• Korean Journal of Remote Sensing
• /
• v.39 no.1
• /
• pp.77-86
• /
• 2023

Ship detection is widely used in areas such as maritime security, maritime traffic, fisheries management, illegal fishing, and border control, and ship detection is important for rapid response and damage minimization as ship accident rates increase due to recent increases in international maritime traffic. Currently, according to a number of global and national regulations, ships must be equipped with automatic identification system (AIS), which provide information such as the location and speed of the ship periodically at regular intervals. However, most small vessels (less than 300 tons) are not obligated to install the transponder and may not be transmitted intentionally or accidentally. There is even a case of misuse of the ship'slocation information. Therefore, in this study, ship detection was performed using high-resolution optical satellite images that can periodically remotely detect a wide range and detectsmallships. However, optical images can cause false-alarm due to noise on the surface of the sea, such as waves, or factors indicating ship-like brightness, such as clouds and wakes. So, it is important to remove these factors to improve the accuracy of ship detection. In this study, false alarm wasreduced, and the accuracy ofship detection wasimproved by removing wake.As a ship detection method, ship detection was performed using machine learning-based random forest (RF), and convolutional neural network (CNN) techniquesthat have been widely used in object detection fieldsrecently, and ship detection results by the model were compared and analyzed. In addition, in this study, the results of RF and CNN were combined to improve the phenomenon of ship disconnection and the phenomenon of small detection. The ship detection results of thisstudy are significant in that they improved the limitations of each model while maintaining accuracy. In addition, if satellite images with improved spatial resolution are utilized in the future, it is expected that ship and wake simultaneous detection with higher accuracy will be performed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.5
• /
• pp.462-469
• /
• 2023

In this study, we propose a method for evaluating the risk of collision between ships to support determination on the risk of collision in a situation in which ships encounter each other and to prevent collision accidents. Because several uncertainties are involved in the navigation of a ship, must be considered when evaluating the risk of collision. We apply the Dempster-Shafer theory to manage this uncertainty and evaluate the collision risk of each target vessel in real time. The distance at the closest point approach (DCPA), time to the closest point approach (TCPA), distance from another vessel, relative bearing, and velocity ratio are used as evaluation factors for ship collision risk. The basic probability assignments (BPAs) calculated by membership functions for each evaluation factor are fused through the combination rule of the Dempster-Shafer theory. As a result of the experiment using automatic identification system (AIS) data collected in situations where ships actually encounter each other, the suitability of evaluation was verified. By evaluating the risk of collision in real time in encounter situations between ships, collision accidents caused by human errora can be prevented. This is expected to be used for vessel traffic service systems and collision avoidance systems for autonomous ships.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.49 no.3
• /
• pp.125-134
• /
• 2023

Objectives: The aim of the study was to quantify and compare craniofacial asymmetry in subjects with and without symptoms of temporomandibular joint disorders (TMDs). Materials and Methods: A total of 126 adult subjects were categorized into two groups (63 with a TMDs and 63 without a TMDs), based on detection of symptoms using the Temporomandibular Joint Disorder-Diagnostic Index (TMD-DI) questionnaire. Posteroanterior cephalograms of each subject were traced manually and 17 linear and angular measurements were analyzed. Craniofacial asymmetry was quantified by calculating the asymmetry index (AI) of bilateral parameters for both groups. Results: Intra- and intergroup comparisons were analyzed using independent t-test and Mann-Whitney U test, respectively, with a P<0.05 considered statistically significant. An AI for each linear and angular bilateral parameter was calculated; higher asymmetry was found in TMD-positive patients compared with TMD-negative patients. An intergroup comparison of AIs found highly significant differences for the parameters of antegonial notch to horizontal plane distance, jugular point to horizontal plane distance, antegonial notch to menton distance, antegonial notch to vertical plane distance, condylion to vertical plane distance, and angle formed by vertical plane, O point and antegonial notch. Significant deviation of the menton distance from the facial midline was also evident. Conclusion: Greater facial asymmetry was seen in the TMD-positive group compared with the TMD-negative group. The mandibular region was characterized by asymmetries of greater magnitude compared with the maxilla. Patients with facial asymmetry often require management of temporomandibular joint (TMJ) pathology to achieve a stable, functional, and esthetic result. Ignoring the TMJ during treatment or failing to provide proper management of the TMJ and performing only orthognathic surgery may result in worsening of TMJ-associated symptoms (jaw dysfunction and pain) and re-occurrence of asymmetry and malocclusion. Assessments of facial asymmetry should take into account TMJ disorders to improve diagnostic accuracy and treatment outcomes.

