Dog Behavior Analytics
A company in Japan specializing in smart electronic devices for pets
Challenges
The client wanted to use an AI model to detect abnormal behaviors in dogs based on sensor data collected from smart collars.
The goal is to identify unusual activity (e.g., excessive scratching) and provide personalized recommendations via a pet care app.
HBLAB's Solutions
- Extracted key features from sensor data (accelerometer & gyroscope) embedded in the dog’s collar
- Trained an AI model using anomaly detection techniques to identify irregular behaviors
- Deployed the AI engine to AWS SageMaker as an endpoint for integration
Project details
-
Used Technologies Auto Encoders, OneVSRest SVM
-
Development Team 2 AI Engineer + 0.5 AI PM
-
Duration 5.5 months (3 phases)
Results
F1 scores ~ 85%
Related cases
Explore our success stories to spark ideas for your business and discover why partnering with us is the right choice.
The client, which is a large Singaporean IT provider, operates an IT issues ticket/request system that allow users to manage equipment, other users, and handle, create, process, and track IT incident requests within the company
The client, which specializes in temporary houses and office equipment rental in Thailand