• Geo-Sci-Info

    GeomLoss : Geometric Loss functions between sampled measures, images and volumes

    Find all the docs and tutorials of the version 0.2.3 in the read the docs website:

    N.B.: This is still an alpha release! Please send me your feedback: I will polish the user interface, implement Hausdorff divergences, add support for meshes, images, volumes and clean the documentation over the summer of 2020.

    The GeomLoss library provides efficient GPU implementations for:

    • Kernel norms (also known as Maximum Mean Discrepancies).

    • Hausdorff divergences, which are positive definite generalizations of the ICP loss, analogous to log-likelihoods of Gaussian Mixture Models.

    • Unbiased Sinkhorn divergences, which are cheap yet positive definite approximations of Optimal Transport (Wasserstein) costs.

    These loss functions, defined between positive measures, are available through the custom PyTorch layers SamplesLoss, ImagesLoss and VolumesLoss which allow you to work with weighted point clouds (of any dimension), density maps and volumetric segmentation masks. Geometric losses come with three backends each:

    • A simple tensorized implementation, for small problems (< 5,000 samples).

    • A reference online implementation, with a linear (instead of quadratic) memory footprint, that can be used for finely sampled measures.

    • A very fast multiscale code, which uses an octree-like structure for large-scale problems in dimension <= 3.

    GeomLoss is a simple interface for cutting-edge Optimal Transport algorithms. It provides:

    • Support for batchwise computations.
    • Linear (instead of quadratic) memory footprint for large problems, relying on the KeOps library for map-reduce operations on the GPU.
    • Fast kernel truncation for small bandwidths, using an octree-based structure.
    • Log-domain stabilization of the Sinkhorn iterations, eliminating numeric overflows for small values of 𝜀
    • Efficient computation of the gradients, which bypasses the naive backpropagation algorithm.
    • Support for unbalanced Optimal Transport, with a softening of the marginal constraints through a maximum reach parameter.
    • Support for the ε-scaling heuristic in the Sinkhorn loop, with kernel truncation in dimensions 1, 2 and 3. On typical 3D problems, our implementation is 50-100 times faster than the standard SoftAssign/Sinkhorn algorithm.

    Note, however, that SamplesLoss does not implement the Fast Multipole or Fast Gauss transforms. If you are aware of a well-packaged implementation of these algorithms on the GPU, please contact me!

    The divergences implemented here are all symmetric, positive definite and therefore suitable for measure-fitting applications. For positive input measures 𝛼 and 𝛽, our Loss

    functions are such that
    Loss(𝛼,𝛽) = Loss(𝛽,𝛼),
    0 = Loss(𝛼,𝛼) ⩽ Loss(𝛼,𝛽),
    0 = Loss(𝛼,𝛽) ⟺ 𝛼=𝛽.

    GeomLoss can be used in a wide variety of settings, from shape analysis (LDDMM, optimal transport…) to machine learning (kernel methods, GANs…) and image processing. Details and examples are provided below:

    GeomLoss is licensed under the MIT license.

    Author and Contributors

    Feel free to contact us for any bug report or feature request:

    Related projects

    You may be interested by:

    • The KeOps library, which provides efficient CUDA routines for point cloud processing, with full PyTorch support.

    • Rémi Flamary and Nicolas Courty’s Python Optimal Transport library, which provides a reference implementation of OT-related methods for small problems.

    • Bernhard Schmitzer’s Optimal Transport toolbox, which provides a reference multiscale solver for the OT problem, on the CPU.

    posted in GSI FORGE read more
  • Geo-Sci-Info

    1-2 Fully funded (4yrs) PhD position on AI/machine learning @ UiT The Arctic University of Norway

    1-2 Fully funded (4yrs) PhD position on AI/machine learning with the Department of Computer Science, UiT The Arctic University of Norway.

    Application Link - https://www.jobbnorge.no/en/available-jobs/job/192788/1-2-phd-fellows-in-computer-science-artificial-intelligence-for-virtual-staining-of-label-free-cell-and-tissue-images

    Deadline - 18th October 2020
    Location- Tromsø, Norway

    Qualification:
    These positions require a Master’s degree or equivalent in Computer Science, or Mathematics and Computing. In addition, the candidates must have:

    Experience of working with computer vision and deep learning toolkits on at least one of the following platforms – Python, C/C++, MATLAB, Keras, PyTorch, Tensor Flow

    Demonstration of programming proficiency in at least two of the following platforms: Python, C/C++, MATLAB, OpenCV, etc.

