DeviceHive’s Kinesis plugin


Amazon Kinesis makes it possible to build custom applications that process and analyze streaming data. With Amazon Kinesis, the user can ingest real-time data such as video, audio, application logs, website clickstreams, and IoT telemetry data for machine learning, analytics, and other applications. The user can access data in real-time, and Kinesis is secure and easy to use. Users can also have multiple Kinesis applications processing the same stream, the throughput of which can scale from megabytes to terabytes per hour.

Amazon Kinesis can

DeviceHive’s Blockchain Plugin


Today blockchain is one of the most popular technologies available given the security and reliability it offers users. Based on these factors, there is a significant chance that it become the standard in many industries. Therefore, any blockchain-integrated ecosystem is equally likely to become a future industry standard as well. It’s public, but protected; it’s decentralized and secure, all these properties make blockchain very attractive compared with other technologies.

Many experts believe that Blockchain technology is the missing link that can address security, privacy

Tutorial: Implement Object Recognition on Live Stream


Image recognition is very widely used in machine learning. There are many different approaches and solutions to it, but none of them fitted our needs. We needed a completely local solution running on a tiny computer to deliver the recognition results to a cloud service. This article describes our approach to building an object recognition solution with TensorFlow.



Sound Classification with TensorFlow


There are many different projects and services for human speech recognition like Pocketsphinx, Google’s Speech API, and many others. Such applications and services recognize speech to text with pretty good quality, but none of them can determine different sounds captured by the microphone. What was on record: human speech, animal sounds, or music playing?

We were faced with this task and decided to investigate and build sample projects which will be able