• Collaboratively administrate empowered markets via plug-and-play networks. 


    Adding Knowledge to IoT


    IoT connectivity and Artificial Intelligence services provide almost unlimited new ways of capturing and analysing a wealth of structured & unstructured data. By using a single, common, knowledge automation tool as the brain of the data ecosystem, real business value can be achieved in the form of expert automated decisions.



    In this sample

    In this sample, a Knowledge Base authored in XpertRule Web Author acts as the intelligent hub for multiple data sources to drive decision making in a Heating, Ventilation & Air Con (HVAC) system. The specific technologies include: 

    XpertRule Web Author (Design Environment)
    XpertRule Node.js Runtime Environment (installed on a BlueMix Instance)
    IBM Watson IoT Platform (for communication with IoT hardware)
    Raspberry Pi running IBM IoT client software
    IBM Alchemy Vision (to count number of people in an image)
    IBM Insights for Weather (for current weather conditions)


    How it works

  • pi

    Edge devices – allow us to collect and interpret real-time data at source, in this case, a Raspberry Pi connected to sensors reading room temperature and lighting


    Cognitive services – enable us to extract meaningful data from unstructured and abstract sources such as photos, images, speech. In this case, IBM Alchemy Vision interprets the number of people in a room from photographs


    Analytics servicesenable us to extract critical information from huge and varied data sources. In this case IBM Insights for Weather give us weather conditions for a chosen location

  • Applied Knowledge

    So the question now is how to interpret and take action on this combination of data using applied knowledge. Our sample uses the following flow of logic and decision making:


  • Option 1



    Option 2


    The main tree reads the current sensor values, converts the thermostat value into Celsius, works out the HVAC state based on the sensors and finally allows the environmental factors to override the default HVAC setting.



    A formula-builder operation to convert the thermostat value from Fahrenheit to Celcius


    The main HVAC tree was automatically built from a set of sample cases. It utilizes various sub-trees (shown in the next slide) to provide a symantic representation of the knowledge


    The various sub-trees which provide a symantic representation of the underlying sensor values



  • The environmental override tree performs image recognition to determine the number of people in the image


    If there are no people in the image, the HVAC is turned off. If there are only a few people in the room, it retrieves the external temperature and checks to see if the outside air can just be vented into the room to provide the desired cooling or heating. If there are more than 4 people, the automatic HVAC setting is unchanged.


    And finally the original HVAC decision is updated.


  • Edge Device




  • Try Now & Live Demos