    Postgraduate coursework or master thesis strongly related to at least four of the following topics:

    • Machine learning/deep learning
    • Computer vision
    • Optimization theory/ convex optimization/computational optimization
    • Linear algebra
    • Statistics/statistical machine learning
    • Computational modelling of differential and integral equations
    • Data science
    • GPU programming
    • Neural networks
    • Distributed learning/extreme learning

    Requirement:
    Your application must include:
    Cover letter explaining your motivation and research interests
    CV - summarizing education, positions and academic work
    Diplomas and transcripts from completed Bachelor’s and Master’s degrees
    Documentation of English proficiency
    1-3 references with contact details
    Master thesis, and any other academic works
    Documentation has to be in English or a Scandinavian language. We only accept applications through Jobbnorge.

    Remuneration -
    approx. 48,000 Euro per annum (Remuneration of the PhD position is in State salary scale code 1017. A compulsory contribution of 2% to the Norwegian Public Service Pension Fund will be deducted.)

    Description
    VirtualStain is a project funded under thematic call for strategic funding by UiT The Arctic University of Norway. It involves developing AI solutions for segmenting, identity allocation, and modeling of the processes of sub-cellular structures such as mitochondria in cells and cellular structures in tissues using label-free images and videos of cells and tissues. Interpreting life processes and label-free images of cells and tissues is a daunting task. The PhD students will work on the following problem:

    Images of unlabeled samples appear as gray scale images devoid of color, texture, and edges. Therefore, they lack features conventionally used in deep models for identification of individual structures. New suitably designed and trained intelligence models have to be developed specific to the chosen label-free imaging technology. If conventional AI approaches such as deep learning and generative networks are used, large training dataset with correlated image sets of labeled and label-free images are needed, which is a significant challenge. There is a need of new out-of-box AI solutions that derive and improve intelligence, as new data becomes available.

    Project page - https://en.uit.no/project/virtualstain

    posted in Jobs offers - Call for projects read more
  • Geo-Sci-Info

    Capture du 2020-08-11 11-18-55.png

    INTRODUCTION LECTURES

    • Introduction and presentation of the conferences by Frederic Barbaresco. VIDEO

    • Presentation of Geometric Sciences of Information and GSI 2021 by Frederic Barbaresco. VIDEO

    LECTURES (90 min)

    1. Langevin Dynamics

    • 1.1 Langevin Dynamics: old and news : Eric Moulines . Part 1 : introduction to Markov chain Monte Carlo Methods VIDEO, Part 2 VIDEO

    2. Computational Information Geometry:

    • 2.1. Information Manifold modeled with Orlicz Spaces : Giovanni Pistone . VIDEO

    • 2.2. Recent contributions to Distances and Information Geometry: a computational viewpoint : Frank Nielsen . VIDEO - SLIDES

    3. Non-Equilibrium Thermodynamic Geometry

    • 3.1. A variational perspective of closed and open systems: François Gay-Balmaz
    • 3.2. Geometry of Non-Equilibrium Thermodynamics: a homogeneous Symplectic approach : Arjan Van Der Schaft . VIDEO- SLIDES

    4. Geometric Mechanics

    • 4.1. Galilean Mechanics and Thermodynamics of continua : Géry de Saxcé. VIDEO - SLIDES

    • 4.2. Souriau-Casimir Lie Groups Thermodynamics and Machine Learning : Frederic Barbaresco. VIDEO - SLIDES

    5. "Structure des Systèmes Dynamiques" (SSD) Jean-Marie Souriau’s book 50th Birthday Wikipedia page

    • 5.1. Souriau Familly and "structure of motion": Jean-Marie Souriau, Michel Souriau, Paul Souriau and Etienne Souriau : Frederic Barbaresco . VIDEO - SLIDES

    • 5.2. SSD Jean-Marie Souriau’s book 50th birthday: Géry de Saxcé SLIDES

    KEYNOTES (60 min)

    • Learning Physics from Data : Francisco Chinesta . VIDEO VIDEO - SLIDES

    • Information Geometry and Integrable Systems : Jean-Pierre Françoise. VIDEO VIDEO - SLIDES

