In this tutorial series, Shawn introduces the concept of Tiny Machine Learning (TinyML), which consists of running machine learning algorithms on microcontrollers and single board computers.
In the previous episode ( • Edge AI Anomaly Detect... ), we trained a couple of machine learning models based on the Mahalanobis Distance and an Autoencoder neural network. These models can be used to detect anomalies in accelerometer data.
For this episode, we need to retrain the model using data collected from the ceiling fan in one particular state. We compute the median absolute deviation (MAD) for our features.
Code and example dataset for this video series can be found here: github.com/Sha...
Once we have the new models, we send them to a Raspberry Pi, where we can run Python to detect anomalies in real time. Our sensor node consists of an ESP32 and MSA301 accelerometer, which transmits data to our Raspberry Pi over WiFi.
The Pi reads this data and performs inference with one of the machine learning models to detect anomalies (i.e. the ceiling fan is not operating normally).
For Mahalanobis Distance, the Raspberry Pi reads the incoming data, computes the MAD value for each axis and computes the Mahalanobis Distance between the MAD values of the new sample and the mean in the model. If that distance is over a particular threshold, we can say that an anomaly has occurred.
For the Autoencoder, the Pi computes the MAD values again, but uses a neural network (in an autoencoder configuration) to predict the same MAD values. The mean squared error (MSE) of the inputs and outputs of the neural network is computed. If the MSE is over a threshold, we determine that an anomaly has occurred.
Before starting, we recommend you watch the following videos:
What is Edge AI - • Intro to Edge AI: Mach...
Getting Started with Machine Learning Using TensorFlow and Keras - • Getting Started with T...
Product Links:
Adafruit Feather Huzzah32 - www.digikey.co...
Adafruit MSA301 Triple Axis Accelerometer - www.digikey.co...
Related Videos:
Edge AI Anomaly Detection Part 1: Data Collection - • Edge AI Anomaly Detect...
Edge AI Anomaly Detection Part 2: Feature Extraction and Model Training: • Edge AI Anomaly Detect...
Related Project Links:
Edge AI Anomaly Detection Part 3: Deploy Machine Learning Models to Raspberry Pi - www.digikey.co...
Edge AI Anomaly Detection Part 3: Machine Learning on Raspberry Pi - www.digikey.co...
Related Articles:
What is Edge AI?
www.digikey.co...
Getting Started with Machine Learning Using TensorFlow and Keras
www.digikey.co...
TensorFlow Lite Tutorial Part 1: Wake Word Feature Extraction
www.digikey.co...
TensorFlow Lite Tutorial Part 2: Speech Recognition Model Training
www.digikey.co...
TensorFlow Lite Tutorial Part 3: Speech Recognition on Raspberry Pi
www.digikey.co...
Low-Cost Data Acquisition (DAQ) with Arduino and Binho for ML
www.digikey.co...
Intro to TinyML Part 1: Training a Model for Arduino in TensorFlow
www.digikey.co...
Intro to TinyML Part 2: Deploying a TensorFlow Lite Model to Arduino
www.digikey.co...
Edge AI Anomaly Detection Part 1: Data Collection
www.digikey.co...
Edge AI Anomaly Detection Part 2: Feature Extraction and Model Training www.digikey.co...
5 окт 2024
