Current projects

AI4FoodLogistics

Retail, and the food sector in particular, is a complex environment that requires close cooperation between multiple partners. At the same time, the sector continuously strives to increase efficiency and sustainability, e.g., by reducing waste. However, although all organizations within the supply chain are connected, data often remains stored in silos within each separate company. Within AI4FoodLogistics, we are exploring a federated data ecosystem that brings together data from different stakeholders in the retail ecosystem. The resulting insights will enable optimized forecasting and the development of intelligent algorithms.

Comunica - RML


BoB

Building Information Modelling (BIM) allows making elaborate, information-rich models of building designs. However, there is no easy way yet to couple these models to what is actually happening on-site, during a construction. The BoB project aims to create a 2-way link between BIM models and the actual building, improving building efficiency and avoiding costly errors.

RML


FRACTION

Today, centralized stores govern the storage and processing of Big Data. Due to regulation (e.g. GDPR) and increasing awareness of people about data sensitivity, a paradigm shift towards decentralization is imminent. This allows people to control their own personal data, by guarding all public and private data they or others create about them in a vault, and selectively granting access to people and organizations of their choice. Future uses of Big Data are thus bound to shift from a small number of large datasets to a large number of small datasets. As such, the fundamental assumptions on which the current approaches are built to deal with the characteristics of Big Data (Volume, Variety & Velocity) are no longer valid, i.e. volume cannot be tackled by centralising data in a single location, high velocity data streams cannot be sent to a centralised data center and the variety problem cannot be resolved by imposing a single data format. FRACTION supports the shift to a decentralized approach by leveraging Semantic Web technologies. It will investigate 1. algorithms that autonomously distribute the analytics across the decentralized network, while hiding its complexity to the user, 2. decentralized and user-friendly data access control policies, and 3. methods to exploit the heterogeneity of the decentralized network to improve scalability and performance of the analytics.

Decentralization - Decentralized scheduling of heterogeneous resources - Semantic reasoning and querying


MareGraph

MareGraph will build a data architecture for cost-efficient, flexible and sustainable data sharing for a Marine Knowledge Graph. In this project we will collaborate with the Flemish Marine Institute (VLIZ), Digital Flanders and the Italian National Research Council (CNR).


Mellon Scholarly Communication

At the basis of this project is a vision of a researcher-centric, institution-enabled scholarly communication system, aligned with the Decentralized Web concepts and technologies, in which researchers use a personal domain and associated storage space as their long-term scholarly hub, and in which the core functions of scholarly communication are fulfilled in a decoupled manner.

Comunica - Solid


Onto-DESIDE

The Onto-DESIDE (Ontology-based Decentralized Sharing of Industry Data in the European Circular Economy) will address the main challenges facing industry that prevent the efficient sharing of data and making it understandable and usable by humans and machines. The project targets four core project outcomes: - A shared vocabulary in the form of network of ontologies. - An open circularity platform, i.e. a secure and privacy-preserving decentralised data sharing platform. - Methods to find, analyse and assess the new circular value chain configurations. - Validation – demonstrating and quantifying the potential for increased retainment of value.

Solid


POSH

POSH (Predictive Optimized Supply Chain) will research and realize methods and software solutions that leverage on the availability of big data to optimize integrated procurement and inventory management strategies. Within the scope of this project, we mainly focus on applications within B2B manufacturing supply chains, incorporating all actions required to bring parts from suppliers to the production or assembly manufacturing companies producing finished products for the consumer market.

RML - RMLMapper - YARRRML


RE-ENNOVATE

RE-ENNOVATE is an ambitious 3-year project to make home renovation smarter, cheaper, faster and better and re-innovate the process of energetic renovation. As the need for more energy efficient homes is only amplified by the current energy crisis, new tools are necessary for homer owners and professionals to understand which renovation measures work for them. With novel data-driven methods, RE-ENNOVATE will make the benefits and cost of renovations more transparent to individuals, propose personalized renovation packages, and increase automation, while continuously improving all steps by a closed feedback loop. The research consortium includes WTCB, imec, Ghent University, Adaptive, Mosard, Scone, Leuven2030 and Vandereyt. The project runs in cooperation with Flux50 and VLAIO.

Streaming MASSIF


SolidLab

To reinforce the trust of its citizens and help companies compete against internet giants, Flanders is leading the race to set a new standard in data protection. A EUR 7 million government investment is providing a major boost for the practical implementations of a technology called Solid. Three of Flanders’ leading universities are joining forces in SolidLab Vlaanderen.

Comunica - LDES - RML - Solid - TREE


Past projects

BESOCIAL

BESOCIAL is a cross-institutional research project, aiming to develop a sustainable strategy for archiving and preserving social media in Belgium. Heterogeneous social media content, provenance information provided by web archivists as well as preservation metadata enclosed in web archive (WARC) files characterize this use case.

RML - RMLMapper - YARRRML


COMBUST

The opportunities of big data are tremendous. However, it is still a major challenge to combine available data from various heterogeneous sources and put it on offer in a way that is reliable, trustworthy and a good business case for the data owners. The COMBUST project was set up to create solutions and guidelines for this data fusion challenge, in a realistic setting and in view of offering a valuable data service.

