Wyniki wyszukiwania - BazTech

1

Wykrywanie defektów z wykorzystaniem termografii aktywnej i algorytmu k-średnich

Dudzik Sebastian

Pomiary Automatyka Robotyka

|

2019

|

R. 23, nr 3

11--15

PL

W pracy przedstawiono nową metodę wykrywania defektów materiałowych z wykorzystaniem termografii aktywnej. W celu zwiększenia kontrastu cieplnego dokonano przetwarzania wstępnego zarejestrowanej sekwencji termogramów metodami morfologii matematycznej. Do wykrywania defektów zastosowano algorytm k-średnich. W pracy zbadano wpływ miary odległości używanej w opisywanym algorytmie oraz doboru danych wejściowych na efektywność opisywanej metody. Eksperyment przeprowadzono dla próbki wykonanej z kompozytu zbrojonego włóknem węglowym (CFRP). W badaniach stwierdzono, że najmniejsze błędy wykrywania defektów za pomocą opisywanej metody uzyskuje się dla kwadratowej odległości euklidesowej.

EN

The paper presents a new method of detecting material defects using active thermography. In order to increase the thermal contrast, preprocessing of the recorded sequence of thermograms was carried out using mathematical morphology methods. The k-means algorithm was used to detect defects. The work examined the impact of distance measure used in the described algorithm and the selection of input data on the effectiveness of the described method. The experiment was carried out for a sample made of carbon fiber reinforced composite (CFRP). Studies have shown that the smallest errors in defect detection using the described method are obtained for the square Euclidean distance.

2

Porównanie wydajności algorytmu k-means zaimplementowanego w języku X10 i środowisku C++/MPI

Wyrzykowski R., Karoń T.

Zeszyty Naukowe Warszawskiej Wyższej Szkoły Informatyki

|

2016

|

nr 14

7--35

PL

W pracy opisano algorytm k-średnich oraz sposób jego implementacji w języku X10. Dokonano porównania tego rozwiązania z implementacją w języku C++11 z wykorzystaniem standardu MPI. Stwierdzono, że implementacja w języku X10 jest szybsza przy większej liczbie procesorów realizujących obliczenia niż implementacja w środowisku C++/MPI. Kod zapisany w języku X10 jest o 59% krótszy od kodu dla kombinacji C++/MPI.

EN

In this work the k-means algorithm and the way of its implementation in the X10 programming language are described. The achieved results are compared with the implementation of the same algorithm in the C++11 programming language using the MPI standard. It was confirmed that the implementation in the X10 programming language is faster on a large number of processors than the implementation in the C++/MPI environment. Additionally, the X10 code is about 59% shorter than the code for the C++/MPI combination.

3

Identification of technogenic emergency situations in railway transport using cluster analysis

Savchuk T., Petrishyn S., Sugurova L., Smolarz A.

Przegląd Elektrotechniczny

|

2014

|

R. 90, nr 11

177--184

EN

The antropogenic load on natural environment is continuously growing. One of important issues is the influence of transport of goods, especially when the cargo is hazardous. Railroad transport in Ukraine shares about 60% of all means of transport so identification of potential emergency situations in this area is an important issue. The article discusses some methodology approaches and describes cluster analysis as a tool for Identification of technogenic emergency situations in railway transport.

PL

Antropogeniczne obciążenie środowiska naturalnego stale rośnie. Jedną z istotnych kwestii jest wpływ transportu towarów, zwłaszcza gdy ładunek jest niebezpieczny. Transport kolejowy na Ukrainie ma około 60% udziału wszystkich środków transportu, więc identyfikacja potencjalnych sytuacji awaryjnych w tej dziedzinie jest ważnym zagadnieniem. W artykule przedstawiono wybrane podejścia metodyczne i opisano analizę skupień jako narzędzie do identyfikacji technogennych sytuacji awaryjnych w transporcie kolejowym.

4

Geodesic distances for clustering linked text data

Tekir S., Mansmann F., Keimer D.

Journal of Artificial Intelligence and Soft Computing Research

|

2012

|

Vol. 2, No. 3

247--258

EN

The quality of a clustering not only depends on the chosen algorithm and its parameters, but also on the definition of the similarity of two respective objects in a dataset. Applications such as clustering of web documents is traditionally built either on textual similarity measures or on link information. Due to the incompatibility of these two information spaces, combining these two information sources in one distance measure is a challenging issue. In this paper, we thus propose a geodesic distance function that combines traditional similarity measures with link information. In particular, we test the effectiveness of geodesic distances as similarity measures under the space assumption of spherical geometry in a 0-sphere. Our proposed distance measure is thus a combination of the cosine distance of the term-document matrix and some curvature values in the geodesic distance formula. To estimate these curvature values, we calculate clustering coefficient values for every document from the link graph of the data set and increase their distinctiveness by means of a heuristic as these clustering coefficient values are rough estimates of the curvatures. To evaluate our work, we perform clustering tests with the k-means algorithm on a subset of the EnglishWikipedia hyperlinked data set with both traditional cosine distance and our proposed geodesic distance. Additionally, taking inspiration from the unified view of the performance functions of k-means and k-harmonic means, min and harmonic average of the cosine and geodesic distances are taken in order to construct alternate distance forms. The effectiveness of our approach is measured by computing microprecision values of the clusters based on the provided categorical information of each article.

