Hostname: page-component-76fb5796d-45l2p Total loading time: 0 Render date: 2024-04-29T21:27:52.748Z Has data issue: false hasContentIssue false
  • English
  • Français

Application of computer vision and deep learning models to automatically classify medically important mosquitoes in North Borneo, Malaysia

Published online by Cambridge University Press:  01 April 2024

Song-Quan Ong Open the ORCID record for Song-Quan Ong [Opens in a new window] ,
Abdul Hafiz Ab Majid ,
Wei-Jun Li  and
Jian-Guo Wang
Song-Quan Ong*
Affiliation:
Institute for Tropical Biology and Conservation, Universiti Malaysia Sabah, Jalan UMS, Kota Kinabalu, Sabah Malaysia
Abdul Hafiz Ab Majid
Affiliation:
Household & Structural Urban Entomology Laboratory, Vector Control Research Unit, School of Biological Sciences, Universiti Sains Malaysia, 11800 Penang, Malaysia
Wei-Jun Li
Affiliation:
Laboratory of Invasion Biology, School of Agricultural Sciences, Jiangxi Agricultural University, Nanchang 330045, China
Jian-Guo Wang
Affiliation:
Laboratory of Invasion Biology, School of Agricultural Sciences, Jiangxi Agricultural University, Nanchang 330045, China
*
Corresponding author: Song-Quan Ong; Email: songquan.ong@ums.edu.my; songguan26@gmail.com
Get access Rights & Permissions [Opens in a new window]

Abstract

Mosquito-borne diseases have emerged in North Borneo in Malaysia due to rapid changes in the forest landscape, and mosquito surveillance is key to understanding disease transmission. However, surveillance programmes involving sampling and taxonomic identification require well-trained personnel, are time-consuming and labour-intensive. In this study, we aim to use a deep leaning model (DL) to develop an application capable of automatically detecting mosquito vectors collected from urban and suburban areas in North Borneo, Malaysia. Specifically, a DL model called MobileNetV2 was developed using a total of 4880 images of Aedes aegypti, Aedes albopictus and Culex quinquefasciatus mosquitoes, which are widely distributed in Malaysia. More importantly, the model was deployed as an application that can be used in the field. The model was fine-tuned with hyperparameters of learning rate 0.0001, 0.0005, 0.001, 0.01 and the performance of the model was tested for accuracy, precision, recall and F1 score. Inference time was also considered during development to assess the feasibility of the model as an app in the real world. The model showed an accuracy of at least 97%, a precision of 96% and a recall of 97% on the test set. When used as an app in the field to detect mosquitoes with the elements of different background environments, the model was able to achieve an accuracy of 76% with an inference time of 47.33 ms. Our result demonstrates the practicality of computer vision and DL in the real world of vector and pest surveillance programmes. In the future, more image data and robust DL architecture can be explored to improve the prediction result.

