• International Journal of Ocean System Engineering
• /
• 제3권3호
• /
• pp.116-130
• /
• 2013

The prediction of ocean currents in real time over the warning times of a few hours or days is required in planning many operation-related activities in the ocean. Traditionally this is done through numerical models which are targeted toward producing spatially distributed information. This paper discusses a complementary method to do so when site-specific predictions are desired. It is based on the use of a recurrent type of neural network as well as the statistical tool of model tree. The measurements made at a site in Indian Ocean over a period of 4 years were used. The predictions were made over 72 time steps in advance. The models developed were found to be fairly accurate in terms of the selected error statistics. Among the two modeling techniques the model tree performed better showing the necessity of using distributed models for different sub-domains of data rather than a unique one over the entire input domain. Typically such predictions were associated with average errors of less than 2.0 cm/s. Although the prediction accuracy declined over longer intervals, it was still very satisfactory in terms of theselected error criteria. Similarly prediction of extreme values matched with that of the rest of predictions. Unlike past studies both east-west and north-south current components were predicted fairly well.

• 한국ITS학회 논문지
• /
• 제18권6호
• /
• pp.11-30
• /
• 2019

교통카드 데이터는 다양한 대중교통 통계 지표 산출, 정책 및 평가를 위한 자료로 활용되어 그 활용범위가 상당히 높다. 그러나 교통카드 데이터 내 주요 문제점은 하차 정류장에서 태그를 안 하고 하차하는 경우가 대부분으로 이는 교통카드 이용자의 불완전한 OD 통행 자료로 활용범위에 있어 한계가 있다. 본 연구는 의사결정 모델 기반 교통카드 데이터 하차 정류장 추정 방법을 적용한 결과 오차 범위 2개 정류장 이하에서 하차 정류장 추정 정확도는 89.7%으로 분석되었다. 이를 통하여 교통카드 데이터의 불완전성을 해소함으로써 다양한 대중교통 분석 및 평가 등에 대한 기초 자료로 활용 될 수 있을 것으로 판단된다.

• 한국컴퓨터정보학회논문지
• /
• 제14권3호
• /
• pp.161-171
• /
• 2009

본 논문에서는 SOA(Service-Oriented Architecture)를 기반으로 서비스간에 상호 작용하는 데이터의 품질 관리를 위한 오류 정제 서비스를 대상으로 데이터 제약조건 설정 시 인간 개입을 최소화하기 위한 기법을 제안한다. 단, 실세계에서 통용되는 일반적인 데이터를 모두 다루는 것은 불가능하므로 비즈니스 도메인에서 자주 사용되는 CRM(Customer Relationship Management)과 ERP(Enterprise Resource Planning) 서비스와 같이 고객 주문 정보 및 처리에 관련된 데이터를 대상으로 한다. 이를 위해, 컴포지션 되는 서비스간의 상호 작용하는 데이터를 의미적으로 확장하여 확장-엘리먼트 벡터를 생성하고 이를 기반으로 의사결정 트리(decision tree) 학습 방법을 적용하여 제약조건 설정을 자동화하기 위한 규칙 기반 시스템을 구축한다. 이 시스템을 오류정제 서비스에 삽입한 결과, 비즈니스 분야의 공개된 서비스로부터 데이터 학습을 통해 제약조건 설정을 41% 넘게 자동화 할 수 있음을 보였다.

• 농촌계획
• /
• 제17권2호
• /
• pp.23-32
• /
• 2011

The purpose of this study is to produce basic planning criteria required in ecological restoration and improvement works of streams in rural area through the application of stream assessment methods (water quality, soil environment, and ecological function assessment) at 6 study sites of Han River basin. The investigation results were as followings; 1) There were the evaluation items like a manure use, salt degree, river peripheral tree, which did not fitted to apply to domestic streams, in the SVAP (Stream Visual Assessment Protocol) and NRCS Riparian Assessment that were evaluation models developed in USDA. The area inhabitants with a little knowledge and education personally seems to utilize the evaluation methods through improvement partly with an aspect that evaluation is slightly easy. 2) From the stream assessment results, the construction of diverse pools, large woody debris and isolated backwater pool are needed to improve a few of problems observed at the mostly study sites. The result of NRCS Riparian Assessment showed that the improvement of stream bank vegetative communities is needed by planting tree with deep-binding root masses, and managing of noxious weeds and exotic undesirable plants. 3) Summing up, the assessment results showed that the assessment scores were higher at upstream than downstream, the stream with totally maintenance than that with partly maintenance, the stream with slope bank than that with vertical bank, and the stream with a flood plain than that without a flood plain. So, the direction of stream maintenance projects must be set by consideration of those results.

