• Journal of Intelligence and Information Systems
• /
• v.10 no.3
• /
• pp.1-10
• /
• 2004

In this paper, a new character segmentation algorithm of machine printed character recognition is proposed. The new approach of the proposed character segmentation algorithm overcomes the weak points of both feature-based approaches and recognition-based approaches in character segmentation. This paper defines side profiles of touching characters. The character segmentation algorithm gives a candidate single character in touching characters by side profiles, without any help of character recognizer. It segments touching characters and decides the candidate single character by side profiles. This paper also defines cutting cost, which makes the proposed character segmentation find an optimal segmenting path. The performance of the proposed character segmentation algorithm in this paper has been obtained using a real envelope reader system, which can recognize addresses in U.S. mail pieces and sort the mail pieces. 3359 mail pieces were tested. The improvement was from $68.92\%\;to\;80.08\%$ by the proposed character segmentation.

• Fire Science and Engineering
• /
• v.31 no.5
• /
• pp.107-116
• /
• 2017

Fires in tunnels are an international concern and fatal accidental fires in tunnels seem to occur on annual. They have the potential to become much worse int the future as more and longer tunnels are constructed and as traffic densities increase. This is a serious problem. The main purpose of this study is to develop operational procedures for fire brigades in road tunnel fires. This study discussed the past to see what can be learned from the incidents that have already done in tunnels. 73 cases of road tunnel fires domestic and outside of Korea were investigated and classified into 4 incident categories. Among them, 4 tunnel fires are highlighted, focusing on the activities of fire brigades and operation. Regarding the establishment of the strategies for fire fighting, 6 kinds of fire scenario curves have been deducted with regard to the relation between intervention time and heat release rate. It made the choice from the defensive or aggressive fire fighting activities depending on two criteria i.e. response limit and maximum response time. Road Tunnel Classification models can be useful when a fire brigade evaluates fire risk levels in the tunnels under its jurisdiction from the firefighting point of view and sets up preventive measures.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2023.11a
• /
• pp.278-281
• /
• 2023

연구목적: 본 연구는 요양병원 등 재난취약시설에 재난이 발생할 경우 잔류한 요구조자를 정확하게 파악하여 소방 등 대응기관에 제공하는 APC(Auto People Counting)의 인식률 개선에 목적이 있다. 현재 재난 발생 시 건물 내 요구조자의 현황 파악을 위해 대응기관이 재난 현장에 도착하여 건물관계자에게 직접 물어보고 있다. 이는 요구조자에 대한 부정확한 정보일 가능성이 있어 대응기관의 업무범위가 확대되고 이로인해 구조자의 안전에도 위험이 될 수 있다. APC는 건물내 출입하는 인원을 자동으로 집계하여 실시간 잔류인원 정보를 제공함으로써 재난 시 요구조자 현황을 정확히 파악할 수 있다. 본 연구에서는 APC가 보다 정확하게 출입 인원을 집계할 수 있도록 최적의 인공지능 알고리즘을 선정하는데 목적이 있다. 연구방법: 본 연구에서는 실제 재난취약시설에 설치되어 운영 중인 APC를 대상으로 카메라를 통해 출입 인원의 이미지를 인식하는 알고리즘을 개선하기 위해 CNN모델을 활용하여 베이스라인 모델링을 하였다. 다양한 알고리즘의 성능을 분석하여 상위 7개의 후보군을 선정하고 전이학습 모델을 활용하여 성능이 가장 우수한 최적의 알고리즘을 선정하는 방법으로 연구를 수행하였다. 연구결과: 실험결과 시간과 성능이 가장 좋은 Densenet201, Resnet152v2 모델의 정밀도와 재현율을 확인한 결과 모든 라벨에 대해서 정확도 100%를 나타내는 것을 확인할 수 있었다. 이 중 Densenet201 모델이 더 높은 성능을 보여주었다. 결론: 다양한 인공지능 알고리즘 중 APC에 적용할 수 있는 최적의 알고리즘을 선정하였고 이는 APC의 인식률을 개선하여 재난시 요구조자의 정보를 정확하게 파악하여 신속하고 안전한 구조작업이 가능할 것이다. 이는 요구조자의 안전한 구조뿐만 아니라 구조작업을 수행하는 구조자의 안전을 확보하는 데 기여할 것으로 기대된다. 향후 연무 등 다양한 재난상황에서 재난취약시설 내 출입인원을 정확하게 파악할 수 있도록 알고리즘 분석 및 학습에 대한 추가 연구가 요구된다.

