SensiML and Neurosense partner on intelligent IoT devices
July 17. 2109
Oregon-based intelligent IoT endpoint developer SensiML is working with South Korean firm Neurosense, a provider of integrated intelligent IoT SoCs, to produce a combination for developers seeking to build intelligent small form factor IoT devices.
The SensiML AI analytics toolkit brings real-time artificial intelligence to the sensor endpoint with a platform that is accessible to any application developer. SensiML's analytic engine takes data sets and creates an optimised device-ready AI algorithm that balances the desired accuracy with the resource constraints of the target hardware.
This algorithm is automatically compiled to optimise machine code that can run in real time on the target embedded platform, making it easy for developers to implement AI at the endpoint quickly and efficiently.
Neurosense specialises in edge computing technology, providing an integrated system-in-package (SiP) platform with an embedded customised pattern-matching algorithm for motion detection and sound recognition. The Neurosense ELA106 platform combines processing, communications and sensing in one package.
"The SensiML data analytics toolkit makes it extremely easy for manufacturers to implement intelligent sensing directly on the endpoint device without the need for large teams of data scientists and firmware engineers," said KS Kim, chief executive officer of Neurosense. "Their toolkit complements our edge computing SIP platform and enables us to deliver an end-to-end solution to our mutual customer base."
The two companies will combine the capabilities of SensiML's toolkit with the Neurosense platform to give IoT developers complete motion detection and sound recognition for endpoint applications.
"Neurosense has proven to be a great partner to showcase the possibilities for endpoint intelligence using SensiML as the analytics engine for their ELA106 system with its highly integrated combination of processor, communications and physical sensing all in one system package," said Chris Rogers, CEO of SensiML.
The SensiML AI analytics toolkit is available today. The Neurosense ELA106 intelligent endpoint SiP will be available to customers starting mid-August 2019.
SensiML, a subsidiary of QuickLogic, offers software that enables low-power IoT endpoints that implement AI to transform raw sensor data into meaningful insight at the device itself. The SensiML toolkit supports Arm Cortex-M class and higher microcontroller cores, Intel x86 instruction set processors, and heterogeneous core QuickLogic SoCs and QuickAI platforms with FPGA optimisations.
Neurosense was established as a start-up company to develop and provide customised edge intelligence algorithms for motion detection and sound recognition together with SiP platforms to implement the Neurosense AI algorithm. It runs on a low computing power Arm core-based CPU with software-based edge intelligence algorithms. Applications include IoT sensors for industrial uses such as predictive maintenance for motors, bearings and conveyor belts, wearable devices, toys, light sticks for pop concerts, voice control of consumer electronics, and smart building control.