Skip to main content
European Commission logo
English English
CORDIS - EU research results
CORDIS

Anomaly Detection combining time series and unstructured data using AI/ML algorithms in a distributed cloud/edge device scenario

Project description

A smart, automated, accurate and secure anomaly detection module

By 2025, the number of connected devices could reach almost 75 billion globally. The huge amount of data generated will require highly efficient and secure management of these devices (cameras, sensors, thermostats, routers, etc). The EU-funded SmartAD project will support the development of a unique embedded Linux automation, provisioning and security tool. As an SME innovation associate programme project, it will assist Norwegian QBee (qbee.io platform) in the development of an innovative module, namely an automated smart, accurate and secure anomaly detection module. The recruitment of an innovation associate will help to lift QBee to the next innovation stage, where forefront artificial intelligence/machine learning and data analytics skills are demanded.

Objective

IoT has taken the world by storm and in 2025 there will be ~75Bn connected devices, creating an amount of data never generated before. This comes with a new set of challenges, which need to be addressed with regards to IoT device management, especially in industrial settings. Currently, there are limited tools for embedded Linux IoT device management (e.g. cameras, sensors, thermostats, routers, etc), which are not able to effectively manage the devices and keep the IoT infrastructure secure.
QBee offers the qbee.io platform, a unique embedded Linux automation, provisioning and security tool enabling a highly efficient IoT device management with high security focus for the overall IoT infrastructure. With the SmartAD project, QBee targets the development of an innovative module to the platform, namely an automated smart, accurate and secure anomaly detection module, which was identified as top priority to disrupt the IoT devices management tools. Intelligent algorithms can be used for detection of malfunctioning/suspicious behavior using advanced anomaly detection, fingerprinting and the awareness of configuration changes that the device should adhere to. To achieve this, time series data as well as file and configuration changes needs to be analyzed.
Although, QBee has a strong team in the area of full-stack development, system administration, embedded devices (Linux), automation and cloud software scaling, which allowed to bring the product to a beta-version, it is also very small, and currently QBee does not have in-house skills for the next innovation stage, where forefront Artificial Intelligence/Machine Learning and data analytics skills are demanded. The SME Innovation Associate Programme fits the QBee plan on boosting R&D activities and the recruitment of an Innovation Associate will be critical to develop this module which will make qbee.io platform unique in terms of detection & prevention of cyberattacks on industrial IoT infrastructures.

Call for proposal

H2020-INNOSUP-2018-2020

See other projects for this call

Sub call

H2020-INNOSUP-2020-02

Coordinator

QBEE AS
Net EU contribution
€ 129 111,25
Address
ROSENHOLMVEIEN 25
1414 TROLLASEN
Norway

See on map

SME

The organization defined itself as SME (small and medium-sized enterprise) at the time the Grant Agreement was signed.

Yes
Region
Norge Oslo og Viken Viken
Activity type
Private for-profit entities (excluding Higher or Secondary Education Establishments)
Links
Total cost
No data