An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform
The wireless sensor nodes used in a growing number of remote sensing applications are deployed in inaccessible locations or are subjected to severe energy constraints. Audio-based sensing offers flexibility in node placement and is popular in low-power schemes. Thus, in this paper, a node architectu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Journal of Low Power Electronics and Applications |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9268/10/1/6 |
| _version_ | 1811264100254089216 |
|---|---|
| author | Swagat Bhattacharyya Steven Andryzcik David W. Graham |
| author_facet | Swagat Bhattacharyya Steven Andryzcik David W. Graham |
| author_sort | Swagat Bhattacharyya |
| collection | DOAJ |
| description | The wireless sensor nodes used in a growing number of remote sensing applications are deployed in inaccessible locations or are subjected to severe energy constraints. Audio-based sensing offers flexibility in node placement and is popular in low-power schemes. Thus, in this paper, a node architecture with low power consumption and in-the-field reconfigurability is evaluated in the context of an acoustic vehicle detection and classification (hereafter “AVDC”) scenario. The proposed architecture utilizes an always-on field-programmable analog array (FPAA) as a low-power event detector to selectively wake a microcontroller unit (MCU) when a significant event is detected. When awoken, the MCU verifies the vehicle class asserted by the FPAA and transmits the relevant information. The AVDC system is trained by solving a classification problem using a lexicographic, nonlinear programming algorithm. On a testing dataset comprising of data from ten cars, ten trucks, and 40 s of wind noise, the AVDC system has a detection accuracy of 100%, a classification accuracy of 95%, and no false alarms. The mean power draw of the FPAA is 43 <inline-formula> <math display="inline"> <semantics> <mi mathvariant="sans-serif">μ</mi> </semantics> </math> </inline-formula>W and the mean power consumption of the MCU and radio during its validation and wireless transmission process is 40.9 mW. Overall, this paper demonstrates that the utilization of an FPAA-based signal preprocessor can greatly improve the flexibility and power consumption of wireless sensor nodes. |
| first_indexed | 2024-04-12T19:58:17Z |
| format | Article |
| id | doaj.art-c3037d39961f4e50af8dd033e1535e71 |
| institution | Directory Open Access Journal |
| issn | 2079-9268 |
| language | English |
| last_indexed | 2024-04-12T19:58:17Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Low Power Electronics and Applications |
| spelling | doaj.art-c3037d39961f4e50af8dd033e1535e712022-12-22T03:18:37ZengMDPI AGJournal of Low Power Electronics and Applications2079-92682020-02-01101610.3390/jlpea10010006jlpea10010006An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal PlatformSwagat Bhattacharyya0Steven Andryzcik1David W. Graham2School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USALane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26506, USALane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26506, USAThe wireless sensor nodes used in a growing number of remote sensing applications are deployed in inaccessible locations or are subjected to severe energy constraints. Audio-based sensing offers flexibility in node placement and is popular in low-power schemes. Thus, in this paper, a node architecture with low power consumption and in-the-field reconfigurability is evaluated in the context of an acoustic vehicle detection and classification (hereafter “AVDC”) scenario. The proposed architecture utilizes an always-on field-programmable analog array (FPAA) as a low-power event detector to selectively wake a microcontroller unit (MCU) when a significant event is detected. When awoken, the MCU verifies the vehicle class asserted by the FPAA and transmits the relevant information. The AVDC system is trained by solving a classification problem using a lexicographic, nonlinear programming algorithm. On a testing dataset comprising of data from ten cars, ten trucks, and 40 s of wind noise, the AVDC system has a detection accuracy of 100%, a classification accuracy of 95%, and no false alarms. The mean power draw of the FPAA is 43 <inline-formula> <math display="inline"> <semantics> <mi mathvariant="sans-serif">μ</mi> </semantics> </math> </inline-formula>W and the mean power consumption of the MCU and radio during its validation and wireless transmission process is 40.9 mW. Overall, this paper demonstrates that the utilization of an FPAA-based signal preprocessor can greatly improve the flexibility and power consumption of wireless sensor nodes.https://www.mdpi.com/2079-9268/10/1/6fpaareconfigurablemixed-signalacoustic classificationwireless sensor nodes |
| spellingShingle | Swagat Bhattacharyya Steven Andryzcik David W. Graham An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform Journal of Low Power Electronics and Applications fpaa reconfigurable mixed-signal acoustic classification wireless sensor nodes |
| title | An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform |
| title_full | An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform |
| title_fullStr | An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform |
| title_full_unstemmed | An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform |
| title_short | An Acoustic Vehicle Detector and Classifier Using a Reconfigurable Analog/Mixed-Signal Platform |
| title_sort | acoustic vehicle detector and classifier using a reconfigurable analog mixed signal platform |
| topic | fpaa reconfigurable mixed-signal acoustic classification wireless sensor nodes |
| url | https://www.mdpi.com/2079-9268/10/1/6 |
| work_keys_str_mv | AT swagatbhattacharyya anacousticvehicledetectorandclassifierusingareconfigurableanalogmixedsignalplatform AT stevenandryzcik anacousticvehicledetectorandclassifierusingareconfigurableanalogmixedsignalplatform AT davidwgraham anacousticvehicledetectorandclassifierusingareconfigurableanalogmixedsignalplatform AT swagatbhattacharyya acousticvehicledetectorandclassifierusingareconfigurableanalogmixedsignalplatform AT stevenandryzcik acousticvehicledetectorandclassifierusingareconfigurableanalogmixedsignalplatform AT davidwgraham acousticvehicledetectorandclassifierusingareconfigurableanalogmixedsignalplatform |