"The launch of Apple Watch has meant that wearable technologies – and smart watches in particular – are getting a lot of attention. Business Insider estimates that the smart watch will be the leading product category on the wearable market and will account for 59% of total wearable device shipments this year, expanding to just over 70% of shipments by 2019. Paired with a smartphone, smart watches can offer rich functionality across a number of verticals like healthcare, travel, the smart home, IoT and capital markets. Their future, however, is tied to two factors:
Here’s what needs to be understood. Smart watches are not another type of a mobile device. They’re a new generation of technology, and call for a whole new approach to application design. For your app to thrive, you need to account for three basic realities:
- The reliability of the hardware;
- Stellar services that could empower the people wearing wearables.
DataArt design and R&D teams took all of the above into consideration when developing the approach for developing apps for wearables. We realized that whatever experiences the app is expected to deliver they should be achieved in fewer than three taps, which requires prioritizing notifications and assuring the app doesn’t become “spammy”, driving users away."
- The screen has a limited amount of space;
- The user flow is entirely different from those of mobile applications;
- Users expect a personalized experience.
- Asthma Health by Mount Sinai. By Icahn School of Medicine at Mount Sinai;
- Parkinson mPower study app. By Sage Bionetworks, a Not-For-Profit Research Organization;
- GlucoSuccess. By The Massachusetts General Hospital;
- Share the Journey. By Sage Bionetworks, a Not-For-Profit Research Organization;
- MyHeart Counts. By Stanford University.
The DataArt IoT / M2M practice is happy to finally present the new release version of the open source IoT / M2M communication platform DeviceHive 1.3.0. The framework was developed to allow users to concentrate more power in innovation & focus on how the machines & gadgets will communicate, instead of the type of data they transmit and what the overall end-user experience could be. This fall the new big things with extended security support and scalability are coming.
You can view more details here.
The new DeviceHive release has the integration with Docker – so version 1.3.0 is now cloud-compatible! Now all deployments to the cloud are easy to make. In previous versions of DeviceHive, the issue of server deployment was resolved by a set of complex scripts that required a very specific environment - not a handy thing.
DeviceHive’s new infrastructure deployment approach provides quick and easy server deployment. DeviceHive Java server is now integrated with Docker, which makes deployments to cloud environments extremely easy. This platform allows fast deployment of the new DeviceHive servers in any Docker-compatible environment, and migration of the configured DeviceHive servers to other hardware or virtual platforms.
The short instruction of how to quick start using Docker is at the DeviceHive site.
To fully enjoy the new DeviceHive 1.3.0, please, use the links below.
Eat’n’Click is an application developed by DataArt that helps people track the nutritional content of foods they consume. The app automatically tracks calorie information by scanning photographs of food.
Its prototype is available on the App Store and can recognize a number of fruits with more than an 85% success rate. Recently the application was demonstrated by the DataArt team during the Health 2.0 Europe 2014 event in London and was highly appreciated by its participants.
Following industry trends and the high attention Apple HealthKit is receiving, DataArt’s Research Lab decided to move forward by automating the tracking of users’ nutrition habits. DataArt is planning to build a PoC prototype to integrate with Apple HealthKit. Also, we plan to implement a voice recognition engine with it. The aim of DataArt’s Orange R&D initiative is to reduce the gap between humanity and computers. And we strongly believe that this step will be highly effective.
- in everyday life we do not deal with ideal pictures: the photos may contain different distortions, irregular brightness etc.;
- the classifier of Euclidian distance cannot provide us with real time work, particularly if we have a lot of classes and etalons.
The color distance method has been tested using 15 fruit types, each type having 10 photos. The following recognition score calculation algorithm has been used:
- Three guesses (ordered best to worst) are considered.
- A correct guess placed first obtains 10 points, placed second – 5, placed third has 1.
- For all tests for a particular fruit type the obtained points are summed up and divided by the absolute maximum result 10 * N, where N – the number of tests for the class, thus yielding the classification quality for the type.
- The overall classification quality for the whole fruit set, the individual classification qualities for every fruit type are averaged.