Information and Communication Technologies has made available a huge amount of heterogeneous data in various real application domains. For example, in the urban scenario, Internet of Things (IoT) systems capture massive data collections describing the overall urban environment and citizen exploitation and perception of available services. In health care systems, electronic health records allow storing various information about patients as adopted treatments and monitored physiological conditions. At the same time, the Internet of Medical Things (IoMT) ensures the availability and processing of healthcare data through smart medical devices and the web. Moreover, in most domains, individuals play a crucial role in generating data on the one side, driving a user and context-aware analysis process, and finally demanding easily accessible and understandable knowledge at the end of the process.
Digging deep in these data collections can unearth a rich spectrum of knowledge in the targeted domain valuable to characterise user behaviours, identify weaknesses and strengths, improve the quality of provided services or even devise new ones. However, data analytics on these data collections is still a daunting task because they are generally too big and heterogeneous to be processed through available data analysis techniques. Consequently, various challenges about data science arise dealing with the creation, storage, search, sharing, modelling, analysis, and visualisation of data, information, and knowledge.
Suitable data fusion techniques and data representation paradigms should be devised to integrate the heterogeneous collected data into a unified representation describing all facets of the targeted domain. Moreover, a massive volume of data demands the definition of novel data analytics strategies that exploit recent analysis paradigms and cloud-based platforms such as Hadoop and Spark. Proper strategies can also be devised for data and knowledge visualisation, possibly also involving interactive user interfaces.
The workshop aims to allow academics and practitioners from various research areas to share their experiences designing cutting-edge analytics solutions for real-life applications. Researchers are encouraged to submit their work-in-progress research activity describing innovative methodologies, algorithms, and platforms that address all facets of a data analytics process that provides interesting and useful services.
Industrial implementations of data analytics applications, design and deployment experience reports on various issues raising data analytics projects are particularly welcome. We call for research and experience papers and demonstration proposals covering any aspect of data analytics solutions for real-life applications.
Topics of interest
We invite the submission of work-in-progress research addressing various aspects of data management and analytics for real-life applications. The workshop welcomes submissions of technical, experimental, methodological papers, application papers, and papers on experience reports in real-life application settings addressing – though not limited to – the following topics:
Data management and analytics
Methodologies, models, algorithms, and architectures for applied data science
Big Data frameworks and architectures
Data warehouses and large-scale databases
NoSQL and NewSQL databases
Energy-efficient computing
Metadata management
Scalable and/or descriptive analytics algorithms
Concepts, transparency methodologies, innovative and transparency solutions for sensing, modeling, managing, mining, understanding citizens behavior, perceptions, activities, desiderata, and needs
Real-time data analytics
Machine learning and deep learning techniques
Reinforcement learning models
Next-Generation Sequencing data analysis
Cloud computing techniques for data science
Parallel and distributed computing for data science
Performance optimization and benchmarks
Crowdsourcing and collaborative analyses
Personalization and recommendation techniques for Big and Small Data
Question answering techniques and systems
Visualization methods for data-intensive applications
Privacy-aware access and usage control
Privacy and security policies enforcement mechanisms
Privacy-preserving data allocation and storage
In one of – though not limited to – the following application scenarios:
Bio-sciences and healthcare
Internet of Things
Network traffic analytics
Urban economy and urban environments
Government transparency and IT against corruption
Public safety and disaster relief
Transportation
Energy
Financial applications
Customer relationship management
Agriculture
Mobile applications
e-commerce
Business analytics and finance
User-generated content (like tweets, micro-blog)
Industry 4.0
Data journalism
Education
Ethical issues, fairness and accountability