Skip to main content

Proceedings

9762 papers found

O. Postolache, J. M. Dias Pereira, P. Girão, H. G. Ramos

WATER QUALITY DATA PROCESSING USING FUZZY NEURAL NETWORKS AND KOHONEN SELF ORGANIZING MAPS

This paper is about different techniques for intelligent processing of data obtained with water quality monitoring distributed systems. The techniques include a set of fuzzy neural networks (FuNNs) for modelling measuring channels and Kohonen Self Organizing Maps (K-SOMs) for information classification. Elements of FuNN and K-SOM optimization in terms of architecture and training are presented and briefly discussed.

TC7 Symposium 2004 · TC7 · 2004 · Download
Boris Ya. Lihtsinder, Lyudmila B. Ivanova

ESTIMATION OF KNOWLEDGE QUALITY ON A BASIS OF PROBABILITY MONITORING AND DIAGNOSING METHODS

At present, the regular validation of the personnel is being practiced by various enterprises. It’s made to determine the level of competency of the staff as well as their professional correspondence. At once automated methods of students’ knowledge control are rapidly integrated in different educational institutions. The knowledge control is a process taken up to determine the knowledge degree. The state of probationers, which shows their knowledge value, corresponds each level. These levels are discreted. This way the check out may be viewed as the process of diagnosing and the states...

TC7 Symposium 2004 · TC7 · 2004 · Download
Andrea Zanobini, Gaetano Iuculano

THE MEASUREMENT OF COLOR IN A QUALITY CONTROL SYSTEM: TEXTILE COLOR MATCHING

In this paper we propose a criterion for uncertainty evaluation in a color quality control. In a joint project between two laboratories of the Faculty of Engineering in Florence we study a PC-CCD system, called Textile Color Match (TCM) for the digital acquisition of the colorimetric coordinates of a wool sample. One of the main result is the achievement of a threshold of tolerance for the reproduction of this colored sample.

TC7 Symposium 2004 · TC7 · 2004 · Download
Vera Artemenko, Polina Martyusheva, Sergey V. Muravyov, Nadezhda Znamenschikova

METHODS OF RATING COMPETITORS FOR QUALITY AWARDS: TENTATIVE COMPARATIVE ANALYSIS

A comparison of three most frequently used methods for quality estimation of complex objects is offered in the paper, namely Overall Integral Index, Analytical Hierarchy Process and Consensus Relation. Such estimation is required, for example, in the European Excellence Model by the European Foundation for Quality Management (EFQM) when making decision on the European Quality Award. Examples of using the estimation methods of five enterprises are given taking into account the Model criteria. Certain advantages of the Consensus Relation method are demonstrated.

TC7 Symposium 2004 · TC7 · 2004 · Download
Boris Ivanov, Vladislav Pavlov, Heinrich Ruser

DISTRIBUTED IR SENSOR ARRAY FOR OBJECT CLASSIFICATION

This paper addresses the problem of recognition and identification of objects with an IR diode array, working on a reflection light scanner principle. Essentially two arrays comprising of 3 emitter-receiver pairs are mounted on two sides of the area of inspection, enabling the estimation of the size of the object in different dimensions and reducing the requirements with regard to the detection range. The sensors are driven successively in time, hence no signal overlapping and cross-talk occur. For the recognition, a neural network approach based on the Backpropagation algorithm has chosen....

TC7 Symposium 2004 · TC7 · 2004 · Download
Thomas Allevard, Eric Benoit, Laurent Foulloy

SIGNAL PROCESSING ON FUZZY NOMINAL SCALES

This paper presents some characteristics of fuzzy nominal scales, more specifically the existence of a distance operator on such scales. How this operator can be used for the processing of linguistic signals is presented. Numerical data provided by a data glove are transformed into linguistic data with fuzzy nominal scales. These linguistic data are then processed to recognize dynamic hand gestures.

TC7 Symposium 2004 · TC7 · 2004 · Download
Makoto Ohki, Kousuke Miyake, Masaaki Ohkita

OPTICAL-FLOW ESTIMATION USING SIMPLE GENETIC ALGORITHM FOR ENVIRONMENTAL MAP GENERATING SYSTEM

A technique to automatically configure an environment map using image processing is proposed in this paper. An autonomous mobile robot, which we are developing travels in indoor environment while referring to the environment map. This technique does not need a great cost in a measurement and can support a change of more indoor environment. Taking the indoor environment by a moving CCD camera, a continuation image is acquired. For each frame image of the continuation image, optical-flow estimation is computed. Straight line elements are extracted from an individual frame image. The straight...

TC7 Symposium 2004 · TC7 · 2004 · Download
Tsunehiko Nakanishi, Kozo Taguchi

AN IMAGE PROCESSING MEASUREMENT ON SPATIAL FREQUENCY DOMAIN

A measurement system of vehicle speed us-ing video camera and its brightness analysis is proposed on this paper. The blur is paid attention above all. Since a blur on an image can be measured by the frequency analysis, the possibility to measure speed of a moving object by using a blur image is considered. However because of partial brightness noise, the object length components are included other than the blur component in the information of moving speed, the some filters are introduced on the brightness domain and frequency domain to eliminate unnecessary components. It was possible to...

TC7 Symposium 2004 · TC7 · 2004 · Download
Andreas Meixner, Andreas Purde, Philipp Kirilenko

APPLYING SPECKLE-INTERFEROMETRY TO THE SHAPE MEASUREMENT OF MOVING OBJECTS

Speckle-interferometry is a very interesting group of measurement methods based on coherent light dissipation properties. There are a lot of applications of this effect, but the most interesting one is shape-measurement. It is astonishing that a nearly random structure of speckle image can contain information about the contour of the object illuminated by coherent light. The method is well-known but it is not so popular because of great disadvantage: method needs very good stability of the measurement object and instrument. So this technique was applied only in laboratory for a long time. In...

TC7 Symposium 2004 · TC7 · 2004 · Download
Manus Henry, Mihaela Duta

ADVANCES IN SELF-VALIDATING INSTRUMENTATION

This paper provides an overview into recent developments in self-validating sensors. This concept assumes the availability of internal computing power for self-diagnostics, and of digital communications to convey measurement and diagnostic data. A generic set of metrics are proposed for describing measurement quality, including on-line uncertainty. A SEVA instrument, based on the Coriolis mass flow meter is described; its ability to detect and compensate for the effects of two-phase flow has been implemented in a commercial meter. SEVA has been incorporated into a British Standard, which is...

TC7 Symposium 2004 · TC7 · 2004 · Download