By Topic

Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on

Date 23-24 May 2009

Filter Results

Displaying Results 1 - 25 of 640
  • [Title page]

    Publication Year: 2009 , Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (108 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2009 , Page(s): 2
    Save to Project icon | Request Permissions | PDF file iconPDF (106 KB)  
    Freely Available from IEEE
  • Welcome Message

    Publication Year: 2009 , Page(s): 3
    Save to Project icon | Request Permissions | PDF file iconPDF (100 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2009 , Page(s): 4
    Save to Project icon | Request Permissions | PDF file iconPDF (99 KB)  
    Freely Available from IEEE
  • Program Committee

    Publication Year: 2009 , Page(s): 5
    Save to Project icon | Request Permissions | PDF file iconPDF (84 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2009 , Page(s): 6 - 33
    Save to Project icon | Request Permissions | PDF file iconPDF (233 KB)  
    Freely Available from IEEE
  • 3D Laser Scanning Technique and Pattern Recognition Algorithms for Rock Fracture Measurements

    Publication Year: 2009 , Page(s): 1 - 4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (485 KB) |  | HTML iconHTML  

    The measurement speed and accuracy are much better than other similar systems or techniques. In rock engineering, 3D laser scanning technique has been used in geology mapping, rock blasting, rock slope maintains, and rock fracture measurement and analyses. This paper mainly presents 3D laser scanning technique and its applications in rock fracture measurement and analyses. In this paper we present that for a 3D laser image, the large scale part and surface roughness can be re-constructed by directly using depth information from laser scanning data; and the more detailed information or micro fractures (fracture network) can be detected by using some smart image segmentation algorithms. Some experiments and tests are illustrated for the above description. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A 3D Color Measurement System

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2041 KB) |  | HTML iconHTML  

    This paper describes a novel 3 dimensional color measurement system. After the sensors and corresponding data processing board were presented, based on a calibration board with right-angled triangle outline, two calibration algorithms are presented to obtain the extrinsic parameters for sensors. One is the calibration algorithm between 2 dimensional laser range finder (2D LRF), the other is for 2D LRF and the color camera. The result parameters were obtained through solving the constrain equations by the correspond data between the 2D LRF and other two sensors. The 3D color reconstruction experiments of real data prove the effectiveness and the efficient of the system and the algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A BBN-Based Approach for Fault Localization

    Publication Year: 2009 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (288 KB) |  | HTML iconHTML  

    Fault localization techniques help programmers find out the locations and the causes of the faults and accelerate the debugging process. The relation between the fault and the failure is usually complicated, making it hard to deduce how a fault causes the failure. Analysis of variance is broadly used in many correlative researches. In this paper, a Bayesian belief network (BBN) for fault reasoning was constructed based on the suspicious pattern, whose nodes consist of the suspicious pattern and the callers of the methods that constitute the suspicious pattern. The constructing algorithm of the BBN, the correlative probabilities, and the formula for the conditional probabilities of each arc of the BBN were defined. A reasoning algorithm based on the BBN was proposed, through which the faulty module can be found and the probability for each module containing the fault can be calculated. An evaluation method was proposed. Experiments were executed to evaluation this fault localization technique. The data demonstrated that this technique could achieve an average accuracy of 0.761 and an average recall of 0.737. This fault localization technique is very effective and has high practical value. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Bottom-Up Method for Facial Feature Extraction Using Active Shape Models

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (336 KB) |  | HTML iconHTML  

    Facial feature extraction attracts much research interest due to its importance value in applications including human-computer interaction and visual surveillance. Model-based algorithms such as active shape models and active appearance models are efficient for facial feature extraction in color images. However, the complexity of the images and the local nature of active shape models optimization presents a challenge to the localization problem . We propose a new bottom-up method in model fitting stage of ASM, which decompose the whole face model search into several sub-feature search.lt enables the models to be combined with other feature location methods as to get good initialization and lead to more accurate estimates. We demonstrate the experiment results of successfully applying this schema on facial feature extraction. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Brief Report to the Symmetry-Relationship Database Management System and its Application in Geomatics

    Publication Year: 2009 , Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (190 KB) |  | HTML iconHTML  

    The symmetrical matrices in geomatics have been generated every day, and their scale have been increasingly and rapidly expanded. The existed data management of symmetrical matrices has been increasingly faced with some great difficulties and challenges. This paper introduces briefly our works on a new expanded relationship database management system, the symmetry-relationship database management system (SRDBMS), that based on a new data model - the symmetry-relationship data model, and then introduce simply our works on the application of the SRDBMS in geomatics. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Clustering Model Inspired by Humoral Immunity

