• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.10
• /
• pp.1108-1120
• /
• 1990

The present study is to develop an intelligent control system for flexible manufacturing system, which is suitable for a variety of manufacturing types with smaller production rates. The controller is designed to integrate heuristic rules with optimization techniques for loading as well as flow rate of parts and ultimately meeting performance indices. The control function implemented by an optimization technique is to calculate short term production rates of parts. The heuristic control determined by production rules requires knowledge base to evaluate selected loading alternatives according to short term production rate and current process information, and also to determine final decision pertaining to loading. In this case, the knowledge base is constructed using the rules for evaluating alternatives, decision criteria, and flow control of parts in manufacturing system. The database is formulated by means of managing and updating current process information. A graphic system to monitor current status of the function and operation of manufacturing system is developed, and computer simulation is carried out to evaluate the performance of the proposed controller.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.635-642
• /
• 2003

Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.3
• /
• pp.15-27
• /
• 2017

In general, increasing train dwell time leads to increasing train service frequency, and it in turn contributes to increasing the congestion level of train and platform. Therefore, the studies on train dwell time have received growing attention in the perspective of scheduling train operation. This study develops a prediction model of train dwell time to enable train operators to mitigate platform congestion by metering passenger inflow at platform gate with respect to platform congestion levels in real-time. To estimate the prediction model, three types of independent variables were applied: number of passengers to get into train, number of passengers to get out of trains, and train weights, which are collectable in real-time. The explanatory power of the estimated model was 0.809, and all of the dependent variables were statistically significant at the 99%. As a result, this model can be available for the basis of on-time train service through platform gate metering, which is a strategy to manage passenger inflow at the platform.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.120-127
• /
• 2011

Checkpointing is one of common methods of realizing fault-tolerance for real-time systems. This paper presents a scheme to determine checkpoint intervals using probabilistic optimization. The considered real-time systems comprises multiple tasks in which transient faults can happen with a Poisson distribution. Also, multi-tasks are scheduled by the non-preemptive Rate Monotonic (RM) algorithm. In this paper, we present an optimization problem where the probability of task completion is described by checkpoint numbers. The solution to this problem is the optimal set of checkpoint numbers and intervals that maximize the probability. The probability computation includes schedulability test for the non-preemptive RM algorithm with respect to given numbers of checkpoint re-execution. A case study is given to show the applicability of the proposed scheme.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.5
• /
• pp.409-416
• /
• 2000

In the shared-memory mutiprocessor systems, shared processing techniques such as time-sharing, space¬sharing, and gang-scheduling are used to improve the overall system utilization for the parallel operations. Recently, LLPC(Loop-Level Process Control) allocation technique was proposed. It dynamically adjusts the needed number of processors for the execution of the parallel code portions based on the current system load in the given job. This method allocates as many available processors as possible, and does not save any processors for the parallel sections of other later-arriving applications. To solve this problem, in this paper, we propose a new processor allocation technique called FPA(Fuzzy Processor Allocation) that dynamically adjusts the number of processors by fuzzifYing the amounts ofueeded number of processors, loads, and estimated execution times of job. The proposed method provides the maximum possibility of the parallism of each job without system overload. We compare the performances of our approaches with the conventional results. The experiments show that the proposed method provides a better performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.324-329
• /
• 2004

This paper presents a coordination method to allocate and schedule tasks for multiagent systems of which agents have fuzzy processing time for their operations earlier on and their processing times are determined at the time the task operations are carried out later on. The proposed method is organized in a two-level genetic algorithm in which the upper level genetic algorithm plays the role of finding efficient task allocation and the lower level genetic algorithm takes charge of searching for efficient schedules corresponding to the task allocation proposed by the upper level genetic algorithm. It presents a strategy to deal with agent failures in the considered multiagent system. It also shows some experiment results for the proposed method.