• 한국환경복원기술학회지
• /
• 제24권1호
• /
• pp.25-36
• /
• 2021

The honey bee has a crucial ecological status for maintaining the natural ecology system. Pollination mediations by honey bees are recognized as an efficient way to enhance the quality of biological diversity and green areas in the nature and the urban ecological system. However, the population of bee around the world is decreasing and we do not know exactly how bees react to the physical environment in the urban area. This study is a basic research for the improvement of pollination services in the Korean urban ecological system. It aims to induce and review environmental variables which have high relations with the activities of pollination mediation insects in the urban area. The study established a Maxent model using five urban environmental variables that reflect the ecology of Bombus ignitus and the place information where Bombus ignitus appears in 18 spots of Seoul city, and compared with previous research results on Apis millifera. Bombus ignitus preferred places with more natural environments such as mountain forest areas and vicinities of streams. They preferred Stratified Tree Area the most among the vegetation types existing in the urban area. Comparing chicken models, both species saw their response value drop as the building coverage rose. In the case of Apis millifera and Bombus ignitus variables, the response value of both species was high in 10 out of 20 types. The result of this study is expected to provide basic information for improving the pollination services in the Korean urban area and to be utilized as the basic materials for the future urban planning.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.37-42
• /
• 2005

This paper presents an autonomous system for reconstruction of three-dimensional indoor environments using a mobile robot. The system is composed of a mobile robot, a three-dimensional scanning system, and a notebook computer for registration, observation planning and real-time three-dimensional data transferring. Three-dimensional scanning system obtains three-dimensional environmental data and performs filtering of dynamic objects. Then, it registers multiple three-dimensional scans into one coordinate system and performs observation planning which finds the next scanning position by using the layered hexahedral-map and topological-map. Then, the mobile robot moves to the next scanning position, and repeats all procedures until there is no scanning tree in topological-map. In concurrence with data scanning, three-dimensional data can be transferred through wireless-LAN in real-time. This system is experimented successfully by using a mobile robot named KARA.

• 국토계획
• /
• 제53권7호
• /
• pp.49-66
• /
• 2018

The purpose of this study is to analyze neighborhood environmental factors affecting bicycle accidents and accidental severity in Seoul, Korea. The use of bicycles has increased rapidly as daily transportation means in recent years. As a result, bicycle accidents are also steadily increasing. Using Traffic Accident Analysis System (TAAS) data from 2015 to 2017, this study uses negative binomial regression analysis to identify neighborhood environmental factors affecting bicycle accidents and accidential severity. The main results are as follows. First, bicycle accidents are more likely to occur in commercial and mixed land use areas where pedestrians, bicycle and vehicles are moving together. Second, bicycle accidents are positively associated with road structures such as four-way intersection. In contrast, three-way intersection is negatively associated with serious bicycle accidents. The density of speed hump or street tree is negatively associated with bicycle accidents and accidential severity. This finding indicates the effect of speed limit or street trees on bicycle safety. Fourth, bicycle infrastructures are also important factors affecting bicycle accidents and accidential severity. Bicycle-exclusive roads or bicycle-pedestrian mixed roads are positively associated with bicycle accidents and accidential severity. Finally, this study suggests policy implications to improve bicycle safety.

