Krisztián Balázs Kis

Traffic speed prediction method for urban networks — an ANN approach

The paper proposes a traffic speed prediction algorithm for urban road traffic networks. The motivation of the prediction is to provide short time forecast in order to support ITS (Intelligent Transport System) functionalities, such as traveler information systems, route guidance (navigation) systems, as well as adaptive traffic control systems. A potential and efficient solution to this problem is the application of a soft computing method. Namely, an artificial neural network (ANN) is used for the forecast by involving the measured speed patterns. The ANN is trained by using data produced by Vissim (a microscopic road traffic simulator) simulations. The proposed algorithm is developed and analyzed on a real-word test network (part of downtown in Budapest).

Support Vector Machine (SVM) based general model building algorithm for production control

Abstract The paper introduces an algorithm for building up the general system model applying the Support Vector Machine (SVM) modeling approach. It finds that input/output configuration of the system model that realizes the most accurate estimation and explores the maximum of dependencies among the related system parameters. Its performance is tested and evaluated under various conditions: after the basic testing using simple mathematical equations a field specific analysis was performed applying the classical equations from the cutting control theory. Experiments were done also for cutting control based on real measured parameters under varying conditions. These validations showed good empirical performance and practical applicability of the algorithm introduced. This model building approach was generalized to various model types having learning capabilities.

Surface resistance of ESD-protected worksurfaces—measurement, modelling and estimation considerations

The prevention of electrostatic discharge (ESD) is of crucial importance in the electronics industry, and surfaces of workstations have to be of specific resistance for effective ESD protection. The paper presents results of an R&D project which investigated the—so far rarely researched—dependence of worksurface resistance on ambient conditions and surface contamination. Upon examination of known and assumed dependencies, measurement and instrumentation are outlined, relying on existing automated facility management, autonomous devices, and manual measurement/logging. Further parts of the paper report on an analysis of the data obtained, as well as their use in building models of surface resistance, employing feature selection metaheuristics applied in combination with artificial neural networks. Surface resistance models built with approximately one year’s worth of measurement data yielded estimations with 12 % average relative error, and showed that surface resistance can be estimated relying on data that can be obtained by contactless and remote measurement, without immediate interference with work processes.

Optimal Neuro-Fuzzy model configuration

The paper is aimed to present how Neuro-Fuzzy Systems can be applied for identifying a general system model of a given problem defined by a set of variables. Neuro-Fuzzy Systems are favored in many application fields because they provide fair accuracy and their inner computational model can be interpreted through the fuzzy rules they encapsulate. The proposed input-output search algorithm is able to find optimal system configuration of an arbitrary set of variables. By placing the algorithm on a Neuro-Fuzzy basis the resulted system model became more interpretable through the inner rules of the Neuro-Fuzzy model. This makes the algorithm more interpretable by revealing more information about the inner connections between the variables of a specific problem.