Future Electronics — Machine Learning Solutions Using SensiML Analytics Studio Toolkit

Future Electronics Compagno-SensiML Machine Learning Solution

Using SensiML Analytics Studio Toolkit for Industrial Edge AI Applications

Compagno (Italian for “Companion”) is a multi-sensor wireless edge node evaluation board designed by Future Electronics System Design Center. It is designed as companion board to work with ST Micro’s STWIN (STEVAL-STWINKT1) SensorTile wireless industrial node development kit. Complementary to the sensors on the STWIN kit, the Compagno board provides additional sensing capabilities including CO2, VOC, particulate matter and 8x8 temperature grid imaging.

The simple streaming firmware for the Compagno board enables easy integration with SensiML Analytics Studio Toolkit. The SensiML Analytics Studio Toolkit is a cloud-based software platform that enable application developers to create smart IoT sensor devices with SensiML’s AI routines optimized device-ready predictive model that rapidly reduce data science complexity.

Hardware Platform: STWIN & Compagno Board:

SensiML Analytics Studio Toolkit:

SensiML Analytics Toolkit suite automates each step of the process for creating optimized AI IoT sensor recognition code. The overall workflow uses a growing library of advanced ML and AI algorithms to generate code that can learn from new data either the development phase or once deployed.

>>SensiML Product Brief

SensiML Analytics ToolKit Components:

Data Capture Lab Train/test data collection Data labeling and metadata annotation Video annotation tools Auto segmentation and triggering Multi-user project collaboration Automated data management WindowsTM and AndroidTM versions

SensiML Data Capture Lab Screen

Analytics Studio Server based Al code-generation engine Classic ML classifiers thru xNN algorithms Automatic or Directed Feature Engineering Simple GUI and Python expert interfaces Cloud Service and Private Server options Test App Test tool for model validation on device Real-time and logged collection Rich visualizations and debug info Windows and Android versions

SensiML Analytics Studio Screen

Tutorial Videos:

1. LiveStreamingGridEyeDataToSensiMLDCL.mp4

2. SetupProject.mp4

3. DataCollection_ImprovedVoice.mp4

4. LabelDataAutoSegment_ImprovedVoice.mp4

5. AnalyticStudioPrepareData_ImprovedVoice.mp4

6. BuildModel_ImprovedVoice.mp4

7. FirstTestOfModel_ImprovedVoice.mp4

8. Testing_Knowledge_pack_in_gateway.mp4

9. DownloadKnowledgePack.mp4

10. Recognition_in_gateway.mp4