• 대한안전경영과학회지
• /
• 제21권4호
• /
• pp.51-58
• /
• 2019

The LBS(Location Based Service) technology plays an important role in reducing wastes of time, losses of human lives and economic losses by detecting the user's location in order by suggesting the optimal evacuation route of the users in case of safety accidents. We developed an algorithm to estimate indoor location, movement path and indoor location changes of smart phone users based on the built-in sensors of smartphones and the dead-reckoning algorithm for pedestrians without a connection with smart devices such as Wi-Fi and Bluetooth. Furthermore, seven different indoor movement scenarios were selected to measure the performance of this algorithm and the accuracy of the indoor location estimation was measured by comparing the actual movement route and the algorithm results of the experimenter(pedestrian) who performed the indoor movement. The experimental result showed that this algorithm had an average accuracy of 95.0%.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.302-305
• /
• 1996

In this paper, an optimal identification method using fuzzy-neural networks is proposed for modeling of nonlinear complex systems. The proposed fuzzy-neural modeling implements system structure and parameter identification using the intelligent schemes together with optimization theory, linguistic fuzzy implication rules, and neural networks(NNs) from input and output data of processes. Inference type for this fuzzy-neural modeling is presented as simplified inference. To obtain optimal model, the learning rates and momentum coefficients of fuzz-neural networks(FNNs) and parameters of membership function are tuned using genetic algorithm(GAs). For the purpose of its application to nonlinear processes, data for route choice of traffic problems and those for activated sludge process of sewage treatment system are used for the purpose of evaluating the performance of the proposed fuzzy-neural network modeling. The show that the proposed method can produce the intelligence model w th higher accuracy than other works achieved previously.

• 산업공학
• /
• 제14권2호
• /
• pp.111-119
• /
• 2001

A tandem AGV system is based on partitioning all the stations into non-overlapping single vehicle closed loops with additional stations provided as an interface between adjacent loops. For an efficient use of this configuration, it is required to solve the load routing problem(LRP), which is primarily based on the fact that a load may be handled by several vehicles and moved through several loops before it reaches its destination. In this paper, a heuristic based on genetic algorithm(GA) is first developed to solve LRP. The first model obtains the optimal route of each job and the optimal direction of each loop when the vehicle in each loop travels unidirectionally. The second GA model obtaines the optimal polling sequence of the empty vehicle in each loop, when the vehicle can move bidirectionally.

• 한국ITS학회 논문지
• /
• 제7권1호
• /
• pp.10-21
• /
• 2008

Wardrop(1952)의 확정적 사용자최적원리(Deterministic User Optimal Principle)에 의한 사용자의 통행행태는 교통망의 상황에 대하여 완전한 정보가 존재한다는 가정을 기반으로 하고 있다. 따라서 확정적 사용자최적원리에 따르면 사용자는 출발지와 도착지를 연결하는 최적경로를 선택하며, 사용자가 경로를 임의로 변경하여 통행비용을 줄일 수 없는 균형 상태에 도달함을 의미한다. 운전자의 통행경로선택기준은 다양하게 생각될 수 있으나, 일반적으로 확정적 사용자최적원리에서 운전자는 최소의 통행시간이 소요되는 경로를 선택한다. 그러나 현실의 교통망에서 발생하는 운전자의 통행행태는 통행시간으로 경로를 선택하지 않는 경향이 빈번하게 목격되며, 확정적 사용자최적원리에서처럼 통행시간만을 경로선택의 기준으로 적용하는 모형은 비합리적인 통행행태를 유도할 가능성이 높다. 이에 본 연구는 운전자의 경로를 인지하는 행태를 보다 현실적으로 모사하는 확정적 최적통행배정모형을 제안한다. 이를 위해 모형을 사용자가 경로를 결정함에 있어 출발지와 도착지에서 경로를 인지하는 일반적인 특성으로 통행시간 정보뿐만 아니라 도로주행 조건, 출발지와 도착지에 대한 교통망 정보의 유무 등을 동시에 반영한다고 가정한다. 또한 본 연구는 출발지를 기준으로 하는 통행을 전개하는 전방탐색기법과 도착지를 기준으로 통행을 후퇴하는 후방탐색기법을 동시에 수식과 알고리즘에 반영하여 사용자의 경로인지특성을 반영하는 노력이 주 내용이다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권7호
• /
• pp.339-349
• /
• 2001

