Wyniki wyszukiwania - BazTech

1

Laboratoryjne systemy zarządzania informacją jako użyteczne źródło danych w pozyskiwaniu wiedzy przy użyciu metod eksploracji danych

Chabior M., Tkacz M.

Studia Informatica

|

2011

|

Vol. 32, nr 2B

403-413

PL

Artykuł wskazuje na Laboratoryjne Systemy Zarządzania Informacją (ang. LIMS – Laboratory Information Management System) jako bazodanowe źródło danych możliwych do wykorzystania w procesie pozyskiwania wiedzy przy użyciu metod eksploracji danych. W artykule opisano zasady funkcjonowania LIMS, kierunki ich rozwoju oraz oczekiwania stawiane tym systemom na dzień dzisiejszy, ze strony laboratoriów badawczych. Na przykładzie systemu Sample-based Laboratory Information Management System (SLIMS) pokazano, że przy użyciu aplikacji pośredniczącej można pobrać określone dane zgromadzone w bazie systemu LIMS i wykorzystać je w celu eksploracji danych przy użyciu jednej z metod Data Mining. Opisano ponadto sposób pozyskiwania wybranych danych z bazy danych systemu laboratoryjnego przy użyciu autorskiej aplikacji, odpytującej przez składnię zapytań języka SQL, i użycie tych danych w metodzie drzew decyzyjnych C4.5. Rozwiązanie opisane w artykule pokazuje możliwość rozszerzenia funkcjonalności LIMS o zakres pozyskiwania wiedzy z danych.

EN

The article describes Laboratory Information Management Systems (LIMS) as a useful source of data to obtain new knowledge by using data mining techniques. Based on the example, article shows that using a simple application user can retrieve data from the LIMS database and use them to explore the data using data mining methods. The article describes also the use of a particular group of data stored in the Genapha SLIMS system to construct a decision tree using the algorithm C4.5. The solution described in the article, shows the possibility to extend the functionality of the LIMS through knowledge discovery from data.

2

Usage of naive Bayes classifier in decision module of e-learning decision support system

Chabior M., Noga A., Tkacz M.

Bio-Algorithms and Med-Systems

|

2009

|

Vol. 5, no. 10

31--34

EN

This article describes adopted, within the scope of one of e-leaming system creation, a method of diagnosis generation based on defined symptoms with the use of the Bayes naive algorithm. It is intended for Medical Faculties students, inference module shall facilitate determination of probability of the influence of individual symptoms on diagnosis. Practical application of such approach presented in the article gives the possibility of distant verification of student's knowledge taking into account not only diagnosis, but also will facilitate gaining skills of appearance materiality determination of symptoms in relation to diagnosed affection. For the testing purposes of adopted assumptions the hundred element database has been applied depending on spine affection in discopathy form and factors, which can affect the origin of the affection - obesity and hard physical work. The operation of the Bayes algorithm has been presented within the scope of influence evaluation of enumerated factors on affection origin.

3

Interactive knowledge base for expert system

Noga A., Chabior M., Sapota G.

Bio-Algorithms and Med-Systems

|

2009

|

Vol. 5, no. 10

39--43

EN

In this article the project of interactive knowledge enabling the record of disease symptoms is presented by doctors to prepare learning set for expert system based on self-organizing networks. Knowledge base will enable the formulation of a diagnosis of disease changes caused by a discopathy and degenerative changes of the backbone. The SpineMedical system can be also used for education purposes for doctor and Medicine faculty students. It enables to complete database by doctors who formulate a diagnosis while examining patients. The SpineMedical system was equipped with the possibility of faulty records' filtering. In the article results of expert system operation which diagnoses patient morbidity was presented.

4

Warunki kapieliskowe w Kołobrzegu

Girjatowicz J.P., Korpalska-Chabior G., Chabior M.

