By Topic

Intelligent Systems (GCIS), 2013 Fourth Global Congress on

Date 3-4 Dec. 2013

Filter Results

Displaying Results 1 - 25 of 69
  • [Front cover]

    Page(s): C4
    Save to Project icon | Request Permissions | PDF file iconPDF (1622 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (30 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (140 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (319 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - x
    Save to Project icon | Request Permissions | PDF file iconPDF (140 KB)  
    Freely Available from IEEE
  • Preface - GCIS 2013

    Page(s): xi - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (256 KB)  
    Freely Available from IEEE
  • Conference Committee

    Page(s): xiii - xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (251 KB)  
    Freely Available from IEEE
  • Additional reviewers

    Page(s): xv
    Save to Project icon | Request Permissions | PDF file iconPDF (141 KB)  
    Freely Available from IEEE
  • Keynotes

    Page(s): xvi - xix
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (477 KB)  

    Provides an abstract for each of the keynote presentations and a brief professional biography of each presenter. The complete presentations were not made available for publication as part of the conference proceedings. View full abstract»

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

    Page(s): xx
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (229 KB)  

    Provides an abstract of the plenary presentation and a brief professional biography of the presenter. The complete presentation was not made available for publication as part of the conference proceedings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ActorGame: Game Semantics for Actors

    Page(s): 5 - 10
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (318 KB) |  | HTML iconHTML  

    Game semantics is suitable to model interactions between the environment (modeled as opponent role) and the system (modeled as player role), and has gained great successes in which the behaviors of the system and the environment are explicitly distinguished. In this paper, game semantics model (exactly asynchronous game) is introduced into the actors which is called Actor Game. The characteristics of actor computation model, such as receiving messages, sending messages and creating new actors, are well interpreted in Actor Game. And also composition of Actor Games and category of Actor Games are concerned. Both the Actor Game, composition of Actor Games, and category of Actor Games have good properties. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Improved Algorithm for CART Based on the Rough Set Theory

    Page(s): 11 - 15
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (351 KB) |  | HTML iconHTML  

    Data prediction and classification is a critical method in medical nutrition data analysis area. As for the characteristics of being intuitive, efficient and easy to understand, the decision tree algorithm is widely used in this field. However, the classification rules extracted from the decision tree are not the most simple and efficient. The paper analyzes the classical decision tree algorithm CART, and proposes a new improved algorithm R2-CART. The core idea of the advanced algorithm is, in order to simplify the classification rules and tree, combining CART algorithm with rough set theory to conduct the attribute and rule reduction on the classification rules of decision tree. The experiment, which compares the Original CART algorithm with the improved algorithm, shows that the improved algorithm has much better classification efficiency with achieving a simple and efficient classification rule set at the same time. This improved algorithm has a potential practical value for large-scale medical nutrition data of classification and predictive analysis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying Genetic Algorithm Combining Operation Tree (GAOT) for Estimating Salinity of Taiwan Strait Using MODIS/Terra

    Page(s): 16 - 20
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (330 KB) |  | HTML iconHTML  

    This paper proposes genetic algorithm combining operation tree (GAOT) and applies it to estimate the sea salinity of Taiwan Strait (TS) using MODIS/Terra data. GAOT is a data mining method, used to automatically discover the relationships among nonlinear systems. The main advantage of GAOT is to optimize appropriate types of function and their associated coefficients simultaneously. In the case study, this GAOT described above combining with MODIS/Terra seven bands was employed. These results are then verified with in situ sea salinity data of TS. The results show that the GAOT generates accurate multi-variable equation and has better performance than linear regression (LR) method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Brain Waves Reflect Your Memories

    Page(s): 21 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (548 KB) |  | HTML iconHTML  

    In this paper, the brain activities for short-term and long-term memory were verified by event-related potentials of the brain. In addition, long-term memory had a proactive interference to short-term memory that could be found by observing the changes of potentials in the brain. In clinical trials, subjects randomly selected a poker card (target) to be memorized. Subsequently, they were tested by the recognition task that was comprised of a target card and two different cards. The changes of ERPs during card presentation reflected the retrieval process of memory in the brain. Experimental results revealed that the amplitude of P300 of ERPs was related to the short-term memory and could be used to identify whether the presented card was in one's memory or not. The card that was memorized in the short-term memory elicited a larger P300 than other cards without memorization. However, experimental results also found that some meaningful cards, for example spade-2, existed in one's long-term memory and elicited larger P300 amplitude than memorized cards in short-term memory, achieving significant levels. Thus, long-term memory affected the recognition task of short-term memory. The electrophysiological changes are an indicator to memory process and reflect the degree of meaning of objects in the memory. The research provided valuable results that support theories about memory in psychology. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Circuit Simulation for Wireless Mini-drifting Buoy in Shallow Sea

