By Topic

Cybernetics and Intelligent Systems, 2004 IEEE Conference on

Date 1-3 Dec. 2004

Go

Filter Results

Displaying Results 1 - 25 of 138
  • 2004 IEEE Conference on Cybernetics and Intelligent Systems (IEEE Cat.04EX912)

    Save to Project icon | Request Permissions | PDF file iconPDF (40 KB)  
    Freely Available from IEEE
  • [Blank page]

    Page(s): 0_2
    Save to Project icon | Request Permissions | PDF file iconPDF (19 KB)  
    Freely Available from IEEE
  • 2004 IEEE Conference on Cybernetics and Intelligent Systems - Title

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (25 KB)  
    Freely Available from IEEE
  • Copyright

    Page(s): ii
    Save to Project icon | Request Permissions | PDF file iconPDF (58 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): iii - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (1333 KB)  
    Freely Available from IEEE
  • Satisfactory design of cogeneration system using genetic algorithm

    Page(s): 671 - 676
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (943 KB) |  | HTML iconHTML  

    This paper introduces the optimum design of co-generation system (CGS) using the genetic algorithm (GA). CGS is the energy reusing system which generates more than two energies from one energy source. To design CGS, the types of machines and load scheduling should be determined. However, the optimum design of CGS is too complicated even for the expert. One of the solutions for this problem is using GA. GA is the optimization model imitating evolution of life. If the coding of the problems is proper, GA can be applicable to many problems. However, proper coding for the problems is difficult, especially for CGS, because it has three different design variables which consist of integer values and real values. To discuss the effective coding, this paper considers four models. First is simplest coding model. Second is two-step optimization model with integer coding. Third is two-step optimization model with the integer coding and the penalty method. Last is three-step optimization model with the integer. As a result of the experiments, three-step optimization model could achieve the higher energy efficiency design of CGS than the expert View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved clearance of flight control laws using hybrid optimisation

    Page(s): 677 - 682
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1155 KB) |  | HTML iconHTML  

    A hybrid optimisation approach to the clearance of flight control laws for highly augmented aircraft is described. The approach is applied to the problem of evaluating a nonlinear clearance criterion for a detailed simulation model of a high performance aircraft with a delta canard configuration and a full authority flight control law. The proposed combination of local and global optimisation methods is shown to offer significantly reduced computation times when compared with using global optimisation methods alone. The accuracy (i.e. closeness to the global solution or true worst-case behavior) of the clearance results derived using the hybrid scheme is also shown to be better than that achieved using either local or global methods on their own View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time genetic lips region detection and tracking in natural video scenes

    Page(s): 683 - 688
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1209 KB) |  | HTML iconHTML  

    In this paper, real-time detection and tracking of lips region of a talking person in natural scenes is addressed. In particular, we try to acquire numerical parameters to represent the lips information. Because, this information is very important for many applications, such as audio-visual speech recognition, robot perception, and interface of mobile devices. The difficulty lies in deformations and geometric change of lips, by speech and free camera work. Our proposed system is based on template matching with genetic algorithms (GAs). In our previous system, there is a trade-off between accuracy and a processing time. However, we can overcome this by two new methods: (a) a flexible control of a search domain, (b) inheritance of genetic information between video frames. We demonstrated the effectiveness of our proposed system by using some 5 seconds video sequences. The average results are that the accuracy is 94,44% and the processing time is 4.50 seconds View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Incremental evolution of autonomous controllers for unmanned aerial vehicles using multi-objective genetic programming

    Page(s): 689 - 694
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1147 KB) |  | HTML iconHTML  

    Autonomous navigation controllers were developed for fixed wing unmanned aerial vehicle (UAV) applications using incremental evolution with multi-objective genetic programming (GP). We designed four fitness functions derived from flight simulations and used multi-objective GP to evolve controllers able to locate a radar source, navigate the UAV to the source efficiently using on-board sensor measurements, and circle closely around the emitter. We selected realistic flight parameters and sensor inputs to aid in the transference of evolved controllers to physical UAVs. We used both direct and environmental incremental evolution to evolve controllers for four types of radars: 1) continuously emitting, stationary radars, 2) continuously emitting, mobile radars, 3) intermittently emitting, stationary radars, and 4) intermittently emitting, mobile radars. The use of incremental evolution drastically increased evolution's chances of evolving a successful controller compared to direct evolution. This technique can also be used to develop a single controller capable of handling all four radar types. In the next stage of research, the best evolved controllers will be tested by using them to fly real UAVs View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-ob ective satisfactory ptimi ation method

    Page(s): 695 - 699
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (726 KB)  

    The multi-objective satisfactory optimi ation method is deveIoped in this paper. The proposed method is based on neural networks and genetic algorithm, and it is able tu overcome the shortcoming of the single-objective optimization on the working unit of the loader, An example of the working unit optimi ation of the loader is given to illustrate the effectiveness of the proposed multi-objective satisfactory optimization method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A pareto based multi-objective genetic algorithm for scheduling of FMS

    Page(s): 700 - 705
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (892 KB) |  | HTML iconHTML  

