• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.19-22
• /
• 2016

Many Studies have been actively conducted on the early diagnosis of the crop pest utilizing IT technology. The purpose of the paper is to discuss on the image processing method capable of detecting the crop leaf pest prematurely by analyzing the image of the leaf received from the camera sensor. This paper proposes an algorithm of diagnosing leaf infection by utilizing an improved K means clustering method. Leaf infection grouping test showed that the proposed algorithm illustrated a better performance in the qualitative evaluation.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.53-60
• /
• 2016

Data of central government and local government was collected automatically from the public data portal. And we did the multidimensional analysis based on various perspective like file format and present condition of public data. To complete this work, we constructed Data Warehouse based on the other countries' evaluation index case. Finally, the result from service level evaluation by using multidimensional analysis was used to display each area, establishment, fields.

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.33-40
• /
• 2018

With the advent of the fourth industrial revolution, each industry has been innovated with new concepts. New concept of each industry takes advantage of new information technologies based on big data infra. Thus quality control of big data is becoming more important. In this paper, we try to develop a framework of big data service quality through a case study. A 'Legal Tech' service was selected for the case study. Especially a big data quality framework was developed for a living law service in the Ministry of Justice.

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.41-46
• /
• 2018

With the advent of the fourth industrial revolution, data becomes very important resource. Now is called as 'Data Revolution Age.' It is said that Data Revolution Age started with Big Data, then accelerated with Open Data, finally completed with My Data. In this paper, we compared Big Data, Open Data, and suggested roles and effects of My Data as a digital resource.

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.47-54
• /
• 2018

Previous studies of business process analysis have analyzed various factors such as task, customer service, operator convenience, and execution time prediction. To accurately analyze these factors, it is effective to utilize actual historical data recorded in information systems. Process mining is a technique for analyzing various elements of a business process from event log data. In this case study, process mining was applied to the transaction data of a purchase agency to analyze the business process of their procurement process, the execution time, and the operators.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.189-195
• /
• 2020

We consider the stale problem which makes the training speed slow in the field of deep learning. The problem can be formulated as a single-machine scheduling problem with generalized due dates in which the objective is to minimize the total earliness and tardiness. We show that the problem can be solved in polynomial time if the orders of the small and the large jobs in an optimal schedule are known in advance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.492-495
• /
• 2019

This study identifies the needs for child care according to population change and movement by region, and analyzes the association with the recruitment rate by type of daycare center to find out the preference of child care facilities by type.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.496-499
• /
• 2019

The study aims to collect detailed movie information from box office of the Korea Film Council and data on Naver's movie ratings to analyze important factors affecting the movie's popularity based on movie audiences and ratings.

• Ocean and Polar Research
• /
• v.44 no.2
• /
• pp.179-190
• /
• 2022

Data missing in optical satellite images caused by natural variations have been a crucial barrier in observing the status of marine surfaces. Although there have been many attempts to fill the gaps of non-observation, there is little research to analyze the ratio of missing grids to overall sea grids and their seasonal patterns. This report introduces the method of quantifying the distribution of missing points and then shows how the missing points have spatial correlation and seasonal trends. Both temporal and spatial integration methods are compared to assess the effectiveness of reducing missing data. The temporal integration shows more outstanding performance than the spatial integration. Moran's I and K-function with statistical hypothesis testing show that missing grids are clustered and there is a non-random distribution from daily integration. The result of the seasonality test for Moran's I through a periodogram shows dependency on full-year, half-year, and quarter-year periods respectively. These analysis results can be used to deduce appropriate integration periods with permissible estimation errors.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.47-48
• /
• 2021

사용자 행동 인식(HAR)은 사용자의 행동을 분석하여 사용자의 현재 행동을 추측하는 것이며, 센서 데이터에서 특성을 추출하는 것이 중요하다. 본 연구에서는 다양한 특징 추출 기법을 사용하여 기계학습 모델을 비교한다. 변수마다 특성에 맞는 기법을 사용했으며, 정확도와 Kappa 통계량, F1 score 모두 SVM 모델에서 95.2%, 94.2%, 95.1%로 가장 높았다. 이는 기계학습 모델에서 특징 추출 기법을 사용하여 우수한 정확도를 달성할 수 있음을 보인다.