는 SQL on Hadoop의 대표적 프레임워크인 Hive와 Impala의 특징과, 연구동향에 대해 살펴보고 예상되는 보안 위협에 대해 고찰한다.