mobile | classic
Dataweek Electronics & Communications Technology Magazine





Follow us on:
Follow us on Facebook Share via Twitter Share via LinkedIn


Search...

Electronics Buyers' Guide

Electronics Manufacturing & Production Handbook 2019


 

AI on a chip
26 June 2019, News

There is still no solution which makes it possible to execute and train neural networks on embedded systems, such as microcontrollers. Nevertheless, it can be useful to conduct the training directly in the embedded system, for example, when an implanted sensor is to calibrate itself.

There is still no solution which makes it possible to execute and train neural networks on embedded systems, such as microcontrollers. Nevertheless, it can be useful to conduct the training directly in the embedded system, for example, when an implanted sensor is to calibrate itself.

The vision is sensor-related AI that can be directly integrated in a sensor system. A team of researchers at Fraunhofer IMS has made this vision a reality in the form of AIfES (Artificial Intelligence for Embedded Systems), a machine learning library programmed in C that can run on microcontrollers, but also on other platforms such as PCs, Raspberry PI and Android.

AIfES demonstrator for handwriting recognition. Numbers written by hand on the PS/2 touchpad are identified and output by the microcontroller.
AIfES demonstrator for handwriting recognition. Numbers written by hand on the PS/2 touchpad are identified and output by the microcontroller.

The library currently contains a completely configurable artificial neural network (ANN), which can also generate deep networks for deep learning when necessary. An ANN is an attempt to mathematically simulate the ­human brain using algorithms in order to make functional contexts learnable for the algorithms. AIfES has been optimised specifically for embedded systems.

“We’ve reduced the source code to a minimum, which means the ANN can be trained directly on the microcontroller or the sensor, i.e. the embedded system. In addition the source code is universally valid and can be compiled for almost any platform. Because the same algorithms are always used, an ANN generated for example on a PC, can easily be ported to a microcontroller. Until now this has been impossible in this form with commercially available software solutions,” says Dr. Pierre Gembaczka, research associate at Fraunhofer IMS.

Protection of privacy

Until now, artificial intelligence and neural networks have been used primarily for image processing and speech recognition, sometimes with the data leaving the local systems. For example, voice profiles are processed in the cloud on external servers, since the ­computing power of the local system is not always adequate.

AIfES demonstrator for handwriting recognition. All functions have been integrated on the Arduino UNO, which reads the sensor values of the touchpad, performs number recognition and outputs the result to the display.
AIfES demonstrator for handwriting recognition. All functions have been integrated on the Arduino UNO, which reads the sensor values of the touchpad, performs number recognition and outputs the result to the display.

“It’s difficult to protect privacy in this process, and enormous amounts of data are transmitted. That’s why we’ve chosen a different approach and are turning away from machine learning processes in the cloud in favour of ­machine learning directly in the embedded system. Since no sensitive data leave the system, data protection can be guaranteed and the amounts of data to be transferred are significantly reduced,” says Burkhard Heidemann, embedded systems group manager at Fraunhofer IMS.

“Of course it’s not possible to implement giant deep learning models on an embedded system, so we’re increasing our efforts toward making an elegant feature extraction to reduce input signals.” By embedding the AI directly in the microcontroller, the researchers make it possible to equip a device with additional functions without the need for expensive hardware modifications.

Reducing data

AIfES doesn’t focus on processing large amounts of data, instead, transferring only the data needed to build very small neural networks. “We’re not following the trend toward processing big data; we’re sticking with the absolutely necessary data and are creating a kind of micro-intelligence in the embedded system that can resolve the task in question. We develop new feature extractions and new data pre-­processing strategies for each problem so that we can realise the smallest possible ANN. This enables subsequent learning on the controller itself,” Gembaczka explains.

The approach has already been put into practice in the form of several demonstrators. For example, the research team implemented the recognition of handwritten numbers on an inexpensive 8-bit microcontroller (Arduino Uno). This was made technically possible by developing an innovative feature extraction method.

Another demonstrator is capable of recognising complex gestures made in the air. Here the IMS scientists have developed a system consisting of a microcontroller and an absolute orientation sensor that recognises numbers written in the air. “One possible application here would be operation of a wearable,” the ­researchers point out.

“In order for this type of communication to work, various persons write the numbers one through nine several times. The neural network receives this training data, learns from it and in the next step identifies the numbers independently. And almost any figure can be trained, not only numbers. “This eliminates the need to control the device using speech recognition: the wearable can be controlled with gestures and the user’s privacy remains protected.

There is a huge range of potential applications of AIfES. For example, a wristband with integrated gesture recognition could be used to control indoor lighting. And not only can AIfES recognise gestures, it can also monitor how well the gestures have been made. Exercises and movements in physical therapy and fitness can be evaluated without the need for a coach or therapist. Privacy is maintained since no camera or cloud is used. AIfES can be used in a variety of fields such as automotive, medicine, smart home and Industry 4.0.