• The KIPS Transactions:PartA
• /
• v.8A no.4
• /
• pp.429-438
• /
• 2001

GPS (Global Positioning System) is the most ideal navigation system which can be used on the earth irrespective of time and weather conditions. GPS has been used for various applications such as construction, survey, environment, communication, intelligent vehicles and airplanes and the needs of GPS are increasing in these days. This paper deals with the design and implementation of the RTOS (Real-Time Operating System) for a GPS navigation computer in the GPS/INS integrated navigation system. The RTOS provides the optimal environment for execution and the base platform to develop GPS application programs. The key facilities supplied by the RTOS developed in this paper are priority-based preemptive scheduling policy, dynamic memory management, intelligent interrupt handling, timers and IPC, etc. We also verify the correct operations of all application tasks of the GPS navigation computer on the RTOS and evaluate the performance by measuring the overhead of using the RTOS services.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.230-240
• /
• 2020

To develop a virtual world-based immersive tutoring system, we would like to develop a simulation in the spatial aspect to maximize the diversity and realism of the situation. This implementation requires the modeling of virtual space as well as the knowledge and intelligent thinking functions of virtual humans. First, information structures are needed to simulate the hierarchical and multifaceted composition of space and the corresponding knowledge of virtual humans. Specifically, four structures for 2.5D spatial distribution expression, complex spatial relationship expression, object expression, and temporal and spatial representation of events are developed respectively. It then uses these expressed knowledge to develop the spatial thinking function of virtual humans needed to make spatial movement. In general, events have a chain effect on adjacent or connected objects through force, resulting in a variety of situations and reflected in the planning of the next action by the virtual humans involved. For this purpose, the development of events according to historical trends is recorded on the representation structure of time and space. It embodies typical events to demonstrate the feasibility of independent behavior in complex spaces among virtual people.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.151-157
• /
• 1999

선석계획 및 크레인 일정계획은 컨테이너 터미널에서 입항하는 선박들의 빈번한 변동상황에 능동적으로 대처하고 유연하면서도 신속한 의사결정이 가능하도록 여러 명의 전문가가 장기적인 계획을 바탕으로 지속적으로 수정 보완해 나가는 방법으로 이루어지고 있다. 본 논문에서는 선사 및 컨테이너 터미널에서 수시로 변경되는 다양한 요구조건을 수용하는 최적의 선석 및 크레인 일정계획 수립을 위하여 제약만족기법과 휴리스틱 교정(Heuristic Repair)기법을 이용하였다. 선석계획 및 크레인 일정 계획문제는 기본적으로 제약조건 만족문제로 정형화할 수 있지만 선박의 접안위치를 결정하는 문제는 목적함수를 가지는 최적화문제이다. 따라서 이 문제는 제약조건 만족문제와 최적화문제가 혼합된 문제(CSOP, Constraint Satisfaction and Optimization Problem)로 볼 수 있다. 이러한 문제를 해결하기 위해서 각 선박의 최적 전압위치를 찾고 최우선 순위 선박의 최적 접안위치로부터 주어진 모든 제약조건을 만족하는 해를 찾는 탐색기법을 활용했고 휴리스틱 교정기법을 사용해서 제약만족기법에서 찾은 해를 교정했다. 우선순위가 가장 높은 선박부터 탐색을 하기 위해 Variable Ordering 기법을 사용했고 그 선박의 최적 접안위치부터 탐색을 해 나가는 Value Ordering 기법을 사용하였다. 실제 부산 신선대 컨테이너 터미널의 선석계획자료를 사용해서 실험을 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.4887-4907
• /
• 2017

Accurate traffic flow forecasting is critical to the development and implementation of city intelligent transportation systems. Therefore, it is one of the most important components in the research of urban traffic scheduling. However, traffic flow forecasting involves a rather complex nonlinear data pattern, particularly during workday peak periods, and a lot of research has shown that traffic flow data reveals a seasonal trend. This paper proposes a new traffic flow forecasting model that combines seasonal relevance vector regression with the hybrid chaotic simulated annealing method (SRVRCSA). Additionally, a numerical example of traffic flow data from The Transportation Data Research Laboratory is used to elucidate the forecasting performance of the proposed SRVRCSA model. The forecasting results indicate that the proposed model yields more accurate forecasting results than the seasonal auto regressive integrated moving average (SARIMA), the double seasonal Holt-Winters exponential smoothing (DSHWES), and the relevance vector regression with hybrid Chaotic Simulated Annealing method (RVRCSA) models. The forecasting performance of RVRCSA with different kernel functions is also studied.