    • Learning with Few Labeled Data : Pratik Chaudhari . VIDEO - SLIDES

    • Information Geometry and Quantum Fields : Kevin Grosvenor SLIDES

    • Port Thermodynamic Systems Control : Bernhard Maschke . VIDEO - SLIDES

    • Dirac Structures in Nonequilibrium Thermodynamics : Hiroaki Yoshimura . VIDEO - SLIDES

    • Thermodynamic efficiency implies predictive inference : Susanne Still . VIDEO - SLIDES

    • Computational dynamics of reduced coupled multibody-fluid system in Lie group setting : Zdravko Terze . VIDEO - SLIDES

    • Exponential Family by Representation Theory : Koichi Tojo . VIDEO - SLIDES

    • Deep Learning as Optimal Control Problems and Structure Preserving Deep Learning : Elena Celledoni . VIDEO - SLIDES

    • Contact geometry and thermodynamical systems : Manuel de León. VIDEO - SLIDES

    • Diffeological Fisher Metric : Hông Vân Lê. VIDEO - SLIDES

    • Mechanics of the probability simplex : Luigi Malagò. VIDEO - SLIDES

    • Covariant Momentum Map Thermodynamics : Goffredo Chirco. VIDEO - SLIDES

    • Sampling and statistical physics via symmetry : Steve Huntsman. VIDEO - SLIDES

    • Geometry of Measure-preserving Flows and Hamiltonian Monte Carlo : Alessandro Barp. VIDEO - SLIDES

    • Schroedinger's problem, Hamilton-Jacobi-Bellman equations and regularized Mass Transportation : Jean-Claude Zambrini. VIDEO - SLIDES

    POSTERS

    PosterImg.png
    PDF of posters:

    • Viscoelastic flows of Maxwell fluids with conservation laws - Sébastien Boyaval - POSTER
    • Bayesian Inference on Local Distributions of Functions and Multi-dimensional Curves with Spherical HMC Sampling - Anis Fradi and Chafik Samir - POSTER
    • Material modeling via Thermodynamics-based Artificial Neural Networks - Filippo Masi Ioannis Stefanou, Paolo Vannucci, Victor Maffi-Berthier - POSTER
    • LEARNING THE LOW-DIMENSIONAL GEOMETRY OF THE WIRELESS CHANNEL - Paul Ferrand, Alexis Decurninge, Luis Garcia Ordóñez and Maxime Guillaud - POSTER
    • A Hyperbolic approach for learning communities on graphs - Hatem Hajri, Thomas Gerald and Hadi Zaatiti - POSTER
    • UNSUPERVISED OBJECT DETECTION FOR TRAFFIC SCENE ANALYSIS - Bruno Sauvalle (superviseur: ARNAUD DE LA FORTELLE) - POSTER
    • Hard Shape-Constrained Kernel Regression - Pierre-Cyril Aubin-Frankowski and Zoltán Szabó - POSTER
    • CONSTRAINT-BASED REGULARIZATION OF NEURAL NETWORKS - Benedict Leimkuhler, Timothée Pouchon, Tiffany Vlaar, Amos Storkey - POSTER
    • CONNECTING STOCHASTIC OPTIMIZATION WITH SCHRÖDINGER EVOLUTION WITH RESPECT TO NON HERMITIAN HAMILTONIANS - C. Couto, J. Mourão, J.P. Nunes and P. Ribeiro - POSTER
    • Geomstats: A Python Package for Geometry in Machine Learning and Information Geometry - Nina Miolane, Nicolas Guigui1, Alice Le Brigant, Hadi Zaatiti, Christian Shewmake, Hatem Hajri, Johan Mathe, Benjamin Hou, Yann Thanwerdas, Stefan Heyder, Olivier Peltre, Niklas Koep, Yann Cabanes, Thomas Gerald, Paul Chauchat, Daniel Brooks, Bernhard Kainz, Claire Donnat, Susan Holmes, Xavier Pennec - POSTER
    • Fast High-order Tensor Learning Based on Grassmann Manifold - O.KARMOUDA, R.BOYER and J.BOULANGER - POSTER
    • A Geometric Interpretation of Stochastic Gradient Descent in Deep Learning and Bolzmann Machines - Rita Fioresi and Pratik Chaudhari - POSTER
    • Lagrangian and Hamiltonian Dynamics on the Simplex - Goffredo Chirco, Luigi Malago, Giovanni Pistone - POSTER
    • Calibrating Bayesian Neural Networks with Alpha-divergences and Normalizing Flows - Hector J. Hortua, Luigi Malago and Riccardo Volpi - POSTER

    image004.jpg

    posted in Joint Structures and Common Foundations of Statistical Physics Information Geometry and Inference for Learning (SP+IG'20)read more
  • Geo-Sci-Info

