.png){kind=small}
Peaks and Valleys: How data segmentation can conserve power and CPU cycles in Edge AI systems
By J. Sieracki When working with real-time streaming data, segmentation will be one of the first issues you encounter. Real-time streaming data has to be
Resources
Blog
Whitepaper
Video
Press
Events
Reality AI CEO, Stuart Feffer, Featured on The Global Safety Podcast from Lloyd’s Register Foundation
Each year, an estimated 2.8mil people die from accidents in the workplace. Families are torn apart, reputations ruined, share prices crash and consumer confidence tumbles.
Reality AI CEO Featured on Latest Mobility Now! Podcast
Stuart explains why sound detection is a critical part of ADAS and autonomous driving. He shares the science behind Reality AI’s technology, and how it finds unique features in sounds to accurately identify them.
Reality AI to Host ARM AI Virtual Tech Talk on January 26
Date: January 26, 2021
Time: 8am PST / 4pm BST / 11pm CST
Stuart Feffer, CEO & Co-Founder Reality AI
EMBEDDED AI AND MACHINE LEARNING ADDING NEW ADVANCEMENTS IN TECH SPACE
With current tools, integrating new options for machine learning for signals (like Reality AI) it is getting simpler.
Mobility Xlab Interviews Future Mobility Award Winners
Nalin Balan is the head of business development at Reality AI and he took some time to talk to us about their work and winning the Future Mobility Award.
Reality AI to work on Industrial Safety Inspection Accelerator
Reality AI Selected to Work with Sellafield Limited and National Nuclear Laboratory on Industrial Safety Inspection Accelerator
Want to Reduce the Cost of Data Collection for Edge AI with Sensors? Only do it once.
If you have ever attempted or completed a machine learning project using sensor data, you probably know already that data collection and preparation is both the most costly part of the project and also the place where you are most likely to go off track.
Edge AI – Difference Between a Project and a Product
Edge AI and TinyML are having a moment. The tech world has woken up to the fact that it is possible to put machine learning models on small, inexpensive microcontrollers, and GitHub is now full of examples of TinyML models for all sorts of things.
Comprehensive AI Engineering Software for Making Smart Edge Devices with Sensors
Welcome to Reality AI 4.0!
How Do You Make AI Explainable? Start with the Explanation.
“No, no! The adventures first. Explanations take such a dreadful time!” – Lewis Carroll, “Alice in Wonderland Explanations for model behavior are starting to get
Bias Isn’t Always Bad
“Facts are stubborn things. But statistics are pliable” -Mark Twain This blog is about statistical bias in machine learning models. But unlike most of what
Reality AI demonstrates Edge AI solutions for real problems running on Cortex M4 and M7 platforms
Edge AI is finally starting to get the attention of the technical trade press. It’s been a real thing for a while – particularly in autonomous driving applications and wearables – but other applications are starting to get some attention too.
FFTs and Stupid Deep Learning Tricks
Deep Learning has nearly taken over the machine learning world — in large part due to its great success in using layers of neural networks to discover the features in underlying data that actually matter to other, higher-level layers of neural networks.
Successful Data Collection for Machine Learning with Sensors
It’s R&D time. The product guys have dreamed up some new features, and now you have to see if its possible to deliver them. If it is possible, you’ll need to build it.
Reality AI Technical Whitepaper
Explore the technical details behind the Reality AI approach to machine learning with signals:
- Why signals require a different approach than other machine learning problems
- The importance of “features” to effective machine learning
- Why the FFT probably isn’t good enough, and what other options are better
- The difference between Reality AI and Deep Learning
Reality AI Technical Whitepaper (Japanese Translation) / テクニカルホワイトペーパー
Explore the technical details behind the Reality AI approach to machine learning with signals:
- Why signals require a different approach than other machine learning problems
- The importance of “features” to effective machine learning
- Why the FFT probably isn’t good enough, and what other options are better
- The difference between Reality AI and Deep Learning
Reality AI Data Collection Whitepaper
Reality AI provides software for R&D engineers who build products and internal solutions using sensors. Working with accelerometers, vibration, sound, electrical (current/voltage/capacitance), radar, RF, proprietary sensors, and other types of sensor data, Reality AI software identifies signatures of events and conditions, correlates changes in signatures to target variables, and detects anomalies.
Since data collection and preparation is both the most costly part of any machine learning project, and also the place where most failed projects go wrong, Reality AI software contains functionality to keep data collection on track, to assist with its pre-ML processing, and to get the most out of it using synthetic augmentation techniques. This whitepaper covers the approach we recommend for data collection planning, execution, and post-collection processing.
The Complete Guide to Machine Learning for Sensors and Signal Data
Machine learning for sensors and signal data is becoming easier than ever: hardware is becoming smaller and sensors are getting cheaper, making IoT devices widely available for a variety of applications ranging from predictive maintenance to user behavior monitoring.
Whether you are using sounds, vibrations, images, electrical signals or accelerometer or other kinds of sensor data, you can build richer analytics by teaching a machine to detect and classify events happening in real-time, at the edge, using an inexpensive microcontroller for processing – even with noisy, high variation data.
