Demo Abstract: How Many Climb the Matterhorn?

In this demo abstract we present a custom-built low-power geophone sensor node which features on-device mountaineer classification using a convolutional neural network. The execution of such a processing-heavy algorithm on an embedded platform is enabled by optimizing the memory requirement of the n...

Full description

Saved in:
Bibliographic Details
Published in2019 18th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) pp. 250 - 251
Main Authors Meyer, Matthias, Farei-Campagna, Timo, Pasztor, Akos, Da Forno, Reto, Beutel, Tan, Thiele, Lothar
Format Conference Proceeding
LanguageEnglish
Published ACM 01.04.2019
Subjects
Convolutional neural networks
Embedded Convolutional Neural Network
Hazards
Machine Learning
Memory management
Monitoring
Natural Hazard Warning System
On-device Classification
Streaming media
Wireless Sensing Platform
Wireless sensor networks
Online AccessGet full text

Cover

More Information
Summary:In this demo abstract we present a custom-built low-power geophone sensor node which features on-device mountaineer classification using a convolutional neural network. The execution of such a processing-heavy algorithm on an embedded platform is enabled by optimizing the memory requirement of the neural network through advanced quantization and pipelining techniques. As a result, real-time classification with low energy consumption can be achieved.