    Registration payment:

    Registration fees for Summer Week is 450 euros, including catering (bedroom and 3 meals a dayon 5 days) and all accommodation on site: https://www.houches-school-physics.com/practical-information/facilities/ https://www.houches-school-physics.com/practical-information/your-stay/
    Registration will be paid at Les Houches reception desk at your arrival by credit card (or VAD payment of your lab).
    Any registration canceled less than two weeks before the arrival date will be due.

    Arrival/Departure:

    The arrival is Sunday July 26th starting from 3:00 pm. On the day of arrival, only the evening meal is planned. On Sunday, the secretariat is open from 6:00 pm to 7:30 pm. Summer Week will be closed Friday July 31st at 4 pm.

    Access to Les Houches:

    https://www.houches-school-physics.com/practical-information/access/
    Ecole de Physique des Houches, 149 Chemin de la Côte, F-74310 Les Houches, France Les Houches is a village located in Chamonix valley, in the French Alps. Established in 1951, the Physics School is situated at 1150 m above sea level in natural surroundings, with breathtaking views on the Mont-Blanc mountain range.

    https://houches-school-physics.com

    Excursion:

    Wednesday afternoon is free. Excursion could be organized to

    · The Mer de Glace (Sea of Ice): It is the largest glacier in France, 7 km long and 200m deep and is one of the biggest attractions in the Chamonix Valley: https://www.chamonix.net/english/leisure/sightseeing/mer-de-glace

    · L’Aiguille du midi: From its height of 3,777m, the Aiguille du Midi and its laid-out terraces offer a 360° view of all the French, Swiss and Italian Alps. A lift brings you to the summit terrace at 3,842m, where you will have a clear view of Mont Blanc: https://www.chamonix.com/aiguille-du-midi-step-into-the-void,80,en.html

    image004.jpg

    posted in Joint Structures and Common Foundations of Statistical Physics Information Geometry and Inference for Learning (SP+IG'20)read more
  • Geo-Sci-Info

    Program

    See attached Poster, Scientific Program and Poster Program.

    8 Lectures (90 min)

    • Langevin Dynamics: Old and News (x 2) – Eric Moulines

    • Computational Information Geometry
      On statistical distances and information geometry for ML – Frank Nielsen
      Information Manifold modeled with Orlicz Spaces – Giovanni Pistone

    • Non-Equilibrium Thermodynamic Geometry
      A variational perspective of closed and open systems - François Gay-Balmaz
      A Homogeneous Symplectic Approach - Arjan van der Schaft

    • Geometric Mechanics
      Gallilean Mechanics & Thermodynamics of Continua - Géry de Saxcé
      Souriau-Casimir Lie Groups Thermodynamics & Machine Learning – Frédéric Barbaresco

    17 Keynotes (60 min)

    • Learning with Few Labeled Data - Pratik Chaudhari
    • Sampling and statistical physics via symmetry - Steve Huntsman
    • The Bracket Geometry of Measure-Preserving Flows and Diffusions - Alessandro Barp
    • Exponential Family by Representation Theory - Koichi Tojo
    • Learning Physics from Data - Francisco Chinesta
    • Information Geometry and Integrable Hamiltonian - Jean-Pierre Françoise
    • Information Geometry and Quantum Fields - Kevin Grosvenor
    • Thermodynamic efficiency implies predictive inference- Susanne Still
    • Diffeological Fisher Metric - Hông Vân Lê
    • Deep Learning as Optimal Control - Elena Celledoni
    • Schroedinger's problem, Hamilton-Jacobi-Bellman equations and regularized Mass Transportation - Jean-Claude Zambrini
    • Mechanics of the probability simplex - Luigi Malagò
    • Dirac structures in nonequilibrium thermodynamics - Hiroaki Yoshimura
    • Port Thermodynamic Systems Control - Bernhard Maschke
    • Covariant Momentum Map Thermodynamics - Goffredo Chirco
    • Contact geometry and thermodynamical systems - Manuel de León
    • Computational dynamics of multibody-fluid system in Lie group setting- Zdravko Terze

    Program Schedule

    image007.png

    Mornings will be dedicated to 3 hours courses. Afternoons will be dedicated to long keynotes.

