Today, the Internet of Things (IoT) touches every corner of the globe. This demo illustrates how knowledge graphs and semantic reasoning are revolutionizing practices such as predictive maintenance and component management for companies worldwide—from the world’s largest buildings, logistics networks, offshore platforms and industrial plants, to one of nature’s smallest—the bonsai tree.
Bonsai trees are tough to look after with relatively complex and specific needs, so maintaining a garden of 20 (including different species, each with their own preferences no less) is no small feat. Critical to their survival is the question: ‘When should I water?’—asked by their owners daily. Too much water suffocates the tree and rots the roots, too little and it’s not long before years of effort are lost. Even harder is the question of what to do when you’re away from home.
The solution lies in soil sensors that monitor moisture levels for a selection of the trees; reporting their readings every minute. Along with weather data, these readings are processed on a central hub—a Raspberry Pi running the knowledge graph and semantic reasoning engine RDFox. Based on this data, the hub can issue alerts to the owner and control a series of pumps, each of which irrigates a different group of trees. The network of sensors, devices, and pumps, along with the trees themselves, are represented as a graph in RDFox, capturing functional properties and their relationships. By incorporating real-time sensor data and applying semantic reasoning, the system intelligently determines when individual trees need watering, activating the appropriate pump and giving the thirsty plants the drink they need.
Although clearly simplified in this scenario, the same principles can be scaled up to the vast and complex situations found in industry and nature. By using semantic reasoning in local hubs, IoT capabilities, industrial control and maintenance, and predictive analytics can be pushed out to the edge, bringing several benefits to real-world situations such as a complex of buildings, ships, or processing plants. By optimizing the device network, upfront capital can be reduced alongside ongoing operational costs. The same can be said for the system being monitored by improving the efficiency of the system itself and increasing the lifespan of its assets through reduced wear.
With this demo, we’ll show how this can all be achieved with a knowledge graph.
The team behind Oxford Semantic Technologies started working on RDFox in 2011 at the Computer Science Department of the University of Oxford with the conviction that flexible and high-performance reasoning was a possibility for data-intensive applications without jeopardising the correctness of the results. RDFox is the first market-ready knowledge graph designed from the ground up with reasoning in mind. Oxford Semantic Technologies is a spin-out of the University of Oxford and is backed by leading investors including Samsung Venture Investment Corporation (SVIC), Oxford Sciences Enterprises (OSE) and Oxford University Innovation (OUI).