Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices
The cacao pod borer (CPB) (<i>Conopomorpha cramerella</i>) is an invasive insect that causes significant economic loss for cacao farmers. One of the most efficient ways to reduce CPB damage is to continuously monitor its presence. Currently, most automated technologies for continuous ins...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/3/502 |
| _version_ | 1797242409989439488 |
|---|---|
| author | Eros Allan Somo Hacinas Lorenzo Sangco Querol Kris Lord T. Santos Evian Bless Matira Rhodina C. Castillo Mercedes Arcelo Divina Amalin Dan Jeric Arcega Rustia |
| author_facet | Eros Allan Somo Hacinas Lorenzo Sangco Querol Kris Lord T. Santos Evian Bless Matira Rhodina C. Castillo Mercedes Arcelo Divina Amalin Dan Jeric Arcega Rustia |
| author_sort | Eros Allan Somo Hacinas |
| collection | DOAJ |
| description | The cacao pod borer (CPB) (<i>Conopomorpha cramerella</i>) is an invasive insect that causes significant economic loss for cacao farmers. One of the most efficient ways to reduce CPB damage is to continuously monitor its presence. Currently, most automated technologies for continuous insect pest monitoring rely on an internet connection and a power source. However, most cacao plantations are remotely located and have limited access to internet and power sources; therefore, a simpler and readily available tool is necessary to enable continuous monitoring. This research proposes a mobile application developed for rapid and on-site counting of CPBs on sticky paper traps. A CPB counting algorithm was developed and optimized to enable on-device computations despite memory constraints and limited capacity of low-end mobile phones. The proposed algorithm has an F<sub>1</sub>-score of 0.88, with no significant difference from expert counts (R<sup>2</sup> = 0.97, <i>p</i>-value = 0.55, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> = 0.05). The mobile application can be used to provide the required information for pest control methods on-demand and is also accessible for low-income farms. This is one of the first few works on enabling on-device processing for insect pest monitoring. |
| first_indexed | 2024-04-24T18:38:46Z |
| format | Article |
| id | doaj.art-5d6c16dad1cc4da9b2a00d9945f78dd5 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-04-24T18:38:46Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-5d6c16dad1cc4da9b2a00d9945f78dd52024-03-27T13:16:43ZengMDPI AGAgronomy2073-43952024-02-0114350210.3390/agronomy14030502Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile DevicesEros Allan Somo Hacinas0Lorenzo Sangco Querol1Kris Lord T. Santos2Evian Bless Matira3Rhodina C. Castillo4Mercedes Arcelo5Divina Amalin6Dan Jeric Arcega Rustia7Department of Computer Technology, De La Salle University, Manila 0922, PhilippinesDepartment of Computer Technology, De La Salle University, Manila 0922, PhilippinesDepartment of Biology, De La Salle University, Manila 0922, PhilippinesDepartment of Biology, De La Salle University, Manila 0922, PhilippinesCollege of Agriculture, Sultan Kudarat State University, Tacurong 9800, PhilippinesBureau of Plant Industry—Davao, Davao City 1004, PhilippinesDepartment of Biology, De La Salle University, Manila 0922, PhilippinesWageningen Plant Research, Wageningen University & Research, 6708 PB Wageningen, The NetherlandsThe cacao pod borer (CPB) (<i>Conopomorpha cramerella</i>) is an invasive insect that causes significant economic loss for cacao farmers. One of the most efficient ways to reduce CPB damage is to continuously monitor its presence. Currently, most automated technologies for continuous insect pest monitoring rely on an internet connection and a power source. However, most cacao plantations are remotely located and have limited access to internet and power sources; therefore, a simpler and readily available tool is necessary to enable continuous monitoring. This research proposes a mobile application developed for rapid and on-site counting of CPBs on sticky paper traps. A CPB counting algorithm was developed and optimized to enable on-device computations despite memory constraints and limited capacity of low-end mobile phones. The proposed algorithm has an F<sub>1</sub>-score of 0.88, with no significant difference from expert counts (R<sup>2</sup> = 0.97, <i>p</i>-value = 0.55, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>α</mi></semantics></math></inline-formula> = 0.05). The mobile application can be used to provide the required information for pest control methods on-demand and is also accessible for low-income farms. This is one of the first few works on enabling on-device processing for insect pest monitoring.https://www.mdpi.com/2073-4395/14/3/502mobile computingmobile applicationinsect peststicky trapdeep learning |
| spellingShingle | Eros Allan Somo Hacinas Lorenzo Sangco Querol Kris Lord T. Santos Evian Bless Matira Rhodina C. Castillo Mercedes Arcelo Divina Amalin Dan Jeric Arcega Rustia Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices Agronomy mobile computing mobile application insect pest sticky trap deep learning |
| title | Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices |
| title_full | Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices |
| title_fullStr | Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices |
| title_full_unstemmed | Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices |
| title_short | Rapid Automatic Cacao Pod Borer Detection Using Edge Computing on Low-End Mobile Devices |
| title_sort | rapid automatic cacao pod borer detection using edge computing on low end mobile devices |
| topic | mobile computing mobile application insect pest sticky trap deep learning |
| url | https://www.mdpi.com/2073-4395/14/3/502 |
| work_keys_str_mv | AT erosallansomohacinas rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT lorenzosangcoquerol rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT krislordtsantos rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT evianblessmatira rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT rhodinaccastillo rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT mercedesarcelo rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT divinaamalin rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices AT danjericarcegarustia rapidautomaticcacaopodborerdetectionusingedgecomputingonlowendmobiledevices |