    Poster session will be organized Wednesday morning.

    image009.png

    posted in Joint Structures and Common Foundations of Statistical Physics Information Geometry and Inference for Learning (SP+IG'20)read more
  • Geo-Sci-Info

    Capture du 2020-05-27 09-37-13.png

    In the context of our research and development in artificial intelligence applied to medical imaging, we are looking for: Data Science and Machine Learning Research Scientist M/F

    Integrated into a multidisciplinary research and development team within the iBiopsy® project, you are a scientist in the research and development of innovative medical imaging solutions using machine learning and other AI methods.

    Medical imaging is one of the fastest growing fields in machine learning. We are looking for an enthusiastic, dynamic, and organized Senior Scientist/Engineer with strong ML experience, excellent communication skills who will thrive at the heart of technological innovation.

    Presentation of activities and main tasks linked to the job

    • Position under the supervision of Head of Data Science and the Chief of Science and Innovation Officer

    Responsibilities:

    1. You will work on content based-image retrieval in medical imaging. You will build efficient search engine services in clinical applications.
    1. You will apply your AI/ML knowledge to develop innovative and robust biomarkers using data coming from medical imaging systems such as MRI and CT scanners and other data sources.
    1. Your work will involve agile research and development of novel machine learning algorithms and systems. Being part of our front-end innovation organization, you will actively scout, keep track of, evaluate, and leverage disruptive technologies, and emerging industrial, academic and technological trends.
    1. You will work with software development team as well as clinical science team.
    1. In addition, you will transfer technology, and share insights and best practices across innovation teams. You will generate intellectual property for the company. You will be expected to author peer reviewed papers, present results at industry/scientific conferences.
    1. We look at you to building breakthrough AI-enabled imaging solutions leveraging cloud computing and apply supervised and unsupervised Machine Learning techniques to create value from the imaging and clinical data repositories generated by our medical research and pharmaceutical industry partners. These AI enabled systems and services go beyond image analysis to transform medical practice and drug development.

    Searched profile :

    • Education: PhD in in Mathematics, Computer Science or related fields
    • Main skills and Experience required:
    • Minimum 5 years of relevant work experience in (deep) machine learning
    • Experience with Medical Imaging, CT/MRI, image signatures, large scale visual information retrieval, features selection
    • Relevant experience with Python, R, DL frameworks (i.e. Pytorch, Keras, Tensorflow) and standard packages as Scikit-learn, Numpy, Scipy, Pandas
    • Semi-Supervised Learning, Self-supervised Learning, Reinforcement Learning, Adversarial methods.
    • Multimodal feature extraction
    • Author on related research publication / conferences
    • Strong experience with opensource technologies to accelerate innovation

    Knowledge:

    • In depth technical knowledge of AI, deep learning and computer vision
    • Strong fundamental knowledge of statistical data processing, regression techniques, neural networks, decision trees, clustering, pattern recognition, probability theory, stochastic systems, Bayesian inference, statistical techniques and dimensionality reduction

    Additional qualities:

    • Strong interpersonal, communication and presentation skills as well as ability to work in global team
    • Fluent in written and oral English

    Legal

    • Job location: Sophia Antipolis, France
    • Contract: Permanent, Open-Ended
    • Start: As Soon As Possible
    • Offered salary: will depend on candidate’s skills and experience.

    Please apply on our website : https://mediantechnologies.com/job-search/#!careers

    posted in Jobs offers - Call for projects read more
  • Geo-Sci-Info

    Capture du 2020-05-27 09-29-30.png
    In the context of our research and development in artificial intelligence applied to medical imaging, we are looking for: Data Structuring and Clustering Research Scientist M/F

    Integrated into a multidisciplinary research and development team within the iBiopsy® project, you are a scientist in the research and development of innovative medical imaging solutions using machine learning and other AI methods.

    Medical imaging is one of the fastest growing fields in machine learning. We are looking for an enthusiastic, dynamic, and organized Senior Scientist/Engineer with strong ML experience, excellent communication skills who will thrive at the heart of technological innovation.