• Journal of Trauma and Injury
• /
• v.23 no.2
• /
• pp.68-74
• /
• 2010

Purpose: The purpose of this study is, first, to analyze the risk factors that influence the severity of injury in pediatric multiple trauma patients and, second, to present solutions for the problems related to the treatment of such patients. Our living situations are so complicated that the danger of accidents is truly open to children who are not prepared. We need to draw attention to the increased numbers of various accidents involving children. Methods: We studied patients who visited the Emergency Medical Center at Chosun University Hospital from January 1, 2006, to December 31, 2008. Using medical records, we evaluated the general characteristics: the mechanism of injury, the vital signs, the revised trauma score (RTS), the injury severity score (ISS), and the hemoglibin value, which was checked at the time of visit, and the presence or the absence of emergent on regular surgery. We divided the level of injury as follows: light level (1-8 points), mid level (9-15 points), and serious level (above 16 points). We analyzed the medical data by using SPSS 17.0 for windows. Results: The average age of the patients examined was 8.6 years. The number of 6- to 11-year-old patients was 96, which was the largest, but the degree of injury severity was the highest among infant (0-2 years), according to ISS 7.95(${\pm}6.85$). The frequency of accidents was highest on sunny days, and most accidents occurred from 16:00 to 20:00. The cause of multiple trauma for children was the greatest in the traffic accident, (95 patients, 49.0%). In addition, the trauma caused by traffic accidents showed the highest ISS value ($9.02{\pm}6.42$) and the most serious degree (P=0.004). The ISS level of injury ($8.40{\pm}6.64$) for patients moved from a secondary hospital was higher than that ($6.49{\pm}5.57$) for patients who visited the medical center directly. The severity of injury was highest for patients who used a 119 ambulance ($8.84{\pm}5.80$). According to the injured parts of body, Injuries to the arms and the feet most frequent (79 patients, 40.7%), but the level of injury was the highest for internal organs and chest, $16.42{\pm}8.56$ and $11.23{\pm}6.97$, respectively. Conclusion: We used Abbreviated Injury Scale (AIS) in order to examine the characteristics by injured body part for pediatric multiple trauma patients. Because the degree of injury was the highest for internal organs or the chest, we need to more seriously examine and provide for patients who are suspected of having injuries to the internal organs or the chest. We need to quickly determine the need for surgery in patients with serious injuries to the arms and the feet, which is the greatest in frequency. In particular, we need to consider the surgical care of patients who are not very high in the severity of injury to their brains.

