• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.295-297
• /
• 2023

우리나라는 항로표지 배치의 적합성 평가를 주기적으로 실시하고 있다. 항로표지의 배치는 전문가의 주관적 경험에 의존하고 배치있으며 검증에 필요한 전처리 작업은 수작업으로 처리한다. 이 연구에서는 데이터 필터링, 항적 HDG설정 및 입출항분리 작업을 부분적으로 자동화 하면서 HTTP로 연동되는 전처리 시스템을 개발하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.355-357
• /
• 2020

최근 에너지 효율의 중요성이 높아지고 에너지 공급 형태가 다변화하면서 다양한 에너지원을 효율적으로 관리할 수 있는 마이크로그리드 개념이 중요해지고 있다. 본 연구의 산업단지 마이크로그리드 열거래 플랫폼은 실증사이트의 전기 및 열에너지 모니터링 기능과 열에너지 거래 정산 기능을 가지며, 이를 위해 정확하고 안정적인 실증사이트 데이터가 필요하다. 하지만 실증사이트 데이터는 에너지 단위의 불일치, 센서 및 현장 운영상태에 따른 불안정성 등의 문제가 있어 수집 직후 열거래 플랫폼에서 활용할 수 없다. 따라서 수집된 데이터를 활용하기 위해 엔진 최대 출력량, 최대 전력 사용량 등의 변수별 특성을 고려하여 데이터 전처리 프로세스를 설계 및 적용하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.27-37
• /
• 2020

In this paper, we propose the methodology based on data-driven approach using Natural Language Processing and Machine Learning for classifying requirements into functional requirements and non-functional requirements. Through the analysis of the results of the requirements classification, we have learned that the trained models derived from requirements classification with data-preprocessing and classification algorithm based on the characteristics and information of existing requirements that used term weights based on TF and IDF outperformed the results that used stemming and stop words to classify the requirements into functional and non-functional requirements. This observation also shows that the term weight calculated without removal of the stemming and stop words influenced the results positively. Furthermore, we investigate an optimized method for the study of classifying software requirements into functional and non-functional requirements.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.79-85
• /
• 2019

Recently, small radar require the development of small millimeter wave radar with high distance resolution to disable the target's system with a single strike. Small millimeter wave radar with high distance resolution need to process large amounts of data in real time to acquire and track target. In this paper, we summarized the real-time data preprocessing method to process the large amount of data required for small millimeter wave radar. In addition, the digital IF(Intermediate Frequency) receiver, Window processing, and, DFT(Discrete Fourier Transform) functions presented by real-time data preprocessing are implemented using FPGA(Field Programmable Gate Array). Finally the implemented real-time data preprocessing module was applied to the signal processor for small millimeter wave radar and verified by performance test related to the real-time preprocessing function.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.4
• /
• pp.361-368
• /
• 2002

The aim of this study was to investigate the effect of preprocessing the transmitted energy spectrum data on development of a robust model to predict the sugar content in intact apples. The spectrum data were measured from 120 Fuji apple samples conveying at the speed of 2 apples per second. Computer algorithms of preprocessing methods such as MSC, SNV, first derivative, OSC and their combinations were developed and applied to the raw spectrum data set. The results indicated that correlation coefficients between the transmitted energy values at each wavelength and sugar contents of apples were significantly improved by the preprocessing of MSC and SNV in particular as compared with those of no-preprocessing. SEPs of the prediction models showed great difference depending on the preprocessing method of the raw spectrum data, the largest of 1.265%brix and the smallest of 0.507% brix. Such a result means that an appropriate preprocessing method corresponding to the characteristics of the spectrum data set should be found or developed for minimizing the prediction errors. It was observed that MSC and SNV are closely related to prediction accuracy, OSC is to number of PLS factors and the first derivative resulted in decrease of the prediction accuracy. A robust calibration model could be d3eveloped by the combined preprocessing of MSC and OSC, which showed that SEP=0.507%brix, bias=0.0327 and R2=0.8823.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.1
• /
• pp.15-27
• /
• 2013

While the vehicle detector is collected from a variety of information was mainly used as a real-time data. Recently scheme of application for archived traffic data has become increasingly important. In this background, this research were conducted on the improvement of the preprocessing for archived traffic data application. The purpose of improving specific preprocessing was reflect transportation phenomena by traffic data. As evaluation result, improvement preprocessing was close to the actual value than exist preprocessing.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.257-264
• /
• 2014

This paper is to construction of the data mining preprocessing tool for efficient database marketing. We compare and evaluate the often used data mining tools based on the access method to local and remote databases, and on the exchange of information resources between different computers. The evaluated preprocessing of data mining tools are Answer Tree, Climentine, Enterprise Miner, Kensington, and Weka. We propose a design principle for an efficient system for data preprocessing for data mining on the distributed networks. This system is based on Java technology including EJB(Enterprise Java Beans) and XML(eXtensible Markup Language).

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.61-71
• /
• 2023

With the development of data-driven decision-making and sophisticated big data processing technique, there is a growing demand for information on how to process data. However, recent studies with data preprocessing mentioned only as a means to achieve a result. Therefore, in this study, we aimed to write in detail about the data processing pipeline, include preprocessing data. In particular, we shares the context and domain knowledge to aid fluent understand of the research.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.377-383
• /
• 2018

Internet of Things (IoT) is producing various data as the smart environment comes. The IoT data collection is used as important data to judge systems's status. Therefore, it is important to monitor the anomaly state of the sensor in real-time and to detect anomaly data. However, it is necessary to convert the IoT data into a normalized data structure for anomaly detection because of the variety of data structures and protocols. Thus, we can expect a good quality effect such as accurate analysis data quality and service quality. In this paper, we propose an anomaly detection system based on big data from collected sensor data. The proposed system is applied to ensure anomaly detection and keep data quality. In addition, we applied the machine learning model of support vector machine using anomaly detection based on time-series data. As a result, machine learning using preprocessed data was able to accurately detect and predict anomaly.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.165-166
• /
• 2018

최근 딥러닝 기술이 발전함에 따라 이를 네트워크 침입탐지 분야에 적용하려는 연구가 활발히 이루어지고 있으며 이에 따라 대용량 네트워크 데이터에 대한 처리 방법이 주목받고 있다. 본 논문에서는 네트워크 데이터를 이미지화하는 전처리 방법을 제안한다. 네트워크 데이터를 세션단위로 처리하여 손실율을 줄이면서 딥러닝 알고리즘에 바로 적용할 수 있도록 정규화된 이미지로 변환하는 방법이다. 이를 통해 딥러닝 기술을 적용한 네트워크 정보보안 분야의 연구 활성화를 기대할 수 있다.