RML - RMLEditor - RMLMapper


DAIQUIRI

During sports events, athletes use wearables and sensors to track their performances. Currently, this data is used for coaching, yet it might be useful for covering the events as well. As such, new Artificial intelligence (AI) applications in professional sports based on sensors, wearables and video data might enrich live sports reporting. However, a platform capable of turning insightful sports data into stories for live commenters, content editors or viewers does not yet exist. The DAIQUIRI project will develop AI algorithms that address current challenges associated with data overload, sensor-video matching, dynamic captioning and multi-modal stories. The outcome will be a sensor data platform and dashboard that supports media professionals in their live sports coverage and the audiences’ viewing experiences.

RML - RMLStreamer


DiSSeCt

DiSSeCt aims to design distributed semantic software solutions and algorithms for continuous exchange of huge streams of data between different partners in specific ecosystems. By converting data to knowledge, and exchanging this knowledge in an intelligent, secure and dynamic manner, personalised and context-aware services can be offered to end-users.


DyVerSIFy

Mining sensor data can give companies valuable insights into their assets and activities. But as technology advances, analyzing and visualizing the data becomes increasingly time- and resource-intensive. The DyVerSIFy project aims to develop software components and methodologies in the domains of dynamic visualization, adaptive anomaly detection and scalability to drive dynamic, adaptive and scalable sensor analytics.

RML - RMLEditor - RMLStreamer


EcoDaLo

Media companies in Flanders today have fragmented consumer data, with each company maintaining its own data management platform. As a result, data remains largely undervalorized. The EcoDaLo project aims to develop a knowledge platform for publishers allowing the integration of many diverse data sources.

RML - RMLMapper - YARRRML


ESSENCE

Human perspectives into a smart city platform that collects many media types, from personal devices and public displays to augmented reality. The ultimate goal is to create interactive stories embedded in the city environment about civic actions that boost engagement in these projects.

RML - RMLStreamer


FAST

Complicated rules, multiple contact points, numerous forms and applications and three administrative levels: processes as common as home renovations in Flanders require a lot of manual administrative work. To streamline customer journeys and simplify processes, municipalities and other public organizations would benefit from e-government applications. However, implementing these solutions is challenging, considering the lack of well-structured content and the need to integrate legacy systems. FAST aims to tackle the challenges to e-government adoption by creating an engine to automatically generate customer journeys from existing unstructured content – the ideal collection of digital interaction points between public services, organizations and citizens – for a range of public tasks.


FREME

The aim of the FREME innovative action is to establish an “Open Framework of E-Services for Multilingual and Semantic Enrichment of Digital Content”. Six enrichment services will be designed, piloted, and validated during the action. Their innovation, usability, and robustness will be shaped by four real world business cases that will bring FREME data innovation and technology transfer directly to the market: (1) authoring and publishing multilingually and semantically enriched eBooks; (2) integrating semantic enrichment into multilingual content during localisation; (3) enhancing cross-language sharing and access to open data and (4) empowering personalised content recommendations.


Hello Jenny

Hello Jenny aims to help senior citizens who have no or limited contact with friends or family. It does this by providing a smart speaker to the senior citizen which allows them to schedule a visit with their assigned buddy. An analysis is performed to determine when a senior needs a visit and suggests this to the senior if this is the case.

N3 - RML - RMLMapper


Hybrid AI for Buildings

To convert office buildings in truly sustainable (to meet climate goals), comfortable & healthy (to improve employee wellbeing and related productivity) and flexible spaces (supporting the balance between telecommuting and on site working) extra (smart) services are needed to help building & facility managers to decide on building upgrade investments, optimally allocate office spaces and optimally control HVAC systems. Such services require access to a broad range of data sources (HVAC data, user feedback, BIM models, etc.) via easy accessible interfaces, but current deployment requires a lot of (manual) work as data is often distributed over many systems, using different protocols and data models. There is a clear need to extend the interoperability capabilities between stakeholders and service providers involved in the building lifecycle, to enable a rapid scaling to many buildings. Hybrid AI for buildings is an imec.AAA project focusing on designing tools and algorithms to easily design building optimization services by leveraging a semantic model for interoperability and easily supporting the design of novel AI services based on this semantically enriched data.

LDES - Streaming MASSIF


i-Learn

Technical support concerning data modeling and integration for the i-Learn framework


MOS2S

The MOS2S project focuses on media orchestration platforms and technologies that allow devices, data and media streams to be orchestrated into a rich and coherent media experience on various end-user devices. Applications include crowd journalism and live events (experience and entertainment).

RML - RMLMapper


Smart Water Way

The volume of roadway traffic is steadily increasing in Belgium despite the introduction of tolls. Consequently, there is a strong focus on increasing quality of life in urban areas by moving last-mile logistics (LML) to local waterways. To drive this modal shift, the SmartWaterWay project will make autonomous pallet shuttle barges cost effective in urban settings by combining low-cost onboard sensors with onshore sensors equipped at bridges, locks and bays.