- This event has passed.
April 18, 2021 - April 22, 2021
ALLDATA 2021 conference tracks:
Challenges in processing Big Data and applications
Data classification: small/big/huge, volume, velocity, veridicity, value, etc; Data properties: syntax, semantics, sensitivity, similarity, scarcity, spacial/temporal, completeness, accuracy, compactness, etc.; Data processing: mining, searching, feature extraction, clustering, aggregating, rating, filtering, etc.; Data relationships: linked data, open data, linked open data, etc. Exploiting big/linked data: upgrading legacy open data, integrating probabilist models, spam detection, datasets for noise corrections, predicting reliability, pattern mining, linking heterogeneous dataset collections, exploring type-specific topic profiles of datasets, efficient large-scale ontology matching etc.; Applications: event-based linked data, large scale multi-dimensional network analysis, error detection of atmospheric data, exploring urban data in smart cities, studying health fatalities, estimating the energy demand at real-time in cellular networks, multilingual word sense disambiguation, creating open source tool for semantically enriching data, etc.
Advanced topics in Deep/Machine learning
Distributed and parallel learning algorithms; Image and video coding; Deep learning and Internet of Things; Deep learning and Big data; Data preparation, feature selection, and feature extraction; Error resilient transmission of multimedia data; 3D video coding and analysis; Depth map applications; Machine learning programming models and abstractions; Programming languages for machine learning; Visualization of data, models, and predictions; Hardware-efficient machine learning methods; Model training, inference, and serving; Trust and security for machine learning applications; Testing, debugging, and monitoring of machine learning applications; Machine learning for systems.
Approaches for Data/Big Data processing using Machine Learning
Machine learning models (supervised, unsupervised, reinforcement, constrained, etc.); Generative modeling (Gaussian, HMM, GAN, Bayesian networks, autoencoders, etc.); Explainable AI (feature importance, LIME, SHAP, FACT, etc.); Bayesian learning models; Prediction uncertainty (approximation learning, similarity); Training of models (hyperparameter optimization, regularization, optimizers); Active learning (partially labels datasets, faulty labels, semi-supervised); Applications of machine learning (recommender systems, NLP, computer vision, etc.); Data in machine learning (no data, small data, big data, graph data, time series, sparse data, etc.)
Big data foundations; Big data architectures; Big data semantics, interoperability, search and mining; Big data transformations, processing and storage; Big Data management lifecycle, Big data simulation, visualization, modeling tools, and algorithms; Reasoning on Big data; Big data analytics for prediction; Deep Analytics; Big data and cloud technologies; Big data and Internet of Things; High performance computing on Big data; Scalable access to Big Data; Big data quality and provenance, Big data persistence and preservation; Big data protection, integrity, privacy, and pseudonymisation mechanisms; Big data software (libraries, toolkits, etc.); Big Data visualisation and user experience mechanisms; Big data understanding (knowledge discovery, learning, consumer intelligence); Unknown in large Data Graphs; Applications of Big data (geospatial/environment, energy, media, mobility, health, financial, social, public sector, retail, etc.); Business-driven Big data; Big Data Business Models; Big data ecosystems; Big data innovation spaces; Big Data skills development; Policy, regulation and standardization in Big data; Societal impacts of Big data
Social networking small data; Relationship between small data and big data; Statistics on Small data; Handling Small data sets; Predictive modeling methods for Small data sets; Small data sets versus Big Data sets; Small and incomplete data sets; Normality in Small data sets; Confidence intervals of small data sets; Causal discovery from Small data sets; Deep Web and Small data sets; Small datasets for benchmarking and testing; Validation and verification of regression in small data sets; Small data toolkits; Data summarization
RDF and Linked data; Deploying Linked data; Linked data and Big data; Linked data and Small data; Evolving the Web into a global data space via Linked data; Practical semantic Web via Linked data; Structured dynamics and Linked data sets; Quantifying the connectivity of a semantic Linked data; Query languages for Linked data; Access control and security for Linked data; Anomaly detection via Linked data; Semantics for Linked data; Enterprise internal data ‘silos’ and Linked data; Traditional knowledge base and Linked data; Knowledge management applications and Linked data; Linked data publication; Visualization of Linked data; Linked data query builders; Linked data quality
Open data structures and algorithms; Designing for Open data; Open data and Linked Open data; Open data government initiatives; Big Open data; Small Open data; Challenges in using Open data (maps, genomes, chemical compounds, medical data and practice, bioscience and biodiversity); Linked open data and Clouds; Private and public Open data; Culture for Open data or Open government data; Data access, analysis and manipulation of Open data; Open addressing and Open data; Specification languages for Open data; Legal aspects for Open data; Open Data publication methods and technologies, Open Data toolkits; Open Data catalogues, Applications using Open Data; Economic, environmental, and social value of Open Data; Open Data licensing; Open Data Business models; Data marketplaces
- April 18, 2021
- April 22, 2021