DEDICATED 3D GEOMETRICAL MODELS FOR REPRESENTING ANATOMICAL STRUCTURES Jean SEQUEIRA pp. IP 3-12 Abstract...
The representation of anatomical structures requires to take into account their topological features such as their morphological ones. Differential geometrical properties also have to be managed through the associated 3D models. Unfortunately, classical geometrical modeling approaches do not provide these possibilities. In this paper, we describe two original approaches that bring a solution to this problem for the representation of tree-like cavities - such as vascular ones - and complex organs - such as the heart. Medical applications were given as an illustration of the use of two new approaches discussed bellow. |
 |
 |
MODELS OF COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS Witold PEDRYCZ pp. IP 13-23 Abstract...
Computational Intelligence has emerged as a synergistic environment of Granular Computing (including fuzzy sets, rough sets, interval analysis), neural networks and evolutionary optimisation. This symbiotic framework addresses the needs of system modelling with regard to its transparency, accuracy and user friendliness. This becomes of paramount interest in various modelling in bioinformatics especially when we are concerned with decision-making processes. The objective of this study is to elaborate on the two essential features of CI that is Granular Computing and the resulting aspects of logic-oriented processing and its transparency. As the name stipulates, Granular Computing is concerned with processing carried out at a level of coherent conceptual entities - information granules. Such granules are viewed as inherently conceptual entities formed at some level of abstraction whose processing is rooted in the language of logic (especially, many valued or fuzzy logic). The logic facet of processing is cast in the realm of fuzzy logic and fuzzy sets that construct a consistent processing background necessary for operating on information granules. Several main categories of logic processing units (logic neurons) are discussed that support aggregative (and-like and or-like operators) and referential logic mechanisms (dominance, inclusion, and matching). We show how the logic neurons contribute to high functional transparency of granular processing, help capture prior domain knowledge and give rise to a diversity of the resulting models. |
 |
 |
ACOUSTIC ENVIRONMENT ANALYSERS AS TOOLS FOR DEAF PERSONS HELPING Juliusz Lech KULIKOWSKI pp. MI 3-12 Abstract...
The paper presents a concept of acoustic field analyser as a tool for helping deaf people, able to perceive visual and/or tactile signals only. The acoustic field is considered as a sum of acoustic waves carrying information about events occurring in a monitored physical space. Recognition of acoustic signals together with identification of their sources give a possibility to recognise events of vital importance to a deaf person. There are presented here general problems of acoustic environment analysers" design, particular attention being paid to acoustic sources localisation in physical space. |
 |
 |
VACCINATION PROGRAMS AGAINST MUMPS IN THE UNITED KINGDOM David GREENHALGH, Nikolaos SFIKAS pp. MI 13-22 Abstract...
This paper deals with minimum elimination vaccination programs for mumps in the UK. A partial differential equation compartmental model is used to describe the spread of the disease. Pre-vaccination age-structured serological data is used to estimate the force of infection in the absence of immunization. Homogeneous, proportional and symmetric mixing are considered. Using the equilibrium equations, for each mixing assumption estimates of the basic reproduction number R0 and the minimum elimination immunization proportions for single age and two age vaccination programs are presented. |
 |
 |
RECOGNITION OF PATHOLOGICAL STATES IN ARTERIAL BLOOD BY DISTANCE BASED TECHNIQUES Beata SOKOŁOWSKA, Adam JÓŹWIK pp. MI 23-30 Abstract...
The paper presents the application of some distance based pattern recognition algorithms for recognition of pathological states in respiratory system on the basis of the arterial blood gasometry (features pH, pCO2, pO2). In our biological model two experimental situations were considered: 1) the intact animals and 2) the main inspiratory muscles paralyzed (after acute of bilateral phrenicotomy). The comparison of the mentioned three features in the two conditions was the main goal of the present study. The analyzed biological data set contained 38 in class 1 (muscle function preserved) and 36 in class 2 (after diaphragm paralyzed) measurements. It was discovered that a significant part of the measurements could be correctly recognized as the ones coming from the first or the second class according to gasometric measurements. |
 |
 |
COLOUR VIDEO FILTERING BASED ON VECTOR ORDER-STATISTICS Rastislav LUKAC, Bogdan SMOLKA, Robert BIEDA, Sebastian BUDZAN pp. MI 31-38 Abstract...