    Presentation of activities and main tasks linked to the job

    • Position under the supervision of the Head of Data Science and the Chief of Science and Innovation Officer.

    • Responsibilities:

    1. You will work on scalable data clustering techniques and develop your know how for knowledge discovery and exploration towards robust biomarkers. You will conduct clustering validity studies

    2. You will work on large scale data mining and feature exraction in medical imaging. You will build and contribute to develop innovative and robust biomarkers for personalized medicine

    3. Your work will involve agile research and development of novel machine learning algorithms and systems. Being part of our front-end innovation organization, you will actively scout, keep track of, evaluate, and leverage disruptive technologies, and emerging industrial, academic and technological trends.

    1. You will work with software development team as well as clinical science team.
    1. In addition, you will transfer technology, and share insights and best practices across innovation teams. You will generate intellectual property for the company. You will be expected to author peer reviewed papers, present results at industry/scientific conferences.
    1. We look at you to building breakthrough AI-enabled imaging solutions leveraging cloud computing and apply supervised and unsupervised Machine Learning techniques to create value from the imaging and clinical data repositories generated by our medical research and pharmaceutical industry partners. These AI enabled systems and services go beyond image analysis to transform medical practice and drug development.

    Searched profile

    • Education: PhD in in Mathematics, Computer Science or related fields
    • Main skills and Experience required:
    • Minimum 3 years of relevant work experience in machine learning
    • Experience with Medical Imaging, CT/MRI, image signatures, large scale visual information retrieval, features selection
    • Relevant experience with Python, R, DL frameworks (i.e. Pytorch, Keras, Tensorflow) and standard packages as Scikit-learn, Numpy, Scipy, Pandas
    • Data structure inference models, clustering and semi-supervised learning, knowledge discovery and data mapping, saliency map
    • Multimodal feature extraction
    • Author on related research publication / conferences
    • Strong experience with opensource technologies to accelerate innovation

    Knowledge:

    *In depth technical knowledge of AI, deep learning and computer vision

    • Strong fundamental knowledge of statistical data processing, regression techniques, neural networks, decision trees, clustering, pattern recognition, probability theory, stochastic systems, Bayesian inference, statistical techniques and dimensionality reduction

    Additional qualities:

    • Strong interpersonal, communication and presentation skills as well as ability to work in global team
    • Fluent in written and oral English

    Legal

    • Job location: Sophia Antipolis, France
    • Contract: Permanent, Open-Ended
    • Start: September 2020
    • Offered salary: will depend on candidate’s skills and experience.

    Please apply on our website : https://mediantechnologies.com/job-search/#!careers

    posted in Jobs offers - Call for projects read more
  • Geo-Sci-Info

    Capture du 2020-05-12 18-26-07.png
    OFFICIAL WEBSITE
    MEMBER RESOURCES
    This website is dedicated to featuring national resources developed by ISO members to support the fight against COVID-19.

    posted in COVID19 open Database ressources and challenges read more
  • Geo-Sci-Info

    600_481995012.jpeg

    Alibaba Cloud - Free CT Image Analytics for COVID-19
    Official WEBPAGE
    This technology can assist realizing quantitative analysis, speeding up CT image analytics, avoiding errors caused by fatigue and adjusting treatment plans in time.
    Free for public research institution
    Email Your Submission: Free Computational and AI Platforms to Help Research, Analyze and Combat COVID-19 ("Program") is intended to support public research institutions worldwide for the research analysis and prevention of COVID-19. This technology is subject to availability upon confirmation. You can submit the summary and description of your research project to wanqing.hwq [at] alibaba-inc.com. All submissions will be reviewed for technical feasibility, and eligible applicants will be contacted for more details and the next steps of the process. Once the submission is successful, the applicant will get a certain amount of coupon according to the project, which is valid for 3months. The coupon can be used for all Alibaba cloud products, including HPC, ECS, and GPU, excluding marketplace products and 3rd party products.
    Disclaimer: The technology is not intended to, by itself and without the exercise of professional judgment and clinical evaluation, diagnose any medical condition or disease or conclusively indicate the absence of any disease, including COVID-19 and the technology is not a substitute for diagnosis and treatment by a certified medical professional. The technology has not been thoroughly tested, and are not guaranteed in any way to be accurate, useful, sufficient, satisfactory, available, or otherwise fit for any purpose. To the maximum extent permissible under applicable law, the Solution is provided "AS IS," "WITH ALL FAULTS," and without any warranties or service guarantees.
    Note: The accuracy is calculated using the model trained on about 5000 samples, and is tested based on a sample size of 660 tests with a 1:1:1 ratio of cases of COVID-19 pneumonia, common pneumonia, and other conditions.

