SensiML Toolkit Documentation
The SensiML Toolkit is a software suite that makes it easy for a software developer to take edge devices with sensors and turn them into advanced event detectors. The toolkit requires a SensiML account login which you can get for free at https://sensiml.com/plans/community-edition/.
The SensiML Toolkit includes four applications which can be downloaded at SensiML Downloads
If this is your first time using the SensiML Toolkit we recommend starting with the SensiML Getting Started Guide which will walk you through how to use each of the tools listed below in a Hello World style project for sensor applications.
Data Capture Lab - The Data Capture Lab is an application that helps you capture, organize, and label raw data from the sensor and transform it into the events you want to detect.
Analytics Studio - The Analytics Studio is an application that filters and optimizes your labeled sensor data through machine learning algorithms. It generates a model (SensiML Knowledge Pack) ready to be flashed into the firmware of your device of choice.
SensiML TestApp - The SensiML TestApp is an Android application that connects to your embedded device over Bluetooth-LE. It can be used to show real-time event classifications from a model running on your embedded device.
Open Gateway - The Open Gateway is an open-source application that connects to your embedded device over Bluetooth-LE, Serial, or Wi-Fi (TCP/IP). It can be used to display real-time classification results from a model or used as a sensor hub for collecting raw sensor data.
In addition to the four applications above, the SensiML Toolkit includes the SensiML Python SDK library that provides a programmatic interface to SensiML APIs through python.
User Guides
- Getting Started
- Overview
- Quick Start Project
- Data Capture Lab
- Setting Up Project Properties
- Capturing Sensor Data
- Labeling Your Data
- Other Useful Features
- Analytics Studio
- Project Summary
- Querying Data
- Building a Model
- Exploring Model Details
- Testing Model Results
- Real-Time Model Classifications
- Running a Model in the Data Capture Lab
- Running a Model On Your Embedded Device
- Debugging Bad Results
- Data Collection Planning
- Where to go next?
Application Examples
Third-Party Devices Integration
User Documentation
Supported Compilers
Supported Devices
- Arduino Nano 33 BLE Sense
- Arduino Nicla Sense ME
- Infineon PSoC™ 6
- Microchip Technology SAMD21 ML Eval Kit (SAM-IoT WG)
- Nordic Thingy
- onsemi RSL10 Sense
- QuickLogic Chilkat
- QuickLogic QuickAI
- QuickLogic QuickFeather
- Raspberry Pi
- Silicon Labs Thunderboard Sense 2
- Silicon Labs xG24 Dev Kit
- SparkFun QuickLogic Thing Plus - EOS S3
- ST SensorTile
- ST SensorTile.box
Simple Streaming Interface
MQTT-SN Interface
Resources