The paper introduces a multichannel filtering approach for colour video denoising taking advantage of an order-statistic theory for vector-valued image signals. The proposed adaptive vector filter utilizes switching between an identity operation and a directional distance smoothing function based on the trimmed set of lowest ranked multichannel samples. Because the proposed method uses the same ordering scheme as the standard vector filters, the computational complexity of the new method is computationally attractive. Moreover, the method outperforms the standard vector filters especially in terms of signal-detail preservation. In this paper, we analyse a three-dimensional filter structure based on a cube filter window spawning 27 samples of three following frames. Thus, the proposed algorithm can be applied for the filtering of spatio-temporal or time-varying vector-valued image signals such as colour image sequences or colour video. |
 |
 |
SWITCHING MEDIAN FILTER WITH A LOCAL ENTROPY CONTROL Rastislav LUKAC, Bogdan SMOLKA, Robert BIEDA, Sebastian BUDZAN pp. MI 39-46 Abstract...
This paper presents a new switching median filter utilising local contrast entropy of the samples inside the filtering window. The proposed method is fully adaptive, it requires no optimisation and eliminates the main disadvantages of the local contrast probability based switching median. Excellent performance of the proposed method is a result of the successful analysis of input samples, as the local contrast entropy concept is able to efficiently differentiate between outliers and desired edge samples. |
 |
 |
AUTOMATIC HUMAN FACE RECOGNITION METHOD BASED ON GEOMETRICAL FACE FEATURES Magdalena MAKIEŁA, Wiesław KOTARSKI, Agnieszka LISOWSKA pp. MI 47-56 Abstract...
There are many ways to describe and recognize the human face. The paper shows one of them - the feature based method. It also considers usefulness of the face geometrical measurements in recognition and also the geometrical dependence on the features. The paper treats on the feature points detection and takes into consideration six of them, which are: two eyes, two eyebrows, nose and lips. It shows a detailed algorithm of the proposed method and describes its advantages and disadvantages. It also describes a filtering, feature points extraction and gives formulas for calculation of a face likeness coordinates. At the very end it concludes with experiments and examples of the proposed method. |
 |
 |
FUNDUS IMAGING - A PROPOSAL OF AN EXTENDED APPLICATION TOOL SUPPORTING MEDICAL DIAGNOSING Maria BERNDT-SCHREIBER, Dariusz SZCZEPANIAK pp. MI 57-60 Abstract...
Digital fundus eye images may reveal essential features being important for the diagnoses of many pathologies once they are correlated with other specific medical data. A proposal of a comprehensive application referring both to the images and various additional medical data has been briefly described and discussed. |
 |
 |
FOURIER ANALYSIS IN CLASSIFICATION OF BLOOD CELLS Krzysztof KOCJAN, Wiesław KOTARSKI pp. MI 61-66 Abstract...
In the paper we present some results concerning the usage of Fourier analysis which we can successfully apply to distinguish between normal and pathological blood cells. We use special area function and different number of Fourier descriptors that are automatically calculated for all objects pointed out in an image. Calculations are performed with the help of the software made by the first author. Experiments performed on the same set of tested images as in [3] and [5] draw as to the same conclusions as there in [3] where the fractal analysis to shape has been used and in [5] where simple geometrical shape parameters have been applied. Other application of Fourier analysis one can find in [9]. |
 |
 |
PREDICTION OF INFECTIOUS DISEASES:AN EXCEPTION REPORTING SYSTEM Gavin MCCABE, David GREENHALGH, George GETTINBY, Eileen HOLMES, John COWDEN pp. MI 67-74 Abstract...
In this paper prediction methods are discussed in the context of developing an exception reporting system for laboratory reports. The detection of outbreaks and longer term trends is briefly addressed, before a consideration of data types and availability to be used in evaluating the prediction methods. Four general prediction methods are outlined and the selection of data to which they are applied is examined. Both real and simulated data are used to evaluate the prediction methods and a strategy for an exception reporting system is proposed. |
 |
 |
FUZZY C-REGRESSION MODELS IN BACTERIAL POPULATION DYNAMICS MODELLING Aleksander OWCZAREK Michał MOMOT, Ewelina SOBIERSKA pp. MI 75-82 Abstract...