5

Finding outliers for large medical datasets

Duraj A., Krawczyk A.

Przegląd Elektrotechniczny

|

2010

|

R. 86, nr 12

188-191

EN

The paper deals with data mining which is a process of extracting valid, previous unknown, and ultimately comprehensible information for large datasets. One of very interesting problems appearing in scientific investigations are detection of mistakes in files of data, or the detection outlier. Finding the rare instance or the outliers is important in many disciplines and KDD (Knowledge Discovery and Data-Mining) applications.

PL

Artykuł dotyczy metody wykrywania wyjątków w zbiorach danych dostrzegane jako różnego rodzaju anomalie, powstałe np. z powodu mechanicznego uszkodzenia, zmiany w zachowaniu systemu, czy choćby poprzez naturalny błąd człowieka. Jak się jednak wydaje, powyżej sformułowany problem badawczy jest bardzo istotny i nadal aktualny, szczególnie w przypadku medycznych zbiorów danych. Wykrycie wyjątków może zidentyfikować defekty, usunąć zanieczyszczenia danych a przede wszystkim stanowi podstawę w procesach podejmowania decyzji.

6

Extending k-means with the description comes first approach

Stefanowski J., Weiss D.

Control and Cybernetics

|

2007

|

Vol. 36, no 4

1009-1035

EN

This paper describes a technique for clustering large collections of short and medium length text documents such as press articles, news stories and the like. The technique called description comes first (DCF) consists of identification of related document clusters, selection of salient phrases relevant to these clusters and reallocation of documents matching the selected phrases to form final document groups. The advantages of this technique include more comprehensive cluster labels and clearer (more transparent) relationship between cluster labels and their content. We demonstrate the DCF by taking a standard k-means algorithm as a baseline and weaving DCF elements into it; the outcome is the descriptive k-means (DKM) algorithm. The paper goes through technical background explaining how to implement DKM efficiently and ends with the description of an experiment measuring clustering quality on a benchmark document collection 20-newsgroups. Short fragments of this paper appeared at the poster session of the RIAO 2007 conference, Pittsburgh, PA, USA (electronic proceedings only).

7

Center selection of RBF neural network based on modified k-means algorithm with point symmetry distance measure

Sing J. K., Basu D. K., Nasipuri M., Kundu M.

Foundations of Computing and Decision Sciences

|

2004

|

Vol. 29, No. 3

247-266

EN

The hidden layer neurons of a radial basis function (RBF) neural network map input patterns from a nonlinearly separable space to a linearly separable space. To locate the centers of those hidden layer neurons, normally k-means clustering algorithm is used. Normal k-means clustering algorithm cannot detect hyper spherical-shaped clusters along the principal axes. In present study, we propose a modified version of the k-means clustering algorithm to select RBF centers, which can eliminate this drawback. In the proposed algorithm, we modify the k-means algorithm in two stages. In trie first stage, the procedure to select the initial cluster centers has been modified to capture more knowledge about the distribution of input patterns. In the second stage, the initial centers, selected in the first stage are updated using point symmetry distance measure instead of using conventional Euclidean distance. The RBF neural network with the proposed algorithm has been tested with three different machine-learning data sets. It has also been applied for the segmentation of medical images. The experimental results show that the RBF neural network using the proposed modified k-means algorithm performs better than that using normal k-means algorithm.

8

Recognition of pathological states in arterial blood by distance based techniques

Sokołowska B., Jóźwik A.

Journal of Medical Informatics & Technologies

|

2003

|

Vol. 5

MI23--30

EN

The paper presents the application of some distance based pattern recognition algorithms for recognition of pathological states in respiratory system on the basis of the arterial blood gasometry (features pH, pCO2, pO2). In our biological model two experimental situations were considered: 1) the intact animals and 2) the main inspiratory muscles paralyzed (after acute of bilateral phrenicotomy). The comparison of the mentioned three features in the two conditions was the main goal of the present study. The analyzed biological data set contained 38 in class 1 (muscle function preserved) and 36 in class 2 (after diaphragm paralyzed) measurements. It was discovered that a significant part of the measurements could be correctly recognized as the ones coming from the first or the second class according to gasometric measurements.