    Whole Genome Sequencing Analysis for COVID-19
    Official WEBPAGE
    When facing a severe epidemic such as COVID-19, rapid and accurate virus screening and detection is particularly important for maintaining control. The AI algorithm avoids the high missed detection rate of nearly 40% of PCR, and can accurately detect virus mutations and shorten the duration of genetic analysis of suspected cases from hours to just 30 minutes, greatly reducing the time of virus screening and detection.
    To read disclaimer, click to see Disclaimer in FAQ.

    • Rapid and accurate testing to improve the handling of local outbreaks
    • Core algorithm optimization and comprehensive monitoring of COVID-19 development and changes
    • Quick deployment and easy to use with modular and simplified operation and configuration

    Elastic High Performance Computing Technology
    Official WEBPAGE
    The development of new drugs and vaccines for COVID-19 requires large amounts of data analysis, as well as large-scale literature screening and scientific computing. HPC and AI technology helps scientific research institutions to perform viral gene sequencing, conduct new drug research and development, and shorten the research and development cycle. The Global Health Drug Discovery Institute (GHDDI) has established a scientific data sharing platform and an AI drug screening platform for COVID-19 with the support of this center's open AI computing power. Some research institutions and universities have increased the speed of biological information transmission by 5 times, and reduced the virtual screening time for antiviral drugs from one month to one week.

    posted in COVID19 open Database ressources and challenges read more
  • Geo-Sci-Info

    CovidBanner-1.png
    Capture du 2020-04-13 23-01-47.png
    LINK TO WEBSITE

    Covid-19 Interactive Dashboard – MULTIVAC

    OPEN SCIENCE
    Open Source and Open Data

    This app was developed by using open data and open-source libraries. Some of the useful APIs, data sources, cisualizations, analysis and open-source libraries:
    Libraries

    • Streamlit
    • Spark NLP
    • JohnSnowLabs Healthcare
    • Apache Spark
    • Tensorflow
    • Tensorflow Hub
    • Plotly
    • Matplotlib

    APIs

    • COVID-19 Grafana API (repo): JSON API to visualize stats in Grafana
    • COVID-19 GraphQL API (repo)
    • CovidAPI.info (repo): Lightweight, Superfast REST API built to be consumed by dashboards.
    • COVID-19 Ruby Gem