The paper describes application of the fuzzy c-regression models algorithm in bacterial population dynamics modelling. Such a well-known algorithm, which provides simultaneous estimates of the parameters of c-regression models, together with a fuzzy partitioning of data, was used to determine bacterial growth curve given by the piecewise continuous function. The real as well as artificial data were used and promising results were obtained even for data with significant errors resulting from the measurement inaccuracy. |
 |
 |
DATA STREAM PROCESSING IN FETAL MONITORING SYSTEM: I. ALGEBRA AND QUERY LANGUAGE Michał WIDERA, Janusz JEŻEWSKI, Ryszard WINIARCZYK, Janusz WRÓBEL, Krzysztof HOROBA, Adam GACEK pp. MI 83-90 Abstract...
The paper presents the algebra and declarative query language developed for fetal monitoring system MONAKO. At present, the system architecture is centralised. Recording, analyzing and visualization of data are carrying out in the central unit. Therefore, the system cannot scale in a simple manner. Presented solution enables to define query based on data streams that makes the updated answers currently available. Applying database management system that carries out its tasks based on presented assumptions enables the construction of monitoring system of distributed architecture. |
 |
 |
THE SLOW ADOPTION OF MEDICAL INFORMATICS IN HOSPITALS Victor LANE, Daniel LANE pp. MI 91-100 Abstract...
This paper examines the use of computing in hospitals and compares this with the use of computing in general practice. In the UK, virtually all GPs, i.e. doctors in primary care, use computers and computer-based records in their care of patients, whereas most doctors in hospitals do not [3, 25]. There are many reasons given for the lower use of computers in hospitals. It has been suggested that hospital medical activities are more complex than those in general practice and that there has been too little investment in hospital information and communication technology (ICT), two truisms. This paper examines and compares the different and contrasting theories that attempt to explain this phenomenum. The paper has relevance to (1) researchers wishing to migrate successful research from a "research laboratory environment" such as in a medical school to a real-world setting in a hospital or a hospital clinic, (2) medical informatics researchers interested in investigating the problems of ICT implementations in hospitals, and (3) medical informatics practitioners involved in real-world hospital ICT developments. |
 |
 |
THE IN-TOWN MONITORING SYSTEM FOR AMBULANCE DISPATCH CENTRE Bartłomiej PŁACZEK, Jolanta GOŁOSZ pp. MI 101-106 Abstract...
The paper presents the vehicles integrated monitoring system giving priorities for emergency vehicles. The described system exploits the data gathered by: geographical positioning systems and geographical information systems. The digital maps and roadside cameras provide the dispatchers with aims for in town ambulances traffic management. The method of vehicles positioning in the city network and algorithms for ambulances recognition by image processing techniques have been discussed in the paper. These priorities are needed for an efficient life-saving actions that require the real-time controlling strategies. |
 |
 |
CASE OF FUZZY LOSS FUNCTION IN MULTISTAGE RECOGNITION ALGORITHM Robert BURDUK pp. MI 107-112 Abstract...
The work deals with a recognition problem using a probabilistic-fuzzy model and multistage decision logic. A case where a loss function is described using fuzzy numbers has been considered. The globally optimal Bayes strategy has been calculated for this case with stage-dependent and dependent on the node of the decision tree fuzzy loss function. The obtained result is illustrated by a calculation example in which some methods for ranking fuzzy numbers were used. |
 |
 |
PROPOSITION OF SUBJECTIVE QUALITY MEASURE FOR EXERT RULES Michał WOŹNIAK pp. MI 113-118 Abstract...
Paper deals with the knowledge acquisition process. Different experts formulate the rules for decision support systems. We assume they have different knowledge about the problem and therefore obtained rules have different qualities. We will formulate the proposition of the confidence measure and its application to the decision process. We will propose how calculate the value of measure under consideration for typical statistical learning process. On the base on the proposed measure of the knowledge quality we propose the procedure of the contradictions elimination for the set of logical rules. |
 |
 |
DIAGNOSIS SUPPORT METHOD OF PLETYSMOGRAPHICAL RECORDS WITH THE USE OF FRAMEWORK TENETS Marek PENHAKER pp. MI 119-126 Abstract...
