Edge computing is a distributed computing paradigm that brings computation and data storage closer to the location where it is needed, which is often referred to as the "edge" of the network. Edge computing is becoming increasingly popular as it allows for faster data processing, lower latency, reduced network traffic, and improved privacy and security.
STM32 is a series of 32-bit microcontrollers developed by STMicroelectronics. These microcontrollers are commonly used in embedded systems, IoT devices, and other applications that require low power consumption, high performance, and a wide range of connectivity options. STM32 microcontrollers are also popular for edge computing applications as they provide the necessary processing power and memory to perform complex computations at the edge of the network.
NanoEdge is a software platform developed by STMicroelectronics for creating machine learning models and deploying them on microcontrollers. It provides a user-friendly graphical interface for data collection, model training, and model deployment. With NanoEdge, it is possible to perform edge computing tasks such as data preprocessing, feature extraction, and model inference directly on the microcontroller, without the need for a cloud-based server or a powerful desktop computer.
These projects demonstrates how STM32 and NanoEdge can be used for edge computing. By collecting and processing data directly on the microcontroller, we can perform machine learning tasks in real-time and without the need for an external server or computer. This approach can be particularly useful for applications that require low latency and high performance, such as predictive maintenance, industrial automation, and robotics.
In these projects, we will use an STM32 microcontroller and the NanoEdge software platform to perform audio classification and anomality detection. We will collect data using the microcontroller and sensors , preprocess the data using NanoEdge, and train a machine learning model. Finally, we will deploy the trained model on the microcontroller and use it to classify real-time audio data.
By using STM32 and NanoEdge for edge computing, we can perform machine learning tasks in real-time and without the need for a powerful server or computer. This approach opens up new possibilities for low-latency, high-performance applications that can be deployed directly on the edge of the network.