By Topic

Applied Machine Intelligence and Informatics (SAMI), 2011 IEEE 9th International Symposium on

Date 27-29 Jan. 2011

Filter Results

Displaying Results 1 - 25 of 66
  • Committees

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (24 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (20 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | PDF file iconPDF (48 KB)  
    Freely Available from IEEE
  • [Title page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (127 KB)  
    Freely Available from IEEE
  • Recent results on migrative triangular norms

    Page(s): 55 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (120 KB) |  | HTML iconHTML  

    This paper summarizes our recent results on continuous triangular norms that are migrative with respect to an arbitrary continuous triangular norm. The content is based on three journal papers. We start with the original notion of migrativity and completely describe all continuous migrative triangular norms. Then we extend the migrative property by allowing an arbitrary but fixed t-norm in the defining equation instead of the originally used product t-norm. Equivalent forms of this extended migrativity are also provided. Two particular cases when the fixed t-norm is either the minimum or the Łukasiewicz t-norm are studied. In these cases all continuous extended migrative t-norms are characterized and represented. Finally, we exploit the ordinal sum structure of continuous t-norms and our mentioned results to describe all continuous triangular norms that are migrative with respect to an arbitrary continuous triangular norm. We illustrate the statements by numerical examples. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recursive tuning algorithm for assist controller of a trolley crane system

    Page(s): 61 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (134 KB) |  | HTML iconHTML  

    The role of a human operator in machine control varies with the level of automation. In applications where the human operator is directly in control, the most significant performance variations are due to the variations in the human performance. Human control is very dexterous and is especially advantageous in complex multi-objective task execution. However, the human performance variations might compromise the safety and accuracy of the system. To compensate the insufficient human performance, parallel human adaptive assist control is developed. The assist control is tuned based on the human operator model identified during normal task execution. Moreover, a new recursive tuning method for the human adaptive assist control is described. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiences in building of context-free grammar tree

    Page(s): 67 - 71
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (93 KB) |  | HTML iconHTML  

    One of the main research areas in current intelligent systems is the development of natural language interfaces for applications. The processing of sentences is controlled by grammar of the language. From the viewpoint of efficiency, the most widely used grammar in computer linguistics is the CFG (context-free grammar) formalism. The paper provides an overview of the structure of CFG and it presents an algorithm for automatic grammar tree construction. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Supervision in synthesis of agents cooperation

    Page(s): 73 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (156 KB) |  | HTML iconHTML  

    The discrete-event systems (DES) modularity and supervision are utilized at synthesis of the agents cooperation. The agents are understood to be (DES) modules. They are described by place/transition Petri-nets (P/T PN). A desired strategy of the agents behavior during the co-operation is expressed by conditions for synthesizing the DES supervisor. Then the strategy is forced on agents. Such a procedure can be utilized step-by-step also at the synthesis of more complex structures of co-operating modules (groups of agents) in order to achieve a prescribed behaviour of the global structure. The approach is illustrated by examples. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Software Product Lines-based development

    Page(s): 79 - 81
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (109 KB) |  | HTML iconHTML  

    Software Product Lines enable the development of a domain-specific set of similar systems. They rely on the predictable reuse of assets and components. Systems following this approach inherently support mass customization and configuration during the entire evolution of the product family. Feature modeling, in conjunction with Software Product Lines, provides a natural and expressive representation for the product variants. It enables the hierarchical description of common and variable features shared by the software product variants. This paper presents a model-driven approach of Software Product Lines, placing an emphasis on product implementation. After discussing the general model, an example is provided and the use of feature models for Product Line specification is introduced. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards automatic norm compliance in construction domain

    Page(s): 83 - 87
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (405 KB) |  | HTML iconHTML  

    This research presents the Ok - build expert system for automatic detection of norm compliance in the construction domain. In the first step, the plan of the building, exported by the CAD tools using the Industry Foundation Classes (IFC) standard, is converted as Jess facts. Then, the construction is checked against the active regulatory norms represented as Jess rules. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Soft computing based anytime modeling methodology for handling resource insufficiency

    Page(s): 89 - 94
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (165 KB) |  | HTML iconHTML  

    Nowadays practical solutions of engineering problems involve model-integrated computing. Model based approaches offer a very challenging way to integrate a priori knowledge into the procedure. Due to their flexibility, robustness, and easy interpretability, the application of soft computing, in particular fuzzy and neural network based models, may have an exceptional role at many fields, especially in cases where the problem to be solved is highly nonlinear or when only partial, uncertain and/or inaccurate data is available. Nevertheless, ever so advantageous their usage can be, it can still be limited by their high computational complexity. Although, a possible solution can be, if we combine soft computing and anytime techniques, because the anytime mode of operation is able to adaptively cope with the available, usually imperfect or even missing information, the dynamically changing, possibly insufficient amount of resources and reaction time. In this paper, a soft computing based anytime modeling methodology is presented for handling resource insufficiency and the applicability of the generated models is analyzed in dynamically changing, complex, time-critical systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On observer-based residual generator design for a class of nonlinear systems

