Linxens is a global leader in electronics, delivering innovative solutions for connectivity, tracking, and authentication across sectors like healthcare, IoT, and transportation. Linxens recently announced E-SmellAir using edge AI technologies from ST.
E-SmellAir pioneers air quality analysis by leveraging Carbon Nanotube (CNT) sensors, renowned for their exceptional sensitivity, integrated with advanced edge AI technology. The system utilizes STM32 microcontrollers as its hardware platform, enabling on-device processing of sensor data. At the core of E-SmellAir’s intelligence is NanoEdge AI Studio, an automated machine learning tool which allows developers to rapidly create and deploy optimized AI models directly onto STM32 devices without requiring deep expertise in data science.
“
NanoEdge AI Studio allowed us to create the E-SmellAir with remarkable speed and efficiency. Its intuitive interface let us build and deploy customized gas classification models in record time. Now, whenever we need to adapt E-SmellAir for a new set of gases, we can easily retrain and update our models, ensuring rapid time-to-market and tailored performance for any application.
”
Laurent Coussonnet, Strategy & Partnership Global Director, Linxens
Approach
We begin by collecting data from the sensor as it measures selected target gases. This data is then processed in NanoEdge AI Studio, which creates optimized classification machine learning libraries for STM32 microcontrollers.
With these libraries, E-SmellAir can analyze the complex electrochemical signals from its 16-channel CNT sensor array in real time, directly on the device, eliminating the need to send data to the cloud. The AI model runs locally, accurately detects and classify airborne substances. This approach ensures fast, reliable identification of known compounds and enables instant alerts for undefined or hazardous odors, such as those linked to lithium battery fires, supporting proactive safety.
By combining the sensitivity of CNT sensors with the embedded intelligence of STM32 and NanoEdge AI Studio, E-SmellAir delivers a robust, scalable, and secure solution for advanced air quality monitoring and anomaly detection at the edge.
Sensor
Linxsens proprietary sensor.
Author: Linxsens | Last update: June, 2025
Resources
Model created with NanoEdge AI Studio
A free AutoML software for adding AI to embedded projects, guiding users step by step to easily find the optimal AI model for their requirements.
The STM32 family of 32-bit microcontrollers based on the Arm Cortex®-M processor is designed to offer new degrees of freedom to MCU users. It offers products combining very high performance, real-time capabilities, digital signal processing, low-power / low-voltage operation, and connectivity, while maintaining full integration and ease of development.