http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
합류하는 두 항공기간 도착순서 결정에 대한 로지스틱회귀 예측 모형
정소연,이금진,Jung, Soyeon,Lee, Keumjin 한국항공운항학회 2015 한국항공운항학회지 Vol.23 No.4
This paper has its purpose on constructing a prediction model of the arrival sequencing strategy which reflects the actual sequencing patterns of air traffic controllers. As the first step, we analyzed a pair-wise sequencing of two aircraft entering TMA from different entering points. Based on the historical trajectory data, several traffic factors such as time, speed and traffic density were examined for the model. With statistically significant factors, we constructed a prediction model of arrival sequencing through a binary logistic regression analysis. With the estimated coefficients, the performance of the model was conducted through a cross validation.
김소윤,이금진,Kim, Soyeun,Lee, Keumjin 한국항공운항학회 2016 한국항공운항학회지 Vol.24 No.4
The departure flow management is the planning tool to optimize the schedule of the departure aircraft and allows them to join smoothly into the overhead traffic flow. To that end, the arrival time prediction to the merge point for the cruising aircraft is necessary to determined. This paper proposes a trajectory prediction model for the cruising aircraft based on the machine learning approach. The proposed method includes the trajectory vectored from the procedural route and is applied to the historical data to evaluate the prediction performances.
홍성권,이금진,Hong, Sungkwon,Lee, Keumjin 한국항공운항학회 2014 한국항공운항학회지 Vol.22 No.2
This paper introduces a new framework of predicting the arrival time of an aircraft by incorporating the probabilistic information of what type of trajectory pattern will be applied by human air traffic controllers. The proposed method is based on identifying the major patterns of vectored trajectories and finding the statistical relationship of those patterns with various traffic complexity factors. The proposed method is applied to the traffic scenarios in real operations to demonstrate its performances.
항공교통관제사의 항공기 합류순서결정에 대한 확률적 예측모형 개발
김민지,홍성권,이금진,Kim, Minji,Hong, Sungkwon,Lee, Keumjin 한국항공운항학회 2014 한국항공운항학회지 Vol.22 No.3
Arrival management is a tool which provides efficient flow of traffic and reduces ATC workload by determining aircraft's sequence and schedules while they are in cruise phase. As a decision support tool, arrival management should advise on air traffic control service based on the understanding of human factor of its user, air traffic controller. This paper proposed a prediction model for air traffic controller sequencing strategy by analyzing the historical trajectory data. Statistical analysis is used to find how air traffic controller decides the sequence of aircraft based on the speed difference and the airspace entering time difference of aircraft. Logistic regression was applied for the proposed model and its performance was demonstrated through the comparison of the real operational data.
감시시스템 성능에 따른 항공기간 최소분리간격 설정에 관한 연구
이효진(Hyojin Lee),이금진(Keumjin Lee) 제어로봇시스템학회 2012 제어로봇시스템학회 합동학술대회 논문집 Vol.2012 No.7
본 논문에서는 지상 관제사를 통한 항공교통관리 시 적용되는 최소분리간격의 설정에 관한 연구를 수행하였다. 항공기간 최소분리간격은 감시 장비의 성능에 의해 일차적으로 결정되는데, 매우 높은 수준의 항공안전기준으로 인해 감시 장비의 성능은 매우 정확하게 추정되어야 한다. 본 논문에서는 감시 장비의 위치정확도를 기존의 최대 우도추정(maximum likelihood estimation) 방법이 아닌, 최대신뢰추정치(upper confidence limit)를 통해 도출하는 기법을 새롭게 제안하였다. 이를 통해 매우 희박하게 발생하지만 상대적으로 큰 수준의 감시오차에 대한 보다 신뢰성 있는 고려가 가능하며, 따라서 보다 안전한 항공기간 최소분리간격의 설정이 가능하게 된다.
이용화,이주환,이금진,Lee, Yonghwa,Lee, Juhwan,Lee, Keumjin 한국항공운항학회 2021 한국항공운항학회지 Vol.29 No.2
Airline schedule is the most basic data for flight operations and has significant importance to an airline's management. It is crucial to know the airline's current schedule status in order to effectively manage the company and to be prepared for abnormal situations. In this study, machine learning techniques were applied to actual schedule data to examine the possibility of whether the airline's fleet state could be artificially learned without prior information. Given that the schedule is in categorical form, One Hot Encoding was applied and t-SNE was used to reduce the dimension of the data and visualize them to gain insights into the airline's overall fleet status. Interesting results were discovered from the experiments where the initial findings are expected to contribute to the fields of airline schedule health monitoring, anomaly detection, and disruption management.