    Page(s): 95 - 99
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (113 KB) |  | HTML iconHTML  

    Generalized principle for designing observer-based residual generators for one class of continuous-time nonlinear MIMO system is treated in this paper. The problem addressed can be indicated as an approach given sufficient conditions for residual generator design based on Thau observers, as well as on fuzzy observers. Linear matrix inequalities are outlined to possess stable structures closest to optimal asymptotic properties. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spoken term detection based on the most probable phoneme sequence

    Page(s): 101 - 106
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (154 KB) |  | HTML iconHTML  

    The aim of the spoken term detection task is to find the occurrence of user-entered keywords in an archive of audio recordings. In this area, besides the accuracy of hits returned, the speed of search is also very important, for which an intermediate representation of recordings is normally used. In this paper we evaluate a spoken term detection method which represents the speech signals by their most probable phoneme sequence, on which a dynamic search is then performed. As the accuracy of the phoneme recognizer used is vital, we shall test this method by using several approaches of phoneme identification. We found that our method already achieves satisfactory accuracy, although its run time is still rather high. We also found that this approach is heavily dependent on the performance of the phoneme recognizer. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of Carnatic raagas using Hidden Markov Models

    Page(s): 107 - 110
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (135 KB) |  | HTML iconHTML  

    Raaga identification is one of the key areas for budding Carnatic musicians and avid listeners. Identification and knowledge of the raaga of a song not only implies knowledge of music but also helps establish the mood of a song. We propose to identify a Carnatic raaga by extracting from the music sample, information about the 12 distinguishable frequencies in an octave. The proposed technique is Specmurt analysis which involves the analysis of a signal in its log-frequency domain. The extracted information is fed to the Hidden Markov Model back-end system where each raaga has its associated model. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Magnetic aura study of small turbojet engine MPM 20 and possibilities of its usability in MPM 20 situational control

    Page(s): 11 - 14
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1020 KB) |  | HTML iconHTML  

    This article is concentrated on research of magnetic aura of aircraft engine MPM 20 during its operating modes. Next aim of this article is description of usability of magnetic aura for MPM 20 situational control by fuzzy controller. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discussions on accessibility in industrial automation systems

    Page(s): 111 - 116
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (242 KB) |  | HTML iconHTML  

    Importance of industrial automation systems [1], also known as technical devices, has been a growing area during the past decades. Web applications from one side and industrial automation systems from the other side have become a standard part of people's daily life and more user groups have to deal with them. Hence they must be accessible to all users. Unfortunately, often by the development of such systems, certain user groups are being neglected. Therefore, a systematic concept is required to support the development of industrial automation systems and Web applications. In this paper, we will present the concept, which is proposed in the context of a research project funded by Deutsche Forschungsgemeinschaft (DFG)a. We will discuss the suited methods to effectively assess accessibility requirements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New model entities for corporate knowledge representations in product model space

    Page(s): 117 - 122
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (125 KB) |  | HTML iconHTML  

    Two main recent achievements of the first decade in this new century in model space based during product definition are representation of corporate knowledge in product model and extended application of contextual feature principle. Contextual connections are applied to define corporate knowledge features as relationships amongst product object parameters. Current product models include comprehensive range of contextual features. However, current user interfaces for product definition processes are not in the possession of capabilities for the required human-computer communication and model representation. Coordination of human originated intent and engineering objective definitions for product feature definitions is not available. The authors of this paper introduced a new contextual chain in which human intent, product behavior, and adaptive action objects are connected in order to establish modeling capabilities for the above communication, representation, and coordination. As a realization of this method, new sets of entities were defined to extend currently applied product model entity sets. This paper starts with characterizing and evaluation of the currently prevailing product modeling. Following this, a new model and its entities are introduced and the method of extension of current model with this model is explained. Implementation of the proposed method is facilitated by the possibility for new object class definition by using of open surface of current industrial product modeling systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid concepts of analytic modeling of the MPM 20 engine

    Page(s): 123 - 128
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (693 KB) |  | HTML iconHTML  

    Mathematical modeling represents an efficient method allowing us to examine properties of a researched object. Realization of mathematic models has become a fundamental part of design of many complex systems. By use of simulation, we can experiment with mathematical model similarly as with the real object without the risk of damage and with much lower expenses. Modeling represents experimental process that asserts the examined original (the modeled system) unambiguously another physical or abstract system. The article deals with approach to virtual particular analytic modeling of a compressor and explores some advanced hybrid concepts in modeling of such engine using methods of artificial intelligence. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of artificial immune systems with the particle swarm optimization in job-shop scheduling problem

    Page(s): 129 - 135
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (439 KB) |  | HTML iconHTML  

