Showing papers in "Intelligent Automation and Soft Computing in 2005"
TL;DR: The hierarchical genetic algorithm (HGA) is employed for automatically searching the number of clusters as well as properly locating the centers for clusters and the Davies-Bouldin index is adopted as a measure of the validity of the clusters.
Abstract: Clustering is a central task for data analysis that partitions heterogeneous data sets into groups of more homogeneous characteristics. However, most of clustering algorithms require the user to provide the number of clusters as input. In this paper, we consider the automatic clustering problem that one has to partition data points without any a priori knowledge about the correct number of clusters. The hierarchical genetic algorithm (HGA) is employed for automatically searching the number of clusters as well as properly locating the centers for clusters. The well-known Davies-Bouldin index is adopted as a measure of the validity of the clusters. Experimental results on artificial and real-life data sets are given to illustrate the effectiveness of the proposed approach.
39 citations
TL;DR: A new a fuzzy simple additive weighting method for multiple attribute decision making problems where fuzzy numbers are ranked prior to any fuzzy arithmetic in this method, which is practical and more realistic.
Abstract: Although simple additive weighting method (SAW) is the most popular approach for classical multiple attribute decision making (MADM), it is not practical any more if information is fuzzy. The existing methods of Fuzzy Simple Additive Weighting method (FSAW) apply defuzzification which distorts fuzzy numbers. Furthermore, most of the methods usually require lengthy and laborious manipulations. In this paper, we develop a new a fuzzy simple additive weighting method for multiple attribute decision making problems. To avoid defuzzification round off errors caused by multiplication or other arithmetic manipulations, fuzzy numbers are ranked prior to any fuzzy arithmetic in this method. The ranking is done by preference ratio concept which compares fuzzy numbers pairwise. Since this method eventually assigns crisp scores to alternatives, it is practical and more realistic. We also present three other algorithms for ranking or normalizing fuzzy numbers which are actually sub algorithms of the main method.
38 citations
TL;DR: An Independent joint adaptive scheme based on fuzzy logic is developed for control of robot manipulators that does not require an accurate manipulator dynamic model and the asymptotic stability of the closed-loop control system can be obtained.
Abstract: Control of multi-link robot arms is a challenging and difficult problem because of the highly nonlinear dynamics. An Independent joint adaptive scheme based on fuzzy logic is developed for control of robot manipulators. Fuzzy logic system aze used to approximate the uncertainties of functions; such as, coupling forces among the each joints, Coriolis force, centrifugal force, gravitational force, and frictional forces. A compensation controller is also proposed to estimate the bound of approximation error so that the chattering effect of the control effort can be reduced. The free parameters of the adaptive fuzzy control can be tuned on-line based on a Lyapunov synthesis approach. Thus the asymptotic stability of the closed-loop control system can be obtained. The proposed scheme does not require an accurate manipulator dynamic model. Numerical simulations results for athree-axis robot manipulator aze included to show the effectiveness of proposed controller.
25 citations
TL;DR: A PGA that combines a new subtour technique with a known migration approach is identified to be the best for the traveling salesman problem among the five PGAs being compared.
Abstract: This paper presents a comparative study of five different coarse-grained parallel genetic algorithms (PGAs) using the traveling salesman problem as the case application. All of these PGAs are based on the same baseline serial genetic algorithm, implemented on the same parallel machine (IBM SP2), tested on the same problem instances, and started from the same set of initial populations. Based on these experiments, a PGA that combines a new subtour technique with a known migration approach is identified to be the best for the traveling salesman problem among the five PGAs being compared.
23 citations
TL;DR: It was seen that AI is a powerful tool in estimating air pollution levels considering the complex and nonlinear structure of the atmospheric parameters, which is the source of the database.
Abstract: In this study, Istanbul city was taken as the study area. A new and powerful technique, Artificial Intelligence (AI), an Inductive Learning Algorithm (RULES-3), was used in predicting the future (next 24 hours) sulfur dioxide (SOZ) air pollutant on the basis of vazious meteorological parameters. The goal of this study is to forecast the 24-h average SOZ concentration levels in the urban atmosphere using AL As a result of this study, it was seen that AI is a powerful tool in estimating air pollution levels considering the complex and nonlinear structure of the atmospheric parameters, which is the source of the database.
