The increase in food safety information quantity (e.g. through online sources) and diversity (e.g. information from social networks vs. structured surveillance programmes), results into a need to adequately discover and display information about food threats in a way that is customized to the user’s specific context and environment, in a highly usable and integrated format. Foodakai would like to take advantage of the identified business opportunity by harmonizing and making more user-friendly the discovery of information on foodborne diseases, food alerts, outbreaks and recalls. We aim to innovate the way information is discovered today, by combining and harmonizing food product recall and foodborne disease data from various, heterogeneous and dynamic online sources. We plan to apply text and data mining techniques, as well as forecasting and other analytical models, so that Foodakai provides tailored tracking, alerting and warning capabilities to its users. It will also be designed in a way that can allow users to adapt and customise the presented information so that it matches their preferences and information needs in a highly professional way - which contrasts this app from previous one-size-fits-all solutions.

A major sustainability challenge for the European society is moving beyond conventional, industrialised food production and agricultural systems, characterised by a high use of external inputs. Mainstream conventional food production systems are posing a serious threat to the environment and to biodiversity and are becoming increasingly unsustainable due to unacceptable levels of food waste in industrialized countries and to shrinking farmers’ incomes. Alternative systems with reduced use of external inputs have to be promoted , based on i) an optimised use of agricultural biodiversity (hereafter ‘agrobiodiversity’), ecological processes and natural resources and on ii) improved food systems based e.g. on short supply chain quality food, where consumers play an active role in driving produce demand and consequently offer. CAPSELLA will address this challenge in two ways: (a) raising awareness on these issues especially within and among local communities (smallholders agriculture, biodiversity, food quality) but also within the broader European public, and (b) offering innovative ICT solutions that will address needs and requirements coming from the communities. To achieve this we will use a combination of participatory bottom up data collection and top down data integration to develop solutions for two domains: agrobiodiversity and local food knowledge. The project aims to (a) build from scratch open data repositories concerning regional agrobiodiversity, and (b) to build upon and enhance existing data sets on the agrobiodiversity and food domains. Based on these, the project will develop a number of community-driven data powered ICT solutions, which will be tested by the communities engaged in the project and will result in a number of pilots. Finally, our project will have a strong societal and business sustainability focus by also including incubation activities for selected pilots.

BigDataEurope will provide support mechanisms for all the major aspects of a data value chain, in terms of the employed data and technology assets, the participating roles and the established or evolving processes. The effectiveness of the provided support mechanisms will be assessed in different domains pertaining to Europe’s major societal challenges with respect to the needs and requirements of the related communities. To this end, BigDataEurope focuses on providing an integrated stack of tools to manipulate, publish and use large-scale data resources; tools that can be installed and used freely in a customised data processing chain with minimal knowledge of the technologies involved and integrating and industrially hardening key open-source Big Data technologies and European research prototypes into a Big Data Integrator Platform, i.e. an ecosystem of specifications and reference implementations that are both attractive to current players from all parts of the data value chain while also lowering the entry barrier for new businesses. In order to realise its objectives, Big Data Europe will focus on two clearly defined coordination and support measures: 1. Coordination: Engaging with a diverse range of stakeholder groups representing particularly the Horizon 2020 societal challenges Health, Food & Agriculture, Energy, Transport, Climate, Social Sciences and Security; Collecting requirements for the ICT infrastructure needed by data-intensive science practitioners tackling a wide range of societal challenges; covering all aspects of publishing and consuming semantically interoperable, large-scale data and knowledge assets; 2. Support: Designing, realizing and evaluating a Big Data Aggregator platform infrastructure that meets requirements, minimises the disruption to current workflows, and maximises the opportunities to take advantage of the latest European RTD developments, including multilingual data harvesting, data analytics, and data visualisation. BigDataEurope will implement and apply two main instruments to successfully realize these coordination and support measures: a) Build Societal Big Data Interest Groups in the W3C interest group scheme and involving a large number of stakeholders from the Horizon 2020 societal challenges as well as technical Big Data experts; b) Design, integrate and deploy a cloud-deployment-ready Big Data aggregator platform comprising key open-source Big Data technologies for real-time and batch processing, such as Hadoop, Cassandra and Storm. BigDataEurope aims to provide an adaptable, easy to deploy and use solution, which will allow the interest-ed user groups and stakeholders to extend their Big Data solutions or introduce Big Data technology to their business processes, based on a concrete methodology for producing a technically sound solution and maximizing its outreach to the relevant communities.