Zeszyty Naukowe. Marine Sciences / Uniwersytet Szczeciński

|

1999

|

Nr 5

25-48

EN

The paper presents an attempt to determine the duration of the bathing season for the Baltic Sea at the coast of Kołobrzeg, based on data records collected within 1961-1990 by Institute of Meteorology and Water Management. The following six conditions were applied to determine the bathing conditions: water temperature (tw >15 °C) at 12 GMT, daily sunshine (U >4 hours), maximal daily (12-13 GMT ) solar radiation intensity (r), air temperature (t), wind speed (v) and relative humidity (f) at 12 GMT. Solar conditions were described using an index S >17. Correction coefficients of the index S were computed statistically. Thermal air conditions were determined in complex way by using effective temperature (TE > 12 °C). For each bathing day, which satisfied the conditions presented above, complex indexes: K and KE (arithmetical means of TE, tw and S) were computed. For particular days from May, 1 to October, 31 within 30-years, probability of favourable bathing conditions occurrence with the division into three degrees of intensity (favourableness) was calculated. Assuming probability of favourable bathing days occurrence at least at 50 % level, the duration of the bathing season in Kołobrzeg was determined. According to K (which does not take into account the colding influence of wind and air humidity) the bathing season lasts from June, 25 to September, 5. But according to KE the bathing season would limit only just to the period from July, 29 to August, 12. No distinct trends of many years' changes of bathing conditions were found. However the 7-8 years periodicity of these conditions, especially of K coefficient, is recorded.

5

Związek parametrów lodowych Zatoki Pomorskiej z typami cyrkulacji atmosferycznej

Girjatowicz J.P., Chabior M.

Przegląd Geofizyczny

|

1999

|

Z. 1-2

61-71

EN

In the present paper there was applied a catalogue of circulations types according to J. Lityński as well as data concerning ice conditions, like the number of days with ice (L), length of ice season (S) and maximum thickness of ice (H) for Świnoujście-sea and Kołobrzeg-sea for winters within 1950/51 - 1989/90. For one month's and several months winter periods the selected circulation types were correlated to the accepted parameters of ice conditions. Equations of linear regression as well as polynomial of the second degree were applied. The statistical significance of relationships was determined with the aid of Fisher-Snedecor's (F) significance test. There was found, that on the number of days with ice (L), length of ice season (S) and maximum height of ice (H) affect mostly the anticyclonic and zero circulation types of eastern component (NE a,o + E a,o), as well as cyclonic and zero circulation types of western component (SW c,o + W c,o + NW c,o). The highest values of correlation coefficient for these directions were obtained in the period from December to February, while relatively high also for December only, what points some prognostic value. For earlier months, in principle, no significant relationships were found. More significant relationship occurred in the of Świnoujście when compared to Kołobrzeg, the highest for maximum thickness of ice (H) and the number of days with ice (L).

6

Warunki kąpieliskowe w Kołobrzegu

Girjatowicz J.P., Korpalska-Chabior G., Chabior M.

Zeszyty Naukowe. Marine Sciences / Uniwersytet Szczeciński

|

1998

|

Nr 5

25-48

EN

The paper presents an attempt to determine the duration of the bathing season for the Baltic Sea at the coast of Kołobrzeg, based on data records collected within 1961-1990 by Institute of Meteorology and Water Management. The following six conditions were applied to determine the bathing conditions: water temperature (tw > 150C) at 12 GMT, daily sunshine (U>4 hours), maximal daily (12-13 GMT) solar radiation intensity (r), air temperature (t), wind speed (v) and relative humidity (f) at 12 GMT. Solar conditions were described using an index S.>17. Correction coefficients of the index S were computed statistically. Thermal air conditions were determined in complex way by using effective temperature (TE.120C). For each bathing day, which satisfied the conditions presented above, complex indexes: K and KE (arythmetical means of TE, tw and S) were computed. For particular days from May, 1 to October, 31 within 30-years, probability of favourable bathing conditions occurence with the division into three degrees of intensity (favourableness) was calculated. Assuming probability of favourable bathing days occurence at least at 50% level, the duration of the bathing season in Kołobrzeg was determined. According to K (which does not take into account the colding influence of wind and air humidity) the bathing season lasts from June, 25 to September, 5. But according to KE the bathing season would limit only just to the period from July, 29 to August, 12. No distinct trends of many years' changes of bathing conditions were found. However the 7-8 years periodicity of these conditions, especially of K coefficient, is recorded.