• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.8-19
• /
• 2023

This paper presents advancement in multi- unmanned aerial vehicle (UAV) cooperative area surveillance, focusing on optimizing UAV route planning through the application of genetic algorithms. Addressing the complexities of comprehensive coverage, two real-time dynamic path planning methods are introduced, leveraging genetic algorithms to enhance surveillance efficiency while accounting for flight constraints. These methodologies adapt multi-UAV routes by encoding turning angles and employing coverage-driven fitness functions, facilitating real-time monitoring optimization. The paper introduces a novel path planning model for scenarios where UAVs navigate collaboratively without predetermined destinations during regional surveillance. Empirical evaluations confirm the effectiveness of the proposed methods, showcasing improved coverage and heightened efficiency in multi-UAV path planning. Furthermore, we introduce innovative optimization strategies, (Foresightedness and Multi-step) offering distinct trade-offs between solution quality and computational time. This research contributes innovative solutions to the intricate challenges of cooperative area surveillance, showcasing the transformative potential of genetic algorithms in multi-UAV technology. By enabling smarter route planning, these methods underscore the feasibility of more efficient, adaptable, and intelligent cooperative surveillance missions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.358-363
• /
• 2003

Optimal tuning plays an important role in operations or tuning of the complex process such as the main steam temperature of the thermal power plant. However, it is very difficult to maintain the steam temperature of power plant using conventional optimization methods, since these processes have the time delay and the change of the dynamic characteristics in the reheater. Up to the present time, the Pm controller has been used. However, it is not easy to achieve an optimal PID gain with no experience, since the gain of the PID controller has to be manually tuned by trial and error. This paper suggests immune algorithm based tuning technique for PID Controller on steam temperature process with long dead time and its results are compared with genetic algorithm based tuning technique.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.523-527
• /
• 2004

This paper presents a new design methods of the short-term load forecasting system (STLFS) using the data mining. The proposed predictor takes form of the convex combination of the linear time series predictors for each inputs. The problem of estimating the consequent parameters is formulated by the convex optimization problem, which is to minimize the norm distance between the real load and the output of the linear time series estimator, The problem of estimating the premise parameters is to find the parameter value minimizing the error between the real load and the overall output. Finally, to show the feasibility of the proposed method, this paper provides the short-term load forecasting example.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.2
• /
• pp.25-33
• /
• 1997

A DEDS is a system whose states change in response to the occurence of events from a predefined event set. In this paper, we consider the optimal control and reasoning problem for Discrete Event Systems(DES) in the Temporal Logic Framework(TEL) which have been recnetly defined. The TLE is enhanced with objective functions(event cost indices) and a measurement space is alos deined. A sequence of event which drive the system form a give initial state to a given final state is generated by minimizing a cost functioin index. Our research goal is the reasoning of optimal trajectory and the design of the optimal controller for DESs. This procedure could be guided by the heuristic search methods. For the heuristic search, we suggested the Stochastic Ruler algorithm, instead of the A algorithm with difficulties as following ; the uniqueness of solutions, the computational complexity and how to select a heuristic function. This SR algorithm is used for solving the optimal problem. An example is shown to illustrate our results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.267-270
• /
• 1996

In this paper, we present a new design method to implement autoassociative memories based on BSB neural networks. With a concrete mathematical model proposed after analyzing some new qualitative properties of autoassociative memories, we reinterpret design of autoassociative memories as a constrained optimization problem and use an evolution program as an optimal search tool to solve this. The proposed method satisfies many of the criteria used to evaluate the effectivencess of a given associative memory and has improvements with respect to correctness and performance. Comparing simulation results with other methods, we demonstrate the effectiveness of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.100-104
• /
• 2003

The SVDD(support vector data description) is one of the most well-known one-class support vector learning methods, in which one tries the strategy of utilizing balls defined on the kernel feature space in order to distinguish a set of normal data from all other possible abnormal objects. The major concern of this paper is to consider the problem of modifying the SVDD into the direction of utilizing ellipsoids instead of balls in order to enable better classification performance. After a brief review about the original SVDD method, this paper establishes a new method utilizing ellipsoids in feature space, and presents a solution in the form of SDP(semi-definite programming) which is an optimization problem based on linear matrix inequalities.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.263-267
• /
• 2005

Building classifiers for financial real-world classification problems is often plagued by severely overlapping and highly skewed class distribution. New performance measures such as receiver operating characteristic (ROC) curve and area under ROC curve (AUC) have been recently introduced in evaluating and building classifiers for those kind of problems. They are, however, in-effective to evaluation of classifier's discrimination performance in a particular class of the classification problems that interests lie in only a local operating range of the classifier, In this paper, a new method is proposed that enables us to directly improve classifier's discrimination performance at a desired local operating range by defining and optimizing a partial area under ROC curve or domain-specific curve, which is difficult to achieve with conventional classification accuracy based learning methods. The effectiveness of the proposed approach is demonstrated in terms of fraud detection capability in a real-world fraud detection problem compared with the MSE-based approach.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.254-268
• /
• 2013

For real-world clustering tasks, the input data is typically not easily separable due to the highly complex data structure or when clusters vary in size, density and shape. Kernel-based clustering has proven to be an effective approach to partition such data. In this paper, we provide an overview of several fuzzy kernel clustering algorithms. We focus on methods that optimize an fuzzy C-mean-type objective function. We highlight the advantages and disadvantages of each method. In addition to the completely unsupervised algorithms, we also provide an overview of some semi-supervised fuzzy kernel clustering algorithms. These algorithms use partial supervision information to guide the optimization process and avoid local minima. We also provide an overview of the different approaches that have been used to extend kernel clustering to handle very large data sets.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1167-1170
• /
• 1993

We look at the problem of defuzzification in situations in which in addition to the usual fuzzy output of the controller there exists some ancillary restriction on the allowable defuzzified values. We provide two basic approaches to address this problem. In the first approach we enforce the restriction by selecting the defuzzified value through a random experiment in which the values which have nonzero probabilities are in the allowable region, this method is based on the RAGE defuzzification procedure and makes use of a nonmonotonic conjunction operator. The second approach which in the spirit of the commonly used methods, a kind of expected value, converts the problem to a constraint optimization problem.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.196-201
• /
• 2008

Statistical learning theory has three analytical tools which are support vector machine, support vector regression, and support vector clustering for classification, regression, and clustering respectively. In general, their performances are good because they are constructed by convex optimization. But, there are some problems in the methods. One of the problems is the subjective determination of the parameters for kernel function and regularization by the arts of researchers. Also, the results of the learning machines are depended on the selected parameters. In this paper, we propose an efficient method for objective determination of the parameters of support vector clustering which is the clustering method of statistical learning theory. Using evolutionary algorithm and bootstrap method, we select the parameters of kernel function and regularization constant objectively. To verify improved performances of proposed research, we compare our method with established learning algorithms using the data sets form ucr machine learning repository and synthetic data.