Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring
Wood-boring beetles are among the most destructive forest pests. The larvae of some species live in the trunks and are covered by bark, rendering them difficult to detect. Early detection of these larvae is critical to their effective management. A promising surveillance method is inspecting the vib...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/14/5/902 |
| _version_ | 1797600133060231168 |
|---|---|
| author | Haopeng Shi Zhibo Chen Haiyan Zhang Juhu Li Xuanxin Liu Lili Ren Youqing Luo |
| author_facet | Haopeng Shi Zhibo Chen Haiyan Zhang Juhu Li Xuanxin Liu Lili Ren Youqing Luo |
| author_sort | Haopeng Shi |
| collection | DOAJ |
| description | Wood-boring beetles are among the most destructive forest pests. The larvae of some species live in the trunks and are covered by bark, rendering them difficult to detect. Early detection of these larvae is critical to their effective management. A promising surveillance method is inspecting the vibrations induced by larval activity in the trunk to identify whether it is infected. As convenient as it seems, it has a significant drawback. The identification process is easily disrupted by environmental noise and results in low accuracy. Previous studies have proven the feasibility and necessity of adding an enhancement procedure before identification. To this end, we proposed a small yet powerful boring vibration enhancement network based on deep learning. Our approach combines frequency-domain and time-domain enhancement in a stacked network. The dataset employed in our study comprises the boring vibrations of <i>Agrilus planipennis</i> larvae and various environmental noises. After enhancement, the SNR (signal-to-noise ratio) increment of a boring vibration segment reaches 18.73 dB, and our model takes only 0.46 s to enhance a 5 s segment on a laptop CPU. The accuracy of several well-known classification models showed a substantial increase using clips enhanced by our model. All experimental results proved our contribution to the early detection of larvae. |
| first_indexed | 2024-03-11T03:44:16Z |
| format | Article |
| id | doaj.art-fd8dea1f1258475ebd7180a30eab5a2d |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-11T03:44:16Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-fd8dea1f1258475ebd7180a30eab5a2d2023-11-18T01:23:25ZengMDPI AGForests1999-49072023-04-0114590210.3390/f14050902Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> MonitoringHaopeng Shi0Zhibo Chen1Haiyan Zhang2Juhu Li3Xuanxin Liu4Lili Ren5Youqing Luo6School of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaWood-boring beetles are among the most destructive forest pests. The larvae of some species live in the trunks and are covered by bark, rendering them difficult to detect. Early detection of these larvae is critical to their effective management. A promising surveillance method is inspecting the vibrations induced by larval activity in the trunk to identify whether it is infected. As convenient as it seems, it has a significant drawback. The identification process is easily disrupted by environmental noise and results in low accuracy. Previous studies have proven the feasibility and necessity of adding an enhancement procedure before identification. To this end, we proposed a small yet powerful boring vibration enhancement network based on deep learning. Our approach combines frequency-domain and time-domain enhancement in a stacked network. The dataset employed in our study comprises the boring vibrations of <i>Agrilus planipennis</i> larvae and various environmental noises. After enhancement, the SNR (signal-to-noise ratio) increment of a boring vibration segment reaches 18.73 dB, and our model takes only 0.46 s to enhance a 5 s segment on a laptop CPU. The accuracy of several well-known classification models showed a substantial increase using clips enhanced by our model. All experimental results proved our contribution to the early detection of larvae.https://www.mdpi.com/1999-4907/14/5/902boring vibration<i>Agrilus planipennis</i>pest managementdeep learningneural networkmachine learning |
| spellingShingle | Haopeng Shi Zhibo Chen Haiyan Zhang Juhu Li Xuanxin Liu Lili Ren Youqing Luo Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring Forests boring vibration <i>Agrilus planipennis</i> pest management deep learning neural network machine learning |
| title | Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring |
| title_full | Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring |
| title_fullStr | Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring |
| title_full_unstemmed | Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring |
| title_short | Enhancement of Boring Vibrations Based on Cascaded Dual-Domain Features Extraction for Insect Pest <i>Agrilus planipennis</i> Monitoring |
| title_sort | enhancement of boring vibrations based on cascaded dual domain features extraction for insect pest i agrilus planipennis i monitoring |
| topic | boring vibration <i>Agrilus planipennis</i> pest management deep learning neural network machine learning |
| url | https://www.mdpi.com/1999-4907/14/5/902 |
| work_keys_str_mv | AT haopengshi enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring AT zhibochen enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring AT haiyanzhang enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring AT juhuli enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring AT xuanxinliu enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring AT liliren enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring AT youqingluo enhancementofboringvibrationsbasedoncascadeddualdomainfeaturesextractionforinsectpestiagrilusplanipennisimonitoring |