Ekkono is an embedded edge machine learning engine, purpose-built for IoT (Internet of Things). The unique design makes it resource efficient with an unusually small footprint. Still, Ekkono does not compromise on functionality:
Simulation of alternative scenarios
Guaranteed confidence calculations on predictions
Ekkono is 100% software and totally platform-agnostic. It is designed for programmers and offers bindings to several programming languages (e.g. C, C# and Python). You need little to no data science background since it comes with tools that decorate data, select machine-learning technique, and optimize algorithms.
The use cases include predictive maintenance, self- healing of faults, alerts when a system deviates from normal behavior, scheduled rather than unscheduled maintenance, optimization of production and performance, more intuitive human-machine interaction, genuine personalization, and tailored recommendations.
This translates into money. Either by being one step ahead of an issue, or one step ahead of the competition:
Less unscheduled downtime and maintenance
Maximum performance through tailored optimization
New business models and added-value services
Lower communication cost
Better use of available processing capacity
Improved costumer loyalty through stickines
Ekkono means cognition, and that is what we add to IoT (Internet of Things). We make connected things smart by embedding advanced machine learning at the edge – on the connected device. This empowers IoT to realize its true potential, where companies save and make money through predictive maintenance, automation and production optimization, and where products become self-learning and intuitive.
Ekkono’s uniqueness, which is the result of seven years of research at the University of Borås, Sweden, is a lightweight machine learning engine that can run on small hardware platforms. It runs closer to the data source, e.g. sensors, on the device, where it can see and process alldata, in real-time, and take instant actions. This reduces network load, make things less dependent of connectivity, and improves data security.