• 선박안전기술공단연구보고서
• /
• s.4
• /
• pp.1-108
• /
• 2007

2007. 7. 23 IMO의 NAV(항해안전전문위원회)53차 회의에서는 e-Navigation을 해상에서의 안전, 보안, 해양환경보호를 목적으로 전자적인 수단에 의해 선박과 육상에서 해양정보를 수집, 교환, 표시함으로써 항구와 항구간의 항해 및 관련된 서비스를 향상시키는 것으로 정의하고 있다.2005년 11월 영국의 교통부 장관 Stephen 박사는 Royal Institute ofNavigation에서의 연설에서 해상안전과 환경보호를 위하여 선박의 항해를 감시하는 관제소 및 항행하는 선박에 유용하고 정확한 정보가 더 많이 필요함을 역설하였다. 그리고 첨단 기술에 의해 자동화된 항공 항법분야를 예로들면서, 선박의 항법 분야도 항해와 관련된 모든 시설 및 작업을 전자적 수단으로 대체하는 개념인 e-Navigation으로 전환되어야 하며 영국은 이에 필요한 작업을 주도하겠다는 의견을 피력하였다. Stephen은 e-Navigation 도입으로 얻을 수 있는 이익으로 첫째, 항해 실수로 인한 사고 확률저감, 둘째,사고 발생 시 인명 구조 및 피해 확산을 위한 효율적 대응, 셋째, 전통적인항해시설 설치 불필요로 인한 비용 저감, 넷째 선박입출항 수속의 간편화 및항로의 효율적 운용으로 인한 상업적 이익 등을 들었다. 반면에e-Navigation 체계로 전환 시 예상되는 장애로는 첫째, 체계 구축을 위한 비용(특히 개발도상국가들의 경우 어려움 예상), 둘째, e-Navigation의 성과 달성을 위하여 세계 전 해역의 모든 선박이 e-Navigation 체계에 동참하도록유도하는 문제, 셋째, 전자해도 표시 및 선교 장비들에 대한 표준화 문제, 넷째, 육상에 설치할 e-Navigation 센터의 설계 및 구축 등을 꼽았다.IMO는 2005년 81차 MSC(해사안전위원회) 회의에서 영국이 일본, 마샬아일랜드, 네덜란드, 노르웨이, 싱가포르, 미국과 공동으로 제안한 ‘e-Navigation전략 개발’ 의제를 2006년 82차 MSC 회의에서 채택하고, NAV(항해 전문위원회)를 통하여 2008년까지 e-Navigation의 구체적 개념을 정립하고 향후 개발하여야 할 전략적 비전과 정책을 수립하기로 하였다. 이어서 영국을 의장으로 e-Navigation 전략개발 통신작업반이 구성되었는데, 지난 년간 19개국, 16개 전문기관이 참여하여 아래의 작업이 수행되었다. ○ e-Navigation 개념의 정의와 목적 ○ e-Navigation에 대한 핵심 이슈 및 우선 순위 식별 ○ e-Navigation 개발에 따른 이점과 단점의 식별 ○ IMO 및 회원국 등의 역할 식별 ○ 이행계획을 포함한 추가 개발을 위한 작업계획의 작성 IMO에서 수행되고 있는 e-Navigation 전략 개발 의제 일정은 2008년까지이다. 이 전략 개발에 있어서 중요한 요소는 e-Navigation이 포함할 서비스범위, 포함하는 서비스 제공에 필요한 인프라 및 장비의 식별, 인프라 구축및 운용비용을 부담할 주체에 대한 논의, e-Navigation으로 인한 이익과 투자비용에 대한 비교 분석 등이다. 이 과정에서 정부, 선주, 항만운영자, 선원등의 입장 차이와 선진국과 개발도상국 간의 경제 수준 차이는 전략 개발에있어 큰 어려움을 줄 것이므로, 이들이 합의된 전략을 만들기 위해서는 예정된 기간보다 다소 늦어질 가능성도 있다.e-Navigation 전략 개발이 완료되면 1단계로는 해상교통 관제시스템, 선박선교 장비, 무선 통신장비 등에 대한 표준화 작업이 이루어질 것이다. 이 과정에서 각국 간에 자국 보유 기술을 표준화시키기 위한 경쟁이 치열할 것으로 예상된다. 2단계에서는 e-Navigation 체계 하에서의 다양하고 풍부한 서비스 제공을 위한 관련 소프트웨어 및 하드웨어의 개발이 이루어질 것으로전망되는데, 이는 지난 10년간 육상에서 인터넷망 설치 후 이루어진 관련 서비스 산업의 발전을 돌아보면 쉽게 짐작할 수 있을 것이다.e-Navigation 체계 하에서 선박의 항해는 현재와는 전혀 다른 패러다임으로 바뀔 것이다. 예를 들어 현재 입출항 시 요구되던 복잡한 절차는one-stop 쇼핑 형태로 단순화되고, 현재 선박 중심의 항해에서 육상e-Navigation 센터가 적극적으로 관여하는 항해 체계로 바뀔 것이며, 해상정보의 공유와 활용이 무선 인터넷을 통해 보다 광범위하게 이루어질 것이 다.e-Navigation의 잠재적 시장 규모는 선박에 새로이 탑재될 지능형 통합 항법시스템 구축과 육상 모니터링 및 지원 시스템 등 직접 시장이 약 50조원,전자해도, 통신장비, 관련 서비스 컨텐츠 등 간접 시장의 규모가 150조원으로 총 200조원으로 대략 추산하고 있다. 향후 이 거대한 시장을 차지하기 위한 전략 수립이 필요한 시점이다. 지금까지 항해 장비 관련 산업은 선진국의일부 업체들에 의해 독점되어 왔다. 우리나라는 조선과 해운에서 모두 선진국임에도 불구하고 이 분야에서는 대부분 수입에 의존해 왔다. e-Navigation체계 하에서는 전체 시장이 커지고 장비의 사양이 표준화됨에 따라 어느 소수 업체가 현재처럼 독점하기는 더 이상 어려울 것으로 예상된다. 따라서e-Navigation은 우리나라도 항해 장비 분야 시장을 차지할 수 있는 좋은 기회라고 할 수 있다. 특히 조선 1위의 장점을 적극 활용한다면 다른 나라보다우위의 경쟁력을 확보할 수도 있다. 또한, 서비스 분야의 시장은 IT 기술과밀접한 관계가 있으므로 IT 강국인 우리나라가 충분한 경쟁력을 갖고 있다고 할 수 있다.그러나, EU를 비롯한 선진국에서는 이미 e-Navigation 에 대비한 연구를10여년 전부터 수행해 왔다. 앞에서 언급한 EU의 MarNIS 사업은 현재 거의마무리 단계로 당장 실용화 할 수 있는 수준에 있는 것으로 보인다. 늦었지만 우리도 이를 따라잡기 위한 연구를 서둘러야 할 것이다. 국내에서도e-Navigation의 중요성을 깊이 인식하고, 2006년에는 관련 산학연 전문가들로 작업반을 구성하여 워크숍 등을 개최한 바 있다. 또한 해양수산부에서도e-Navigation 핵심기술 개발을 위한 연구사업을 기획 추진하고 있다.그러나 현재 항해통신장비들의 기술기준은 ITU의 전파규칙(RR)과 IMO결의 및 SOLAS 협약을 따르고 있는데 이들 규약이나 결의에 대한 국제적인 추이와 비교할 때 국내의 기술은 표준화되지 못한 부분이 많은 실정이다.본 연구에서는 e-Navigation sytem중 표준화가 필요한 요소와 전자해도,AIS 등 e-Navigation(통합전자항법시스템)관련 국내산업현황 실태조사를 통해 국내 e-Navigation기술개발 동향에 대해 조사하고자 한다.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.47-60
• /
• 2012