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (279 KB) |  | HTML iconHTML  

    In biological immune system, B-cells secrete large numbers of antibodies to recognize and eliminate the antigens. Inspired by the relationship of B-cells and antibodies, an effective immune model is presented in this paper. As its learning capability, this model can recognize not only the existing antigens but also the antigens that are unknown. The structure of the model and the detailed algorithm are given in this paper. And the validity of the model is proved through an experiment of motor fault data clustering. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Control Method of Tendency Surface Based on Cubic Polynomial

    Publication Year: 2009 , Page(s): 1 - 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (295 KB) |  | HTML iconHTML  

    A new control method of tendency surface based on cubic polynomial (TSCP) is proposed; the definition of the tendency of control output is given; the cubic polynomial correlation coefficients are determined to meet the requirements of tendency of control output. At the same time, the procedure to expand the univariate polynomial curves into surface is suggested. Further, tendency surface is optimized by genetic algorithm. Simulation results verify the effectiveness of the given method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Design of the Automatic Anti-Collision System

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB) |  | HTML iconHTML  

    This paper presents the design of an automatic anti- collision system which composed by embedded FPGA, DSP and ARM. TMS320DM6437 DSP as the core of the system, and Spartan-3 FPGA, S3C2410 ARM9, EP1C3T144C6 FPGA is its best match. First, we designed FPGA + DSP 3 way video surveillance system and DSP + ARM + FPGA automatic warning and control system, then combined them together to complete the whole car automatic anti-collision system. The system can make full use of the function, characteristic and operation of the three chips, which effectively implemented sound and light warning and helped cars automatically slow down and brake. The "dual control" function can gain the ends of helping the drivers minimize and avoid traffic accidents. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A DNA Algorithm of Horse Traversing Problem Based on Adleman Model

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (271 KB) |  | HTML iconHTML  

    Horse traversing problem was a hard problem to solve with traditional computer; and there were no efficient algorithms to solve this problem with traditional computer when the measurement of problem was very great. In order solve this problem, the extended horse traversing problem was transformed into directed Hamilton path problem, and was solved by using Adleman DNA computing model. A DNA algorithm was introduced to solve this kind of problems through an instance on a chess-board, the experiment steps were also given; at the same time, the solution of the instance was got by simulation experiment. At last, the complexity of the algorithm was illustrated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Dynamic and Self-Adaptive TCP-Friendly Congestion Control Mechanism in Next-Generation Networks

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB) |  | HTML iconHTML  

    TCP-friendly congestion control is the key technique in next-generation-networks. An effective congestion control which uses the predominance of dynamic thresholds self- adaptive TCP-friendly congestion control (DATFCC) is proposed. The size of the receiver buffer butter was dynamically adjusted according to the state of the networks, the dropping probability was determined by the type and the size of the flows. It can keep multimedia flows available share bandwidth fairly with TCP flow. Network simulator (NS) simulation results show that the proposed DATFCC algorithm outperforms TCP-friendly rate control protocol and the TCP NewReno in terms of rate smoothness and fairness to TCP flows. It really improves routers' ability on network congestion control in IP network. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Dynamic Bandwidth Allocation Based Call Access Strategy of Wireless Multimedia Service

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (222 KB) |  | HTML iconHTML  

    We propose a new framework called dynamic adaptive quality of service (DAQoS) to guarantee the quality of service (QoS) of multimedia traffic generally classified as Constant Bandwidth Service (CBS) and variable Bandwidth Service (VBS). DAQos implements a traffic-based admission control, bandwidth reallocation and reservation schemes to support multimedia traffics. The objectives that DAQoS framework tries to accomplish are minimum new call blocking and handoff dropping rates. This scheme is developed to control the bandwidth operation of ongoing connections when the system is overloaded. VBS can borrow bandwidth from CBS when CBS have spare bandwidth, and can give back in times to avoid call drop and block. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Extended DCCP Congestion Control in Wireless Sensor Networks

    Publication Year: 2009 , Page(s): 1 - 4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (238 KB) |  | HTML iconHTML  

    Transmission control protocol (TCP) is a reliable, end-to-end transport protocol, which is widely used for data services and is very efficient for wired networks. However, experiments and research showed that TCP's congestion control algorithm performs very poorly over wireless sensor networks with degraded throughputs. This paper studies TCP's throughput issues in wireless sensor networks, and designs an improved congestion control algorithm based on the characteristics of the wireless sensor networks. The protocol is designed as extension to DCCP (datagram congestion control protocol) with a new congestion control component. We also implemented this congestion control algorithm in NS2.Simulation results show improvements on throughput achieved by using Extended congestion control algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Fast Method for Building and Updating Background Model

    Publication Year: 2009 , Page(s): 1 - 4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (271 KB) |  | HTML iconHTML  

