27 February - 1 March 2018 // Nuremberg, Germany

Conferences and supporting programme

back to day overview
Session 23 - Autonomous Systems IV Machine Learning

Python-based Framework for Analytics / Neural Networks in Industrial IOT Vortragssprache Englisch

By 2020 forecasts are calling for over 25 Billion devices to be Internet Connected. These connected Internet of Things (IoT) platforms provide intelligence from a broad spectrum of sensor input. These IoT platforms will require and must provide increased levels of intelligence and control of their systems and the surrounding environment they reside in. With the combined configurable IO, software Intelligence and hardware optimization in a single device, Programmable SoCs provide an ideal platform for architecting and implementing these IoT platforms. This paper describes a new innovative open-source Python based productivity framework and infrastructure that effectively binds Programmable SoC hardware around Python simplifying the addition of ad-hoc hardware modules in the programmable logic. The primary goal of the open source framework is to make it easier and rapidly enable designers of embedded systems to exploit the unique benefits of programmable SOCs in IoT and other applications. Specifically, the framework enables architects, engineers, and programmers to design Programmable SOC-based embedded systems without having to use ASIC-style design tools to design programmable logic circuits. This innovative approach provides sufficient abstraction for all the main actors: data scientists, embedded engineers, hardware engineers and system engineer to implement the intelligence critical to IoT platforms. Instead of the traditional approach, focusing on beginning with the hardware and moving to software, the Python-based framework provides an early stage platform development that starts from software for an immediate use, then it delivers all the methods and instruments to improve performances and capability diving into the HW. This top down approach makes the programmable logic, visible as a library. The paper/presentation will cover real world example implementations, utilizing the standard Jupyter Notebook browser based interactive computing environment templates for ease of programming in Python, in terms of applying intelligence to architect a programmable SOC-based IoT platform. the presentation will conclude with a live demo of this new approach to easily and rapidly design these embedded IoT platforms.

--- Date: 28.02.2018 Time: 3:00 PM - 3:30 PM Location: Conference Counter NCC Ost

Speakers

top

The selected entry has been placed in your favourites!

If you register you can save your favourites permanently and access all entries even when underway – via laptop or tablet.

You can register an account here to save your settings in the Exhibitors and Products Database and as well as in the Supporting Programme.The registration is not for the TicketShop and ExhibitorShop.

Register now

Your advantages at a glance:

  • Advantage Save your favourites permanently. Use the instant access to exhibitors or products saved – mobile too, anytime and anywhere – incl. memo function.
  • Advantage The optional newsletter gives you regular up-to-date information about new exhibitors and products – matched to your interests.
  • Advantage Call up your favourites mobile too! Simply log in and access them at anytime.