Video data comes in the form of the unstructured and the complex structure. As the importance of efficient management and retrieval for video data increases, studies on the video parsing based on the visual features contained in the video contents are researched to reconstruct video data as the meaningful structure. The early studies on video parsing are focused on splitting video data into shots, but detecting the shot boundary defined with the physical boundary does not cosider the semantic association of video data. Recently, studies on structuralizing video shots having the semantic association to the video scene defined with the semantic boundary by utilizing clustering methods are actively progressed. Previous studies on detecting the video scene try to detect video scenes by utilizing clustering algorithms based on the similarity measure between video shots mainly depended on color features. However, the correct identification of a video shot or scene and the detection of the gradual transitions such as dissolve, fade and wipe are difficult because color features of video data contain a noise and are abruptly changed due to the intervention of an unexpected object. In this paper, to solve these problems, we propose the Scene Detector by using Color histogram, corner Edge and Object color histogram (SDCEO) that clusters similar shots organizing same event based on visual features including the color histogram, the corner edge and the object color histogram to detect video scenes. The SDCEO is worthy of notice in a sense that it uses the edge feature with the color feature, and as a result, it effectively detects the gradual transitions as well as the abrupt transitions. The SDCEO consists of the Shot Bound Identifier and the Video Scene Detector. The Shot Bound Identifier is comprised of the Color Histogram Analysis step and the Corner Edge Analysis step. In the Color Histogram Analysis step, SDCEO uses the color histogram feature to organizing shot boundaries. The color histogram, recording the percentage of each quantized color among all pixels in a frame, are chosen for their good performance, as also reported in other work of content-based image and video analysis. To organize shot boundaries, SDCEO joins associated sequential frames into shot boundaries by measuring the similarity of the color histogram between frames. In the Corner Edge Analysis step, SDCEO identifies the final shot boundaries by using the corner edge feature. SDCEO detect associated shot boundaries comparing the corner edge feature between the last frame of previous shot boundary and the first frame of next shot boundary. In the Key-frame Extraction step, SDCEO compares each frame with all frames and measures the similarity by using histogram euclidean distance, and then select the frame the most similar with all frames contained in same shot boundary as the key-frame. Video Scene Detector clusters associated shots organizing same event by utilizing the hierarchical agglomerative clustering method based on the visual features including the color histogram and the object color histogram. After detecting video scenes, SDCEO organizes final video scene by repetitive clustering until the simiarity distance between shot boundaries less than the threshold h. In this paper, we construct the prototype of SDCEO and experiments are carried out with the baseline data that are manually constructed, and the experimental results that the precision of shot boundary detection is 93.3% and the precision of video scene detection is 83.3% are satisfactory.