    Many real-world engineering and scientific problems involve simultaneous optimization of multiple objectives that often are competing. In this work, we have addressed issues relating to scheduling with multiple (and competing) objectives of flexible manufacturing system (FMS) and have developed a mechanism by employing a Pareto based GA to generate nearer optimal schedules. In the proposed method we have applied Pareto ranking to identify the elite solutions and their fitness values are derated using fitness sharing method. The procedure is evaluated with sample problem environment found in literature and results are compared with other available heuristics found in literature. The proposed niched Pareto genetic algorithm (NPGA) exhibits a superiority over the other heuristics and scheduling rules View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization of a hard disk drive servo system using multiobjective genetic algorithm

    Page(s): 706 - 711
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (787 KB) |  | HTML iconHTML  

    For a hard disk drive servo system, there are multiple control objectives to be met simultaneously. While some of the objectives are constraint objectives, some of them are simply optimization objectives. In this paper, we describe a new approach for tuning the controller parameters such that the resultant servo system can perform and meet all the requirements. Unlike the Pareto ranking multiobjective genetic algorithm, our approach is able to place higher priority for the constraint objectives than the optimization objectives. Some experimental results are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pareto archived simulated annealing for permutation flow shop scheduling with multiple objectives

    Page(s): 712 - 717
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1115 KB) |  | HTML iconHTML  

    In this paper, a metaheuristic procedure based on simulated annealing (SA) is proposed to find Pareto-optimal or non-dominated solution set for the permutation flow shop scheduling problems (FSPs) with the consideration of regular performance measures of minimizing the makespan and the total flow time of jobs. A new perturbation mechanism called "segment-random insertion (SRI)" scheme is used to generate the neighbourhood of a given sequence. The performance of the proposed algorithm is evaluated by solving benchmark FSP instances provided by (B. Taillard, 1993). The results obtained are evaluated in terms of the number of non-dominated schedules generated by the algorithm and the proximity of the obtained non-dominated front to the Pareto front. The results and simple quality measures suggested in this paper can be used to evaluate the quality of the non-dominated fronts obtained by different algorithms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-objective genetic algorithms for scheduling mateiral handling equipment at automated air cargo terminals

    Page(s): 718 - 723
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (988 KB) |  | HTML iconHTML  

    In order to improve the productivities of a typical cargo handling system, it is important to reduce the waiting time of stacker cranes (SCs) and the total traveling time of automated guided vehicles (ACVs) through efficient scheduling of SCs and ACVs, which are cooperating tightly to perform cargo handling operations in an optimal way. In this paper, we develop and investigate the application of the multi-objective genetic algorithm (MOGA) to solve such scheduling problem with the objectives of minimizing the AGV total traveling time and the total delay time of the SC. The results of the experiments demonstrated that MOGA produces better solutions than the single objective genetic algorithms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network-based improvement in class separation of physiological signals for emotion classification

    Page(s): 724 - 728
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (940 KB) |  | HTML iconHTML  

    Computer scientists have been slow to become aware of the importance of emotion on human decisions and actions. Recently, however, a considerable amount of research has focused on the utilisation of affective information with the intention of improving both human-machine interaction and artificial humanlike inference models. It has been argued that valuable information could be obtained by analysing the way affective states and environment interact and affect human behaviour. A method to improve pattern recognition among four bodily parameters employed for emotion recognition is presented. The utilisation of autoassociative neural networks has proved to be a valuable mechanism to increase inter-cluster separation related to emotional polarity (positive or negative). It is suggested that the proposed methodology could improve performance in pattern recognition tasks involving physiological signals. Also, by way of grounding the immediate aims of our research, and providing an insight into the direction of our work, we provide a brief overview of an intelligent-dormitory test bed in which affective computing methods was applied and compared to non-affective agents View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An evaluation of the level of daily activities: LDA using neural networks for medical treatment

    Page(s): 729 - 734
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1081 KB) |  | HTML iconHTML  

    In this paper, a new evaluating method of LDA (level of daily activities) is proposed using neural networks. In the new evaluating method, a neural network acquires specific rules for a specific subject by learning with the measurement signals of the subject using accelerometers, and LDA of the subject is judged with the neural network which has obtained the specific rules. The effectiveness of the proposed evaluating method of LDA is shown by judging it with the actual measurement signals of a healthy subject View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust neural network controller design for a biaxial servo system

    Page(s): 735 - 740
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (890 KB) |  | HTML iconHTML  

    A robust control method for synchronizing a biaxial servo system motion is proposed in this paper. A new neural network based cross-coupled control and neural network techniques are used together to cancel out the skew error. In the proposed control scheme, the conventional lived gain PID cross-coupled controller (PIDCCC) is replaced with the neural network cross-coupled controller (NNCCC) to maintain biaxial servo system synchronization motion. In addition, neural network PID position velocity and velocity controllers provide the necessary control actions to maintain synchronization while following a variable command trajectory. This scheme provides strong robustness with respect to uncertain dynamics and nonlinearities. The simulation results reveal that the proposed control structure adapts to a wide range of operating conditions and provides promising results under parameter variations and load changes View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Single exponential smoothing method and neural network in one method for time series prediction

