University of Architecture, Civil Engineering and Geodesy

About: University of Architecture, Civil Engineering and Geodesy is a education organization based out in Sofia, Bulgaria. It is known for research contribution in the topics: Finite element method & Beam (structure). The organization has 3808 authors who have published 3822 publications receiving 30736 citations. The organization is also known as: Sofia Polytechnic.

Divergent Patterns of Built-up Urban Space Growth Following Post-Socialist Changes

Abstract: An important challenge for the research on post-socialist big cities is to identify the mechanisms of their uncontrolled urban space growth. This analysis is focused on the built-up urban space affected by transformations from a centrally planned to a market-based economy. Post-socialist changes in Bucharest are clearly reflected in the dynamics of built-up space. Land cover dynamics were evaluated using spectral mixture analysis of Landsat 5 TM (Thematic Mapper) data to map percent impervious surface area in 1988 and 2010. Change analysis reveals (1) a decrease of built space in central and peri-central areas of Bucharest, (2) an expansion of new residential areas to the south, (3) land fragmentation to the east and southeast, (4) a mixture of densities to the north, and (5) the role of the ring road in spurring recent development. A key challenge facing Bucharest is the disposition and repurposing of the lands covered by old large housing estates and shuttered heavy industries.

Blockchain-Based Privacy Preserving Deep Learning

Abstract: Smart mobile devices have access to huge amounts of data appropriate to deep learning models, which in turn can significantly improve the end-user experience on mobile devices. But massive data collection required for machine learning introduce obvious privacy issues. To this end, the notion of federated learning (FL) was proposed, which leaves the training data distributed on the mobile devices, and learns a shared model by aggregating locally-computed updates. However, in many applications one or more Byzantine devices may suffice to let current coordination learning mechanisms fail with unpredictable or disastrous outcomes. In this paper, we provide a proof-of-concept for managing security issues in federated learning systems via blockchain technology. Our approach uses decentralized programs executed via blockchain technology to establish secure learning coordination mechanisms and to identify and exclude Byzantine members. We studied the performance of our blockchain-based approach in a collective deep-learning scenario both in the presence and absence of Byzantine devices and compared our results to those obtained with an existing collective decision approach. The results show a clear advantage of the blockchain approach when Byzantine devices are part of the members.