• The Korean Journal of Air & Space Law and Policy
• /
• v.33 no.2
• /
• pp.61-114
• /
• 2018

Recently airspace became a hot issue considering today's international relations. However, there was no data that could be fully explained about a legal system of korean airspace, so I looked at law and practice about korean airspace together. The nation's aviation law sector is comletely separate from those related to civil and military aircraft, at least in legal terms. The Minister of Land, Infrastructure and Transport shall carry out his/her duties with various authority granted by the "Aviation Safety Act". The nation's aviation-related content is being regulated too much by the Ministry of Land, Infrastructure and Transport's notice or regulation, and there are many things that are not well known about which clauses of the upper law are associated with. The notice should be clearly described only in detail on delegated matters. As for the airspace system, the airspace system is too complex for the public to understand, and there seems to be a gap between law and practice. Therefore, I think it would be good to reestablish a simple and practical airspace system. Airspace and aviation related tasks in the military need to be clearly understood by distinguishing between those entrusted by the Minister of Land, Infrastructure and Transport and those inherent in the military. Regarding matters entrusted by the Minister of Land, Infrastructure and Transpor, it is necessary to work closely with the Minister of Land, Infrastructure and Transport when preparing related work guidelines, and to clarify who should prepare the guidelines. Regarding airspace control as a military operation, policies or guidelines that are faithful to military doctrine on airspace control are needed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.7
• /
• pp.848-857
• /
• 2018

Recently, around the world, active development of new renewable energy sources including solar power, waves, and fuel cells, etc. has taken place. Particularly, floating offshore wind farms have been developed for saving costs through large scale production, using high-quality wind power and minimizing noise damage in the ocean area. The development of floating wind farms requires an evaluation of the Maritime Safety Audit Scheme under the Maritime Safety Act in Korea. Floating wind farms shall be assessed by applying the line and area concept for systematic development, management and utilization of specified sea water. The development of appropriate evaluation methods and standards is also required. In this study, proper standards for marine traffic surveys and assessments were established and a systemic treatment was studied for assessing marine spatial area. First, a marine traffic data collector using AIS or radar was designed to conduct marine traffic surveys. In addition, assessment methods were proposed such as historical tracks, traffic density and marine traffic pattern analysis applying the line and area concept. Marine traffic density can be evaluated by spatial and temporal means, with an adjusted grid-cell scale. Marine traffic pattern analysis was proposed for assessing ship movement patterns for transit or work in sea areas. Finally, conceptual design of a Marine Traffic and Safety Assessment Solution (MaTSAS) was competed that can be analyzed automatically to collect and assess the marine traffic data. It could be possible to minimize inaccurate estimation due to human errors such as data omission or misprints through automated and systematic collection, analysis and retrieval of marine traffic data. This study could provides reliable assessment results, reflecting the line and area concept, according to sea area usage.