    Page(s): 741 - 745
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (939 KB) |  | HTML iconHTML  

    The purpose of this paper is to present a new method that combines statistical techniques and neural networks in one method for the better time series prediction. In this paper we presented single exponential smoothing method (statistical technique) merged with feed forward back propagation neural network in one method named as smart single exponential smoothing method (SSESM). The basic idea of the new method is to learn from the mistakes. More specifically, our neural network learns from the mistakes made by the statistical techniques. The mistakes are made by the smoothing parameter, which is constant. In our method, the smoothing parameter is a variable. It is changed according to the prediction of the neural network. Experimental results show that the prediction with a variable smoothing parameter is better than with a constant smoothing parameter View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hands-free control of power wheelchairs using Bayesian neural network classification

    Page(s): 746 - 750
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (624 KB) |  | HTML iconHTML  

    This paper describes the formulation and implementation of Bayesian neural networks for head-movement classification in a hands-free wheelchair navigation system. Bayesian neural network training adjusts the weight decay parameters automatically to their near-optimal values that give the best generalisation. Moreover, no separate validation set is used so all available data can be used for training. Experimental results are presented showing that Bayesian neural network can classify the head movement accurately View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance oriented anti-windup for a class of neural network controlled systems

    Page(s): 751 - 756
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1079 KB)  

    This paper presents a conditioning scheme for a linear control system which is enhanced by a neural network (NN) controller and subjected to a control signal amplitude limit. The neural network controller improves the performance of the linear control system by directly estimating an actuator-matched, un-modeled, nonlinear disturbance, in closed-loop, and compensating for it. As disturbances are generally known to be bounded, the nominal NN-control element is modified to retain the known bound of the disturbance as its maximum amplitude. The linear control element is conditioned by an anti-windup (AW) compensator which ensures performance close to the nominal controller and swift recovery from saturation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic power system harmonic detection using neural network

    Page(s): 757 - 762
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (796 KB) |  | HTML iconHTML  

    Conventional approaches for harmonics measurement usually employ either FFT or DFT. They, however, are susceptible to the presence of noise in the distorted power line. This paper proposes an alternative neural network based algorithm to detect the location of dynamic power harmonics in noisy environments. Sensitivity considerations are also conducted to determine the key parameters that affect the model performance efficiency in the lowest errors of testing patterns View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian learning for object based image segmentation

    Page(s): 763 - 768
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1136 KB) |  | HTML iconHTML  

    This paper proposed an algorithm using Bayesian on-line learning for object based video image segmentation. First the strengths of image pixel's spatial location, color and motion segments are weighted and then unified in one framework for image clustering and segmentation. Here, the appropriate modeling of probability distribution functions (PDF) of each feature cluster is obtained through Gaussian distribution. In this paper, unsupervised Bayesian learning is implemented to identify these distribution parameters. The online Bayesian learning process is carried out with the previous clustered image pixels information and feature clusters Gaussian PDF information. This algorithm has shown good results on different video files. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic detection of hilum and parenchymal bands on HRCT lung images

    Page(s): 769 - 774
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1137 KB) |  | HTML iconHTML  

    High-resolution computed tomography (HRCT) images have been found to be more sensitive than chest radiographs and conventional CT in diffuse lung disease diagnosis. Parenchymal bands are a type of reticular opacity commonly seen in patients with asbestosis. We have developed automated techniques to detect parenchymal bands on HRCT images of the lung that can help reduce the amount of data radiologists must process to arrive at a diagnosis. This technique also includes detection of the hilum an anatomical landmark, which is essential to parenchymal band detection. Preliminary results are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The utilization of closing algorithm and heuristic information for broken character segmentation

    Page(s): 775 - 779
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (792 KB) |  | HTML iconHTML  

    In Thai printed character recognition systems, an important problem that decreases the accuracy is broken characters. These characters could cause the error in segmentation process. To solve this problem, a method for broken character segmentation in Thai printed document is presented. It consists of two main steps: text line detection, for extracting text lines from an image, and character segmentation, for extracting broken characters from a text line. The character segmentation consists of four steps: Gap reduction using closing algorithm, character segmentation using space, large character splitting and small character merging using heuristic information. The advantage of this approach is the ability to segment broken character even when it is split into a large number of segments. The experimental result shown that our method achieves 91.09% View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analog CMOS circuit implementation of motion detection with wide dynamic range based on vertebrate retina

    Page(s): 780 - 785
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1048 KB) |  | HTML iconHTML  

    Analog complementary metal oxide semiconductor (CMOS) circuits for edge detection were proposed based on the vertebrate outer retina. A simple analog CMOS circuit for generating the motion signal, which inputs the edge signal, was also proposed based on the amacrine cell in the inner retina. The simulation results with the simulation program with integrated circuit emphasis (SPICE) showed that the proposed edge detection circuits can detect edge positions with a dynamic range of 5 decades. The simulation results with SPICE showed that the proposed circuit can generate the motion signal of the edge. A chip for processing a moving image in real time with the wide dynamic range can be realized by applying the proposed circuits View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.