Towards Knowledge Infusion for Robust and Transferable Machine Learning in IoT

Presented at: Open Journal of Internet Of Things (OJIOT)

Machine learning (ML) applications in Internet of Things (IoT) scenarios face the issue that supervision signals,such as labeled data, are scarce and expensive to obtain.

Discover more

Tutor4RL: Guiding Reinforcement Learning with External Knowledge

Presented at: AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering 2020

We introduce Tutor4RL, a method to improve reinforcementlearning (RL) performance during training, using externalknowledge to guide the agents’ decisions and experience.

Discover more

Extensible Data Skipping

Presented at: 2020 IEEE International Conference on Big Data

Data skipping reduces I/O for SQL queries by skipping over irrelevant data objects (files) based on their metadata. We extend this notion by allowing developers to define their own data skipping metadata types and indexes using a flexible API.

Discover more

Scalable Enrichment of Mobility Data with Weather Information

Presented at: GeoInformatica Journal (Springer)

More and more real-life applications for mobility analytics require the joint exploitation of positional information of moving objects together with weather data that correspond to the movement.

Discover more

Policy4Data Policy Brief

This policy brief reflects current developments within the several Big Data research projects funded under H2020 and, combined with insights from the BDV PPP summit in Riga 1, aims to contribute to ongoing challenges in Europe around the regulation of big data.

Discover more

Variational Bayesian Context-aware Representation for Grocery Recommendation

Grocery recommendation is an important recommendation use case, which aims to predict which items a user might choose to buy in the future, based on their shopping history. However, existing methods only represent each user and item by single deterministic points in a low-dimensional continuous space.

Discover more

Big data skipping in the cloud

Cloud compute and storage services should be deployed and managed independently; huge datasets need to be shipped from the storage service to the compute service to analyse the data.
Data skipping is a technique which minimizes the amount of data sent across the network for SQL style analytics on structured data.

Discover more

Integration of Mobility Data with Weather Information

Mobility databases usually do not contain weather information, thus hindering the joint analysis of mobility and weather data. Motivated by this evident need of many real-life applications, in this paper, we develop a system for integrating mobility data with external weather sources.

Discover more

Fog Function: Serverless Fog Computing for Data Intensive IoT Services

To achieve both flexibility and efficiency, we propose a data-centric programming model called Fog Function and also introduce its underlying orchestration mechanism that leverages three types of contexts: data context, system context, and usage context.

Discover More

Reinforcement Learning based Orchestration for Elastic Services

In order to provide this adaptation efficiently, we propose a Reinforcement Learning (RL) based Orchestration for Elastic Services

Discover more