    Page(s): 25 - 29
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (425 KB) |  | HTML iconHTML  

    Ocean buoys is an important tool of Marine Environmental Monitoring, The design of drifting buoy plays a significant role in field of shallow sea environmental monitoring. In order to solve the problem that the shallow marine physical parameters acquisition costs are high and the accuracy of data is low, this paper designed a mini-drifting buoy in shallow sea based on AT89S51 single-chip microcomputer, which were used in measuring shallow seawater temperature, salinity and depth. It is low cost and easy to move. It is not only can wireless remote control, but also can " Beidou " positioning. Moreover, the data is accurate and the mini-drifting buoys in shallow sea can return real-time data as soon as possible. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decomposing Utility Functions in Bounded Max-sum for Distributed Constraint Optimization

    Page(s): 30 - 33
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (199 KB) |  | HTML iconHTML  

    Bounded Max-Sum is a message-passing algorithm for solving Distributed Constraint Optimization Problems (DCOP) able to compute solutions with a guaranteed approximation ratio. In this paper we show that the introduction of an intermediate step that decomposes functions may significantly improve its accuracy. This is especially relevant in critical applications (e.g. automatic surveillance, disaster response scenarios) where the accuracy of solutions is of vital importance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mining Core Motivations among Motivational Agents

    Page(s): 34 - 39
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (417 KB) |  | HTML iconHTML  

    Motivation is an important factor in reasoning about rational behavior of intelligent agents and analyzing the property of social network circles. Recent study on motivational agent paid their main attention on the mechanism of reasoning and multi-agent Cooperation. How motivation affects the internal structure of the allied agent groups are less considered. This paper proposes a methodology for motivational agent clustering, cohesion property analyzing and core motivational agent identifying. The methodology first finds clustered agents from the underlying graph that captures the similarity based interconnection topology of the agents. Then, the subgroups of agents that have high degrees of connectivity are extracted which can be thought of as the key representatives of the whole agent clusters. Our empirical results on real survey data and simulation platform show that our method is quite favorable for clearly partitioning large body of motivational agents and helping the analyzer to identify internal structure of the agent groups. Our algorithms can be adapted in various ways for social network behavior analyzing, intrusion detection and marketplace bidding strategy designing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation for Land Use Dynamic Change of Dian-Chi Lake Watershed Using Agent-Based Modeling

    Page(s): 40 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (818 KB) |  | HTML iconHTML  

    The land use structure and biological service function of Dian-chi lake watershed are being changed by the rapid development of social economy and urbanization, which finally leads to the generation and aggravation of agriculture and urban non-point source pollution in whole basin. Thereby, it is necessary to study the relationship and spatiotemporal process between human activities and land use/cover change (LUCC) of watershed, which is hopeful to offer the scientific decision support for reasonable land planning and land use. Through being combined with GIS technologies of spatial analysis and using the artificial intelligence algorithm called Ant Colony Optimization(ACO) for optimizing, this paper has applied the method of Agent-based modeling to establish the spatiotemporal process model of LUCC in order to simulating the dynamic change of land use in whole watershed. Generally, what has been explored is as fellows. Firstly, make a choice and evaluation for impact factors of land dynamic use, and then create the classes of Agents and their rules in LUCC process. Based on the Java language and Repast platform of modeling, the program design, implementation and simulation of model are given in detail. And finally, the validation for model and analysis for the simulating results are also discussed clearly. We could infer three conclusions from the results of experience. Ant colony algorithm is effective to promote the science express for moving and decision of agents, and the simulating results have better accuracy in both mathematics and geometry than no using it. And the highest accuracy reaches 78.6% in numbers and 68.5% in shape similarity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Forex Prediction Based on SVR Optimized by Artificial Fish Swarm Algorithm

    Page(s): 47 - 52
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (780 KB) |  | HTML iconHTML  

