SensiML Launches Open Source Initiative to Drive TinyML Implementations for Smart IoT Applications

May 11, 2021

News

SensiML Corporation announced that it has launched an Open Source Initiative to accelerate the adoption of TinyML smart sensing IoT applications.

The initiative builds upon SensiML’s existing efforts to design flexibility, transparency, and efficiency into its product suite by giving developers control and insight over aspects of their ML workflow, tools, data, and resulting models. SensiML’s Open Source Initiative is the next logical step in the company’s ongoing commitment to provide its embedded developers and partners with the confidence to build AI code into supportable, commercial IoT products.

Developers integrating AI into commercial products need both explainable and adaptable AI code to be able to support their products. By publishing file formats, interface protocols, reference data handling applications, embedded code functions, and reference datasets in open source, SensiML aims to offer developers flexibility and assurance. SensiML provides the insight needed to enable developers to maintain control of their data and firmware functionality while still leveraging SensiML’s proprietary AutoML search engine technology to build optimized AI code for the IoT edge.

SensiML’s Open Source Initiative includes the introduction of four specific components for building AI at the IoT edge:

• SensiML Open Gateway – A fully open source, user-extensible, multi-protocol application for connecting embedded IoT sensor devices to SensiML’s data collection tools for train and test data collection (SensiML Data Capture Lab and SensiML TestApp), as well as connectivity to cloud IoT platforms and other endpoints. SensiML Open Gateway is a connectivity tool that can be extended and modified as it is written in platform-agnostic Python code. Out of the box, the application can accommodate different connection types and sensor configurations. It also allows for customization as it can be tailored to meet user-specific needs for getting data out of the IoT/embedded sensor node and into AI software tools, cloud analytics, and application code running on PCs and smartphones.

• SensiML Open Data Interfaces – With support for both simple streaming binary output and full IoT device command/control using MQTT-SN, SensiML’s application-level protocols for bringing sensor data into its tools are published and available using open source reference code examples. SensiML’s project data can be imported and exported as CSV data at any time, and device configurations are defined using a published format (.DCLI) based on readily edited JSON attribute/value pairs.

• SensiML Open Mobile TestApp – This Android variant of the device testing tool is offered as open source software to support flexible options for data testing in mobile settings.
• SensiML Open Source Embedded SDK (coming later this summer) – The full library of SensiML segmenters, transforms, features, and classifiers as implemented by the AutoML and Python-based SensiML Analytics Toolkit Notebook will become available in open source format. The SensiML Open Source Embedded SDK will provide insight and transparency of model operation and leverage the collective expertise of our partners, users, and the embedded and AI community at large to make available updates and platform-specific optimizations over time.

The SensiML Open Gateway, Open Data Interfaces, and Open Mobile TestApp tools are all available now. The SensiML Open Source Embedded SDK will be released later this summer.

For more information, visit https://sensiml.com/blog/open-source-initiative.