• Korean Journal of Radiology
• /
• v.24 no.2
• /
• pp.145-154
• /
• 2023

Objective: We aimed to evaluate the efficacy of EmboTrap II in terms of first-pass recanalization and to determine whether it could yield favorable outcomes. Materials and Methods: In this multicenter, prospective study, we consecutively enrolled patients who underwent mechanical thrombectomy using EmboTrap II as a front-line device. The primary outcome was the first pass effect (FPE) rate defined by modified Thrombolysis In Cerebral Infarction (mTICI) grade 2c or 3 by the first pass of EmboTrap II. In addition, modified FPE (mFPE; mTICI grade 2b-3 by the first pass of EmboTrap II), successful recanalization (final mTICI grade 2b-3), and clinical outcomes were assessed. We also analyzed the effect of FPE on a modified Rankin Scale (mRS) score of 0-2 at 3 months. Results: Two hundred-ten patients (mean age ± standard deviation, 73.3 ± 11.4 years; male, 55.7%) were included. Ninety-nine patients (47.1%) had FPE, and mFPE was achieved in 150 (71.4%) patients. Successful recanalization was achieved in 191 (91.0%) patients. Among them, 164 (85.9%) patients underwent successful recanalization by exclusively using EmboTrap II. The time from groin puncture to FPE was 25.0 minutes (interquartile range, 17.0-35.0 minutes). Procedure-related complications were observed in seven (3.3%) patients. Symptomatic intracranial hemorrhage developed in 14 (6.7%) patients. One hundred twenty-three (58.9% of 209 completely followed) patients had an mRS score of 0-2. Sixteen (7.7% of 209) patients died during the follow-up period. Patients who had successful recanalization with FPE were four times more likely to have an mRS score of 0-2 than those who had successful recanalization without FPE (adjusted odds ratio, 4.13; 95% confidence interval, 1.59-10.8; p = 0.004). Conclusion: Mechanical thrombectomy using the front-line EmboTrap II is effective and safe. In particular, FPE rates were high. Achieving FPE was important for an mRS score of 0-2, even in patients with successful recanalization.

• The Korean Society of Law and Medicine
• /
• v.24 no.4
• /
• pp.67-101
• /
• 2023

The utilization of generative AI in the medical field is also being rapidly researched. Access to vast data sets reduces the time and energy spent in selecting information. However, as the effort put into content creation decreases, there is a greater likelihood of associated issues arising. For example, with generative AI, users must discern the accuracy of results themselves, as these AIs learn from data within a set period and generate outcomes. While the answers may appear plausible, their sources are often unclear, making it challenging to determine their veracity. Additionally, the possibility of presenting results from a biased or distorted perspective cannot be discounted at present on ethical grounds. Despite these concerns, the field of generative AI is continually advancing, with an increasing number of users leveraging it in various sectors, including biomedical and life sciences. This raises important legal considerations regarding who bears responsibility and to what extent for any damages caused by these high-performance AI algorithms. A general overview of issues with generative AI includes those discussed above, but another perspective arises from its fundamental nature as a large-scale language model ('LLM') AI. There is a civil law concern regarding "the memorization of training data within artificial neural networks and its subsequent reproduction". Medical data, by nature, often reflects personal characteristics of patients, potentially leading to issues such as the regeneration of personal information. The extensive application of generative AI in scenarios beyond traditional AI brings forth the possibility of legal challenges that cannot be ignored. Upon examining the technical characteristics of generative AI and focusing on legal issues, especially concerning the protection of personal information, it's evident that current laws regarding personal information protection, particularly in the context of health and medical data utilization, are inadequate. These laws provide processes for anonymizing and de-identification, specific personal information but fall short when generative AI is applied as software in medical devices. To address the functionalities of generative AI in clinical software, a reevaluation and adjustment of existing laws for the protection of personal information are imperative.