Search results for "Graph based"
showing 4 items of 4 documents
Graph-based characterisations of cell types and functionally related modules in promoter capture Hi-C Data
2019
Graph-based analysis of ethylene glycol decomposition on a palladium cluster
2017
The ethylene glycol, CH2OH-CH2OH, decomposition mechanism, occurring on a subnanometric palladium cluster shaped by 12 atoms, was investigated by means of density functional theory. Different reaction routes were identified leading to H2 and CO. The whole reaction network was analyzed, framing the results within the graph theory. The possible decomposition pathways were discussed and compared, allowing one to draw a whole picture of all the parallel, possibly competitive, routes that starting from CH2OH-CH2OH originate H2 and CO.
Contribution à l’apprentissage de représentation de données à base de graphes avec application à la catégorisation d’images
2020
Graph-based Manifold Learning algorithms are regarded as a powerful technique for feature extraction and dimensionality reduction in Pattern Recogniton, Computer Vision and Machine Learning fields. These algorithms utilize sample information contained in the item-item similarity and weighted matrix to reveal the intrinstic geometric structure of manifold. It exhibits the low dimensional structure in the high dimensional data. This motivates me to develop Graph-based Manifold Learning techniques on Pattern Recognition, specially, application to image categorization. The experimental datasets of thesis correspond to several categories of public image datasets such as face datasets, indoor and…
A Graph-Based Method for PET Image Segmentation in Radiotherapy Planning: A Pilot Study
2013
Target volume delineation of Positron Emission Tomography (PET) images in radiation treatment planning is challenging because of the low spatial resolution and high noise level in PET data. The aim of this work is the devel- opment of an accurate and fast method for semi-automatic segmentation of me- tabolic regions on PET images. For this purpose, an algorithm for the biological tumor volume delineation based on random walks on graphs has been used. Va- lidation was first performed on phantoms containing spheres and irregular in- serts of different and known volumes, then tumors from a patient with head and neck cancer were segmented to discuss the clinical applicability of this algo- rith…