• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

• Journal of Navigation and Port Research
• /
• v.39 no.3
• /
• pp.157-163
• /
• 2015

Recently, there has been much interest in the e-Navigation that applies a variety of digital devices to shipboard thanks to the high interest to maritime safety and the rapid development of ICT technologies. The e-Navigation proposes a new ICT paradigm in maritime information service and maritime safety. This study proposes the shore-based maritime information service platform that enables the converged services of various kinds of maritime data and the standard ENC based on IHO S-100. The proposed maritime information service platform enables the harmonized integration, presentation and web services of ENC, sensed data such as AIS, ocean weather and currents, and geospatial data. Also, the platform enables the mobile maritime information service through WebApp or App software operating in mobile devices of smart phone or web pad. Finally, the proposed platform accommodates the standard ENC of the existing S-57 and the new S-101, and the standard web services of WMS and WMTS of ISO 19100 and OGC.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.47-56
• /
• 2010

In navigation, officers receive data about inside and outside of ship from several devices(ex, GPS / AIS / ECDIS / ARPA Radar / etc) in bridge, and use it to recognize and predict safety situations. However, observation work of a officer is still hard for a torrent of data from several devices, and the problem of inconsistent data among the devices. In previous research, we presented the conceptual model of Intelligent Navigation Safety Information System based on information fusion, and showed the example of the conceptual model using CF (Certainty Factor) expert system to solve this problem. The information fusion technology needs various reasoning skills, and CF expert system is not enough to express ambiguous or indefinite factors. In this paper, we propose the concept of an intelligent navigation information fusion using fuzzy expert system to describe the ambiguous factors, and show the validity of applying fuzzy expert system to the Navigation Safety Information System through the design and implementation of the proposed concept.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.5
• /
• pp.501-506
• /
• 2015

This study seeks to analyze ships traffic characteristics according to water time in order to provide the necessary data for efficient traffic management development. To analyze maritime traffic volume according to water time, 1 year amount of solar calendar data were converted into lunar calendar, and then applied the traditional water time system of West Sea by using AIS(Automatic Identification System) observation data gathered in Mokpo port for a year of 2013. As a result, it was found herein that the number of outbound ships was larger on the $2^{nd}-3^{nd}$ water times than the $7^{th}$ water times by 23-24 %. And the number of inbound ships was higher on the $12^{th}-13^{th}$ water times than the $9^{th}$ water time by 29-33 %. The hourly variation index of inbound and outbound ships according to time, in particular, was found to change in the form of sine function model. This study is expected to serve as a necessary basic material for development of maritime traffic management according to water time.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2012.06a
• /
• pp.323-325
• /
• 2012

충남 보령시 오천면 인근해역에 건설될 신보령화력 1,2호기 건설사업과 관련하여 항만공사(연료하역부두, 석회석하역부두 축조)로 인하여 선박통항에 미치는 영향을 사전에 조사 측정 및 평가하여 설계에 반영토록 하고, 부두축조에 따른 대상 선박 항로 통항 및 접 이안에 대한 안전성 평가, 해상교통류 시뮬레이션, 계류안전성 평가 등을 시행하였으며, 이에 대한 결과를 소개하고자 한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.24-25
• /
• 2019

최근 빅데이터 기술 개발로 방대한 데이터의 유의미한 분석 및 예측이 용이해졌다. 선박교통관제센터에서는 각종 센서와 다양한 정보를 기반으로 VHF 교신을 통해 선박교통관제를 수행한다. 관제사가 활용하는 레이더, AIS, Port-MIS. 센서 등의 데이터들이 디지털로 저장되고 있으며, 관제사의 VHF 교신내용은 디지털파일로 저장되어 선박교통관제센터의 서버 2개월간 보관된다. 본 논문에서는 관제 결과로 저장되고 있는 관제 로그 데이터를 활용하여 빅데이터를 구성하고 이를 기반으로 유의미한 정보를 생성할 수 있는 방안을 연구하였다.

• Journal of the Korean Institute of Navigation
• /
• v.22 no.4
• /
• pp.21-29
• /
• 1998

The marine self-organizing VHF data link is a digital radio link with self-organizing ability, which exploits the STDMA algorithm and operates in marine VHF channels. It can support the applications of surveillance, situation awareness and communication. It is the core technology of the Universal AIS which is considered as a future surveillance system at sea by the IMO. In this paper, the operational principle of the marine self-organizing VHF data link is introduced. Simultaneously, a new access protocol is proposed to enhance the marine self-organizing VHF data link so as to support point-to-point communication. The point-to-point communication is one of the most important bases to establish dynamic internetworks among computers on the bridges in the future.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.3
• /
• pp.253-258
• /
• 2015

The purpose of this study is to find suitable probability distribution function of complex distribution data like multimodal. Normal distribution is broadly used to assume probability distribution function. However, complex distribution data like multimodal are very hard to be estimated by using normal distribution function only, and there might be errors when other distribution functions including normal distribution function are used. In this study, we experimented to find fit probability distribution function in multimodal area, by using AIS(Automatic Identification System) observation data gathered in Mokpo port for a year of 2013. By using chi-squared statistic, gaussian mixture model(GMM) is the fittest model rather than other distribution functions, such as extreme value, generalized extreme value, logistic, and normal distribution. GMM was found to the fit model regard to multimodal data of maritime traffic flow distribution. Probability density function for collision probability and traffic flow distribution will be calculated much precisely in the future.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.6
• /
• pp.658-665
• /
• 2019

Among the renewable energy resources, wind power is growing rapidly in terms of technological development and market share. Recently, onshore wind farm have been affected by limitations of terrestrial space and environmental problems. Consequently, installation sites have been moved to the sea, and the development of floating offshore wind farms that are installed at deep waters with more abundant wind conditions is actively underway. In the context of maritime traffic, the optimal site of offshore wind farms is required to minimize the interference between ships and wind turbines and to reduce the probability of accidents. In this study, genetic algorithm based AIS(Automatic Indentification System) data composed of genes and chromosomes has been used. The optimal site of floating offshore wind farm was selected by using 80 genes and by evaluating the fitness of genetic algorithm. Further, the final site was selected by aggregating the seasonal optimal site. During analysis, 11 optimal site were found, and it was verified that the final site selected usng the genetic algorithm was viable from the perspective of maritime traffic.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.209-215
• /
• 2022

On the Jeju coast, international cruise ships, passenger ships, and other ships pass frequently, as well as many fishing boats. Thus, there is a high risk of marine accidents and frequent ship collisions. Accordingly, it is urgent to establish a coastal VTS for systematic safety management of ships passing through the coastal waters of Jeju. The purpose of this study was to set the area of the VTS to be newly established. In this study, to calculate the workload of the VTS operators, a formula was proposed that reflects the monitoring workload considering the monitoring frequency and required time for target as well as non-target ships and the workload for ship collision situations. The proposed formula was applied to the newly established VTS area in Jeju. Three control sectors were set up in each VTS center. The average number of workstations per hour was approximately 1, so the division between sectors was appropriate. Thus, it was deduced that there would be no workload for the VTS operators. It is expected that the method proposed in this study can be used as primary data for calculating the appropriate number of workstations for the current VTS, and setting the VTS area for a new coastal VTS in the future.