13 citations
TL;DR: A GA (genetic algorithm) search procedure was employed to explore a best set of sensory feedback parameters in designing a human-machine interface for improved performance, which incorporated tradeoffs between speed and accuracy in tracking.
Abstract: A GA (genetic algorithm) search procedure was employed to explore a best set of sensory feedback parameters in designing ahuman-machine interface for improved performance. The optimization concerned two objective functions of interest, which incorporated tradeoffs between speed and accuracy in tracking. APareto-optimal front was calculated involving the two cost functions selected. This approach differs from the traditional minimum of anon-convex cost function (scalaz) describing the desired closed loop performance. Also, this methodology used a parsimonious experimental design method. By making a few runs with a limited number of subjects, a response model was first developed. This model was then simulated and a complex vector response surface was generated by the performance variables of interest. The GA seazch procedure was then used to locate the minimum of this response surface. Finally, in a post hoc experimental study to confirm that the selected design parameters were the best from the cl...
5 citations
TL;DR: A dedicated micro-controller based fuzzy logic controller for three-phase shunt active power filter is presented, used to improve power quality by compensating harmonics and reactive power requirement of non-linear loads.
Abstract: This paper presents a dedicated micro-controller based fuzzy logic controller for three-phase shunt active power filter. It is used to improve power quality by compensating harmonics and reactive power requirement of non-linear loads. The compensation process proposed is simple, which is based on sensing line currents and regulating the do link voltage. It operates without sensing the harmonic or reactive volt-ampere requirement of the load. Fuzzy logic control is used to regulate the do link voltage in place of the conventional PI controller, as the fuzzy control is based on simple linguistic variables and does not require the mathematical model of the system. Response of the fuzzy controller is compared with the conventional PI controller by simulation study. An attempt is made to implement a complex control like fuzzy logic on an inexpensive 8-bit micro-controller (INTEL 8031). Various experimental results are presented under steady state and transient conditions.
5 citations
TL;DR: An evolutionary strategy -Differential Evolution (DE) has been proposed in order to tune automatically the parameter gains in a systematic approach and it is found that the system is robust and stable even under influence of disturbances.
Abstract: In this paper, the application of Active Force Control (AFC) incorporated with a conventional Proportional-Derivative (PD) controller to a five-link biped robot has been studied and simulated. The efficacy and robustness of the AFC strategy in suppressing external disturbances was examined on a model using Crude Approximation (CA) method. However, the task of tuning the PD controller parameters and the inertia matrix coefficient is tedious and time-consuming. Thus, an evolutionary strategy -Differential Evolution (DE) has been proposed in order to tune automatically the parameter gains in a systematic approach. The effectiveness of the proposed method is investigated, and it is found that the system is robust and stable even under influence of disturbances.
4 citations
TL;DR: Fuzzy state automata as mentioned in this paper derive from the integration of traditional Finite State Automata and neuro-fuzzy systems, where a fmite state automaton tra... is used for control applications.
Abstract: This paper introduces Fuzzy State Automata for control applications. They derive from the integration of traditional Finite State Automata and neuro-fuzzy systems, where a fmite state automaton tra...
3 citations
TL;DR: An algorithm is presented for computing an exact aggregation of fuzzy sets that represent the rule consequents feed by the inference engine of a fuzzy controller that requires fewer operations, improving also the accuracy of the controller’s output.
Abstract: An algorithm is presented for computing an exact aggregation of fuzzy sets that represent the rule consequents feed by the inference engine of a fuzzy controller. Simple closed form expressions of the center of gravity defuzzification method are used to obtain the controller’s crisp output. The basic idea is to determine characteristics such as overlapping, intersection points and level of activation among the activated fuzzy sets in every control cycle. When compared to other techniques that use discrete universes of discourse, this exact aggregation and defuzzification method requires fewer operations, improving also the accuracy of the controller’s output. Several simulations are presented using the algorithm to regulate the neutron power in a research reactor.
2 citations
TL;DR: The proposed scheme is based on fuzzy logic decision to efficiently determine handover and considers three important parameters, including blocking rate, dropping rate, and bandwidth utilization and can achieve the higher bandwidth utilization, the lower new call blocking rates, and the lower handover call dropping rate.
