Wyniki wyszukiwania - BazTech

1

The body balance measures for neurological disease estimation and classification

Chandzlik S., Piecha J.

Journal of Medical Informatics & Technologies

|

2003

|

Vol. 6

IT87--94

EN

The paper describes body balance characteristics needed for neurological diseases classification and for rehabilitation processes controlling during patient recovery processes. These diagnosis factors allow simplify the PSW (Parotec System for Windows) records recognition [1, 2] then a walk-motor disturbances level estimation. The discussed clinical experiments illustrate new methods for Parkinson disease and stroke progress monitoring. This study was based on many observations of patient walk disturbances recorded in PSW files describing the pressure distribution on an insole set of sensors [1, 2, 8]. The gait regular asymmetry in a data spectrum has been noticed as an independent factor from the disease duration and its severity. In majority of analysed cases for Parkinson disease a gravity centre of the body moved into a heel region. Trajectories of foot gravity centre elongation, their irregularities, a floor-contact time and paresis limb loading values increase also were observed. The PSW system has successfully been used for recognition and quantification of walk-motor disturbances, marking the neurological diseases level. Options available in PSW [1, 2] give the user many aims in putting proper diagnosis anyhow, due to simplify the training process of conclusion making unit several methods for data records modifications and the diagnosis factors extraction were also considered.

2

The fault analysis made by PSW data recorder for neurological disease classification

Kopicera K., Piecha J.

Journal of Medical Informatics & Technologies

|

2002

|

Vol. 4

SN9--13

EN

The paper describes an analysis of measuring errors that are responsible for not satisfactory conclusion quality. The analysis concerns the PSW (Parotec System for Windows) [1] equipment developed for walking abnormality diagnosis. The paper shows the analysis principles that indicate what kind of faults are acceptable, for an adequate disease classification.

3

Modelling the data record of a patient walk by langrange-polynomial method

Chandzlik S., Piecha J.

Journal of Medical Informatics & Technologies

|

2002

|

Vol. 3

MI143--152

EN

Various options available in PSW footprint and walking characteristics measuring equipment [6], [7], give the user many aims in putting diagnosis. A Conclusion-Making Unit (CMU) that has been described in this paper supports the diagnosis automation procedures. Due to simplifying the CMU training process some affords in a field of the input record length reduction have been undertaken. The paper describes an analytical method of the data record description that allows converting discrete data samples into continuous function. This way a redigitalisation of the record can be done, where sampling period is matched with the walk length. This normalization allows reducing the data record length used for fast training of the CMU.

4

A patient walk-data-record modelling using a spline interpolation method

Chandzlik S., Piecha J.

Journal of Medical Informatics & Technologies

|

2002

|

Vol. 3

MI153--159

EN

The paper describes an analytical method of data record description that allows converting samples of discrete data record into continuous function. This operation allows re-sampling the data record with a sampling rate that is adequate to step duration. The record length is limited to an efficient size for training the Conclusion-Making Unit (CMU). Various options available in the PSW equipment [6], [7] give the user many aims in putting diagnosis anyhow, due to simplification of the CMU training process several methods for data records modifications are considered.

5

Fuzzy logic implementation for a foot pathology recognition

Zyguła J.

Journal of Medical Informatics & Technologies

|

2000

|

Vol. 1

CS 57--63

EN

The paper presents the data base structure where fuzzy logic defines the threshold of the foot abnormality. The conclusion making unit supports Parotec System for Windows (PSW) [1], the diagnostic equipment that allows to discus the diseases factors observed on a patient’s static and dynamic footprint. The fuzzy logic roles are used for pathological features selection. They classify the data records putting them into the most relevant pathology. The presented system allows to enter roles describing the disease instead of giving a strict definition. When number of roles grows the fuzzy threshold is getting the strict value. The early results of the system development are described in the paper. The conclusion making unit has been evaluated by several records. For full evaluation of the system more experiments are planed to be done in clinics.

PL

Praca prezentuje system wspomagania diagnozy wykorzystujący regułową bazę wiedzy z pojęciami rozmytymi. System nie rozpoznaje schorzeń, lecz podpowiada patologie związane z nieprawidłowym (nie fizjologicznym) obciążeniem wybranych stref stopy w statyce i dynamice. Informacją potrzebną do prawidłowego funkcjonowania systemu jest zbiór pomiarów pozyskanych przy użyciu narzędzia Parotec System for Windows (PSW). Drugim elementem wykorzystywanym w procesie wnioskowania jest baza wiedzy z regułami rozmytymi ekstrahowana od lekarza – eksperta. Wiedza zapisywana jest w formie koniunkcji warunków pierwotnych opartych na relacji wartości funkcji filtracji do lingwistycznego pojęcia względnego – oddającego wartość wybranego czynnika do odpowiedniej wartości dla całej populacji zebranej w bazie pomiarów. W dynamicznym procesie wnioskowania udostępniono trzy metody wyznaczania term (trójkąty o równych i nierównych podstawach) obejmujących całą dziedzinę pomiarów, oraz odrzucenie pomiarów obarczonych błędem przypadkowym wykraczających poza odchylenie standardowe wyznaczone funkcją Gaussa. Prezentowany system udostępnia możliwość wprowadzania reguł w sposób opisowy bez konieczności dokładnej analizy wartości wielkości mierzonych przez PSW. W procesie defuzyfikacji wyznaczona jest ostra wartość wynikła z superpozycji wartości warunków pierwotnych składających się na regułę wnioskowania lecz końcowym rezultatem diagnozy jest pojęcie rozmyte opisujące „natężenie” występującej patologii.

6

Experiments with neural networks. Structure and training process selection

Piecha J.

Journal of Medical Informatics & Technologies

|

2000

|

Vol. 1

CS 21--29

EN

The paper presents software units developed for visualisation and the automatic conclusion within feet abnormalities. These diagnostic interfaces provide the user with various tools for the disease analysis. They are having a pressure and load distribution on the feet, while taking into account the individual characteristics of the patient standing and walking [1],[2],[3]. A big number of options gives the user many aims in putting the diagnosis. The conclusion making system design methodology, described in this paper, shows how to avoid difficulties with a neural network structure and training methods selection, especially when limited number of data records is available. The experiments with the neural networks proved assumption that an artificial data record can be used for the network selection and for the neural network training. The artificial records are examined by filtering tools that have been developed as well.