Filters








9 Hits in 9.9 sec

Infringement of Tweets Geo-Location Privacy: an approach based on Graph Convolutional Neural Networks [article]

Luca Luceri, Davide Andreoletti, Silvia Giordano
2019 arXiv   pre-print
In fact, our approach is able to localize almost 50% of the tweets with an accuracy below 1km relying only on a small percentage of available information.  ...  For this purpose, we employ a graph-based deep learning architecture to learn a model between the users' known and unknown geo-location during a considered period of time.  ...  Notice that we do not base our analysis on the content of the tweets (which is often informative of their locations) but only on signals (i.e., the geo-tags) from the social network users.  ... 
arXiv:1903.11206v1 fatcat:gjcwseq3tbaidashdkklqefjry

Spatiotemporal enabled Content-based Image Retrieval

Mariana Belgiu, Martin Sudmanns, Tiede Dirk, Andrea Baraldi, Stefan Lang
2016 International Conference on GIScience Short Paper Proceedings  
In this paper, we propose a probabilistic method for estimation of the coverage of a sensor network based on 3D vector representation of the environment.  ...  The efficiency of the coverage of a sensor network depends on optimal position of each sensor node within the network.  ...  Acknowledgment This report was prepared as an account of work sponsored by an agency of the United States government.  ... 
doi:10.21433/b311729295dw fatcat:fulw4pw3kfh5nmfzcsy3pkisvm

Data-Driven, Personalized Usable Privacy

Hamza Harkous
2017
Researchers have explored several combinations of Convolutional Neural Networks (CNNs) [FXG + 15], Long short-term memory networks (LSTMs), Attention-based Networks [TdSXZ16] , and pointwise neural networks  ...  Segment Classification with CNNs A building block of our two approaches is a multi-class classifier that uses convolutional neural networks (CNNs).  ...  PrivyShare-Web: A browser-based application that analyzes the content and metadata of files that users desire to upload to Google Drive.  ... 
doi:10.5075/epfl-thesis-7841 fatcat:6y4qqq36prdzbiqwfpumgeig2m

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022 arXiv   pre-print
We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel resources.  ...  As a result, a growing community of researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of risks and opportunities of automated decision-making  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc Behaghel, Asia Biega, Marko Bohanec, Chris  ... 
arXiv:2202.01711v3 fatcat:kd546yklwjhvtkrbhtzgbzb2xm

eTRIKS analytical environment: a practical platform for medical big data analysis

Axel Oehmichen, Yi-Ke Guo
2020
We will present the use of location data in the context of public health research, the work done in the context of data privacy for location data and the ex [...]  ...  While the collection of data is greatly accelerating, improving patient care by developing personalised therapies and new drugs depends increasingly on an organization's ability to rapidly and intelligently  ...  Most modern deep learning models are based on artificial neural networks such as deep neural networks (Convolutional Neural Networks or Recurrent Neural Networks), deep belief networks and recurrent neural  ... 
doi:10.25560/82541 fatcat:snbou7u3qfgm5cswvm4o4xxb4m

Compendium Of Best Practices And Methodologies

Freyja van den Boom
2017 Zenodo  
Chapter 1 starts with the introduction followed by a description of the methodology used for this report in Chapter 2. Chapter 3 provides an overview of the main insights gained from the interviews.  ...  The case studies are set up in such a way that will highlight the apparent barriers and showcase a compendium of practices and methodologies that may help improve the uptake of TDM in Europe.  ...  Some are very simple some are very complex such as convolutional neural networks but you don't know in advance which one will work for what you want to do based on time and resources available.  ... 
doi:10.5281/zenodo.1240766 fatcat:ne3wludapfg43h57iqx4qcbybm

Technology Giants, the Moligopoly Hypothezis and Holistic Competition: A Primer

Nicolas Petit
2016 Social Science Research Network  
Against this backdrop, what emerges is the necessity of a humble, evidenced-based approach to novel theories of harm.  ...  Risks and costs of focus on cloud based services 3.  ...  In general both the revenues and employment levels of these companies grew over this period, especially during the 1990s, and these companies were highly profitable".  ... 
doi:10.2139/ssrn.2856502 fatcat:f5o7btjskjbjrdsgeccmhmuy4i

Algorithmic business and EU law on fair trading

Federico Galli
2021
In particular, the following are addressed: the monitoring and analysis of consumer behaviour based on data; the personalisation of offers and customer experience; the capture of information on consumers  ...  The "algorithmic business" phenomenon refers to the increased deployment of artificial intelligence tools in marketing organisations which -based on large quantities of consumer dataallow companies to  ...  See more in his treatise on free will: Harry G.  ... 
doi:10.48676/unibo/amsdottorato/9750 fatcat:rb4rikb24vgbpj3v6ps24b7ugq

The emergence of the data science profession

Philipp Soeren Brandt
2017
Consistent with this critique, data nerds largely define their work on an informal basis. Yet, they also draw heavily on a formalized stock of knowledge.  ...  This question responds to the two-sided public debate, wherein data science is associated with problems such as discriminatory consequences and privacy infringements, but has also become linked with opportunities  ...  deep convolutional neural network by about like half of the final error rate on the entire set.  ... 
doi:10.7916/d8bk1ckj fatcat:xzraspk2tfbkppfcadrjpguvcu