The aim of this study is the processing and evaluating of plethysmographical records giving important information about the blood vessel function. Result of this study is to present the methodology for classifying the records by means of mathematical methods that would contribute to systematic evaluation of what has been found by finger plethysmography. Thereafter the experimental expert system based on framework systems serves to determine the diagnosis on the basis of previous mathematical processing is introduced. The goal of the project was also creation of application by the form of the extension of kernel for the use of framework that is determined for support of control and information systems development in the area of signal processing, elaborate and describe the methodology of extension hereof setting in the nature of specific applications. Beyond above-mentioned outputs the solution of the project should give the specific knowledge about the usage effectiveness of evolutional frameworks. Fundamental implementation idea is based on the usage of MATLAB as the basis for extension of common kernel. |
 |
 |
ADVANCED INTERFACES FOR REMOTE USERS OF NETWORK MULTIMEDIA DATABASES Jan PIECHA, Iwona KOSTORZ, Paweł PAWEŁCZYK pp. MI 127-134 Abstract...
The multimedia databases organisation and management needs various standardisation for simplifying their structure and access methods. They allow integrating different levels and different techniques of programming. The paper describes several aspects of Medical Centre Services organisation that offers various services via Internet standards. Several multimedia systems for training processes have been implemented in this package for network information content development and distribution. |
 |
 |
APPLICATION OF WEB SERVICES ARCHITECTURE TO INFORMATION SYSTEM FOR COORDINATION OF KIDNEY TRANSPLANTATION Wiktor Wandachowicz, Zbigniew Filutowicz pp. MI 135-144 Abstract...
Cooperation Supporting System (CSS) is a project with one goal of prevailing importance: to improve information exchange between all participants of the kidney transplantation process. The project designed for the Regional Dialysis and Transplantation Centre in N. Copernicus Hospital in ?ód? is carried on by the Artificial Intelligence and Software Engineering team of Institute of Computer Science. Since kidney transplantation engages many institutions, quick and effective flow of information plays a key role in the whole process. Given the current state of the system and the new concepts of its development, we decided to restructure the communication layer of the system. The present paper discusses how this change influences the overall system design, capabilities of the system, possibilities of future enhancements as well as possible integration with other information systems. To this purpose, the Web Services standard is presented and a brief overview of the evolution of distributed computing technologies is also given. |
 |
 |
SPECIALISED LINUX SOFTWARE AIDING WORK OF BLIND PERSONS Piotr PORWIK, Karol BĘDKOWSKI, Łukasz ŻELECHOWSKI, Agnieszka LISOWSKA pp. MI 145-156 Abstract...
For many years Linux environment has been evaluated from the only server system to desktop computer system. Thanks to this Linux has became serious competition for systems from the very popular Microsoft Windows family. Unfortunately sightless users of computer do not have wide choice of software speech synthesisers that may help them during working on computer in the Linux environment. The "Speakup" application is the one of the better ones designed for Linux. But, nevertheless, it does not support the maintenance in the same degree as popular applications for the Microsoft Windows. So in this paper the significant improvement of the "Speakup" is presented. This improvement allows blind users to quite comfortable work with the Linux system in the console text mode with the maintenance of Polish fonts, too. The application has become the user-friendly one with wide spectrum of possibilities, what many blind users confirm. The one of them is the co-author of this paper. |
 |
 |
THE MULTIMEDIA FILES DEVELOPMENT IN FRAMES OF INTERACTIVE FAST EXPLORER Jan PIECHA, Robert KRÓL, Adrian OLSZEWSKI pp. MI 157-166 Abstract...
The multimedia files settings need various standardisations for simplifying the application development then the files content exploration. The application platform has to provide the user with integrating tools for various data objects. The paper describes several aspects of programming techniques implemented in common platform, called Multimedia Applications Management Shell (MAMS) under Quality Repetitions Unit. This platform has been applied for training system development available by the computer workstation in wide area network. |
 |
 |