Use cases

The E2Data project needs to respond to diverse and strict requirements, in terms of performance and infrastructure costs. Such requirements are driven by the four participating use cases, in the following domains:

Health Use Case

It is necessary to improve the predictive capability of a hospital readmission risk prediction algorithm. To achieve this, the patient discharge profile is enhanced with profiles of highly correlated patients (in terms of recent hospital activity). The patient correlations are established based on their medical conditions. The algorithmic solution enters into time sensitive matrix calculations which need to be accelerated appropriately.

Fintech (Natural Language Processing)

Processing of unstructured data (text) is a powerful tool to extract knowledge from articles and messages, including social media. Processing of such online streams within the financial sector is useful when you need to correlate financial news with trade facts; also useful in several other business domains where sentiment analysis needs to be applied (i.e. tourism). In E2Data, we focus on processing large amounts of messages from social media, such as Twitter, in order to perform semantic information extraction, sentiment analysis, summarization, interpretation and organization of their contents. Critical language processing algorithms are falling in the critical path in the knowledge extraction process; therefore, acceleration is considered as a solution towards enhanced performance.

Green Building Infrastructure

Management and monitoring of buildings employs an Internet-of-Things (IoT) Framework cloud platform with high scalability both in terms of users, number of connected devices and volume of data processed. It accommodates real-time processing of information collected from mobile sensors and smartphones and offers fast analytic services. The Cloud Services offer real time processing and analysis of unlimited IoT data streams with minimal delay and processing costs.

Security and biometric recognition

Biometric authentication, using facial recognition, is fast becoming a mainstream method of authenticating customers for high value transactions, such as the creation of Bank Accounts, issuing of Travel Visas and unmanned border crossing by pre-registered users. Such processes are coupled with tight SLA to ensure user experience is maintained, even when a single transaction involves the processing of 30 images and the execution of deep neural networks. The nature of security results in the complexity of processing that is continuously increasing. E2Data will be asked to both optimize the cost base of the platform and automate the performance optimization of code which is currently undertaken by highly skilled engineers.
This project has received funding from the European Union's Horizon H2020 research and innovation programme under grant agreement No 780245.