Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes
A wireless sensor network that consists of nodes with a sound sensor can be used to obtain context awareness in home environments. However, the limited processing power of wireless nodes offers a challenge when extracting features from the signal, and subsequently, classifying the source. Although m...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/10/1586 |
| _version_ | 1798003894757883904 |
|---|---|
| author | Etto L. Salomons Paul J. M. Havinga Henk van Leeuwen |
| author_facet | Etto L. Salomons Paul J. M. Havinga Henk van Leeuwen |
| author_sort | Etto L. Salomons |
| collection | DOAJ |
| description | A wireless sensor network that consists of nodes with a sound sensor can be used to obtain context awareness in home environments. However, the limited processing power of wireless nodes offers a challenge when extracting features from the signal, and subsequently, classifying the source. Although multiple papers can be found on different methods of sound classification, none of these are aimed at limited hardware or take the efficiency of the algorithms into account. In this paper, we compare and evaluate several classification methods on a real sensor platform using different feature types and classifiers, in order to find an approach that results in a good classifier that can run on limited hardware. To be as realistic as possible, we trained our classifiers using sound waves from many different sources. We conclude that despite the fact that the classifiers are often of low quality due to the highly restricted hardware resources, sufficient performance can be achieved when (1) the window length for our classifiers is increased, and (2) if we apply a two-step approach that uses a refined classification after a global classification has been performed. |
| first_indexed | 2024-04-11T12:16:17Z |
| format | Article |
| id | doaj.art-88f6436fe7ed4133a8e43d96acf7fac6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:16:17Z |
| publishDate | 2016-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-88f6436fe7ed4133a8e43d96acf7fac62022-12-22T04:24:19ZengMDPI AGSensors1424-82202016-09-011610158610.3390/s16101586s16101586Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor NodesEtto L. Salomons0Paul J. M. Havinga1Henk van Leeuwen2Ambient Intelligence Group, Saxion University of Applied Science, P.O. Box 70000, 7500 KB Enschede, The NetherlandsPervasive Systems Group, University of Twente, P.O. Box 217, 7500 AE Enschede, The NetherlandsAmbient Intelligence Group, Saxion University of Applied Science, P.O. Box 70000, 7500 KB Enschede, The NetherlandsA wireless sensor network that consists of nodes with a sound sensor can be used to obtain context awareness in home environments. However, the limited processing power of wireless nodes offers a challenge when extracting features from the signal, and subsequently, classifying the source. Although multiple papers can be found on different methods of sound classification, none of these are aimed at limited hardware or take the efficiency of the algorithms into account. In this paper, we compare and evaluate several classification methods on a real sensor platform using different feature types and classifiers, in order to find an approach that results in a good classifier that can run on limited hardware. To be as realistic as possible, we trained our classifiers using sound waves from many different sources. We conclude that despite the fact that the classifiers are often of low quality due to the highly restricted hardware resources, sufficient performance can be achieved when (1) the window length for our classifiers is increased, and (2) if we apply a two-step approach that uses a refined classification after a global classification has been performed.http://www.mdpi.com/1424-8220/16/10/1586wireless sensor networkssoundcontext awarenessfeature extraction |
| spellingShingle | Etto L. Salomons Paul J. M. Havinga Henk van Leeuwen Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes Sensors wireless sensor networks sound context awareness feature extraction |
| title | Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes |
| title_full | Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes |
| title_fullStr | Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes |
| title_full_unstemmed | Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes |
| title_short | Inferring Human Activity Recognition with Ambient Sound on Wireless Sensor Nodes |
| title_sort | inferring human activity recognition with ambient sound on wireless sensor nodes |
| topic | wireless sensor networks sound context awareness feature extraction |
| url | http://www.mdpi.com/1424-8220/16/10/1586 |
| work_keys_str_mv | AT ettolsalomons inferringhumanactivityrecognitionwithambientsoundonwirelesssensornodes AT pauljmhavinga inferringhumanactivityrecognitionwithambientsoundonwirelesssensornodes AT henkvanleeuwen inferringhumanactivityrecognitionwithambientsoundonwirelesssensornodes |