Imagimob and Syntiant Integrate tinyML and Neural Decision Processor for the Development of Production-Ready Applications
October 10, 2022
Stockholm and Irvine, Calif., – Imagimob and Syntiant Corp are collaborating to integrate Imagimob’s tinyML platform with Syntiant’s ultra-low-power NDP120 Neural Decision Processor, enabling the development of production-ready deep learning tinyML applications and ML models using the NDP120 for sound event detection, keyword spotting, fall detection, anomaly detection, gesture detection and more.
The Imagimob platform enables the aforementioned use cases with a built-in fall detection starter project comprised of an annotated dataset with metadata, and a pre-trained ML-model (in h5-format) to detect falls using IMU data, which can be improved with the addition of more data. The platform is also ideal for consumer and industrial products, as the NDP120 provides always-on voice and sensor neural processing
“Pairing our NDP120 with the Imagimob platform will enable developers to quickly and easily deploy deep learning models,” said Kurt Busch, CEO of Syntiant. “Studies suggest that there are more than 35 million falls in the U.S. alone that require some kind of medical attention, so there is significant opportunity for applications across both consumer and industrial use cases.”
Awarded “Best Product of the Year” by the tinyML Foundation and packaged with the Syntiant Core 2™, the company’s 2nd generation, flexible deep neural network, the NDP120 also supports Ok Google and Hey Google hotwords under 280uW, while running multiple applications simultaneously at under 1mW.
Imagimob AI allows developers to collect data and deploy projects on edge devices using production-ready models for audio, gesture recognition, human motion, predictive maintenance, material detection and more, through an end-to-end platform for machine learning on edge devices.
Imagimob will demonstrate the joint solution at the tinyML EMEA Innovation Forum 2022 held October 10-12 in Limassol, Cyprus.