http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
합성곱 신경망 기반 환경잡음에 강인한 교통 소음 분류 모델
이재준,김완수,이교구,Lee, Jaejun,Kim, Wansoo,Lee, Kyogu 한국음향학회 2018 한국음향학회지 Vol.37 No.6
As urban population increases, research on urban environmental noise is getting more attention. In this study, we classify the abnormal noise occurring in traffic situation by using a deep learning algorithm which shows high performance in recent environmental noise classification studies. Specifically, we classify the four classes of tire skidding sounds, car crash sounds, car horn sounds, and normal sounds using convolutional neural networks. In addition, we add three environmental noises, including rain, wind and crowd noises, to our training data so that the classification model is more robust in real traffic situation with environmental noises. Experimental results show that the proposed traffic sound classification model achieves better performance than the existing algorithms, particularly under harsh conditions with environmental noises.
이재준,이우주,김정환,Lee, JaeJune,Lee, Woojoo,Kim, Junghwan 한국통계학회 2015 응용통계연구 Vol.28 No.3
Accurate demand forecasting is a crucial component in revenue management(RM). The booking data of departed flights is used to forecast the demand for future departing flights; however, some booking requests that were denied were omitted in the departed flights data. Denied booking requests can be interpreted as censored in statistics. Thus, unconstraining demand is an important issue to forecast the true demands of future flights. Several unconstraining methods have been introduced and a method based on expectation maximization is considered superior. In this study, we propose a new unconstraining method based on a regression model that can entertain such censored data. Through a simulation study, the performance of the proposed method was evaluated with two representative unconstraining methods widely used in RM.
이재준(Jaejun Lee),박상민(Sangmin Park),강선일(Sunil Kang),오화영(Hwayoung Oh),정은상(Eun Sang Jung) 한국추진공학회 2016 한국추진공학회지 Vol.20 No.4
Korean Space Launch Vehicle (KSLV-II) Propellant Supply System charges liquid oxygen and kerosene to each propellant tank for the stages. To charge the launch vehicle propellant tank safety, the propellant charge flow rates and scenarios should be defined. First, the Propellant Supply System was modeled with 1D flow analysis program. The control valve capacity and orifice size were calculated by performing the 1D steady state simulation. Second, the 1D transient simulation was performed by using the steady state simulation results. As propellants were being charged at the each tank, the increased tank liquid level decreases the charge flow rate. Consequently, the proposed supply system satisfies the required design charging conditions.
발사체용 지상고정장치 구동유압실린더의 운동특성에 관한 해석적 연구
이재준(Jaejun Lee),박상민(Sangmin Park),양성필(Seongpil Yang),김대래(Daerae Kim) 한국추진공학회 2017 한국추진공학회지 Vol.21 No.1
Vehicle Holding Device(VHD) has a role that holding the launch vehicle on its launch pad until the engine therust reaches a steady condition. The analytical study of shape parameters and dynamic characteristics of hydraulic cylinders is carried out. The contraction of cylinder is considered as the major factor of releasing mechanism. Through the analysis, the decreasing of cylinder slit size and increasing initial charging pressure increase the contraction force. Through the transient analysis, cylinder load, displacement and inner pressure distribution are confirmed. The cylinder contraction force is converged to the cylinder external force when the cylinder starts to move. Also, the pressure distribution in the hydraulic cylinder is constant.
이재준 ( Lee Jaejun ) 성균관대학교 성균중국연구소 2024 중국사회과학논총 Vol.6 No.1
시진핑 시기 중국 공산당은 왜 국유기업 중심의 경제 발전을 추구하는가? 본 연구는 중국 공산당이 국유기업 중심의 경제 발전 모델을 추구하게 된 요인으로 세 가지를 지적하고자 한다. 먼저 지방 정부가 국유기업에 대해 갖고 있는 이해관계를 들 수 있다. 각 지방의 국유기업은 지방 정부에 세금을 납부하고, 지역민들에게는 일자리를 제공하는 데 큰 비중을 갖는다. 시장 중심적 경제 개혁에 따른 국유기업 비중의 축소는 지방 정부에게는 정치적인 부담으로 작용할 수 있다는 것이다. 다음 중국 공산당의 경제 통제 강화를 들 수 있다. 국유기업을 통해 중국 공산당이 경제 분야에 대한 통제력을 유지할 수 있다는 것이다. 그리고 마지막으로 미중 전략 경쟁에 따라 국유기업의 중요성이 불가피하게 확대되었다는 점을 지적할 수 있다. This study explores the motivations behind the Chinese Communist Party’s (CCP) pursuit of an economic development model centered on State-Owned Enterprise(SOE) in Xi Jinping era. Three key factors are identified as shaping the CCP’s inclination towards an SOE-centered approach. Firstly, the crucial role that local governments play in SOEs, where these enterprises contribute taxes and employment opportunities in each province. The potential reduction of SOEs due to market-oriented economic reforms poses a political risk for local governments, prompting the CCP to carefully navigate this dynamic. Secondly, the CCP’s strategic focus on tightening economic control is exemplified through its reliance on SOEs, serving as instruments to assert authority over key economic sectors. The strategic positioning of SOEs aligns with the CCP’s overarching goal of maintaining a firm grip on economic dynamics. Lastly, the study highlights the increased significance of SOEs in the context of the US-China trade conflict.
이재준(Jaejun Lee),김동성(Dongsung Kim) 한국정보과학회 2006 정보과학회논문지 : 소프트웨어 및 응용 Vol.33 No.4
본 논문에서는 수술 도중에 심장내부로 삽입한 초음파 탐침을 통해 획득된 초음파 심장영상에서 강인하게 심장 영역을 고속 자동 분할하는 방법을 제안한다. 제안한 방법은 심장 초기 경계 추출, 신뢰도 경쟁을 통한 전체 경계 검출, 회전 국부 방사선 기법을 이용한 국부 경계 보완으로 세 단계로 구성된다. 첫째, 초음파 탐침의 중심에서 방사선을 만들어 각 방사선에서 밝기값 기반 임계값 기법으로 얻어진 심장외부 영역을 이용하여 대략적인 초기 심장영역의 경계를 추출한다. 둘째, 각각의 방사선에서 임계치로추출된 초기 심장영역의 위치를 포함하여 경계와 영역정보를 이용해 추출된 새로운 후보들과 신뢰도의 경쟁을 수행하여 높은 신뢰성을 가진 심장 경계를 검출한다. 셋째, 방사선 기법으로 경계획득이 어려운 심장의 오목한 영역에서 경계를 따라 회전하면서 국부적으로 방사선 조사법을 적용하여 경계를 보완한다. 제안된 방법은 실제 환자의 심장 수술 도중에 얻어진 초음파 영상에 적용되어 고무적인 결과를 획득했다. This paper proposes a robust and efficient segmentation method for a cardiac ultrasound image taken from a probe inserted into the heart in surgery. The method consists of three steps: initial boundary extraction, whole boundary modification using confidence competition, and local boundary modification using the rolling spoke method. Firstly, the initial boundary is extracted with threshold regions along the global spokes emitted from the center of an ultrasound probe. Secondly, high confidence boundary edges are detected along the global spokes by competing among initial boundary candidate and new candidates achieved by edge and appearance information. Finally, the boundary is modified by rolling local spokes along concave regions that are difficult to extract using the global spokes. The proposed method produces promising segmentation results for the ultrasound cardiac images acquired during surgery.