{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T07:45:47Z","timestamp":1791877547480,"version":"4.3.4"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Malaysia Science Endowment"},{"name":"Malaysia-China Science and Technology People to People Exchange Programme 2025"},{"name":"Ministry of Higher Education Malaysia","id":[{"id":"https:\/\/ror.org\/05mcs2t73","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Prototype Research Grant Scheme","award":["PRGS-WAS-1\/2025"],"award-info":[{"award-number":["PRGS-WAS-1\/2025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Fire ants (Solenopsis spp. Westwood) pose a major ecological and economic threat, mainly due to the invasive potential of certain species. Current identification methods are highly dependent on taxonomic expertise, which can slow down decision-making. The development of an automated detection system could therefore support the identification process. We present SolenopsisDetector (SolenopD), an automated system for identifying Solenopsis ants using computer vision and deep learning. Following taxonomic practice, which emphasizes diagnostic body segments (head, thorax, abdomen), we evaluated 2 classification strategies: the use of whole-body images or segment-based images. To localize and crop out the target ants\/segments, we first trained and compared 3 detection algorithms (YOLOv5, YOLOv8, and YOLOv11) to localize ants and their body segments. We then tested 3 classification models (ResNet, MobileNet, and InceptionV3) to categorize the ants into 4 classes. A total of 8,300 images were used to develop SolenopD. Among the detection models, whole-body detection achieved 0.931 mAP, whereas segment-based detection achieved 0.788 mAP, representing an average improvement of 18.15% using YOLOv8 and YOLOv11. However, for classification, segment-based images\u2014especially thorax and abdomen\u2014provided higher accuracy than head or whole-body images, with InceptionV3 performing best. To further validate our approach, we used Grad-CAM to visualize the features used in the classification. The highlighted regions corresponded to the taxonomically relevant segments and emphasized the biological interpretability of the system. In summary, SolenopD integrates YOLOv11 for precise localization of ants and body segments, followed by InceptionV3 for accurate classification of Solenopsis spp.<\/jats:p>","DOI":"10.1093\/jee\/toag230","type":"journal-article","created":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T11:34:14Z","timestamp":1784460854000},"page":"3625-3635","source":"Crossref","is-referenced-by-count":0,"title":["<i>SolenopsisDetector<\/i>\n                    : development of an automatic detection system for fire ants using computer vision and deep\u00a0learning"],"prefix":"10.1093","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2869-4000","authenticated-orcid":false,"given":"Song-Quan","family":"Ong","sequence":"first","affiliation":[{"name":"Institute for Tropical Biology and Conservation (ITBC), Universiti Malaysia Sabah , Kota Kinabalu, Sabah,","place":["Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5297-8981","authenticated-orcid":false,"given":"Abdul Hafiz Ab","family":"Majid","sequence":"additional","affiliation":[{"name":"Household and Structural Urban Entomology Laboratory, Vector Control Research Unit, School of Biological Sciences, Universiti Sains Malaysia , Minden, Penang,","place":["Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Laboratory of Invasion Biology, School of Agricultural Sciences, Jiangxi Agricultural University , Nanchang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2560-8587","authenticated-orcid":false,"given":"Jian-Guo","family":"Wang","sequence":"additional","affiliation":[{"name":"Laboratory of Invasion Biology, School of Agricultural Sciences, Jiangxi Agricultural University , Nanchang,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"2026101302541291200_toag230-B1","first-page":"37","article-title":"Leptogenys ants (Hymenoptera: Formicidae: Ponerinae) of Sabah","volume":"15","author":"Bakhtiar","year":"2010","journal-title":"Serangga"},{"key":"2026101302541291200_toag230-B2","first-page":"139","author":"Bal\u00e1zs","year":"2021"},{"key":"2026101302541291200_toag230-B3","doi-asserted-by":"publisher","first-page":"102278","DOI":"10.1016\/j.ecoinf.2023.102278","article-title":"Hierarchical classification of insects with multitask learning and anomaly detection","volume":"77","author":"Bjerge","year":"2023","journal-title":"Ecol. Inform"},{"key":"2026101302541291200_toag230-B55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1101\/407452","article-title":"Taxonomic classification of ants (Formicidae) from images usingdeep learning","author":"Boer","year":"2018","journal-title":"bioRxiv"},{"key":"2026101302541291200_toag230-B4","doi-asserted-by":"publisher","author":"Brako-Medina","year":"2024","DOI":"10.1109\/ICECCE63537.2024.10823570"},{"key":"2026101302541291200_toag230-B5","doi-asserted-by":"publisher","author":"Brandt","year":"2023","DOI":"10.1007\/978-3-031-47715-7_2"},{"key":"2026101302541291200_toag230-B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11252-019-00893-3","article-title":"Ecological