data

IoT Week Belgrade COSMOS presentation

Madrid Hackathon

NTUA Hackathon Awards Ceremony

NTUA Hackathon

Hardware Security Board

The Hardware Security Board consists of a physical hardware device which provides the link between sensors (data generators) and the COSMOS environment/platform. The Hardware Security Board can be either attached to one sensor or can be a hub for an entire collection of sensors (e.g. temperature, pressure, humidity, surveillance cameras, etc.).

Inference and Prediction

Inference and Prediction functional component is responsible for providing high-level knowledge from raw IoT data using different pattern recognition techniques. In this context, we have explored several supervised machine learning techniques including different variants of Support Vector Machines and K- Nearest Neighbor, in addition to statistical techniques such as Hidden Markov Model (HMM).

Data Pre-Processing

Thing's data pre-processing functional component provides several functions at Things and platform level which are summarized below:

Storlets

Storlets are computational objects that run inside the object store system. Conceptually, they can be thought of the object store equivalent of database store procedures. The basic idea behind storlets of performing the computation near the storage is saving on the network bandwidth required to bring the data to the computation.

Data Mapper

The Data Mapper functional component is responsible for the ingestion of IoT data flowing on the COSMOS Message Bus into the cloud storage, annotating them with enriching metadata.

Situational Awareness

The large volume of data which is made available in an IoT environment does not necessarily mean applications can take effective decisions directly or make correct interpretations. For example, a single vehicle reporting a low speed is not always an indication of a traffic jam.

Pages