    This article compares two approaches by jobshop scheduling problem (JSSP) in real manufacturing system. The first approach is based on mechanisms inspired by biological evolution and the immune system. The second stochastic optimization algorithm is based on social simulation models. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving the performance of artificial immune system in estimation problems with normalization technique: A case study of USA, Japan and France electricity consumption

    Page(s): 137 - 141
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (81 KB) |  | HTML iconHTML  

    This paper presents an artificial immune system (AIS) for electricity consumption estimation as a common problem in estimation domain. We study the impact of data normalization on artificial immune system (AIS) performance and two hundred AIS are constructed for this. Also, fifty AIS have been constructed and tested in order to finding best AIS for electricity consumption estimation in each case. Another unique feature of this study is the utilization of AIS in estimation domain and especially in electricity consumption estimation as the first time. Two standard inputs are used in order to training and testing developed AIS. The mentioned input parameters are gross domestic product (GDP) and population (POP). All of trained AIS are then compared with respect to mean absolute percentage error (MAPE). To meet the best performance of the intelligent based approaches, data are normalized. To show the applicability and superiority of the AIS, actual electricity consumption in USA, Japan and France from 1980 to 2007 is considered. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Linear scale calibration machine

    Page(s): 143 - 147
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (227 KB)  

    A Zeiss length measuring machine was retrofitted for the calibration of linear scales, with a pitch distance in the order of a few micrometers. High resolution optics, equipped with a CCD camera with a built in computer was added, for capturing the line sizes and distances. An appropriate LED illumination system is responsible for through the lens illumination and backlighting. The carriage on which the scale rests provides linear positioning motion. The paper discusses various definitions of the pitch distance. From these definitions simple algorithms are derived to determine the pitch distance. Important issue is the elimination of the influence of scale contamination. The main point is to minimize the effect of non-linearity and diffraction, by using appropriate optics and illumination, hereby improving measurement accuracy. The carriage carrying the scale is driven by ultrasonic piezomotor providing nanometer resolution. The displacement is measured by an HP laser interferometer. For higher resolution the CCD camera system can be replaced by a near field microscope. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SVM-based knowledge topic identification toward the autonomous knowledge acquisition

    Page(s): 149 - 154
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB) |  | HTML iconHTML  

    One of the most serious problems that conventional knowledge management (KM) encompasses has been pointed out tardy and ineffective acquisition of knowledge. To resolve this problem, knowledge must be autonomously acquired according to its context of use by applying the technique of keyword extraction in machine learning algorithm-based text mining. Once the topic of the given knowledge can be identified in an automated manner, then a set of knowledge can be explicitly stored in a knowledge repository; fully automated acquisition of knowledge can be achieved. This paper, therefore, suggests an amended knowledge acquisition framework, especially focused on the autonomous acquisition of knowledge in ordinary dialogues. The suggested methodology is underpinned by the functionality of the support vector machine (SVM) which was demonstrated to identify the topic of knowledge in the most accurate and efficient way. To validate the feasibility of the proposed concepts, CKAS (Context-based Knowledge Acquisition System), a prototype system, is implemented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ensuring software quality by formal modeling

    Page(s): 155 - 159
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (171 KB) |  | HTML iconHTML  

    Software quality is always the target of disagreement between developers and users because of its subjective nature. The problem with software quality is the lack of formal definitions. Furthermore, quality metrics are based on empirical indices. This paper presents a method to the application of formal modeling techniques in the subject of software quality verification. We give a high-level view of the approach, leaving the deep details for a later discussion. We also provide a short summary of Software Quality models and standards. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time simulations of environmentally friendly flight control system

    Page(s): 161 - 164
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (256 KB) |  | HTML iconHTML  

    Presented work discusses a proposal of an environmentally friendly flight control system for Light Aircraft or Unmanned Air Vehicle (UAV). The noise and emissions reducing flight control system is based on Total X Control System (TXCS) and assumes the reduction of the total energy dissipation. A general description of the flight control system, control laws, as well as results of preliminary tests performed on a LSA flight simulator are presented in the following parts of this paper. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent prediction of crude oil price using Support Vector Machines

    Page(s): 165 - 169
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (124 KB) |  | HTML iconHTML  

    The price of crude oil is tied to major economic activities in all nations of the world, as a change in the price of crude oil invariably affects the cost of other goods and services. This has made the prediction of crude oil price a top priority for researchers and scientists alike. In this paper we present an intelligent system that predicts the price of crude oil. This system is based on Support Vector Machines. Support Vector Machines are supervised learners founded upon the principle of statistical learning theory. Our system utilized as its input key economic indicators which affect the price of crude oil and has as its output the price of crude oil. Data for our system was obtained from the West Texas Intermediate (WTI) dataset spanning 24 years and experimental results obtained were very promising as it proved that support vector machines could be used with a high degree of accuracy in predicting crude oil price. View full abstract»

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