An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
Feature Extraction, Construction and Selection: A Data Mining Perspective
Feature Extraction, Construction and Selection: A Data Mining Perspective
Feature Selection for Knowledge Discovery and Data Mining
Feature Selection for Knowledge Discovery and Data Mining
Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System
ISWC '04 Proceedings of the Eighth International Symposium on Wearable Computers
YALE: rapid prototyping for complex data mining tasks
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Sensing from the basement: a feasibility study of unobtrusive and low-cost home activity recognition
UIST '06 Proceedings of the 19th annual ACM symposium on User interface software and technology
Power and accuracy trade-offs in sound-based context recognition systems
Pervasive and Mobile Computing
Rapid Prototyping of Activity Recognition Applications
IEEE Pervasive Computing
ICCHP '08 Proceedings of the 11th international conference on Computers Helping People with Special Needs
Hi-index | 0.00 |
This paper presents a low-cost, easy to install sound-based system for water usage monitoring in a household environment. It extends the state of the art but not only detecting that water is flowing in a pipe, but also quantifying the flow thus allowing us to compute the amount of water used. We describe the system architecture including hardware, software and the signal processing and pattern recognition algorithms used. We present an extensive evaluation in a real life noisy kitchen environment. We show an accuracy of over 90 percent on classifying six different water flow levels. We also demonstrate good performance measuring water consumption when compared with the home's water meter.