    Data Sources

    Visualizations

    • Covid19 Visualizer (repo): Covid19 Graphical Visualizer
    • EU stats report on COVID-19 (repo): COVID-19 tracker for EU countries
    • CoronaStatistics.live (repo): COVID-19 Global Report
    • COVID-19 World (repo): COVID-19 Global Report
    • COVID-19 Comparator (repo): Coronavirus cases comparator by countries, from chosen date and number of days (PWA)
    • Mobile Friendly COVID-19 Report (repo): Coronavirus daily report in a mobile friendly website (PWA)
    • COVID-19 Daily Report (repo): Coronavirus daily report, updated hourly
    • COVID-19 GLOBAL Report (repo)
    • covid-charts (repo): chart widget with Coronavirus stats for specified country
    • COVID-19 Global Chart (repo): Chart GeoMap with last status by country.
    • COVID-19 Stats (repo): A simple mobile friendly dashboard visualizing the latest stats of the COVID-19 outbreak.
    • Corona.log (repo): A simple COVID-19 data checker per region
    • COVID-19 How Bad Is It (repo): Live graphs with latest news involving Covid-19,
    • COVID-19 Sri Lanka Tracker (repo): Live Updates of COVID-19 Patients in Sri Lanka
    • COVID-19 Countries Trends & Comparison (repo): Country comparison of COVID-19 cases, with per-capita and growth views.
    • felipec covid-19 (repo): Trajectory of confirmed COVID-19 cases per country after 100 in logarithmic scale and growth factor.
    • COVID-19 Global Report (repo): Vue.js app for monitoring the spread of the new coronavirus
    • COVID-19 Regional Relative TimeSeries (repo): Normalized regional comparative timeseries.
    • COVID-19 Country Travel Bans (repo): An interactive map showing countries with travel restrictions and infection counts.
    • COVID-19 Stats and Trends (repo)
    • COVID Reports (repo): Coronavirus trends comparison by country
    • #daysbehinditaly (repo): Number of days various countries are behind Italy in total COVID-19 cases assuming similar case growth rate
    • Covid-19 Project to track the spread of coronavirus (repo): Coronavirus information by country
    • Covid-19 Progress Reports by Country (repo): Coronavirus (Fight against) Progress by country
    • COVID-19-LK (repo): A Sri Lankan COVID-19 Tracker with a map and dark theme <3
    • COVID-19 Mauritius Statistics (repo): A simple page with stats about the current COVID-19 situation in the small island of Mauritius.
    • Flattening the Curve by Country | COVID-19 🦠 (repo): A simple dashboard to showcase flattening of the curve by each country affected with COVID-19 - plotted over time.
    • World map and country comparison timeline: Select multiple countries on the map for a clean comparison of how the number of cases develop.
    • COVID-19 Panel for Digital Signage (repo): Digital Signage-ready and configurable Panel with COVID-19 data.
    • COVID-19 Trends (repo): Simple charts showing COVID-19 trends
    • Covid-19 Race (repo) A basic html5/css/js webapp to compare the cases from a select few countries.
    • COVID-19 India dashboard (repo) - A simple dashboard made with Flask specifically for India with stats of various states and predictions of what's going to happen in the next five days.
    • Open COVID19 Map (repo) Open map visualization with alternative data sources, containment scores, testing rate projection, replay mode
    • I am Covid -19 🦠 (repo) - Visualization of the covid-19 dataset using Nuxtjs(vuejs), Graphql and valuable information about getting through the Covid-19 pandemic.
    • Simple COVID-19 Tracker (repo): Mobile-friendly and minimal page that displays the current total count of coronavirus cases and deaths in a selected region.
    • COVID-19 Report (repo): Coronavirus information by country in a mobile-friendly SPA.
    • Visualizing COVID-19 with D3 (repo): A responsive D3-based data visualization that leverages a Sankey diagram to display the breakdown of the worldwide COVID-19 cases.
    • Coronavirus-meter (repo): Coronavirus meter provides statistics from cases all around the world. View cases from each country up to two months before. Coronavirus cases, deaths, recovered in statistical numbers from all around the world.
    • Telegram COVID-19 Monitoring Telegram alert everyday with the statistics of COVID-19 in each country.
    • Coronavirus Infections (repo): Track Coronavirus infections, deaths, recovers and active cases per country in chart and table.
    • Corona in Charts (repo): Corona graphs for each country with total cases, active cases, recovered and fatalities.
    • COVID-19 Monitoring And Charting(repo): World COVID-19 Tracking, historical data and overview using NodeJS Server
    • COVID-19 Reaction Tracker (repo): Track user reactions across the globe
    • COVID-19 Data Visualization Using R Shiny(repo): Data Summary, Data Visualization, World Map and differnt Analytics plots.
      *Made in r shiny
    • covid19-psvita-data: An app for viewing COVID-19 Data and graphs on a Playstation Vita
    • COVID-19 Timeline: A Flutter app for tracking COVID-19 data
    • COVID-19 in Numbers (repo): Covid-19 stats and charts by country. Made with Blazor.
      Corona-Virus-Numbers: Android and iOS app for visualising COVID-19 graphs developed using Flutter

    Analysis

    • COVID-19 Trends and Growth Rate: A Python implementation of growth rate and other trend analysis
    • Are we dead yet (repo): Live graphs of confirmed, infected and infection rate. Outbreak normalised for comparison.
    • epidemic-simulator (repo): Mathematical model using Macroscopic Rate Equations for simulating the future of the epidemic
    • Coronavirus Cases, Deaths, and Recoveries by Country (repo) - a blog post with charts that update daily
    • COVID-19 Best fit evolution Visualizing the evolution of a best-fit logistic curve over time, showing the difficulty of predicting the number of future cases and deaths
    • PowerBI-driven COVID-2019 Tracking: Power BI Desktop dashboard based on JSON data about COVID-2019 spread

    posted in COVID19 open Database ressources and challenges read more

Internal error.

Oops! Looks like something went wrong!