Page 41

EETE JUNE 2013

Models residing on the accessory will be cost and poweroptimized to create a sensing platform for multi-sport activity monitoring, providing high quality sensor data that will then be processed on mobile devices for compelling applications, such as activity monitoring, sleep analysis, and sport performance tracking. A third-party data source Beyond sensors on the device, third party and external data are necessary to create the next generation of intelligent applications. Data from users’ GPS, agenda, email, the cloud and social networks are collected and processed by data fusion models, enabling application developers to quickly and easily integrate useful functions into their smart apps. Data fusion models can be device models, based on data processing from the phone, such as an indoor map, a user’s agenda or habits, or processed data from the cloud. The cloud model can leverage data from a Facebook or Twitter API, Big Data analysis connection, etc. Using models that combine sensor data with external data enables applications developers to create more integrated apps, delivering intelligent services based on their location, activity, agenda, weather, etc. Data fusion as a service The data fusion service functions at the operating system layer, merging sensors, device and cloud models, enabling applications developers to create advanced intelligent applications. Data fusion service manages models and data fusion models (installation, enumeration, instantiation) with messages that define management features. These messages can be between multiple data fusion models, or between data fusion models and the application interface. Merging different data sources and formats is an ecosystem challenge and should be tackled automatically and systematically. Many sources of data in vastly different formats need to be accommodated across heterogeneous networks. Solutions need to be tuned to new data types and new use cases. Different data rates, data synchronization, and data loss need to be taken into account, which is why smart apps integrating several complex data sets are not easy to create. In addition, effective learning strategies need to be implemented when no a-priori knowledge exists about mappings from data to response. The challenges are due to a lack of data and metadata representation standards in the industry. Then if we extend the model and enable third parties to contribute to data fusion models, adding bricks and models to offer additional services, it is uncertain that they could all work together, hence the need for standards. Data fusion opens new opportunities for smarter applications to do the following automatically, for example: • Turn off a cellphone when entering a theater • Analyze activity and schedules to indicate the best route to an appointment • Locate where you are, what you are doing (walking, sitting, running) and send useful notifications in certain situations. For example, notifying you when your train is late, so you can One less hat to wear. Let us be your power expert. We understand that you don’t have the time to master every aspect of electronic design. As a leading manufacturer of power supplies we are here to collaborate with you to ensure your next project is a success. Novum® Advanced Power Ac-Dc Power Supplies Dc-Dc Converters www.cui.com/PowerExpert www.electronics-eetimes.com Electronic Engineering Times Europe June 2013 33


EETE JUNE 2013
To see the actual publication please follow the link above