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.181-190
• /
• 2005

The time required for airport process is considered more important as the airports are becoming bigger. International Civil Aviation Organization mattes this international standards and recommends not to exceed it. The passenger forecasting model is developed to predict the number of passengers at the check-in counter, and the area of formalities for departure and entry. In case of forecasting the number of outbound-passengers. the patterns of show-up lead time(SLT) at the check-in counter and lag time from check-in counter to the area of departure formalities are modeled in terms of time. On the other hand, the matter of the choice of check-in counters and areas of departure formalities are modeled in terms of space. In case of forecasting the number of inbound-passengers and transfer passengers, the time of airplane movement from arrival to block on at the gate and the time of passengers required from gate to the area of formalities for entry are modeled in terms of time. While the matter of the choice of gates and the areas of formalities for entry are modeled in terms of space. The average error of forecasting outbound-passengers and inbound-passengers is respectively 15% and 10%, which are considered excellent with the 5% error of passenger reservation information as input data. Through the development of passenger forecasting models, we assure we could provide passengers with valuable service because we allocate resource such as employees and equipments according to the degree of concentration of passengers.

• Journal of Korea Port Economic Association
• /
• v.26 no.3
• /
• pp.42-55
• /
• 2010

This paper primarily deals with a decision-making for determining the number of voyages in each ship size under a specific port structure in order to minimize the total transport cost consisting of transport cost at sea, queuing cost in port, and inventory cost in yard. As a result of computer simulation using queuing model characterized by inter-arrival time distribution, we were able to find out some combination of voyage numbers of 3 ship-size(50,000-ton, 100,000-ton, and 200,000-ton), where the total transport cost can be minimized under a specific port structure. The simulation model also allows us to figure out any trade-off relationship among sea transport cost, queuing cost in port, and inventory cost in yard. Put it differently, an attempt to reduce the sea transport cost by increasing the number of voyages of the largest ship size, the transport cost incurred in both port and yard is hypothesized to be increased and vice versa. Consequently, Port managers are required to adjust the number of annual number of voyages allocated in each ship size, put into the sea lines for importing raw materials, in order to optimize the transport costs incurred under the specific port system. We may consider a net present value(NPV) model for performing an economic feasibility analysis on port investment project. If a total discounted net benefit, including cost savings, exceeds the initial investment for an additional berth construction, then we accept the port investment project. Otherwise, we reject the proposed port investment plan.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.10A
• /
• pp.912-921
• /
• 2005

Optical burst switching(OBS) is a promising solution for building terabit optical routers and realizing If over WDM. Channel scheduling Algorithm for reduce contention is one of the major challenges in OBS. We address the issue of how to provide basic burst channel scheduling in optical burst switched WDM networks with fiber delay lines(FDLs). In OBS networks the control and payload components or a burst are sent separately with a time gap. If CHP arrives to burst switch node, because using scheduling algorithm for data burst, reservation resources such as wavelength and transmit data burst without O/E/O conversion, because contention and void between burst are happened at channel scheduling process for data burst that happened the link utilization and bust drop probability Existent proposed methods are become much research to solve these problems. Propose channel scheduling algorithm that use Release Time of bust to emphasize clearance between data and data dissipation that is happened in data assignment in this treatise and maximize bust drop probability and the resources use rate (RTUC : Release Time Unscheduled Channel). As simulation results, Confirmed that is more superior in terms of data drop and link utilization than scheduling algorithm that is proposed existing. As simulation results, confirmed improved performance than scheduling algorithm that is proposed existing in terms of survival of burst, efficiency resource and delay. However, In case load were less, degradation confirmed than existent scheduling algorithm relatively, and confirmed that is superior in data drop aspect in case of load increased.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.4
• /
• pp.287-296
• /
• 2015

Recent navigation systems provide quick guide services, based on processing real-time traffic information and past traffic information by applying predictable pattern for traffic information. However, the current pattern for traffic information predicts traffic information by processing past information that it presents an inaccuracy problem in particular circumstances(accidents and weather). So, this study presented a more precise predictive traffic information system than historical traffic data first by analyzing route search data which the drivers ask in real time for the quickest way then by grasping traffic congestion levels of the route in which future drivers are supposed to locate. First results of this study, the congested route from Yang Jae to Mapo, the analysis result shows that the accuracy of the weighted value of speed of existing commonly congested road registered an error rate of 3km/h to 18km/h, however, after applying the real predictive traffic information of this study the error rate registered only 1km/h to 5km/h. Second, in terms of quality of route as compared to the existing route which allowed for an earlier arrival to the destination up to a maximum of 9 minutes and an average of up to 3 minutes that the reliability of predictable results has been secured. Third, new method allows for the prediction of congested levels and deduces results of route searches that avoid possibly congested routes and to reflect accurate real-time data in comparison with existing route searches. Therefore, this study enabled not only the predictable gathering of information regarding traffic density through route searches, but it also made real-time quick route searches based on this mechanism that convinced that this new method will contribute to diffusing future traffic flow.