This paper suggests an optimal identification method for complex and nonlinear system modeling that is based on Fuzzy-Neural Networks(FNN). The proposed Hybrid Identification Algorithm is based on Yamakawa's FNN and uses the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. In this paper, the FNN modeling implements parameter identification using HCM algorithm and hybrid structure combined with two types of optimization theories for nonlinear systems. We use a HCM(Hard C-Means) clustering algorithm to find initial apexes of membership function. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are adjusted using hybrid algorithm. The proposed hybrid identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregated objective function(performance index) with weighting factor is introduced to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity(distribution of I/O data), we show that it is available and effective to design an optimal FNN model structure with mutual balance and dependency between approximation and generalization abilities. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2012년도 춘계학술발표대회논문집
• /
• pp.190-192
• /
• 2012

Vehicular Ad hoc Networks (VANETs) is the new wireless networking concept of mobile ad hoc networks in research community. Routing in vehicular is a major challenge and research area. The majority of current routing algorithms for VANETs utilize indirect metrics to select the next hop and produce optimal node path. In this paper, we propose a distance and angle based routing algorithm for VANETs, which combines a distance approach with an angle based geographical strategy for selecting the next hop, with the purpose of using direct metrics to build a optimal node route. The proposed algorithm has better performance than the previous scheme.

• 대한산업공학회지
• /
• 제20권4호
• /
• pp.5-21
• /
• 1994

We have described the optimal process route selection model for the PCB(printed circuit board) auto-insertion line. This PCB assembly line is known as a FFL(flexible flow line) which produces a range of products keeping the flow shop properties. Under FFL environments, we have emphasized the balancing of work-loads in order to maximize total productivity of PCB auto-insertion line. So we have developed a heuristic algorithm based on a work-order selection rule and min-max concept for the job route selection model.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1260-1263
• /
• 1987

This paper describes the mobile robot system to recognize the guidance tape, and presents the locomotion algorithm. This system converts video imago to binary image by setting an optimal threshold and obtains the parameters to move the robot. The mobile robot moves according to the programmed route in memory. But after recognized the obstacle on the locomotion routs, this system constructs the new route and the robot moves following the new route.

• 한국철도학회논문집
• /
• 제17권6호
• /
• pp.433-442
• /
• 2014

이 연구는 도시철도 교통량 배정 알고리즘의 적합성 평가를 목적으로 수행되었다. 이 알고리즘의 정확도는 교통수요 예측뿐만 아니라 네트워크의 취약성 분석이나 철도 운영기관간 운임수입 정산 등의 응용분야에서도 중요한 요소이다. 그럼에도 불구하고 알고리즘의 적합성이나 발전방향에 대한 논의는 부족하였다. 이에 본 연구는 대표적 교통량 배정 알고리즘인 최적전략 알고리즘, 경로선택 알고리즘, Dial 알고리즘을 대상으로 수도권 도시철도 이용자의 통행행태 연구에 적합한 알고리즘의 특성에 대하여 논의하였다. 이를 위해 각 알고리즘의 이론적 가정을 검토하고, 수도권 도시철도 네트워크에 적용해 그 성능을 살펴보았다. 그 결과 Dial 알고리즘이 이론적 가정의 합리성과 분석단위에 따른 계산적 효율성 측면에서 도시철도 이용자의 통행행태 분석에 우수한 것으로 나타났다.

• 인터넷정보학회논문지
• /
• 제23권1호
• /
• pp.1-9
• /
• 2022

Recently, interest in living safety and crime prevention is increasing. The reality is that most women have anxiety about social safety and ultimately want a safe return to home. As a result of these issues, the Seoul Metropolitan Government and the National Police Agency are implementing various services to alleviate them. However, there are limitations such as that the service can be used only during a limited time or the process of checking whether the patrol is really completed is complicated. Therefore, in this paper, we propose a service platform that overcomes these limitations and suggests the best and shortest patrol route to the police based on the desired patrol location applied by citizens. It is designed based on the MVC pattern, and the functions are divided for each user. It is hoped that the platform will reduce crime rates and allow citizens to ultimately return home with peace of mind. Also we expect that the police will ablet to find places where they did not know about or need to patrol with more attention through the recommended route of the platform, which will be helpful in their task.