Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance
This study introduces a hybrid approach that combines unsupervised self-organizing maps (SOM) with a supervised convolutional neural network (CNN) to enhance model accuracy in vector-borne disease modeling. We applied this method to predict insecticide resistance (IR) status in key malaria vectors a...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016125000469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087513027575808 |
|---|---|
| author | Komi Mensah Agboka Elfatih M. Abdel-Rahman Daisy Salifu Brian Kanji Frank T. Ndjomatchoua Ritter A.Y. Guimapi Sunday Ekesi Landmann Tobias |
| author_facet | Komi Mensah Agboka Elfatih M. Abdel-Rahman Daisy Salifu Brian Kanji Frank T. Ndjomatchoua Ritter A.Y. Guimapi Sunday Ekesi Landmann Tobias |
| author_sort | Komi Mensah Agboka |
| collection | DOAJ |
| description | This study introduces a hybrid approach that combines unsupervised self-organizing maps (SOM) with a supervised convolutional neural network (CNN) to enhance model accuracy in vector-borne disease modeling. We applied this method to predict insecticide resistance (IR) status in key malaria vectors across Africa. Our results show that the combined SOM/CNN approach is more robust than a standalone CNN model, achieving higher overall accuracy and Kappa scores among others. This confirms the potential of the SOM/CNN hybrid as an effective and reliable tool for improving model accuracy in public health applications. • The hybrid model, combining SOM and CNN, was implemented to predict IR status in malaria vectors, providing enhanced accuracy across various validation metrics. • Results indicate a notable improvement in robustness and predictive accuracy over traditional CNN models. • The combined SOM/CNN approach demonstrated higher Kappa scores and overall model accuracy. |
| format | Article |
| id | doaj-art-6bdf687ca58b4036a174416295a1d0ea |
| institution | Kabale University |
| issn | 2215-0161 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj-art-6bdf687ca58b4036a174416295a1d0ea2025-02-06T05:11:50ZengElsevierMethodsX2215-01612025-06-0114103198Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistanceKomi Mensah Agboka0Elfatih M. Abdel-Rahman1Daisy Salifu2Brian Kanji3Frank T. Ndjomatchoua4Ritter A.Y. Guimapi5Sunday Ekesi6Landmann Tobias7International Centre of Insect Physiology and Ecology (ICIPE), P.O. Box 30772 00100, Kenya; Corresponding author.International Centre of Insect Physiology and Ecology (ICIPE), P.O. Box 30772 00100, Kenya; School of Agricultural, Earth, and Environmental Sciences, University of KwaZulu-Natal, Pietermaritzburg 3209, South AfricaInternational Centre of Insect Physiology and Ecology (ICIPE), P.O. Box 30772 00100, KenyaInternational Centre of Insect Physiology and Ecology (ICIPE), P.O. Box 30772 00100, KenyaDepartment of Plant Sciences, School of the Biological Sciences, University of Cambridge, Cambridge CB2 3EA, United KingdomBiotechnology and Plant Health Division, Norwegian Institute of Bioeconomy Research (NIBIO), P.O. Box 115, Ås NO-1431, NorwayInternational Centre of Insect Physiology and Ecology (ICIPE), P.O. Box 30772 00100, KenyaInternational Centre of Insect Physiology and Ecology (ICIPE), P.O. Box 30772 00100, KenyaThis study introduces a hybrid approach that combines unsupervised self-organizing maps (SOM) with a supervised convolutional neural network (CNN) to enhance model accuracy in vector-borne disease modeling. We applied this method to predict insecticide resistance (IR) status in key malaria vectors across Africa. Our results show that the combined SOM/CNN approach is more robust than a standalone CNN model, achieving higher overall accuracy and Kappa scores among others. This confirms the potential of the SOM/CNN hybrid as an effective and reliable tool for improving model accuracy in public health applications. • The hybrid model, combining SOM and CNN, was implemented to predict IR status in malaria vectors, providing enhanced accuracy across various validation metrics. • Results indicate a notable improvement in robustness and predictive accuracy over traditional CNN models. • The combined SOM/CNN approach demonstrated higher Kappa scores and overall model accuracy.http://www.sciencedirect.com/science/article/pii/S2215016125000469Combining Self-Organizing Maps (SOM) and Convolutional Neural Network (CNN) for improving model accuracy |
| spellingShingle | Komi Mensah Agboka Elfatih M. Abdel-Rahman Daisy Salifu Brian Kanji Frank T. Ndjomatchoua Ritter A.Y. Guimapi Sunday Ekesi Landmann Tobias Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance MethodsX Combining Self-Organizing Maps (SOM) and Convolutional Neural Network (CNN) for improving model accuracy |
| title | Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance |
| title_full | Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance |
| title_fullStr | Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance |
| title_full_unstemmed | Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance |
| title_short | Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance |
| title_sort | towards combining self organizing maps som and convolutional neural network cnn for improving model accuracy application to malaria vectors phenotypic resistance |
| topic | Combining Self-Organizing Maps (SOM) and Convolutional Neural Network (CNN) for improving model accuracy |
| url | http://www.sciencedirect.com/science/article/pii/S2215016125000469 |
| work_keys_str_mv | AT komimensahagboka towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT elfatihmabdelrahman towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT daisysalifu towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT briankanji towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT franktndjomatchoua towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT ritterayguimapi towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT sundayekesi towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance AT landmanntobias towardscombiningselforganizingmapssomandconvolutionalneuralnetworkcnnforimprovingmodelaccuracyapplicationtomalariavectorsphenotypicresistance |