Filter Results
95326 results
# Installation conda create -n deep_texture python=3.6 source activate deep_texture conda install numpy pillow conda install keras-gpu conda install keras # if GPUs are not available pip install git+https://github.com/keras-team/keras-applications.git@d506dc82d0 # downgrade keras-application ## usage import deep_texture (prep, dnn) = deep_texture.setup_texture(arch = 'nasnet', layer = 'normal_concat_11', cbp_dir = '/tmp') dtr = deep_texture.calc_features_file("./test.png", prep, dnn)
Data Types:
  • Other
  • Software/Code
Integrating data from multiple sources with the aim to identify records that correspond to the same entity is required in many real-world applications including healthcare, national security, and businesses. However, privacy and confidentiality concerns impede the sharing of personal identifying values to conduct linkage across different organizations. Privacy-preserving record linkage (PPRL) techniques have been developed to tackle this problem by performing clustering based on the similarity between encoded record values, such that each cluster contains (similar) records corresponding to one single entity. When employing PPRL on databases from multiple parties, one major challenge is the prohibitively large number of similarity comparisons required for clustering, especially when the number and size of databases are large. While there have been several private blocking methods proposed to reduce the number of comparisons, they fall short in providing an efficient and effective solution for linking multiple large databases. Further, all of these methods are largely dependent on data. In this paper, we propose a novel private blocking method for efficiently linking multiple databases by exploiting the data characteristics in the form of probabilistic signatures and introduce a local blocking evaluation step for validating blocking methods without knowing the ground-truth. Experimental results show the efficacy of our method in comparison to several state-of-the-art methods.
Data Types:
  • Other
  • Software/Code
ATC-Anno is an annotation tool for the transcription and semantic annotation of air traffic control utterances. It was developed at the Spoken Language Systems (LSV) group at Saarland University. The latest version of the tool can always be found on the LSV GitHub account. If you use the tool in your research, please cite the associated paper: Marc Schulder, Johannah O'Mahony, Yury Bakanouski, Dietrich Klakow (2020). ATC-Anno: Semantic Annotation for Air Traffic Control with Assistive Auto-Annotation. In Proceedings of the International Conference on Language Resources and Evaluation (LREC), Marseilles, France.
Data Types:
  • Other
  • Software/Code
MATLAB codes used to model arsenic(III) remediation using a composite TiO2-Fe2O3 sorbent in batch and continuous-flow systems, using a modified form of the pseudo-second order (PSO) adsorption kinetic model. This data supports the manuscript provisionally titled 'A kinetic adsorption model to inform the design of arsenic(III) treatment plants using photocatalyst-sorbent materials'
Data Types:
  • Software/Code
Tools for interacting with the publicly available California Delta Fish Salvage Database, including continuous deployment of data access, analysis, and presentation.
Data Types:
  • Software/Code
This patch fixes an issue affecting the "nngt" backend (for users not using any of the standard graph libraries) that led to weights set after edge creation (using set_weights) to be incorrectly updated in some cases, notably when using NNGT with NEST. (note that the Travis test for graph-tool on Python 2 fails solely because Tiago is no longer supporting it and removed the package from his repo, it is not linked to any issue with this release)
Data Types:
  • Software/Code
sasartifact-master.zip has been obtained from https://gricad-gitlab.univ-grenoble-alpes.fr/verimag/reproducible-research/sasartifact (sha:d78a48f1) artifacts.zip has been obtained from a Gitlab CI/CP pipeline of this gitlab repository
Data Types:
  • Software/Code
See https://viresclient.readthedocs.io/en/latest/release_notes.html
Data Types:
  • Software/Code
RADWave is Python package that provides a mechanism to access altimeter datasets through web-enabled data services (THREDDS). The package capabilities are illustrated based on the the Australian Ocean Data Network (AODN database that spans from 1985-present and that has already been calibrated and validated by [Ribal and Young, 2019]. RADWave allows to query over a range of spatial and temporal scales altimeter parameters in specific geographical regions and subsequently calculates significant wave heights, periods, group velocities, average wave energy densities and wave energy fluxes.
Data Types:
  • Software/Code
This file contains the R code which was used to generate the statistics in the Table 1 of the article "Altered hematopoietic system and self-tolerance in Bardet-Biedl Syndrome".
Data Types:
  • Software/Code
1