and socio-economic impacts of the red imported fire ant, Solenopsis invicta, on urban agricultural ecosystems","volume":"23","author":"Chan","year":"2020","journal-title":"Urban Ecosyst"},{"key":"2026101302541291200_toag230-B7","doi-asserted-by":"crossref","first-page":"10182","DOI":"10.3390\/su122310182","article-title":"Mapping the potential global distribution of Solenopsis invicta using machine learning","volume":"12","author":"Chen","year":"2020","journal-title":"Sustainability"},{"key":"2026101302541291200_toag230-B8","doi-asserted-by":"publisher","first-page":"103391","DOI":"10.1016\/j.ecoinf.2025.103391","article-title":"An automated approach for counting ants in densely populated images and gaining insight into ant foraging behavior","volume":"91","author":"Das","year":"2025","journal-title":"Ecol. Inform"},{"key":"2026101302541291200_toag230-B9","doi-asserted-by":"crossref","DOI":"10.1201\/9781315368023","volume-title":"Ants of Florida: identification and natural history","author":"Deyrup","year":"2016"},{"key":"2026101302541291200_toag230-B10","doi-asserted-by":"crossref","first-page":"12485","DOI":"10.1038\/ncomms12485","article-title":"Global threats from invasive alien species","volume":"7","author":"Early","year":"2016","journal-title":"Nat. Commun"},{"key":"2026101302541291200_toag230-B11","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.3390\/agronomy12081733","article-title":"Insect pest image recognition: a few-shot machine learning approach","volume":"12","author":"Gomes","year":"2022","journal-title":"Agronomy"},{"key":"2026101302541291200_toag230-B12","doi-asserted-by":"publisher","author":"He","year":"2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026101302541291200_toag230-B13","author":"Howard","year":"2017"},{"key":"2026101302541291200_toag230-B14","doi-asserted-by":"publisher","first-page":"470","DOI":"10.3390\/biology15060470","article-title":"AntID_APP: Empowering citizen scientists with YOLO models for ant identification in Taiwan","volume":"15","author":"Hsiung","year":"2026","journal-title":"Biology. (Basel)"},{"key":"2026101302541291200_toag230-B15","doi-asserted-by":"publisher","first-page":"e06279","DOI":"10.1111\/ecog.06279","article-title":"Using computer vision to understand global biogeography of ant color","volume":"2023","author":"Idec","year":"2023","journal-title":"Ecography"},{"key":"2026101302541291200_toag230-B16","doi-asserted-by":"publisher","author":"Ihrmark","year":"2025","DOI":"10.58009\/AERE-PERENNIUS0184"},{"key":"2026101302541291200_toag230-B17","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1093\/jee\/99.2.313","article-title":"Guidelines to improve identification of fire ants","volume":"99","author":"Jacobson","year":"2006","journal-title":"J. Econ. Entomol"},{"key":"2026101302541291200_toag230-B19","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1067\/mai.2000.105707","article-title":"Expanding habitat of Solenopsis invicta","volume":"105","author":"Kemp","year":"2000","journal-title":"J. Allergy Clin. Immunol"},{"key":"2026101302541291200_toag230-B20","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1002\/fee.1436","article-title":"Assessing data quality in citizen science","volume":"14","author":"Kosmala","year":"2016","journal-title":"Front. Ecol. Environ"},{"key":"2026101302541291200_toag230-B21","doi-asserted-by":"publisher","first-page":"75","DOI":"10.22364\/bjmc.2025.13.1.05","article-title":"Mobile device-based ants recognition and tracking system: methodology and frameworks","volume":"13","author":"Kushnir","year":"2025","journal-title":"BJMC"},{"key":"2026101302541291200_toag230-B22","doi-asserted-by":"publisher","first-page":"111673","DOI":"10.1016\/j.dib.2025.111673","article-title":"An annotated image dataset of urban insects for the development of computer vision and deep learning models with detection tasks","volume":"60","author":"Lim","year":"2025","journal-title":"Data Brief"},{"key":"2026101302541291200_toag230-B23","doi-asserted-by":"publisher","author":"Lotfi","year":"2021","DOI":"10.52458\/978-93-91842-08-6-38"},{"key":"2026101302541291200_toag230-B24","first-page":"102161","article-title":"A comprehensive review on YOLO versions for object detection. Eng. Sci. Technol","author":"Murat","year":"2025"},{"key":"2026101302541291200_toag230-B25","doi-asserted-by":"publisher","first-page":"e0279094","DOI":"10.1371\/journal.pone.0279094","article-title":"Next generation insect taxonomic classification by comparing different deep learning algorithms","volume":"17","author":"Ong","year":"2022","journal-title":"PLoS One"},{"key":"2026101302541291200_toag230-B26","doi-asserted-by":"publisher","first-page":"110741","DOI":"10.1016\/j.dib.2024.110741","article-title":"An annotated image dataset of pests on different coloured sticky traps acquired with different imaging devices","volume":"55","author":"Ong","year":"2024","journal-title":"Data