Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking
Wireless acoustic sensor networks (WASNs) and intelligent microsystems are crucial components of the Internet of Things (IoT) ecosystem. In various IoT applications, small, lightweight, and low-power microsystems are essential to enable autonomous edge computing and networked cooperative work. This...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3630 |
| _version_ | 1797606906637844480 |
|---|---|
| author | Lulu Hou Wenrui Duan Guozhe Xuan Shanpeng Xiao Yuan Li Yizheng Li Jiahao Zhao |
| author_facet | Lulu Hou Wenrui Duan Guozhe Xuan Shanpeng Xiao Yuan Li Yizheng Li Jiahao Zhao |
| author_sort | Lulu Hou |
| collection | DOAJ |
| description | Wireless acoustic sensor networks (WASNs) and intelligent microsystems are crucial components of the Internet of Things (IoT) ecosystem. In various IoT applications, small, lightweight, and low-power microsystems are essential to enable autonomous edge computing and networked cooperative work. This study presents an innovative intelligent microsystem with wireless networking capabilities, sound sensing, and sound event recognition. The microsystem is designed with optimized sensing, energy supply, processing, and transceiver modules to achieve small size and low power consumption. Additionally, a low-computational sound event recognition algorithm based on a Convolutional Neural Network has been designed and integrated into the microsystem. Multiple microsystems are connected using low-power Bluetooth Mesh wireless networking technology to form a meshed WASN, which is easily accessible, flexible to expand, and straightforward to manage with smartphones. The microsystem is 7.36 cm<sup>3</sup> in size and weighs 8 g without housing. The microsystem can accurately recognize sound events in both trained and untrained data tests, achieving an average accuracy of over 92.50% for alarm sounds above 70 dB and water flow sounds above 55 dB. The microsystems can communicate wirelessly with a direct range of 5 m. It can be applied in the field of home IoT and border security. |
| first_indexed | 2024-03-11T05:24:26Z |
| format | Article |
| id | doaj.art-09812bafdea5474b9aa87db27a1965b0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:24:26Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-09812bafdea5474b9aa87db27a1965b02023-11-17T17:35:25ZengMDPI AGSensors1424-82202023-03-01237363010.3390/s23073630Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh NetworkingLulu Hou0Wenrui Duan1Guozhe Xuan2Shanpeng Xiao3Yuan Li4Yizheng Li5Jiahao Zhao6School of Instrument Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaSchool of Instrument Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaDepartment of Precision Instrument, Tsinghua University, Beijing 100084, ChinaChina Mobile Research Institute, Beijing 100053, ChinaChina Mobile Research Institute, Beijing 100053, ChinaChina Mobile Research Institute, Beijing 100053, ChinaDepartment of Precision Instrument, Tsinghua University, Beijing 100084, ChinaWireless acoustic sensor networks (WASNs) and intelligent microsystems are crucial components of the Internet of Things (IoT) ecosystem. In various IoT applications, small, lightweight, and low-power microsystems are essential to enable autonomous edge computing and networked cooperative work. This study presents an innovative intelligent microsystem with wireless networking capabilities, sound sensing, and sound event recognition. The microsystem is designed with optimized sensing, energy supply, processing, and transceiver modules to achieve small size and low power consumption. Additionally, a low-computational sound event recognition algorithm based on a Convolutional Neural Network has been designed and integrated into the microsystem. Multiple microsystems are connected using low-power Bluetooth Mesh wireless networking technology to form a meshed WASN, which is easily accessible, flexible to expand, and straightforward to manage with smartphones. The microsystem is 7.36 cm<sup>3</sup> in size and weighs 8 g without housing. The microsystem can accurately recognize sound events in both trained and untrained data tests, achieving an average accuracy of over 92.50% for alarm sounds above 70 dB and water flow sounds above 55 dB. The microsystems can communicate wirelessly with a direct range of 5 m. It can be applied in the field of home IoT and border security.https://www.mdpi.com/1424-8220/23/7/3630wireless acoustic sensor networkintelligent microsystemsound event recognitionedge computingBLE meshacoustic signal processing |
| spellingShingle | Lulu Hou Wenrui Duan Guozhe Xuan Shanpeng Xiao Yuan Li Yizheng Li Jiahao Zhao Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking Sensors wireless acoustic sensor network intelligent microsystem sound event recognition edge computing BLE mesh acoustic signal processing |
| title | Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking |
| title_full | Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking |
| title_fullStr | Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking |
| title_full_unstemmed | Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking |
| title_short | Intelligent Microsystem for Sound Event Recognition in Edge Computing Using End-to-End Mesh Networking |
| title_sort | intelligent microsystem for sound event recognition in edge computing using end to end mesh networking |
| topic | wireless acoustic sensor network intelligent microsystem sound event recognition edge computing BLE mesh acoustic signal processing |
| url | https://www.mdpi.com/1424-8220/23/7/3630 |
| work_keys_str_mv | AT luluhou intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking AT wenruiduan intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking AT guozhexuan intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking AT shanpengxiao intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking AT yuanli intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking AT yizhengli intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking AT jiahaozhao intelligentmicrosystemforsoundeventrecognitioninedgecomputingusingendtoendmeshnetworking |