Abstract: Due to the property of low propagation delay, LEO (Leo Earth Orbit) satellite network is an indispensable solution for providing a global coverage and multimedia communication. However, since the LEO satellites move very fast in orbits, to offer a smooth handover is regarded as the most significant service feature. In this paper, an effective handover management is proposed. The proposed scheme is based on fuzzy logic decision to efficiently determine handover and considers three important parameters, including blocking rate, dropping rate, and bandwidth utilization. From the simulation results, this scheme can achieve the higher bandwidth utilization, the lower new call blocking rate, and the lower handover call dropping rate.
TL;DR: A novel adaptive robust fuzzy tracking control algorithm is proposed for a class of nonlinear systems with uncertain system and gain functions, which are all the unstructured (or non-repeatable) state-dependent functions coming from modelling errors and external disturbances.
Abstract: A novel adaptive robust fuzzy tracking control (ARFTC) algorithm is proposed for a class of nonlinear systems with uncertain system and gain functions, which are all the unstructured (or non-repeatable) state-dependent functions coming from modelling errors and external disturbances. The Takagi-Sugeno type fuzzy logic systems are used to approximate uncertain functions and a systematic procedure is developed for synthesis of ARFTC by use of small gain approach and dissipative system theory. The algorithm preserves three advantages: (1) the asymptotic stability of adaptive control in the presence of unstructured uncertainties can be guaranteed, (2) possible controller singularity problem in some of existing adaptive control schemes using feedback linearization techniques can be avoided, (3) the adaptive mechanism with minimal learning parameterizations can be obtained. The effectiveness of the proposed ARFTC for the tracking control ofpole-balancing robots is demonstrated though numerical examples.
TL;DR: An exploration algorithm for partially or totally unknown environrnents based on a representation that integrates metric and topological pazadigms that can operate in known and known areas in a fast and efficient way.
Abstract: This paper presents an exploration algorithm for partially or totally unknown environrnents. The method is based on a representation that integrates metric and topological pazadigms. The metric paradigm produces an accurate representation of the environrent. The topological map is built over the metric map by means of a hierarchical structure. It reduces the metric data volume and can be processed in a more efficient way. The representation of the environrent is used to calculate a route through unexplored areas. The main advantage of the proposed scheme is that it can operate in known and urdmown areas in a fast and efficient way.
TL;DR: The AC level of the space vector current modulation (SVCM) has been used to identify all the additional components, their frequencies and their superimposition under distorted voltage supply and results confirm the accuracy and validity of these indexes of diagnostic.
Abstract: This paper presents an investigation on detection and identification of stator and rotor faults in three-phase induction motors from components frequency specific. The AC level of the space vector current modulation (SVCM) has been used to identify all the additional components, their frequencies and their superimposition under distorted voltage supply. The induced harmonic components are specific to each type of fault and are also distinguished relatively to time harmonics. Experimental results confirm the accuracy and validity of these indexes of diagnostic.
TL;DR: This paper focuses on the design of robust full order and reduced order filters, which can guarantee a prescribed energy-to-peak disturbance attenuation level and incorporates a new parameter-dependent stability result into the filter designs.
Abstract: This paper deals with the robust l∞-l∞ filtering problem for discrete-time systems with multiple delays in the state and uncertain parameters residing in a polytope. We focus on the design of robust full order and reduced order filters, which can guarantee a prescribed energy-to-peak disturbance attenuation level. Two approaches are presented to solve the filtering problem: delay-independent (suitable for systems with unknown delay bounds) and delay-dependent (suitable for systems with known delay bounds). Sufficient conditions for the existence of admissible filters are formulated in terms of linear matrix inequalities, upon which both the delay-independent and dependent filtering problems are cast into convex optimization problems. These two approaches also incorporate a new parameter-dependent stability result into the filter designs. This greatly reduces the conservatism of the quadratic framework.
TL;DR: The capability of Reinforcement Learning techniques for behavior arbitration in robotic soccer is investigated by using Sarsa(λ) algorithm with apseudo-fuzzy technique for function approximation and comparing it with Q, and CMAC function approximation with the proposed APF technique.
Abstract: Most of the proposed approaches for behavior coordination neglect the issue of learning from experience, which is essential to make an agent capable of adapting to the environrnent. This subject is mostly addressed by researchers in the area of Reinforcement Learning. In order to investigate the capability of Reinforcement Learning techniques for behavior arbitration, we considered asub-problem in robotic soccer. We have solved this problem by using Sarsa(λ) algorithm with apseudo-fuzzy technique for function approximation. We also compared Sarsa(λ) with Q(λ), and CMAC function approximation with the proposed APF technique.
