• 한국콘텐츠학회논문지
• /
• 제7권1호
• /
• pp.58-64
• /
• 2007

패턴 인식 분야에는 지수적 탐색 공간을 가진 최적화 문제가 많이 있다. 이를 해결하기 위해 부 최적해를 구하는 순차 탐색 알고리즘이 사용되어 왔고, 이들 알고리즘은 국부 최적점에 빠지는 문제점을 안고 있다. 최근 이를 극복하기 위해 유전 알고리즘을 사용하는 사례가 많아졌다. 이 논문은 특징 선택, 분류기 앙상블 선택, 신경망 가지치기, 군집화 문제의 지수적 탐색 공간 특성을 설명하고 이를 해결하기 위한 유전 알고리즘을 살펴본다. 또한 향후 연구로서 가치가 높은 주제들에 대해 소개한다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제15권2호
• /
• pp.151-160
• /
• 2011

Typically, it is hard to find a closed form solution of option pricing formula under an asset governed by a change point process. In this paper we derive a closed-form solution of the valuation function for an American perpetual put option under an asset having a change point. Structural changes are formulated through a change-point process with a Markov chain. The modified smooth-fit technique is used to obtain the closed-form valuation function. We also guarantee the optimality of the solution via the proof of a corresponding verification theorem. Numerical examples are included to illustrate the results.

• 대한산업공학회지
• /
• 제3권1호
• /
• pp.49-53
• /
• 1977

The coordinated control of the traffic signals of adjacent intersections can reduce delays, relative number of stops and congestions in the coordinated traffic area. The road capacity can be increased to a certain extend because the stopping and starting of vehicles facing red traffic lights can be avoided in many instances due to the progression established along an artery. However, if traffic centers or leaves the main flow in irregular volumes on the intermediate road section, a coordination of traffic signals is unnecessary and may even be harmful. Therefore, a computer simulation model to simulate and predict the effectiveness of a synchronized traffic signal system in the CBD of Seoul was developed and alternative policy variables, such as cycle time, offsets, phase splits, to be fed into the simulation model had to be generated. This is a report of (1) the development of a heuristic algorithm for the determination of phase splits when there are amber periods specifically reserved for left turns and (2) the computerization of time-space diagramming.

• 경영과학
• /
• 제11권1호
• /
• pp.91-106
• /
• 1994

In mixed model assembly lines, products are assembled seqeuntially that have different combination of options specified by customers. In just in time (JIT) environment, production smoothing becomes an important issue for sub-lines which supply the necessary parts to each workstation of the assembly line. Another important issue is to avoid line stopping caused by work overload in workstations. To find a sequence which minimizes the costs associated with line stoppage and the option parts inventory level, a nonlinear mixed integer programming is formulated. Recognizing the limit of the Branch and Bound technique in large sized problems, a heuristic solution procedure is proposed. The performance of the heuristic is compared with the Branch and Bound technique through randomly generated test problems. The computational results indicate that on the average the heuristic solutions deviate approximately 3.6% from the optimal solutions.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2009년도 추계학술대회
• /
• pp.131-135
• /
• 2009

This paper considers the sequencing of products in car assembly lines. The sequence which minimizes overall utility work in car assembly lines reduce the cycle time and the risk of conveyor stopping. The sequencing problem is solved using Tabu Search. Tabu Search is a heuristic method which can provide a near optimal solution in real time. The performance of proposed technique is compared with existing heuristic methods in terms of solution quality and computation time. Various examples are presented and experimental results are reported to demonstrate the efficiency of the technique.

• 대한안전경영과학회지
• /
• 제5권1호
• /
• pp.69-82
• /
• 2003

The sequence which minimizes overall utility work in car assembly lines reduces the cycle time, the number of utility workers, and the risk of conveyor stopping. This study suggests mathematical formulation of the sequencing problem to minimize overall utility work, and present a genetic algorithm which can provide a near optimal solution in real time. To apply a genetic algorithm to the sequencing problem in car assembly lines, the representation, selection methods, and genetic parameters are studied. Experiments are carried out to compare selection methods such as roullette wheel selection, tournament selection and ranking selection. Experimental results show that ranking selection method outperforms the others in solution quality, whereas tournament selection provides the best performance in computation time.

• Annals of Clinical Neurophysiology
• /
• 제15권2호
• /
• pp.37-41
• /
• 2013

Saccades are rapid eye movements that shift the line of sight between successive points of fixation. The cerebellum calibrates saccadic amplitude (dorsal vermis and fastigial nucleus) and the saccadic pulse-step match (flocculus) for optimal visuo-ocular motor behavior. Based on electrophysiology and the pharmacological inactivation studies, early activity in one fastigial nucleus could be important for accelerating the eyes at the beginning of a saccade, and the later activity in the other fastigial nucleus could be critical for stopping the eye on target, which is controlled by inhibitory projection from the dorsal vermis. The cerebellum could monitor a corollary discharge of the saccadic command and terminate the eye movement when it is calculated to be on target. The fastigial nucleus and dorsal vermis also participate in the adaptive control of saccadic accuracy.

• 한국통신학회논문지
• /
• 제41권1호
• /
• pp.83-85
• /
• 2016

LS 신호검출 OFDM은 채널 행렬이 불량 조건이 될 확률이 증가하여 고속 시변 채널에서 성능이 저하된다. LS 신호검출의 성능저하를 방지하기 위하여 다양한 안정화 방식이 적용되고 있다. 본 논문에서는 변조방식의 특성이 반영된 실행중지 기준을 적용한 CGLS 방식을 제안하였으며 최적의 LMMSE에 근접한 성능을 얻을 수 있었다.

• 한국정보기술학회 영문논문지
• /
• 제10권2호
• /
• pp.33-48
• /
• 2020

By Digital Transformation, new technologies like ML (Machine Learning), Big Data, Cloud, VR/AR are being used to video streaming technology. We choose ML to provide optimal QoE (Quality of Experience) in various network conditions. In other words, ML helps DASH in providing non-stopping video streaming. In DASH, the source video is segmented into short duration chunks of 2-10 seconds, each of which is encoded at several different bitrate levels and resolutions. We built and compared the performances of five prototypes after applying five different machine learning algorithms to DASH. The prototype consists of a dash.js, a video processing server, web servers, data sets, and five machine learning models.

• 한국자동차공학회논문집
• /
• 제24권6호
• /
• pp.649-659
• /
• 2016

This paper describes control algorithm and control structure of vehicle control unit for range-extended electric vehicle equipped with engine-generator system, and specially presents methods which determine optimal operating points and decreases a vibration or a shock for operating the engine-generating system. The vehicle control algorithm is consisted of several parts which are sequence control, calculation of wheel demand torque, determination of operating points, and management of operating points and so vehicle controller has be made possible to efficiently manage calibration parameters. The control algorithm is evaluated by driving test modes, launching performance and operating engine-generator system and so on. In conclusion, this paper present methods for extending a mileage, improving a launching performance and reducing vibration or shock when the engine-generating system is starting or is stopping.