Keywords

Borneo Nusantara citydengueintegrated pest management
Type
Research Paper
Information
Bulletin of Entomological Research , First View , pp. 1 - 6
Check for updates
Copyright
Copyright © The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Asmai, SA, Abidin, ZZ and Nizam AFNAR, MAM (2020) Aedes mosquito larvae recognition with a mobile app. Int J Adv Trends Comput Sci Eng 9, 5059–5065.CrossRefGoogle Scholar
Bin Said, I, Kouakou, YI, Omorou, R, Bienvenu, AL, Ahmed, K, Culleton, R and Picot, S (2022) Systematic review of Plasmodium knowlesi in Indonesia: a risk of emergence in the context of capital relocation to Borneo? Parasites & Vectors 15, 258.CrossRefGoogle ScholarPubMed
Cerf, VG (2013) Augmented intelligence. IEEE Internet Computing 17, 96–96.Google Scholar
Cheong, YL, Rosilawati, R, Mohd-Khairuddin, CI, Siti-Futri, FF, Nur-Ayuni, N, Lim, KH, Khairul-Asuad, M, Mohd-Zahari, TH, Mohd-Izral, YU, Mohd-Zainuldin, T, Nazni, WA and Lee, HL (2021) PesTrapp mobile app: a trap setting application for real-time entomological field and laboratory study. Tropical Biomedicine 38, 171–179.Google ScholarPubMed
Cioffi, R, Travaglioni, M, Piscitelli, G, Petrillo, A and De Felice, F (2020) Artificial intelligence and machine learning applications in smart production: progress, trends, and directions. Sustainability 12, 492.CrossRefGoogle Scholar
Han, S (2017) Efficient methods and hardware for deep learning (Doctoral dissertation, Stanford University).Google Scholar
Harshit, D. (2021) Different architectures of machine learning model deployment! Available at https://medium.com/mlearning-ai/different-architectures-of-machine-learning-model-deployment-250a4a3a37b4Google Scholar
Howard, AG, Zhu, M, Chen, B, Kalenichenko, D, Wang, W, Weyand, T, Andreetto, M and Adam, H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861./.Google Scholar
Isawasan, P, Abdullah, ZI, Ong, SQ and Salleh, KA (2023) A protocol for developing a classification system of mosquitoes using transfer learning. MethodsX 10, 101947.CrossRefGoogle ScholarPubMed
Kittichai, V, Pengsakul, T, Chumchuen, K, Samung, Y, Sriwichai, P, Phatthamolrat, N, Tongloy, T, Jaksukam, K, Chuwongin, S and Boonsang, S (2021) Deep learning approaches for challenging species and gender identification of mosquito vectors. Scientific Reports 11, 4838.CrossRefGoogle ScholarPubMed
Lee, S, Kim, H and Cho, BK (2023) Deep learning-based image classification for major mosquito species inhabiting Korea. Insects 14, 526.CrossRefGoogle ScholarPubMed
Li, Y, Kamara, F, Zhou, G, Puthiyakunnon, S, Li, C, Liu, Y, Zhou, Y, Yao, L, Yan, G and Chen, XG (2014) Urbanization increases Aedes albopictus larval habitats and accelerates mosquito development and survivorship. PloS Neglected Tropical Diseases 8, e3301.CrossRefGoogle ScholarPubMed
Maclaurin, D, Duvenaud, D and Adams, R (2015) June. Gradient-based hyperparameter optimization through reversible learning. In International conference on machine learning (pp. 2113–2122). PMLR.Google Scholar
Maluda, MCM, Jelip, J, Ibrahim, MY, Suleiman, M, Jeffree, MS, Aziz, AFB, Jani, J, Yahiro, T and Ahmed, K (2020) Nineteen years of Japanese encephalitis surveillance in Sabah, Malaysian borneo. The American Journal of Tropical Medicine and Hygiene 103, 864.CrossRefGoogle Scholar
Minakshi, M (2018) A Machine Learning Framework to Classify Mosquito Species From Smart-Phone Images. USF Tampa Graduate Theses and Dissertations. https://digitalcommons.usf.edu/etd/7340Google Scholar
Nitatpattana, N, Apiwathnasorn, C, Barbazan, P, Leemingsawat, S, Yoksan, S and Gonzalez, J (2005) First isolation of Japanese encephalitis from Culex quinquefasciatus in Thailand. Southeast Asian Journal of Tropical Medicine and Public Health 36, 875.Google ScholarPubMed
Okayasu, K, Yoshida, K, Fuchida, M and Nakamura, A (2019) Vision-based classification of mosquito species: comparison of conventional and deep learning methods. Applied Sciences 9, 3935.CrossRefGoogle Scholar
Ong, SQ (2016) Dengue vector control in Malaysia: a review for current and alternative strategies. Sains Malays 45, 777–785.Google Scholar
Ong, SQ, Ahmad, H, Nair, G, Isawasan, P and Majid, AHA (2021a) Implementation of a deep learning model for automated classification of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) in real time. Scientific Reports 11, 9908.CrossRefGoogle ScholarPubMed
Ong, SQ, Ahmad, H and Mohd Ngesom, AM (2021b) Implications of the COVID-19 lockdown on dengue transmission in Malaysia. Infectious Disease Reports 13, 148–160.CrossRefGoogle ScholarPubMed
Ong, SQ, Nair, G, Yusof, UK and Ahmad, H (2022) Community-based mosquito surveillance: an automatic mosquito-on-human-skin recognition system with a deep learning algorithm. Pest Management Science 78, 4092–4104.CrossRefGoogle ScholarPubMed
Pereira-dos-Santos, T, Roiz, D, Lourenço-de-Oliveira, R and Paupy, C (2020) A systematic review: is Aedes albopictus an efficient bridge vector for zoonotic arboviruses? Pathogens 9, 266.CrossRefGoogle ScholarPubMed
Qi, H, Liu, W and Liu, L (2017) November. An efficient deep learning hashing neural network for mobile visual search. In 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP) (pp. 701–704). IEEE.CrossRefGoogle Scholar
Schaffner, F and Mathis, A (2014) Dengue and dengue vectors in the WHO European region: past, present, and scenarios for the future. The Lancet Infectious Diseases 14, 1271–1280.CrossRefGoogle Scholar
Siddiqua, R, Rahman, S and Uddin, J (2021) A deep learning-based dengue mosquito detection method using faster R-CNN and image processing techniques. Annals of Emerging Technologies in Computing (AETiC) 5, 11–23.CrossRefGoogle Scholar
Siddiqui, AA and Kayte, C (2023) August. Transfer Learning for Mosquito Classification Using VGG16. In First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022) (pp. 471–484). Atlantis Press.CrossRefGoogle Scholar
Tang, G, Liang, R, Xie, Y, Bao, Y and Wang, S (2019) Improved convolutional neural networks for acoustic event classification. Multimedia Tools and Applications 78, 15801–15816.CrossRefGoogle Scholar
Vela, D, Sharp, A, Zhang, R, Nguyen, T, Hoang, A and Pianykh, OS (2022) Temporal quality degradation in AI models. Scientific Reports 12, 11654.CrossRefGoogle ScholarPubMed