Go beyond the Fast Fourier Transform (FFT). This definitive guide to machine learning for high sample-rate sensor data is packed with tips from our signal processing and machine learning experts.
Download the full version of the e-book to read it at your own pace.
The 2020 Ultimate Guide to Machine Learning for Embedded Systems
Machine learning is a powerful method for building models that use data to make predictions. In embedded systems — typically running microcontrollers and constrained by processing cycles, memory, size, weight, power consumption, and cost — machine learning can be difficult to implement, as these environments cannot usually make use of the same tools that work in cloud server environments.
This Ultimate Guide to Machine Learning for Embedded Systems includes information on how to make machine learning work in microcontroller and other constrained environments when the data being monitored comes from sensors.
So now you know a little more about what we mean by “machine learning for embedded systems”, but maybe you’re still unsure about where or how to start?
Download this entire guide to read it at your leisure.
Automotive Sound Recognition and Localization - See Around Corners with Sound - Winner of 2020 Future Mobility Award
RealityCheckTM Voice Anti-Spoofing for Wakeword and Voice UI
Predictive Maintenance and Condition Monitoring Demo - Built with Reality AI ToolsTM
Predictive Maintenance and Condition Monitoring Demo - Built with Reality AI ToolsTM (Japanese Translation)
Reality AI - Cars can see with Sound (Japanese)
Building products using TinyML on Arm MCUs | Reality AI
RealityCheck AD - Short Intro (Japanese)
Automated Anomaly Detection using Sound - Webinar Video
Renesas to Acquire Reality AI to Bring Advanced Signal Processing and Intelligence to the Endpoint
Reality AI has signed definitive agreements to be acquired by Renesas Electronics. For full text of the announcement see: https://www.renesas.com/us/en/about/press-room/renesas-acquire-reality-ai-bring-advanced-signal-processing-and-intelligence-endpoint
Reality AI wins Best of Sensors 2021 for its Automotive SWS sensor
Reality AI was named the winner of the most innovative product in the Automotive/Autonomous Technologies category of the Best of Sensors Awards, recently held at
The 2021 Best of Sensors winners announced
Honors the Best in Sensor Technologies and the Sensor Ecosystem, People and Companies SAN JOSE, Calif., Sept. 24, 2021 (GLOBE NEWSWIRE) — Yesterday, Questex’s Sensors Converge and Fierce Electronics announced the
Reality AI partners with Fujitsu Component for AI-Enabled Contactless Vibration Sensing
Reality AI to demonstrate AI-enabled, contactless vibration sensing based on doppler radar at Sensors Converge 9/21-23 MARYLAND (15 Sept) – Reality AI today announced it will
Reality AI launches Edge AI solution for Industrial Anomaly Detection
To be demonstrated live for the first time at Sensors Converge expo Sept 22-23 MARYLAND (13th Sept 2021) – Reality AI today announced the availability
REALITY AI NAMED 2021 BEST OF SENSORS AWARD FINALIST
Reality AI, Automotive SWSTM Recognized for excellence in Sensors Innovation Columbia, Maryland– September 1, 2021 – (Reality AI) has been named a 2021 “Best of
Reality AI Wins 2020 Future Mobility Award in “AI for Safety” Category
GOTHENBURG, SWEDEN (October 6, 2020) – In a ceremony held both virtually and in-person, Reality AI was recognized with the 2020 Future Mobility Award in the
REALITY AI ANNOUNCES “REALITY AI FOR MATLAB”
Reality AI today announced the beta program for “Reality AI for MATLAB”, an add-on to its Reality AI Tools® software that enables users to develop optimized feature computations and machine learning models for advanced sensing automatically.
REALITY AI LETS CARS “SEE AROUND CORNERS WITH SOUND”
Working with its partner DENSO Corporation, Reality AI has developed a new software solution that uses external microphones on cars to detect targets that are not in the direct line of sight.
Reality AI named “Tech Innovator in Edge AI” for 2020 by Gartner
In a new report on emerging technologies, the technology research and advisory company, Gartner named Reality AI as one of twelve “Edge AI Tech Innovators for 2020.”
Reality AI Announces Partnership with ARM for Machine Learning on Low-Cost Microcontrollers
Reality AI, a provider of AI-enabled software for R&D engineers building products with sensors, today announced that it has joined the Arm AI Partner Program.
New Software from Reality AI for Engineers Building Products with Sensors
Reality AI today announced the latest version of its groundbreaking software for research and development engineers building products with sensors. Reality AI Tools® version 4.0 will allow customers to use artificial intelligence to reduce the cost of developing, procuring and manufacturing smart devices.
Date: 14-15 October 2021| 9:00- 5:00 pm PT
Location: Virtual Event
Companies leading the automotive, transportation, and mobility industries into the future are committed to innovation – both to innovating themselves and to partnering with the best innovations available whether those are found in their existing supply chain, a venture funded startup, or a university lab.
Meet us at this leading automotive fair and discover technologies that are transforming mobility. We will be showcasing how the automotive industry can leverage SWS Auto and other Reality AI tools and solutions.
What we do
Events
