• Journal of The Korean Society For Urban Railway
• /
• v.6 no.4
• /
• pp.233-241
• /
• 2018

Recently, integrated railway safety monitoring and control system, which is a convergence system based on data distribution service for railway safety monitoring and control, is under development. It collects safety data of vehicle, signal, power and safety monitoring facilities in real time and adopts communication middleware based on distributed service for mass data processing. However, in the case of a server device used as an existing control server, the performance of the distributed service middleware can not be exhibited due to low hardware performance due to safety reasons. In the safety control system, 200,000 packets per second were set as the transmission target, but the performance test of the LAB was not satisfied. In this paper, we analyze the characteristics of railway data to improve the data collection performance of existing equipment and apply DDS-based streaming transmission method to the data model of signal facilities and vehicle facilities with large packet amount according to the analysis result. As a result, it was confirmed that the throughput was improved about 30.4 times when the hardware performance was the same. We plan to improve the data processing performance by applying it to real-time railway safety integrated monitoring and control system in the future.

• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.17-31
• /
• 2017

With the development of the big data environment, public institutions also have been providing big data infrastructures. Public data is one of the typical examples, and numerous applications using public data have been provided. One of the cases is related to the employment insurance. All employers have to make contracts for the employment insurance for all employees to protect the rights. However, there are abundant cases where employers avoid to buy insurances. To overcome these challenges, a data-driven approach is needed; however, there are lacks of methodologies to integrate, manage, and analyze the public data. In this paper, we propose a methodology to build a predictive model for identifying whether employers have made the contracts of employment insurance based on public data. The methodology includes collection, integration, pre-processing, analysis of data and generating prediction models based on process mining and data mining techniques. Also, we verify the methodology with case studies.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10a
• /
• pp.167-171
• /
• 2006

무선 센서 네트워크는 유비쿼터스 컴퓨팅에서 생활 환경과 컴퓨터 사이의 중계자 역할을 하는 매우 중요한 연구 분야이다. 매우 제약적인 자원 환경에서 동작하여야 하는 센서 노드의 동작 환경적 특성 때문에 제한된 자원을 효율적으로 관리할 수 있는 센서 노드용 운영체제가 요구된다. 센서 노드는 제약적인 자원을 가지고 있지만 데이터 수집, 데이터 프로세싱, 다른 노드로부터 수신된 데이터의 전달 등 여러 가지 작업들이 동시에 발생된다. 기존의 범용 센서네트워크 운영체제에서는 극도로 제한된 자원을 최대한 효율적으로 사용할 수 있는 방법에 대하여 주로 연구해 왔다. 무선 센서 네트워크의 응용 범위가 점차 넓어지고 있다. 방사능 감지와 같이 실시간성을 요구하는 응용분야들이 생겨나기 시작하면서 센서 네트워크에서도 실시간성의 필요성이 대두되게 되었다. 실시간 센서 네트워크 연구 분야에서 실시간 통신 프로토콜의 연구 결과가 발표되고 있지만, 실시간 운영체제의 지원없이 완전한 실시간성을 보장하기 힘들다. 하지만 센서 노드용 실시간 운영체제에 대한 연구는 아직까지 활발히 진행되지 않고 있다. 본 논문에서는 정시성을 보장하는 분산 객체 모델인 TMO를 센서네트워크의 제한된 자원 환경에 알맞도록 경량화 시킨 $\mu$TMO 모델을 제시하고, 센서 노드용 운영체제에 $\mu$TMO 모델 을 적용하여 실시간성 지원에 따른 오버헤드를 감소시킨 실시간 센서 네트워크 운영체제의 구조를 제안한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.1-7
• /
• 2009

An approach for the classification of music genres using a Fuzzy c-Means(FcM) with divergence-based kernel is proposed and presented in this paper. The proposed model utilizes the mean and covariance information of feature vectors extracted from music data and modelled by Gaussian Probability Density Function (GPDF). Furthermore, since the classifier utilizes a kernel method that can convert a complicated nonlinear classification boundary to a simpler linear one, he classifier can improve its classification accuracy over conventional algorithms. Experiments and results on collected music data sets demonstrate hat the proposed classification scheme outperforms conventional algorithms including FcM and SOM 17.73%-21.84% on average in terms of classification accuracy.

• The KIPS Transactions:PartA
• /
• v.9A no.4
• /
• pp.519-524
• /
• 2002

In this paper we study the qualify of sequential coverage analysis under a scenario of distributed stochastic simulation known as MRIP(Multiple Replications In Parallel) in terms of the confidence intervals of coverage and the speedup. The estimator based in the F-distribution was applied to the sequential coverage analysis of steady-state means. in simulations of the $M/M/1/{\infty},\;M/D/I/{\infty}\;and\;M/H_{2}/1/{\infty}$ queueing systems on a single processor and multiple processors. By using multiple processors under the MRIP scenario, the time for collecting many replications needed in sequential coverage analysis is reduced. One can also easily collect more replications by executing it in distributed computers or clusters linked by a local area network.

