Abstract: This paper provides an overview of our research activities aimed at efficient use of Grid infrastructure to solve various text mining tasks. Grid-enabling of various text mining tasks was mainly driven by increasing volume of processed data. Utilizing the Grid services approach therefore enables to perform various text mining scenarios and also open ways to design distributed modifications of existing methods. Especially, some parts of mining process can significantly benefit from decomposition paradigm, in particular in this study we present our approach to data-driven decomposition of decision tree building algorithm, clustering algorithm based on self-organizing maps and its application in conceptual model building task using the FCA-based algorithm. Work presented in this paper is rather to be considered as a 'proof of concept' for design and implementation of decomposition methods as we performed the experiments mostly on standard textual databases.
Keywords: Grid services, text mining, clustering, classification, formal concept analysis
Abstract: An application of fuzzy systems to nonlinear system adaptive control design is proposed in this paper. The fuzzy system is constructed to approximate the nonlinear system dynamics. Based on this fuzzy approximation suitable adaptive control laws and appropriate parameter update algorithms for nonlinear uncertain (or unknown) systems are developed to achieve H∞ tracking performance. It is shown that the effects of approximation errors and external disturbance can be attenuated to a specific attenuation level using the proposed adaptive fuzzy control scheme. The nonlinear gradient law guarantees the convergence of the training algorithm.
Keywords: adaptive fuzzy control, Riccati equation, uncertain system, nonlinear systems
Abstract: It is evident that industrial robots are able to generate forces high enough to injure a human. To prevent this, robots have to work within a restricted space that includes the entire region reachable by any part of the robot. However, more and more robot applications require human intervention due to superior abilities for some tasks performance. In this paper we introduce danger/safety indices which indicate a level of the risk during interaction with robots, which are based on a robot’s critical characteristics and on a human’s physical and mental constrains. Collision model for a 1 DOF robot and “human” was developed. Case study with further simulations was provided for the PUMA 560 robot.
Keywords: robotics, safety, human-robot interaction, danger index
Abstract: The paper describes the influence of shot-peening onto aluminium alloy D16-T surface. There are estimates focusing into microgeometry of the shot peened surfaces, their roughness and a size of selected shot peened material - the corund. Based on the results of measurements, the evaluation was oriented on the curve of roughness, functionality of the surface roughness Ra and the necessary quantity of shot peening material qnR of estimated material depending on the grain size dz.
Keywords: shot peening, functional surface, surface roughness
Abstract: Customer relationship management (CRM) can help organizations manage customer interactions more effectively to maintain competitiveness in the present economy. As more and more organizations realize the significance of becoming customer-centric in today’s competitive era, they adopted CRM as a core business strategy and invested heavily. CRM, an integration of information technology and relationship marketing, provides the infrastructure that facilitates long-term relationship building with customers at an enterprise-wide level. Successful CRM implementation is a complex, expensive and rarely technical projects. This paper presents the successful implementation of CRM from process perspective in a trans-national organization with operations in different segments. This study will aid in understanding transition, constraints and the implementation process of CRM in such organizations.
Keywords: Customer Relationship Management, Customer, CRM, Implementation
Abstract: Paper presents a family of helical two-revolutional cyclical surfaces, which are created by movement of the circle alongside the helical cycloidal curve, where circle is located in the curve normal plane and its centre is on this curve. Helical cycloidal curve can be created by simultaneous revolution of a point about two different axes 3o, 2o and by screwing about axis 1o in the space. Form of the helical cycloidal curve and also of the helical two-revolutional cyclical surface is dependent on the relative position of the three axes of revolutions, on multiples of angular velocities and orientations of separate revolutions. Analytic representation, classification of surfaces and some of their geometric properties are derived.
Keywords: revolution, angular velocity, cyclical surface
Abstract: In this paper a multi-agent based mobile robot simulation system will be presented where the behaviour of the system is studied with different number of agents (1, 3,6) and also with different number of ultrasonic range sensors on agents (8 or 16 US sensors on individual agents). The task of the autonomous agents is to create the potential field (PF) of an unknown environment. The classic problems of PF building, like oscillation and trapping, are not the focus of the article, but instead, the article is concerned with the agents’ self-organizing ability where self-organizing is controlled by a genetic algorithm (GA). The GA is equipped with two fitness functions where one “maintains” the distances between certain agents (spat distr), while another “watches” the area coverage (area cover). In fact, the paper can be divided into three main parts. The first part describes the ultrasonic sensing and range measuring with systematic errors, the potential field (PF) building and the moving strategies. The second part contains description of the GA, the operation of the GA, the structure of the system, the fitness functions and a general systemerror determination. In the final third part, the obtained results are analyzed and presented in the appendices.
Keywords: Genetic algorithm (GA), Mobile Robot, Multi-agent, Potential Field
Abstract: A neural implementation of a harmonic elimination strategy for the control a uniform step asymmetrical 9-level inverter is proposed and described in this paper. A Multi-Layer Perceptrons (MLP) neural network is used to approximate the mapping between the modulation rate and the required switching angles. After learning, the neural network generates the appropriate switching angles for the inverter. This leads to a lowcomputational- cost neural controller which is therefore well suited for real-time applications. This neural approach is compared to the well-known Multi-Carrier Pulse- Width Modulation (MCPWM). Simulation results demonstrate the technical advantages of the neural implementation of the harmonic elimination strategy over the conventional method for the control of an uniform step asymmetrical 9-level inverter. The approach is used to supply an asynchronous machine and results show that the neural method ensures a highest quality torque by efficiently canceling the harmonics generated by the inverter.
Keywords: Uniform step asymmetrical multilevel inverter, Harmonics Elimination Strategy, Artificial Neural Networks, Multi-Layer Perceptron, Multi-Carrier Pulse-Width Modulation
Abstract: The use of alternative energy sources like pyrolysis gases as a source of renewable energy for combined heat and power generation could provide an effective and alternative way to fulfil remarkable part of the increasing energy demand of the human population as a possible solution of decentralized power generation. Therefore the role of utilization of pyrolysis gases rapidly grows in Europe and all around the world. The energetic utilization of these low heating value renewable gaseous fuels is not fully worked out yet because their combustion characteristics significantly differ from natural gas, and this way they are not usable or their utilization is limited in devices with conventional build-up. At the Department of Energy Engineering of BME the IC Engine utilization of pyrolysis gases was investigated. The power, efficiency, consumption and exhaust emission were measured and indication was made to determine the pressure and heat release in the cylinder at different engine parameters.
Keywords: renewable, pyrolysis gas, IC engine, power, efficiency, indication, heat release, exhaust emission