Wyniki wyszukiwania - BazTech

1

Technique Based on Fuzzy Logic for Cotton Bale Lay-down Management

Das S., Ghosh A.

Fibres & Textiles in Eastern Europe

|

2017

|

Vol. 25, no. 2 (122)

30--33

EN

In this paper a new technique has been proposed for cotton bale management using fuzzy logic. The fuzzy c-means clustering algorithm has been applied for clustering cotton bales into 5 categories from 1200 randomly chosen bales of the J-34 variety. In order to cluster bales of different categories, eight fibre properties, viz., the strength, elongation, upper half mean length, length uniformity, short fibre content, micronaire, reflectance and yellowness of each bale have been considered. The fuzzy c-means clustering method is able to handle the haziness that may be present in the boundaries between adjacent classes of cotton bales as compared to the K-means clustering method. This method may be used as a convenient tool for the consistent picking of different bale mixes from any number of bales in a warehouse.

PL

W artykule zaproponowano nową technikę zarządzania składowaniem bawełny opartą na logice rozmytej. Badaniu poddano 1200 losowo wybranych bel bawełny. W celu pogrupowania bel w 5 kategoriach zbadano właściwości, tj. wytrzymałość, wydłużenie, średnią długość, jednorodność długości, zawartość włókien krótkich, dojrzałość, współczynnik odbicia i zażółcenie każdej beli. Opracowana metoda może być stosowana jako wygodne narzędzie do sortowania różnych mieszanek z dowolnej liczby bel w magazynie.

2

Fuzzy classification of medical data derived from diagnostic devices

Byczkowska-Lipińska L., Wosiak A.

Przegląd Elektrotechniczny

|

2016

|

R. 92, nr 12

85--88

EN

The research described in this paper concerns fuzzy classification of medical datasets obtained from diagnostic devices. Experimental studies were performed with use of fuzzy c-means algorithm. It was shown that despite the low accuracy of the results, fuzzy classification reduce the risks associated with the loss of internal relationships in the characteristics of the data, and thus increases the chances of finding the pathological cases, as well as taking preventive actions or therapy.

PL

W ramach niniejszej pracy przeprowadzona została klasyfikacja rozmyta w odniesieniu do medycznych zbiorów danych pozyskanych z urządzeń diagnostycznych. Zastosowana została rozmyta metoda k-średnich. Badania wykazały, że pomimo niskiej dokładności rezultatów, klasyfikacja rozmyta zmniejsza ryzyko związane z utratą wewnętrznych zależności w charakterystyce danych, a tym samym zwiększa szanse na stwierdzenie ryzyka patologii i tym samym szybsze podjęcie działań zapobiegawczych lub terapeutycznych.

3

Multi-step process in computer assisted diagnosis of posterior cruciate ligaments

Zarychta P.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

657--669

EN

A multi-step methodology resulting in a three-dimensional visualization and construction of feature vector of posterior cruciate ligament is presented. In the first step the location of the posterior cruciate ligament is established using the fuzzy image concept. The fuzzy image concept is based on the entropy measure of fuzziness extended to two dimensions. In order to reduce the area of analysis, the region of interest including the ligament structures is detected. In this case, the fuzzy C-means algorithm with median modification helping to reduce blurred edges was implemented. After finding the region of interest, the fuzzy connectedness procedure was performed. This procedure permitted to extract the ligament structures. On the basis of the extracted posterior cruciate ligament structures, the three-dimensional visualization of this ligament was built and, with the support of experts' knowledge, an appropriate feature vector was constructed and its values assigned for normal and pathological cases. Correct results were obtained for over 88% of 97 cases.

4

Optymalizacja struktur neuronowo-rozmytych estymatorów zmiennych stanu układu dwumasowego

Kamiński M., Tran-Van T., Szabat K.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 7

173--176

PL

W niniejszym artykule zaprezentowano zastosowanie modeli neuronowo-rozmytych w odtwarzaniu zmiennych stanu napędu elektrycznego o złożonej części mechanicznej. Istotnym zagadnieniem w procesie projektowania testowanych estymatorów jest optymalizacja ich struktury, w tym celu zastosowano metodę rozmytą K-średnich. Uzyskano wysoką precyzję estymowanych sygnałów (prędkości obciążenia oraz momentu skrętnego) oraz odporność, w badanym zakresie, na zmiany wybranych parametrów napędu, a także w przypadku wprowadzania dodatkowych nieliniowości elementów sprzęgających.

EN

In this paper application of neuro-fuzzy models in state variables estimation of electrical drive with composite mechanical part is presented. Important task in design process is structure optimization, for this purpose fuzzy c-means algorithm is applied. High precision of selected signals estimation (load speed and torsional torque) is obtained. Moreover estimators are robust, in tested range, against parameter changes and introduction of additional nonlinear elements in coupling between motor and load.

5

Cuda Based Fuzzy C-Means Acceleration for the Segmentation of Images with Fungus Grown in Foam Matrices

Rowińska Z., Gocławski J

Image Processing & Communications

|

2012

|

Vol. 17, no. 4

191--200

EN

In the paper authors verify the advantages of GPU computing applied to fuzzy c-means segmentation. Three different algorithms implementing FCM method have been compared by their execution times. All tests refer to the images of polyurethane foam matrices filled with fungus (mould). They are aimed at separating mould regions from the matrix base. The authors proposed a method using CUDA programming tools, which significantly speedsup FCM computations with multiple cores built in a graphic card.

6

Fuzzy image processing : a review and comparison of methods

Tzafestas S., Raptis S.

Image Processing & Communications

|

1999

|

Vol. 5, no 1

3--24

EN

This paper presents a comprehensive review of fuzzy image processing methods. Specifically the following image processing problems are considered: (i) Image comprehension. (ii) image segmentation, (iii) image classification, (iv) image analysis, (v) image filtering, (vi) image understanding. In practice, an image cannot always be interpreted always exactly and perfectly. This is due to the existence of noise or the way the image is obtained, or, finally, to incorrect understanding of the image information content. These difficulties can be faced successfully through fuzzy logic and fuzzy reasoning. The field of image processing via fuzzy logic was initialed after Zadeh's 1965 seminar paper and is still expanding with new important results and applications. This paper is devoted to the treatment of still images, but some of the methods can be extended to the case of moving (video) images. The methods considered are critically discussed. Finally, a comparison of the effectiveness of (i) c-means, (ii) classical c-means, and (iii) adaptive clustering algorithms is made.