Wyniki wyszukiwania - BazTech

1

FARC-Hezbollah: The success of Venezuela-Iran proxy groups and their convergence in the Americas

Guarin P. Jeferson

Security and Defence Quarterly

|

2020

|

Vol. 31, No. 4

117--134

EN

Persistence and adaptation are the main characteristics that have allowed FARC and Hezbollah to become perhaps the most successful proxy groups in recent years. Both Iran and Venezuela have sponsored the military, political and criminal actions of these alleged insurgent organisations. The main objective of this research was to identify and conceptualise the mitotic evolution of FARC and Hezbollah from purely armed organisms into consolidated political organisations in Colombia and Lebanon, and how this evolution has presented a criminal convergence in Venezuela based on drug trafficking and money laundering. This article is based on a comparative case-study of published research papers, documents, and official statements of FARC and Hezbollah, by applying a rational perspective that allows their performance to be deduced. The research results showed a constant mutation of these hybrid threats. Thus, not only was the political and military success of these organisations established but also the strategic support of a criminal dimension which converged in Venezuela, where the FARC drug trafficking and Hezbollah money laundering were amalgamated. Consequently, the investigation exposes the possible consequences of the FARC-Hezbollah criminal convergence in the Americas and its destabilising effects in the next decade.

2

Automatic mitosis detection in breast histopathology images using Convolutional Neural Network based deep transfer learning

Sabeena Beevi K., Nair Madhu S., Bindu G. R.

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 1

214--223

EN

The exact measure of mitotic count is one of the crucial parameters in breast cancer grading and prognosis. Detection of mitosis in standard H & E stained histopathology images is challenging due to diffused intensities along object boundaries and shape variation in different stages of mitosis. This paper explores the feasibility of transfer learning for mitosis detection. A pre-trained Convolutional Neural Network is transformed by coupling random forest classifier with the initial fully connected layers to extract discriminant features from nuclei patches and to precisely prognosticate the class label of cell nuclei. The modified Convolutional Neural Network accurately classify the detected cell nuclei with limited training data. The designed framework accomplishes higher classification accuracy by carefully fine tuning the pre-trained model and pre-processing the extracted features. Moreover, proposed method is evaluated on MITOS dataset provided for the MITOS-ATYPIA contest 2014 and clinical data set from Regional Cancer Centre, Thiruvananthapuram, India. Significance of Convolutional Neural Network based method is justified by comparing with recently reported works including a Multi Classifier System based on Deep Belief Network. Experiments show that the pre-trained Convolutional Neural Network model outperforms conventionally used detection systems and provides at least 15% improvement in F-score on other state-of-the-art techniques.

3

Metoda automatycznego wyznaczania indeksu mitotycznego populacji komórek cebuli z wykorzystaniem drzewa decyzyjnego

Gocławski J., Sekulska-Nalewajko J., Anioł P.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2008

|

T. 12, z. 3

641-656

PL

Wyznaczanie indeksu mitotycznego jest metodą oceny zdolności podziału komórek w populacjach poddawanych oddziaływaniom różnorodnych czynników hamujących lub ułatwiających ich wzrost. Zaproponowano algorytmy segmentacji obrazów komórek cebuli i elementów jąder komórkowych wyodrębniających się w procesie podziału mitotycznego. Następnie wydobyto zestaw cech geometrycznych, teksturalnych i topologicznych elementów jąder komórkowych odróżniających interfazę od faz mitozy. Zbudowano drzewo decyzyjne oparte na algorytmie C4.5. W celu oszacowania błędu klasyfikacji przeprowadzono próby 10-krotnych walidacji skrośnych. Dokonano także redukcji przestrzeni cech za pomocą metody PCA. Wyliczono wartość indeksu mitotycznego badanej populacji komórek cebuli, błąd estymatora tego indeksu i przeprowadzono porównanie ze średnim błędem klasyfikacji.

EN

The evaluation of mitotic index is the method of estimation of cell division ability in cell populations treated by growth inhibitors or accelerators. The image processing algorithms for the segmentation of onion cells and their nuclei elements appearing in the process of mitosis is proposed. Then a set of geometrical, textural and topological features of nuclei elements was extracted, which can distinguish interphase from the stages of mitosis. A decision tree was built according to C4.5 method using the maximum of information gain ratio of the feature values. To evaluate classification error, a series of 10-fold crossvalidations were performed. The feature space was reduced by applying PCA method. The value of mitotic index for the tested onion cell population as well as the estimator index error was evaluated. The errors were compared with an average classification error.