    Taking the radial basis function as a kernel function, a prediction model is developed based on the support vector regression machine (SVR). The optimization of the model parameters, including penalty factor and kernel function variance, is realized by the artificial fish swarm algorithm. The model is used to predict nine foreign exchange rate data with updating and rolling. At the same time, simulating by the cross validation, genetic algorithm, particle swarm optimization algorithm and then evaluating the results from the total error (TE), relative error (RE), absolute root mean square error (ARMSE) and correct trend rate (CTR) comprehensively, the comparison shows that the errors of the model based on SVR optimized by artificial fish swarm algorithm are all minimum and CTR are maximum. In the end, in order to improve the convergence speed and precision further, the self-adaption artificial fish swarm algorithm is presented which is joined the attenuation factor and based on the average distance visual. The result is ideal. Therefore, SVR optimized by the improved artificial fish swarm algorithm can be effectively used in forex prediction. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Study on the Emergency Rescue VRP Based on Ant Colony Optimization and Generalized Distance

    Page(s): 53 - 57
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (304 KB) |  | HTML iconHTML  

    This paper defines a generalized distance index which reflects the comprehensive factors or multiple objectives in emergency rescue, and presents an improved model of emergency rescue VRP based on the generalized distance, after this discusses several kinds of algorithms based on ant colony optimization. From the methods, research results would better suit the characteristics and requirements of emergency rescue. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Further Discussion of the Problem about Conditions of Neighborhoods Forming a Partition

    Page(s): 61 - 65
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (231 KB) |  | HTML iconHTML  

    There is an open question regarding Rough Set theory propsosed by Yun and Qiu(2011), which are how to characterize the conditions for a neighborhood of a data item approximations to form a partition of the universe U of the data by using only their upper and lower operators. The first part of the question has been solved Fan and Hu(2012). In this paper, another part of the question is addressed by a special and simple method, and some significant results are obtained. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Pedestrian Detection and Tracking System Based on Video Processing Technology

    Page(s): 69 - 73
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (627 KB) |  | HTML iconHTML  

    Pedestrian detection and tracking are widely applied to intelligent video surveillance, intelligent transportation, automotive autonomous driving or driving-assistance systems. We select OpenCV as the development tool for implementation of pedestrian detection, tracking, counting and risk warning in a video segment. We introduce a low-dimensional soft-output SVM pedestrian classifier to implement precise pedestrian detection. Experiments indicate that the system has high recognition accuracy, and can operate in real time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Fast Parameters Selection Method of Support Vector Machine Based on Coarse Grid Search and Pattern Search

    Page(s): 77 - 81
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (342 KB) |  | HTML iconHTML  

    Parameters selection of support vector machine (SVM) is a key problem in the application of SVM, which has influence on generalization performance of SVM. The commonly used method, grid search (GS), is time-consuming especially for very large dataset. By using coarse grid search and pattern search (PS) to select kernel parameters and penalty factor, a fast method of parameters selection of SVM based on hybrid optimization strategy is proposed in this paper. The proposed method adequately combines the advantages of GS and PS. The experiment results demonstrate that this proposed method can not only improve accuracy and generalization performance of SVM, but also save much more time. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Research on the GC Property for RNNs with Limited Matrix 2-Norm

    Page(s): 82 - 86
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (244 KB) |  | HTML iconHTML  

    The global convergence (GC) analysis of recurrent neural networks (RNNs) is a first and necessary step for any practical applications of them. In the present paper, when the connecting matrix of the RNNs with projection mapping owning limited norm, the GC property is assured under the critical condition. The results given here not only improve deeply upon the existing relevant critical as well as non-critical dynamics conclusions in literature, but also can be used in the practical application of RNNs directly. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Conceptual Logic-Based Creation Method for Operational Plan Ontology Class Hierarchies

    Page(s): 89 - 93
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (382 KB) |  | HTML iconHTML  

    The quality of the creation of Operational Plan Ontology Class Hierarchies directly affects the quality and efficiency of the entire ontology creation. Starting from analyzing the logical basis of Class Hierarchies creation, this paper puts forward the rules and requirements of Class Hierarchies creation. In addition, it demonstrates concrete procedures of Class Hierarchies creation. Combining with the application example and analysis of the surface warship operational plan, it is proved that the proposed method has a guiding significance and reference value for the effective creation of Operational Plan Ontology Class Hierarchies. View full abstract»

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