An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance
An essential aspect of controlling and preventing mosquito-borne diseases is to reduce mosquitoes that carry viruses. We designed a smart mosquito trap system to reduce the density of mosquito vectors and the spread of mosquito-borne diseases. This smart trap uses computer vision technology and deep...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2023.1100968/full |
| _version_ | 1797946993065066496 |
|---|---|
| author | Wei-Liang Liu Yuhling Wang Yu-Xuan Chen Yu-Xuan Chen Bo-Yu Chen Arvin Yi-Chu Lin Sheng-Tong Dai Chun-Hong Chen Chun-Hong Chen Chun-Hong Chen Lun-De Liao |
| author_facet | Wei-Liang Liu Yuhling Wang Yu-Xuan Chen Yu-Xuan Chen Bo-Yu Chen Arvin Yi-Chu Lin Sheng-Tong Dai Chun-Hong Chen Chun-Hong Chen Chun-Hong Chen Lun-De Liao |
| author_sort | Wei-Liang Liu |
| collection | DOAJ |
| description | An essential aspect of controlling and preventing mosquito-borne diseases is to reduce mosquitoes that carry viruses. We designed a smart mosquito trap system to reduce the density of mosquito vectors and the spread of mosquito-borne diseases. This smart trap uses computer vision technology and deep learning networks to identify features of live Aedes aegypti and Culex quinquefasciatus in real-time. A unique mechanical design based on the rotation concept is also proposed and implemented to capture specific living mosquitoes into the corresponding chambers successfully. Moreover, this system is equipped with sensors to detect environmental data, such as CO2 concentration, temperature, and humidity. We successfully demonstrated the implementation of such a tool and paired it with a reliable capture mechanism for live mosquitos without destroying important morphological features. The neural network achieved 91.57% accuracy with test set images. When the trap prototype was applied in a tent, the accuracy rate in distinguishing live Ae. aegypti was 92%, with a capture rate reaching 44%. When the prototype was placed into a BG trap to produce a smart mosquito trap, it achieved a 97% recognition rate and a 67% catch rate when placed in the tent. In a simulated living room, the recognition and capture rates were 90% and 49%, respectively. This smart trap correctly differentiated between Cx. quinquefasciatus and Ae. aegypti mosquitoes, and may also help control mosquito-borne diseases and predict their possible outbreak. |
| first_indexed | 2024-04-10T21:20:49Z |
| format | Article |
| id | doaj.art-8bdf63742e624bb4854def570d57663b |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-04-10T21:20:49Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-8bdf63742e624bb4854def570d57663b2023-01-20T05:18:06ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852023-01-011110.3389/fbioe.2023.11009681100968An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillanceWei-Liang Liu0Yuhling Wang1Yu-Xuan Chen2Yu-Xuan Chen3Bo-Yu Chen4Arvin Yi-Chu Lin5Sheng-Tong Dai6Chun-Hong Chen7Chun-Hong Chen8Chun-Hong Chen9Lun-De Liao10National Mosquito-Borne Diseases Control Research Center, National Health Research Institutes, Zhunan Township, TaiwanInstitute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Zhunan Township, TaiwanNational Mosquito-Borne Diseases Control Research Center, National Health Research Institutes, Zhunan Township, TaiwanDepartment of Biotechnology and Bioindustry Sciences, National Cheng Kung University, Tainan, TaiwanNational Mosquito-Borne Diseases Control Research Center, National Health Research Institutes, Zhunan Township, TaiwanInstitute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Zhunan Township, TaiwanInstitute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Zhunan Township, TaiwanNational Mosquito-Borne Diseases Control Research Center, National Health Research Institutes, Zhunan Township, TaiwanNational Institute of Infectious Diseases and Vaccinology, National Health Research Institutes, Zhunan Township, TaiwanInstitute of Molecular Medicine, College of Medicine, National Taiwan University, Taipei, TaiwanInstitute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Zhunan Township, TaiwanAn essential aspect of controlling and preventing mosquito-borne diseases is to reduce mosquitoes that carry viruses. We designed a smart mosquito trap system to reduce the density of mosquito vectors and the spread of mosquito-borne diseases. This smart trap uses computer vision technology and deep learning networks to identify features of live Aedes aegypti and Culex quinquefasciatus in real-time. A unique mechanical design based on the rotation concept is also proposed and implemented to capture specific living mosquitoes into the corresponding chambers successfully. Moreover, this system is equipped with sensors to detect environmental data, such as CO2 concentration, temperature, and humidity. We successfully demonstrated the implementation of such a tool and paired it with a reliable capture mechanism for live mosquitos without destroying important morphological features. The neural network achieved 91.57% accuracy with test set images. When the trap prototype was applied in a tent, the accuracy rate in distinguishing live Ae. aegypti was 92%, with a capture rate reaching 44%. When the prototype was placed into a BG trap to produce a smart mosquito trap, it achieved a 97% recognition rate and a 67% catch rate when placed in the tent. In a simulated living room, the recognition and capture rates were 90% and 49%, respectively. This smart trap correctly differentiated between Cx. quinquefasciatus and Ae. aegypti mosquitoes, and may also help control mosquito-borne diseases and predict their possible outbreak.https://www.frontiersin.org/articles/10.3389/fbioe.2023.1100968/fullmosquito-borne diseasesAedes aegyptiCulex quinquefasciatuscomputer vision technologydeep learning |
| spellingShingle | Wei-Liang Liu Yuhling Wang Yu-Xuan Chen Yu-Xuan Chen Bo-Yu Chen Arvin Yi-Chu Lin Sheng-Tong Dai Chun-Hong Chen Chun-Hong Chen Chun-Hong Chen Lun-De Liao An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance Frontiers in Bioengineering and Biotechnology mosquito-borne diseases Aedes aegypti Culex quinquefasciatus computer vision technology deep learning |
| title | An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance |
| title_full | An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance |
| title_fullStr | An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance |
| title_full_unstemmed | An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance |
| title_short | An IoT-based smart mosquito trap system embedded with real-time mosquito image processing by neural networks for mosquito surveillance |
| title_sort | iot based smart mosquito trap system embedded with real time mosquito image processing by neural networks for mosquito surveillance |
| topic | mosquito-borne diseases Aedes aegypti Culex quinquefasciatus computer vision technology deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2023.1100968/full |
| work_keys_str_mv | AT weiliangliu aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT yuhlingwang aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT yuxuanchen aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT yuxuanchen aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT boyuchen aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT arvinyichulin aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT shengtongdai aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT chunhongchen aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT chunhongchen aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT chunhongchen aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT lundeliao aniotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT weiliangliu iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT yuhlingwang iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT yuxuanchen iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT yuxuanchen iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT boyuchen iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT arvinyichulin iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT shengtongdai iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT chunhongchen iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT chunhongchen iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT chunhongchen iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance AT lundeliao iotbasedsmartmosquitotrapsystemembeddedwithrealtimemosquitoimageprocessingbyneuralnetworksformosquitosurveillance |