IoT middelware for Anomaly Detection

Phileas framework give you access to last academic research on IoT behaviours analytics with Machine Learning. Severals mathematical models are adapted and tuned for IoT behaviours, forming a framework of good practice knowledge.

Data visualisation

Anomaly Detection Graph n°1 Anomaly Detection Graph n°2


Data and MetaData Audit
Your IoT log data is precious. It can be the starting point of an investigation to detect anomalies that have not been spotted yet

Real Time Analysis
Our framework is designed to be used with BigData technologies, like ‘Spark streaming’™ for scalable real time analytics.

Belgian Academic Data Center
Calculation can be operated on your infrastructure, on the cloud or on our Academic Data Center for increasing privacy from non-european entities.

Protocol Agnostic
IoT ecosystems have to deal with many IoT protocols and payload formats. As an agnostic framework, Philéas can work with all the existing protocols. Our conversion module can import popular formats such as LoRa, Sigfox, MB-Iot, wifi, Tcp/Ip.

Dashboard Integration
As we focus on anomaly detection, the data visualization through dashboard is crucial to keep you notified and have a clear view on what’s going on on your IoT traffic. The dashboard solutions can be implemented to your current infrastructure. Or we can propose Jupyter notebook and datadog as default dashboards.

Protocol Agnostic

LoRa <
SigFox <
MB-IoT <
Zigbee <
Tcp/ip <

Iot Platform

LoRaWan <
AWS:Ivent <
Azure IoT Suite <
Interact <
AllThingsTalk <
The Things Network <
Google CLoud <

Machine Learning

Autoencoders <
Long short-term memory <
Local Outlier Factor <
Clustering <


Jupyter <
Kibana <
DataDog <
ElasticSearch <

Data Exploration with Phileas