• Spatial Information Research
• /
• v.10 no.1
• /
• pp.77-92
• /
• 2002

In order to prevent indiscreet urban growth and harmonize urban development with environmental preservation, it is strongly required in Korea that urban planning should be reasonable and transparent. From this societal demand, the urban planning system was changed to be strengthened for the establishment of harmonious land-use order in urban space. However, implementation of the urban planning system demands a lot of information to analyze and estimate the present condition and problems of urban area. For this purpose, the information should quickly be collected, managed and analyzed. The urgent demand of information in urban planning field is able to be fulfilled with recent GIS and its relevant information technique, which can quickly, accurately and conveniently collect various spatial and statistical information, systematically analyze and manage them, and visually present the result of spatial analysis. This study suggested a urban planning information system and its basic implementing scheme to support the urban planning system with GIS and presented a development model of the urban planning information system using the recent GIS and its relevant information technique.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.10
• /
• pp.309-318
• /
• 2023

Recently, each country has been moving to introduce an LCA (Life Cycle Assessment) to regulate greenhouse gas emissions. The LCA is a mean of measuring and evaluating greenhouse gas emissions generated over the entire life cycle of a vehicle. Reliable data for each electric vehicle component is needed to increase the reliability of the LCA results. To this end, studies on life cycle evaluation models using blockchain technology have been conducted. However, in the existing model, key product information is exposed to other participants. And each time parts data information is updated, it must be recorded in the blockchain ledger in the form of a transaction, which is inefficient. In this paper, we proposed a DID(Decentralized Identity)-based data collection model for LCA to collect vehicle component data and verify its validity effectively. The proposed model increases the reliability of the LCA by ensuring the validity and integrity of the collected data and verifying the source of the data. The proposed model guarantees the validity and integrity of collected data. As only user authentication information is shared on the blockchain ledger, the model prevents indiscriminate exposure of data and efficiently verifies and updates the source of data.

• Journal of Convergence for Information Technology
• /
• v.9 no.1
• /
• pp.45-53
• /
• 2019

We face problems from excessive information served with websites in this rapidly changing information era. We find little information useful and much useless and spend a lot of time to select information needed. Many websites including search engines use web crawling in order to make data updated. Web crawling is usually used to generate copies of all the pages of visited sites. Search engines index the pages for faster searching. With regard to data collection for wholesale and order information changing in realtime, the keyword-oriented web data collection is not adequate. The alternative for selective collection of web information in realtime has not been suggested. In this paper, we propose a method of collecting information of restricted web sites by using Web crawling distributed monitoring system (R-WCMS) and estimating collection time through detailed analysis of data and storing them in parallel system. Experimental results show that web site information retrieval is applied to the proposed model, reducing the time of 15-17%.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.362-369
• /
• 2012

Recently, a target detection based on a distributed sensor network has been much studied in active sonar. Zhou et al. proposed a target localization method using line fitting based on a distributed sensor network which consists of low complexity sensors that only report binary detection results. This method has three advantages relative to ML estimator. First, there is no need to estimate propagation model parameters. Second, the computation is simple. Third, it only use sensors with "detection", which implies less data to be collected by data processing center. However, this method has larger target localization error than the ML estimator. In this paper, a target localization method which modifies Zhou's method is proposed for reducing the localization error. The modified method shows the performance improvement that the target localization error is reduced by 40.7% to Zhou's method in the point of RMSE.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.2
• /
• pp.35-40
• /
• 2019

Traditional Malware Detection is susceptible for detecting malware which is modified by polymorphism or obfuscation technology. By learning patterns that are embedded in malware code, machine learning algorithms can detect similar behaviors and replace the current detection methods. Data must collected continuously in order to learn malicious code patterns that change over time. However, the process of storing and processing a large amount of malware files is accompanied by high space and time complexity. In this paper, an HDFS-based distributed processing system is designed to reduce space complexity and accelerate feature extraction time. Using a distributed processing system, we extract two API features based on filtering basis, 2-gram feature and APICFG feature and the generalization performance of ensemble learning models is compared. In experiments, the time complexity of the feature extraction was improved about 3.75 times faster than the processing time of a single computer, and the space complexity was about 5 times more efficient. The 2-gram feature was the best when comparing the classification performance by feature, but the learning time was long due to high dimensionality.