Decentralised AI

The AIfES library makes it possible to decentralise computing power, for example by allowing small embedded systems to receive data before processing and pass on the results to a superordinate system. This dramatically reduces the amount of data to be transferred. In addition, it’s possible to implement a network of small learning-capable systems which distribute tasks among themselves.

Deep learning

AIfES currently contains a neural network with a feedforward structure that also supports deep neural networks. “We programmed our solution so that we can describe a complete network with one single function,” says Gembaczka. The integration of additional network forms and structures is currently in development. Furthermore the researcher and his colleagues are developing hardware components for neural networks in addition to other learning algorithms and demonstrators.

Fraunhofer IMS is currently working on a RISC-V microprocessor which will have a hardware accelerator specifically for neural networks. A special version of AIfES is being optimised for this hardware in order to optimally exploit the resource.

For more information visit www.fraunhofer.de


  Share on Facebook Share via Twitter Share via LinkedIn    

Further reading:

  • Electronics news digest
    26 June 2019, News
    South Africa • South Africa is looking to take on a leading role in the international space weather monitoring community. Space weather events are capable of seriously disrupting modern technologies ...
  • Clearing the static: ESD testing and monitoring – Part 2
    26 June 2019, Altico Static Control Products, News
    Once you’ve identified an ESD protected area (EPA) and the combination of ESD (electrostatic discharge) control products your facility requires, continuous testing and monitoring need to be conducted. ...
  • From the editor’s desk: Local developments using solar power
    26 June 2019, Technews Publishing, News
    It’s always great to see local developers doing good work, and Dataweek always enjoys getting a chance to feature them. Sadly, people seldom share with us the interesting things they’re working on, whether ...
  • CSIR pushes to localise technologies
    26 June 2019, News
    The Council for Scientific and Industrial Research (CSIR) has pledged to work closely with the private sector and innovation partners in developing and localising technologies to support the advancement ...
  • SIMCom product seminar to be held next week
    26 June 2019, Otto Wireless, News
    Otto Wireless Solutions, in conjunction with SIMCom, will be hosting an informative half-day seminar at Riversands, Fourways on 10 July 2019. In addition to a brief product presentation by Otto Wireless ...
  • Demand for local products highlighted at LME expo
    26 June 2019, News
    The Local Southern African Manufacturing Expo (LME), held in Johannesburg in late May, managed to draw a respectable 3473 visitors in its first ever outing. “The Expo was the culmination of a vision that ...
  • Electronics news digest
    29 May 2019, News
    South Africa • South Africa will soon join the World Economic Forum’s (WEF) Centre for the Fourth Industrial Revolution Network (C4IR Network) alongside China, India and Japan by launching an affiliate ...
  • Clearing the static: ESD testing and monitoring - Part 1
    29 May 2019, Altico Static Control Products, News
    Static energy is an unseen threat, and the only way of knowing how to control it is by testing. Depending on your industry and application, there will be specific resistivity requirements that will govern ...
  • From the editor’s desk: US-China trade war hits chip makers
    29 May 2019, Technews Publishing, News
    The escalating trade war between the US and China has the global economy on high alert, and unless things normalise soon it is going to have massive ramifications on many industries. Following US president ...
  • Otto Wireless scoops two new agencies
    29 May 2019, Otto Wireless, News
    Otto Wireless Solutions has recently been appointed as the official distributor for two overseas manufacturers of RF and microwave components: Taiwanese microwave ceramic components designer and manufacturer, ...
  • Actum acquires Band-It business in South Africa
    29 May 2019, Actum Electronics, News
    The Actum Group has acquired Banding and Identification Solutions Africa (BISA), the leading distributor of Band-It clamping and fastening products in South Africa. The transaction, which was finalised ...
  • CSIR outlines new strategy
    29 May 2019, News
    The CSIR (Council for Scientific and Industrial Research) has revealed details about its new strategic direction, built around the vision of accelerating socioeconomic prosperity in South Africa through ...

 
 
         
Contact:
Technews Publishing (Pty) Ltd
1st Floor, Stabilitas House
265 Kent Ave, Randburg, 2194
South Africa
Publications by Technews
Dataweek Electronics & Communications Technology
Electronics Buyers’ Guide (EBG)

Hi-Tech Security Solutions
Hi-Tech Security Business Directory

Motion Control in Southern Africa
Motion Control Buyers’ Guide (MCBG)

South African Instrumentation & Control
South African Instrumentation & Control Buyers’ Guide (IBG)
Other
Terms & conditions of use, including privacy policy
PAIA Manual





 

         
    Classic | Mobile

Copyright © Technews Publishing (Pty) Ltd. All rights reserved.