    On the basic of the video traffic surveillance system, the Vehicle detection is a crucial step. A typical method is background subtraction. Extracting and updating the background plays an important role on speed and efficiency of detection. For this reason, the author puts forward a fast and effective method for building and updating the background model. First, adopt the improved statistical method to build initial background. Second, get the vista of the picture per frame by means of background subtraction, and bring forward the background updating method based on the container technology. Finally, in its updating stage, use the pixel excluding the pixel in vista region to renew the background model. The data of experimental picture states clearly that competed with the traditional method, detection technology is robust and accurate. Furthermore, on the realization of arithmetic, it is easier to operate and it has higher timeliness. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Flexible CBR Tool for Intelligent System of Vehicle Body Conceptual Design

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (210 KB) |  | HTML iconHTML  

    Designing a new vehicle is an extremely challenging and a complex process and design experience is needed very much. To reuse the design experience in vehicle body conceptual design system, a flexible CBR (case-base reasoning) module is developed to manage and index the case in design. The concepts of meta-meta-case and meta-case are represented and the method to construct hierarchical structure case schema in the module. Meta-cases and cases are stored in a relational database. An open-structure CBR tool is also developed to describe more complex hierarchic structure for CAD and CAE data in vehicle body concept design, which can offer good support for body case-based design. It can support case definition, case store, case reusing, case retrieving and modifying. Detail design of case is shown and the mechanism of case management is also described in the paper. The module has been embedded in vehicle body concept design system as knowledge core and can guidance user to implement his vehicle concept design. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Formal Refinement Method for Transactional Web Service Composition Compensation Based on Paired Petri Net

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (381 KB) |  | HTML iconHTML  

    Long running Web Services composition has weaker notion of atomicity, which makes the traditional ACID mechanism for transaction processing no longer fit for Web Services composition transaction. Therefore, this paper first formally defines Web services composition compensation based on paired Petri net. Then it proposes five composition compensation patterns on the basis of paired Petri net: sequence, parallel, selection, discriminator and iteration. Finally, it discusses the refinement of Web services composition compensation process and the abstract replacement process of complex multi-partner Web services composition compensation business refinement. This refinement method not only can effectively eliminate the effects of accomplished activities, but also realize the abstract hierarchical modeling of complex multi- partner business process. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Gait Recognition Method Based on KFDA and SVM

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (348 KB) |  | HTML iconHTML  

    The algorithm based on KFDA and SVM is proposed. The information of width and angle is extracted from the human motion image sequences. The features of width and angle is merged and reduced by the KPCA. The Low-dimensional gait characteristic is extracted by modified KFDA, which can obtain the best projection direction and enhance the capacity of data classification. Then the support vector machine (SVM) models are trained by the decomposed feature vectors. The gaits are classified by the trained SVM models. This algorithm is applied to a data-set including thirty individuals. Extensive experimental results demonstrate that the proposed algorithm performs at an encouraging recognition rate of 92% and at a relatively lower computational cost. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A General QoS-Aware Service Composition Model for Ubiquitous Computing

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (368 KB) |  | HTML iconHTML  

    Due to the large success of wireless networks and portable devices, the ubiquitous computing paradigm is becoming a reality. Service-oriented architectures are among the premier middleware approaches to coping with the dynamicity of ubiquitous computing environments. One of the most challenging objectives to be achieved in ubiquitous computing environments is to allow a user to perform tasks by composing on the fly the environment's service and resource components. In this paper we propose a general service composition model for ubiquitous computing which based on semantic service matchmaking and genetic algorithm-based optimization of service selection. Based on the model, a ubiquitous computing architecture is given. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Hybrid Approach of Path Planning for Mobile Robots Based on the Combination of ACO and APF Algorithms

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (195 KB) |  | HTML iconHTML  

    This paper presents an optimal method based on combination of artificial potential field (APF) and ant colony optimization (ACO) algorithms for global path planning of mobile robots working in partially known environments. Two steps constitute this approach. Firstly, free space model of mobile robot is established by using visible graph method and ACO algorithm is utilized in this model to search a global collision-free path which is the shortest routine through known static obstacles. Secondly, when unknown obstacles are encountered, APF algorithm is employed to generate a real-time local path so as to avoid collision. Results of simulation experiments show that the proposed approach has good performance in convergence speed, dynamic behavior and is fit for complex environment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Hybrid Fault-Tolerant Scheduling Algorithm of Periodic and Aperiodic Real-Time Tasks to Partially Reconfigurable FPGAs

    Publication Year: 2009 , Page(s): 1 - 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (269 KB) |  | HTML iconHTML  

    FPGAs have been used widely in space related design engineers and the probability of fault occurring increases when they are subject to total ionization dose. In this paper, the problem of fault-tolerant is solved by task scheduling and a fault tolerant scheduling algorithm of hardware real-time tasks is proposed based on primary/backup copy. By scheduled backwards, the backup copy executes as late as possible before its deadline. So that the primary copy has no overlap or as small overlap as possible with the backup copy on the execution time. When the primary copy executes successfully, the backup copy is released. The experimental results demonstrate that the algorithm is effective and can make full use of FPGAs. View full abstract»

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