Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: hybrid neural networks

Sortuj według:

Ogranicz wyniki do:

Wybrane problemy efektywnego rozpoznawania pisma odręcznego

Kacalak W., Majewski M.

Pomiary Automatyka Kontrola

2011

R. 57, nr 5

479-482

W artykule przedstawiono nowatorską metodę efektywnego rozpoznawania pisma odręcznego z zastosowaniem opracowanych sposobów analiz geometrycznych znaków i wybranych metod sztucznej inteligencji. Proponowana metoda analiz geometrycznych znaków oparta na opracowanym sposobie odpowiednich pomiarów odległości wybranych ich punktów pozwala na rozpoznawanie pisma odręcznego niezależnie od stylu i charakteru pisma operatora. W rezultacie zastosowania metody otrzymuje się zakodowaną reprezentację znaku dla efektywnego rozpoznawania przez sztuczne sieci neuronowe. Artykuł również przedstawia system rozpoznawania odręcznego pisma operatora zbudowany z podsystemów wstępnego przetwarzania, analiz geometrycznych, logiki rozmytej, sieci neuronowych oraz ich wyspecjalizowanych modułów. Proponowany inteligentny system może stanowić nowoczesny i efektywny system interakcji urządzeń technicznych i ich operatorów w zadaniach sterowania.

In this paper, an innovative method for effective handwriting recognition is presented. It uses the developed methods of geometrical analyses of isolated handwritten characters and selected artificial intelligence methods. The proposed geometrical feature analysis method, based on the developed manner of appropriate measurements of distances of selected character points, allows handwriting recognition independent of different writing and character styles, and writing conditions. As a result of using the method, encoded representations of characters are obtained for effective recognition by artificial neural networks. The paper also presents an operator's handwriting recognition system consisting of the subsystems of preprocessing, geometrical analyses, fuzzy logic, neural networks, and their specialized modules. Handwriting recognition has always been a challenging problem for artificial intelligence researchers, and remains an open issue. It is because of the complexity of the handwriting recognition task. The intelligent handwriting recognition system of the technical device operator's natural writing can be a modern and effective interaction system [3, 5]. In the paper, a review of selected issues is carried out with regards to the handwriting recognition issues, new geometrical analysis method (fig. 1, 2, 3, 4) and concept of a handwriting recognition system (fig. 5, 6). The proposed system is novel in that it integrates efficient geometrical processing with artificial intelligence methods to use neural networks and fuzzy logic for effective handwriting recogni-tion.

Inteligentny system obustronnej głosowej komunikacjisystemu pomiarowego z operatorem dla technologii mobilnych

Kacalak W., Majewski M.

Pomiary Automatyka Kontrola

2009

R. 55, nr 4

221-224

W artykule przedstawiono nową koncepcję inteligentnych systemów obustronnej głosowej komunikacji urządzeń pomiarowych z operatorem w systemach pomiarowych. Opracowany dla technologii mobilnych, system komunikacji przy pomocy mowy i języka naturalnego pomiędzy urządzeniami pomiarowymi i ich operatorami, wyposażony jest w inteligentne mechanizmy służące do identyfikacji operatora, rozpoznawania słów składowych i całych komunikatów operatora, analizy składni i skutków poleceń, oceny bezpieczeństwa poleceń, nadzorowania procesu pomiarowego oraz oceny reakcji operatora.

In the paper a new concept of the intelligent two-way speech communication system between a measurement device and the operator for measuring systems is presented. Developed for mobile technologies, the communication system by speech and a natural language between measurement devices and their operators consists of intelligent mechanisms for operator identification, speech recognition, word and command recognition, command meaning and effect analysis, command safety assessment, measurement process supervision as well as operator reaction assessment. In the paper there are presented selected problems of the new concept of speech communication in measurement systems (Figs. 1, 2, 3) as well as advantages of recognition and evaluation of speech commands in a natural language with use of hybrid neural networks. Application of hybrid neural networks allows recognising commands of similar meanings but of different lexical and grammatical patterns, which will undoubtedly be the most important way of communication between humans and devices. The condition of the effectiveness of the presented system (Fig. 4) is to equip it with mechanisms of command meaning and effect analysis, as well as safety assessment. In the measurement systems (Fig. 5), the condition of safe communication between operators and measurement devices is the analysis of the measurement device and process state before giving the command and use of artificial intelligence for the effect analysis and safety assessment of the command. The development of a basis for building and applying remote mobile systems of control, supervision and optimisation of measurement processes which communicate an operator with a measurement system is an important goal. These systems enable a remote control of the measurement process quality by an operator being in any distance. It is very significant for development of new effective and flexible methods of measurements. The system for remote control, supervision and optimisation is an innovative solution making it possible to exploit better the measurement methods used nowadays. The presented solution can be included to the attempts of creating the standard of mobile applications for control, supervision and optimisation of measurement processes using two-way speech communication between the measurement device and the operator for measuring systems.