Brief"},{"key":"2026101302541291200_toag230-B27","doi-asserted-by":"publisher","first-page":"e10212","DOI":"10.1002\/ece3.10212","article-title":"Digitization of natural history collections: a guideline and nationwide capacity building workshop in Malaysia","volume":"13","author":"Ong","year":"2023","journal-title":"Ecol. Evol"},{"key":"2026101302541291200_toag230-B51","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1017\/S000748532400018X","article-title":"Application of computer vision and deep learning models to automatically classify medically important mosquitoes in North Borneo, Malaysia","volume":"114","author":"Ong","year":"2024","journal-title":"Bull. Entomol. Res"},{"key":"2026101302541291200_toag230-B54","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1002\/ps.8464","article-title":"Trap colour strongly affects the ability of deep learning models to recognize insect species in images of sticky traps","volume":"81","author":"Ong","year":"2025","journal-title":"Pest Manag. Sci"},{"key":"2026101302541291200_toag230-B52","doi-asserted-by":"publisher","first-page":"103383","DOI":"10.1016\/j.ecoinf.2025.103383","article-title":"AntPi: A Raspberry Pi based edge-cloud system for real-time ant species detection using YOLO","volume":"18","author":"Palazzetti","year":"2025","journal-title":"Ecol. Inform"},{"key":"2026101302541291200_toag230-B28","doi-asserted-by":"publisher","first-page":"308","DOI":"10.4289\/0013-8797.120.2.308","article-title":"Revision of the fire ants of the Solenopsis saevissima species-group (Hymenoptera: Formicidae)","volume":"120","author":"Pitts","year":"2018","journal-title":"Proc. Entomol. Soc. Wash"},{"key":"2026101302541291200_toag230-B29","doi-asserted-by":"crossref","first-page":"100252","DOI":"10.1016\/j.atech.2023.100252","article-title":"AntTracker: computer vision for leaf-cutter ants","author":"Sabattini","year":"2023","journal-title":"Smart Agric. Technol"},{"key":"2026101302541291200_toag230-B30","doi-asserted-by":"publisher","author":"Selvaraju","year":"2017","DOI":"10.1109\/ICCV.2017.74"},{"key":"2026101302541291200_toag230-B31","doi-asserted-by":"publisher","first-page":"54362","DOI":"10.1007\/s11356-021-15961-5","article-title":"Impact of invasive ant species on native fauna across similar habitats under global environmental changes","volume":"28","author":"Siddiqui","year":"2021","journal-title":"Environ. Sci. Pollut. Res. Int"},{"key":"2026101302541291200_toag230-B32","doi-asserted-by":"publisher","first-page":"5277","DOI":"10.1002\/ps.8254","article-title":"The implementation of robotic dogs in automatic detection and surveillance of red imported fire ant nests","volume":"80","author":"Su","year":"2024","journal-title":"Pest Manag. Sci"},{"key":"2026101302541291200_toag230-B33","doi-asserted-by":"publisher","author":"Szegedy","year":"2016","DOI":"10.1109\/CVPR.2016.308"},{"key":"2026101302541291200_toag230-B34","first-page":"141","article-title":"A revision of the fire ants, Solenopsis geminata group (Hymenoptera: Formicidae: Myrmicinae)","author":"Trager","year":"1991","journal-title":"J. NY. Entomol. Soc"},{"key":"2026101302541291200_toag230-B53","doi-asserted-by":"publisher","first-page":"e59133","DOI":"10.3897\/biss.4.59133","article-title":"An Overview of Computer Vision in iNaturalist","volume":"4","author":"Ueda","year":"2020","journal-title":". Biodivers. Inf. Sci. Stand"},{"key":"2026101302541291200_toag230-B35","doi-asserted-by":"publisher","author":"Van Horn","year":"2018","DOI":"10.1109\/CVPR.2018.00914"},{"key":"2026101302541291200_toag230-B36","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.1111\/2041-210X.13075","article-title":"Machine learning for image based species identification","volume":"9","author":"W\u00e4ldchen","year":"2018","journal-title":"Methods Ecol. Evol"},{"key":"2026101302541291200_toag230-B38","doi-asserted-by":"publisher","first-page":"11566","DOI":"10.1038\/s41598-023-28734-6","article-title":"Learning from algorithm-generated pseudo-annotations for detecting ants in videos","volume":"13","author":"Zhang","year":"2023","journal-title":"Sci. Rep"},{"key":"2026101302541291200_toag230-B39","doi-asserted-by":"publisher","author":"Zhou","year":"2016","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Journal of Economic Entomology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jee\/article-pdf\/119\/5\/3625\/70479285\/toag230.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jee\/article-pdf\/119\/5\/3625\/70479285\/toag230.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T06:54:22Z","timestamp":1791874462000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jee\/article\/119\/5\/3625\/8751014"}},"subtitle":[],"editor":[{"given":"David","family":"Oi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":42,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,8,4]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jee\/toag230","relation":{},"ISSN":["0022-0493","1938-291X"],"issn-type":[{"value":"0022-0493","type":"print"},{"value":"1938-291X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,8,4]]}}}