TL;DR: A signal filter for a feed-forward controller based on the application of fuzzy logic, combined with statistical process control (SPC) is described, capable of over-riding the actions of, a feedback controller.
Abstract: In this work we describe a signal filter for a feed-forward controller based on the application of fuzzy logic, combined with statistical process control (SPC). The feed-forward controller is for a three-phase oil field centrifuge. The centrifuge system is used to separate meta-stable three-phase oil and water emulsions that are stabilized by solids. These emulsions are considered to be unusable wastes and must be disposed of in an environrnentally acceptable manner. The centrifuge is capable of turning these wastes into clean saleable oil, water that can be reused in an operating process or re-injected into oil wells, and solids that can be disposed of in landfills. The feed-forwazd controller is used for feed disturbance rejection. It works in conjunction with, and is capable ofover-riding the actions of, a feedback controller. The measured feed variables for the feed-forward controller each exhibit reasonably large random fluctuations. It is therefore quite important to use a signal filter tha...
TL;DR: An equation for predicting where the phase transition might be in randomly generated distributed asymmetric CSPs (DisACSPs) is developed and tested by compazing the performances of six evolutionazy protocols referred to as Evolutionazy protocols.
Abstract: The distributed constraint satisfaction problem (DisCSP) can be viewed as a 4-tuple (X, D, C, A), where X is a set of n variables, D is a set of n domains (one domain for each of the n vaziables), C is a set of constraints that constrain the values that can be assigned to the n variables, and A is a set of agents for which the variables and constraints are distributed. The objective in solving a DisCSP is to allow the agents in A to develop a consistent distributed solution by means of message passing. The constraints are typically considered private and are not allowed to be communicated to fellow agents. When constraint privacy is enforced, inter-agent constraints that exist between the variables of multiple agents will most likely be asymmetric. In this paper, we develop an equation for predicting where the phase transition might be in randomly generated distributed asymmetric CSPs (DisACSPs). We then test this equation by compazing the performances of six evolutionazy protocols referred to as...
TL;DR: Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content.
Abstract: Taylor & Francis makes every effort to ensure the accuracy of all the information (the “Content”) contained in the publications on our platform. However, Taylor & Francis, our agents, and our licensors make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by Taylor & Francis. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information. Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content.
TL;DR: In this paper, a computer simulation using fuzzy logic controls on a large optical membrane mirror being researched at the U.S. Air Force Reseazch Laboratory has been presented.
Abstract: Very lazge space based membrane mirror technology is of current interest to NASA, JPL, DOE, DOD, and in particular to the U.S. Air Force Research Laboratory. The membrane mirror technology is driven by the expectation of achieving very large optics with lower costs, through reductions in structural mass and volume. Diverse groups are reseazching and developing membrane technology for RF antennae, optical telescopes, and solar power collection for propulsion applications. A key component for success of membranes used as optical telescopes is the control and maintenance of the accuracy of the membrane mirror surface. This paper will give a description of a computer simulation using fuzzy logic controls on a large optical membrane mirror being researched at the U.S. Air Force Reseazch Laboratory. The control of a membrane mirror is a new challenge, which has not previously been addressed. Fuzzy logic is the natural choice for the controller, since there is little correlation between the optical aber...
TL;DR: The main advantage of the proposed method resides in its departing from the analytical approach, as it does not employ formal descriptions of the locations and shape of the obstacles, nor does it solve the kinematic equations of the mechanism.
Abstract: A robotic mechanism for locomotion along rigid aerial lines and reticulated structures is presented. A biomimetic method for obstacle avoidance is also introduced. The computation of collision-free trajectories requires the analytical description of the physical structure of the environrnent and the solution of the inverse kinematic equations. For dynamic environrnents with unknown obstacles, however, it is extremely difficult to get real-time collision avoidance by means of analytical techniques. The main advantage of the proposed method resides in its departing from the analytical approach, as it does not employ formal descriptions of the locations and shape of the obstacles, nor does it solve the kinematic equations of the mechanism. Instead, the method follows the perception-reason-action cycle and is based on a reinforcement learning process guided by perceptual feedback. From this perspective, obstacle avoidance is modeled as amulti-objective optimization process. Finally, the concept of lo...