The organised activities of Brazilian Tribology started in the end of the 1980s and, at that time, were mainly focused on abrasive wear, mining and metallurgy of wear-resistant materials. The first Brazilian Seminar on wear-resistant materials was held at the University of Sao Paulo in 1989. Six additional seminars were held in the following 20 years, during which the content evolved from wear-resistant materials, mainly abrasion, to tribology in general. Throughout those years, Brazilian tribology has experienced significant growth, up to a point where almost every Brazilian conference on related areas has a track/session on tribology.The TriboBR 2010 presented a landmark in Brazilian Tribology, since none of the previous meetings had as much international visibility. The conference included plenary lectures by Dr Ali Erdemir, Prof. Karl-Heinz zum Gahr, Prof. Jean Michel Martin, Prof. Hugh Spikes, Prof. Kenneth Holmberg, Prof. Staffan Jacobson and Prof. J. A. Williams, as well as invited contributions by Prof. Izhak Etsion, Prof. Akemi Ito, Dr Maria Isabel De Barros Bouchet and Dr Bronovets Marat Aleksandrovich. Additionally, delegates from 23 countries attended the conference. This participation may be regarded as a sign of the extent of development that tribological studies have reached in Brazil. This development has given rise to a conference where not only tribologists from different parts of the world may discuss their results and findings among themselves, but Brazilian tribologists also have the opportunity and the challenge of discussing their results with the international community and vice versa.This special issue contains 10 selected papers from TriboBR 2010. The great majority are experimental works and address a variety of topics, confirming that the conference has attracted and directed discussions that cover many areas of the wide field of tribology. Thus, although the conference provided an environment for the continuity in the discussion of the tribological behaviour of more traditional wear-resistant materials, such as high-chromium white cast iron alloys and hardfacing deposits, it also had room for the discussion of the fundamentals of tribology (surface texturing and finishing, first-principle calculations and wear regime transitions), tribomaterials {from advanced (fluorinated diamond-like carbon [DLC]) to green tribomaterials (plantain fibres reinforced polymer)}, abrasion tests and modelling of porous bearings.
Deep clustering (DC) leverages the representation power of deep architectures to learn embedding spaces that are optimal for cluster analysis. This approach filters out low-level information irrelevant for clustering and has proven remarkably successful for high dimensional data spaces. Some DC methods employ Generative Adversarial Networks (GANs), motivated by the powerful latent representations these models are able to learn implicitly. In this work, we propose HC-MGAN, a new technique based on GANs with multiple generators (MGANs), which have not been explored for clustering. Our method is inspired by the observation that each generator of a MGAN tends to generate data that correlates with a sub-region of the real data distribution. We use this clustered generation to train a classifier for inferring from which generator a given image came from, thus providing a semantically meaningful clustering for the real distribution. Additionally, we design our method so that it is performed in a top-down hierarchical clustering tree, thus proposing the first hierarchical DC method, to the best of our knowledge. We conduct several experiments to evaluate the proposed method against recent DC methods, obtaining competitive results. Last, we perform an exploratory analysis of the hierarchical clustering tree that highlights how accurately it organizes the data in a hierarchy of semantically coherent patterns.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.