VideoLibrary

Edge AI Anomaly Detection Part 3: Deploy Machine Learning Models to Raspberry Pi | DigiKey

In the third episode, we train a new set of machine learning models and deploy them to a Raspberry Pi. We rely on the Mahalanobis Distance and a neural network to detect anomalies in accelerometer data.

Edge AI Anomaly Detection Part 3: Deploy Machine Learning Models to Raspberry Pi Blog
5/29/2020 5:30:37 PM

Part List

AbbildungHersteller-TeilenummerBeschreibungVerfügbare MengePreisDetails anzeigen
HUZZAH32 ESP32 FEATHER MALE HDR3591HUZZAH32 ESP32 FEATHER MALE HDR17 - Sofort$18.03Details anzeigen
MSA301 TRIPLE AXIS ACCELEROMETER4344MSA301 TRIPLE AXIS ACCELEROMETER0 - SofortSee Page for PricingDetails anzeigen

Related Videos

Edge AI Anomaly Detection Part 4: Deploy TinyML Model in Arduino to ESP32 | DigiKey
Edge AI Anomaly Detection Part 4: Deploy TinyML Model in Arduino to ESP32 | DigiKey

Datum der Veröffentlichung: 2020-05-29

Edge AI Anomaly Detection Part 1: Data Collection | DigiKey
Edge AI Anomaly Detection Part 1: Data Collection | DigiKey

Datum der Veröffentlichung: 2020-04-24

Edge AI Anomaly Detection Part 2: Feature Extraction and Model Training | DigiKey
Edge AI Anomaly Detection Part 2: Feature Extraction and Model Training | DigiKey

Datum der Veröffentlichung: 2020-04-24

Related Articles and Blogs

How to Use Cloud Storage on the Atmosphere IoT How to save specific values from Atmosphere IoT to the cloud and retrieve that data.
How to Use the Average Element in the Atmosphere IoT Studio Increasing sensor accuracy is possible by averaging the data points to eliminate extreme points. It’s simple with Atmosphere IoT Studio programming blocks.
How to Use the Pi Weather Shield with Atmosphere IoT Studio The Pi Weather Shield is a perfect tool for measuring the world around your project, on the move or not, with Atmosphere IoT Studio stay updated everywhere.