Wyniki wyszukiwania - Biblioteka Nauki

1

A dynamic model of classifier competence based on the local fuzzy confusion matrix and the random reference classifier

100%

Trajdos P. , Kurzynski M.

|

tom 26

|

nr 1

175-189

EN

Nowadays, multiclassifier systems (MCSs) are being widely applied in various machine learning problems and in many different domains. Over the last two decades, a variety of ensemble systems have been developed, but there is still room for improvement. This paper focuses on developing competence and interclass cross-competence measures which can be applied as a method for classifiers combination. The cross-competence measure allows an ensemble to harness pieces of information obtained from incompetent classifiers instead of removing them from the ensemble. The cross-competence measure originally determined on the basis of a validation set (static mode) can be further easily updated using additional feedback information on correct/incorrect classification during the recognition process (dynamic mode). The analysis of computational and storage complexity of the proposed method is presented. The performance of the MCS with the proposed cross-competence function was experimentally compared against five reference MCSs and one reference MCS for static and dynamic modes, respectively. Results for the static mode show that the proposed technique is comparable with the reference methods in terms of classification accuracy. For the dynamic mode, the system developed achieves the highest classification accuracy, demonstrating the potential of the MCS for practical applications when feedback information is available.

2

Electronic Learning of Business English

88%

Milošević D.

Romanian Journal of English Studies

|

2014

|

tom 11

|

nr 1

272-278

EN

This paper deals with one approach to organising electronic learning of a Business English language course. The paper will explain the basic structure of electronic learning, explore its principles and focus on the effects of this type of learning, trying to make English language teachers aware of the possibilities that this system has to offer to its users.

3

A dynamic model of classifier competence based on the local fuzzy confusion matrix and the random reference classifier

75%

Trajdos P. , Kurzynski M.

International Journal of Applied Mathematics and Computer Science

|

2016

|

tom Vol. 26, no. 1

175--189

EN

Nowadays, multiclassifier systems (MCSs) are being widely applied in various machine learning problems and in many different domains. Over the last two decades, a variety of ensemble systems have been developed, but there is still room for improvement. This paper focuses on developing competence and interclass cross-competence measures which can be applied as a method for classifiers combination. The cross-competence measure allows an ensemble to harness pieces of information obtained from incompetent classifiers instead of removing them from the ensemble. The cross-competence measure originally determined on the basis of a validation set (static mode) can be further easily updated using additional feedback information on correct/incorrect classification during the recognition process (dynamic mode). The analysis of computational and storage complexity of the proposed method is presented. The performance of the MCS with the proposed cross-competence function was experimentally compared against five reference MCSs and one reference MCS for static and dynamic modes, respectively. Results for the static mode show that the proposed technique is comparable with the reference methods in terms of classification accuracy. For the dynamic mode, the system developed achieves the highest classification accuracy, demonstrating the potential of the MCS for practical applications when feedback information is available.

4

Feedback processing as parallel task in P300 conditioning

75%

Michalski A.

Acta Neurobiologiae Experimentalis

|

1999

|

tom 59

|

nr 2

5

Komunikacja z rodziną pacjenta chorego onkologicznie

63%

Winch B.

Current Gynecologic Oncology

|

2014

|

tom 12

|

nr 2

155-171

EN

Most physicians’ working time is filled communicating with their patients – talking, listening, responding to their needs. The communication is aimed at identifying the patient’s medical, social and psychological circumstances. Understanding all these aspects allows to perceive the patient as a person. Communication is the exchange of information, but also everything that occurs between people communicating at a given moment, including the mutual impressions, the mutual sense of being heard and understood, being on a “similar wavelength,” or emotional distance. We communicate to explain things to one another, to share information, to make a shared decision or arrangement, or to negotiate things. When we think about the messages we convey and the way we convey them, we think about the information the message includes, its sense, the emotions it may evoke, its resonance in the patient’s individual circumstances. On the side of the “sender” i.e. the doctor, the quality of the communication depends on their knowledge of both oncology and psychology facts, the skill of forming a message, the ability to keep the right balance between distance and involvement, and adjusting feedback information. On the side of the “receiver,” i.e. the patient and their family, the communication is affected by the common myths and presumptions surrounding the disease, the knowledge of medical facts, communication skills, message decoding process – the interpretation, evaluation, response and the attitude of the patient towards the disease and its treatment, the emotional inclination of the patient and their family. From the very beginning of the diagnostic process, the patients and their relatives seek information on the disease and available treatment, support resources for the patient, emotional help and support for the family.

PL

Czas pracy większości lekarz wypełnia komunikacja z pacjentem – mówienie, słuchanie, reagowanie na jego potrzeby. Celem komunikacji jest zidentyfikowanie medycznego, społecznego i psychologicznego otoczenia pacjenta. Zrozumienie tych wszystkich aspektów pozwala na postrzeganie pacjenta jako osoby. Komunikacja to przekazywanie informacji, ale także wszystko to, co dzieje się między osobami porozumiewającymi się w danym momencie, a zatem również ich wrażenia na swój temat, poczucie wzajemnego słyszenia się i rozumienia, współgranie lub dystans emocjonalny. Komunikujemy się, by sobie coś wyjaśnić, by się o czymś poinformować, by coś ustalić lub wynegocjować. Gdy zastanawiamy się nad tym, co i jak przekazujemy, to zastanawiamy się nad: informacją, jaką zawiera przekaz, jej znaczeniem, emocjami, jakie może wywołać, jej umieszczeniem w kontekście życiowym pacjenta. Od strony „nadawcy” – lekarza – jakość komunikacji zależy od: znajomości zagadnień onkologicznych i psychologicznych, umiejętności tworzenia przekazu, umiejętności utrzymania granicy pomiędzy dystansem a zaangażowaniem, adaptacji informacji zwrotnej. Od strony „odbiorcy” – pacjenta i jego rodziny – na komunikację wpływają: mity i wyobrażenia związane z chorobą i leczeniem, znajomość zagadnień medycznych, sprawność komunikacyjna, dekodowanie komunikatu – interpretacja, ocena, reakcja, postawy pacjenta wobec chorowania i leczenia, nastawienie emocjonalne pacjenta i rodziny. Od początku procesu diagnozowania pacjenci i rodziny poszukują: informacji o chorobie i leczeniu, umiejętności wspierania chorego, wsparcia emocjonalnego dla siebie.

6

Potencjał oraz zastosowanie komputerowej analizy i przetwarzania obrazu w przemyśle rolno-spożywczym

63%

Guzek D. , Głąbska D. , Wierzbicka A.

|

tom R. 15, nr 4

67-73

PL

Celem pracy było określenie potencjału oraz możliwości zastosowania komputerowej analizy i przetwarzania obrazu w przemyśle rolno-spożywczym w Polsce, ze szczególnym uwzględnieniem sektora mięsnego. Zakres pracy obejmował analizę dostępnych danych literaturowych dotyczących zastosowania komputerowej analizy obrazu w przemyśle rolno-spożywczym. Zaprezentowano możliwości zdefiniowania parametrów produktów rolno-spożywczych w celu określenia ich jakości przy zastosowaniu instrumentalnego, szybkiego i pozwalającego na uzyskiwanie powtarzalnych wyników metod wizyjnych.

EN

The purpose of the presented article was to determine the potential and possibilities for employing computer analysis and image processing in the agricultural and food industry in Poland, with particular consideration of meat production sector. The scope of works included analysis of available data from the literature concerning the use of computer image analysis in the agricultural and food industry. It presents possibilities for defining parameters of the agricultural and food products in order to determine their quality using visual methods that would be instrumental, quick and allow to obtain repeatable results.