• Journal of Korean Society of Transportation
• /
• v.23 no.2
• /
• pp.117-130
• /
• 2005

In both deteministic user Optimal Traffic Assignment Model (UOTAM) and stochastic UOTAM, travel time, which is a major ccriterion for traffic loading over transportation network, is defined by the sum of link travel time and turn delay at intersections. In this assignment method, drivers actual route perception processes and choice behaviors, which can become main explanatory factors, are not sufficiently considered: therefore may result in biased traffic loading. Even though there have been some efforts in Stochastic UOTAM for reflecting drivers' route perception cost by assuming cumulative distribution function of link travel time, it has not been fundamental fruitions, but some trials based on the unreasonable assumptions of Probit model of truncated travel time distribution function and Logit model of independency of inter-link congestion. The critical reason why deterministic UOTAM have not been able to reflect route perception cost is that the route perception cost has each different value according to each origin, destination, and path connection the origin and destination. Therefore in order to find the optimum route between OD pair, route enumeration problem that all routes connecting an OD pair must be compared is encountered, and it is the critical reason causing computational failure because uncountable number of path may be enumerated as the scale of transportation network become bigger. The purpose of this study is to propose a method to enable UOTAM to reflect route perception cost without route enumeration between an O-D pair. For this purpose, this study defines a link as a least definition of path. Thus since each link can be treated as a path, in two links searching process of the link label based optimum path algorithm, the route enumeration between OD pair can be reduced the scale of finding optimum path to all links. The computational burden of this method is no more than link label based optimum path algorithm. Each different perception cost is embedded as a quantitative value generated by comparing the sub-path from the origin to the searching link and the searched link.

• Journal of Yeungnam Medical Science
• /
• v.16 no.2
• /
• pp.283-295
• /
• 1999

Background: Patients with acute non-traumatic chest pain are among the most challenging patients for care by emergency physicians, so the correct diagnosis and triage of patients with chest pain in the emergency department(ED) becomes important. To avoid discharging patients with acute myocardial infarction(AMI) without medical care, most emergency physicians attempt to admit almost all patients with acute chest pain and order many laboratory tests for the patients. But in practice, many patients with non-cardiac pain can be discharged with simple tests and treatment. These patients occupy expensive intensive care beds, substantially increasing financial cost and time of stay at ED for the diagnosis and treatment of myocardial ischemia and AMI. Despite vigorous efforts to identify patients with ischemic heart disease, approximately 2% to 5% of patients presented to the ED with AMI and chest pain are inadvertently discharged. If the cause for the chest pain is known, rapid and accurate diagnosis can be implemented, preventing wastes in time and money and inadvertent discharge. Methods and Results: The medical records of 488 patients from Jan. 1 to Dec. 31, 1997 were reviewed. There were 320(angina pectoris 140, AMI 128) cases of cardiac diseases, and 168(atypical chest pain 56, pneumothorax 47) cases of non-cardiac diseases. The number of associated symptoms were $1.1{\pm}0.9$ in non-cardiac diseases, $1.4{\pm}1.1$ in cardiac diseases and $1.7{\pm}1.1$ in AMI(p<0.05). In laboratory finding the sensitivity of electrocardiography(EKG) was 96.1%, while the sensitivity of myoglobin test ranked 45.1%. Admission rate was 71.6% in for cardiac diseases and 50.6% for non-cardiac diseases(p<0.01). Mortality rate was 8.8% in all cases, 13.8% in cardiac diseases, 0.6% in non-cardiac diseases, and 28.1% especially in AMI. Conclusion: In conclusion, all emergency physicians should have thorough knowledge of the clinical characteristics of the diseases which cause non-traumatic chest pain, because a patient with any of these life-threatening diseases would require immediate treatment. Detailed history on the patient should be taken and physical examination performed. Then, the most simple diagnostic approach should be used to make an early diagnosis and to provide treatment.

• Korean Journal of Poultry Science
• /
• v.35 no.2
• /
• pp.177-182
• /
• 2008

This studies were conducted to investigate the effect of holding time of broiler at slaughter house on chicken meat quality. Short holding time ($1{\sim}2hrs $) increased chicken meat quality compared to long holding time ($14{\sim}15 hrs$), which resulted in 14% higher grade $1^+$ chicken. In portioned meat, short holding time ($1{\sim}2 hrs$) resulted in 15% higher incidence of grade $1^+$ chicken breast. Also, long holding time occurred higher PSE incidence of chicken breast. pH value of the chicken meat with short holding time was similar to that with long holding time, and that with medium holding time showed the lowest. $L^*$ (lightness) value of the chicken meat was lower with medium holding time than with short holding time, but that in muscle and skin showed increasing tendency with long holding time. Holding time showed no effect on $a^*$ (redness) of the chicken meat, but longer holding time decreased $b^*$ (yellowness) value. This indicated that long holding time adversely affected chicken meat quality.