• 농촌계획
• /
• 제15권2호
• /
• pp.81-96
• /
• 2009

This study has found out the status of the environment ecology(topography structure. land-use, flora, plant community structure, wildbird) in 10 uninhabited islands(i.e. Kei island, Hadon island, Sangdon island, Daewa island, Hwanggang island, Naebi island, Oebi island, Prickly castor-oil tree island, Tongin island, Yuk island), Namhae-gun, Gyeongsangnam-do. Moreover, It has suggested ways of improving the environment ecology status by classifying the type of environment ecology about the degree of use and damage that based on the results of environment ecology survey. According to the results of topography structure survey, the survey site altitude was ranged within 1m$\sim$25m, otherwise, the radient was classified the rock area(.i.e. slope of less than $5^{\circ}$ the dead level) and the slope area where is steep slope. Moreover, there was showed evenly a variety of aspect. Land-use were divided the field(Kei island), dry native grasslands(Hadon island), naturalized grasslands(Sangdon island), Pinus thunbergii community(Dacwa island, Hwanggang island, Naebi island, Yuk island), the rock area(Oebi island, Prickly castor-oil tree island, Tongin island). As the results of flora survey, the number of plant species were 30$\sim$115 species and the naturalized species were found 2$\sim$12 species in each site. The results of plant community structure analysis, The dominant species were Pinus thunbergii and Pinus densiflora were in upper tree layer, furthermore, it were Pinus thunbergii, Eurya japonica, Prunus sargentii, Celtis sinensis, Morus bombycis, ect. in cannopy tree layer. In shrub layer, the dominant species were Rosa multiflora, Rubus crataegifolius, Parthenocissus tricuspidata, etc. The status of wildbird bird, had been found 42 species 938 individuals, especially, there were Bubo bubo kiautschensis(natural monument No. 324) and Haematopus ostralegus osculans(natural monument No. 326). According to these synthetic results, we are able to classify the 5 types of environment ecology such as the natural coast forest that composed of Pinus thunbergii and Pinus densiflora(Daewa island, Hwanggang island, Naebi island, Oebi island, Tongin island, Yuk island), the field in vegetation area(Kei island), vegetation succession area of fallow field type(Hadon island), vegetation damage area by the forest fire and disturbance elements(Prickly castor-oil tree island), dominant naturalized species grassland by grazing cattle(Sangdon island).

• 제어로봇시스템학회논문지
• /
• 제22권3호
• /
• pp.192-198
• /
• 2016

Motion planning problem is still one of the important issues in robotic applications. In many real-time motion planning problems, it is advisable to find a feasible solution quickly and improve the found solution toward the optimal one before the previously-arranged motion plan ends. For such reasons, sampling-based approaches are becoming popular for real-time application. Especially the use of a rapidly exploring random $tree^*$ ($RRT^*$) algorithm is attractive in real-time application, because it is possible to approach an optimal solution by iterating itself. This paper presents a modified version of informed $RRT^*$ which is an extended version of $RRT^*$ to increase the rate of convergence to optimal solution by improving the sampling method of $RRT^*$. In online motion planning, the robot plans a path while simultaneously moving along the planned path. Therefore, the part of the path near the robot is less likely to be sampled extensively. For a better solution in online motion planning, we modified the sampling method of informed $RRT^*$ by combining with the sampling method to improve the path nearby robot. With comparison among basic $RRT^*$, informed $RRT^*$ and the proposed $RRT^*$ in online motion planning, the proposed $RRT^*$ showed the best result by representing the closest solution to optimum.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권6호
• /
• pp.491-502
• /
• 2022

The purpose of this study was to retrospectively investigate the upper and lower control limits of treatment planning parameters using EBT film based delivery quality assurance (DQA) results and to analyze the results of statistical process control (SPC) in helical tomotherapy (HT). A total of 152 patients who passed or failed DQA results were retrospectively included in this study. Prostate (n = 66), rectal (n = 51), and large-field cancer patients, including lymph nodes (n = 35), were randomly selected. The absolute point dose difference (DD) and global gamma passing rate (GPR) were analyzed for all patients. Control charts were used to evaluate the upper and lower control limits (UCL and LCL) for all the assessed treatment planning parameters. Treatment planning parameters such as gantry period, leaf open time (LOT), pitch, field width, actual and planning modulation factor, treatment time, couch speed, and couch travel were analyzed to provide the optimal range using the DQA results. The classification and regression tree (CART) was used to predict the relative importance of variables in the DQA results from various treatment planning parameters. We confirmed that the proportion of patients with an LOT below 100 ms in the failure group was relatively higher than that in the passing group. SPC can detect QA failure prior to over dosimetric QA tolerance levels. The acceptable tolerance range of each planning parameter may assist in the prediction of DQA failures using the SPC tool in the future.