DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning
<b>Background/Objectives</b>: The accurate identification of insect bites from images of skin is daunting due to the fine gradations among diverse bite types, variability in human skin response, and inconsistencies in image quality. <b>Methods</b>: For this work, we introduce...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/15/1841 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239616210599936 |
|---|---|
| author | Doston Khasanov Halimjon Khujamatov Muksimova Shakhnoza Mirjamol Abdullaev Temur Toshtemirov Shahzoda Anarova Cheolwon Lee Heung-Seok Jeon |
| author_facet | Doston Khasanov Halimjon Khujamatov Muksimova Shakhnoza Mirjamol Abdullaev Temur Toshtemirov Shahzoda Anarova Cheolwon Lee Heung-Seok Jeon |
| author_sort | Doston Khasanov |
| collection | DOAJ |
| description | <b>Background/Objectives</b>: The accurate identification of insect bites from images of skin is daunting due to the fine gradations among diverse bite types, variability in human skin response, and inconsistencies in image quality. <b>Methods</b>: For this work, we introduce DeepBiteNet, a new ensemble-based deep learning model designed to perform robust multiclass classification of insect bites from RGB images. Our model aggregates three semantically diverse convolutional neural networks—DenseNet121, EfficientNet-B0, and MobileNetV3-Small—using a stacked meta-classifier designed to aggregate their predicted outcomes into an integrated, discriminatively strong output. Our technique balances heterogeneous feature representation with suppression of individual model biases. Our model was trained and evaluated on a hand-collected set of 1932 labeled images representing eight classes, consisting of common bites such as mosquito, flea, and tick bites, and unaffected skin. Our domain-specific augmentation pipeline imputed practical variability in lighting, occlusion, and skin tone, thereby boosting generalizability. <b>Results</b>: Our model, DeepBiteNet, achieved a training accuracy of 89.7%, validation accuracy of 85.1%, and test accuracy of 84.6%, and surpassed fifteen benchmark CNN architectures on all key indicators, viz., precision (0.880), recall (0.870), and F1-score (0.875). Our model, optimized for mobile deployment with quantization and TensorFlow Lite, enables rapid on-client computation and eliminates reliance on cloud-based processing. <b>Conclusions</b>: Our work shows how ensemble learning, when carefully designed and combined with realistic data augmentation, can boost the reliability and usability of automatic insect bite diagnosis. Our model, DeepBiteNet, forms a promising foundation for future integration with mobile health (mHealth) solutions and may complement early diagnosis and triage in dermatologically underserved regions. |
| format | Article |
| id | doaj-art-d2a308e449834b85866e79b85d5f0e6a |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-d2a308e449834b85866e79b85d5f0e6a2025-08-20T04:00:54ZengMDPI AGDiagnostics2075-44182025-07-011515184110.3390/diagnostics15151841DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep LearningDoston Khasanov0Halimjon Khujamatov1Muksimova Shakhnoza2Mirjamol Abdullaev3Temur Toshtemirov4Shahzoda Anarova5Cheolwon Lee6Heung-Seok Jeon7Department of Data Communication Networks and Systems, Tashkent University of Information Technologies, Tashkent 100084, UzbekistanDepartment of Computer Engineering, Gachon University, Seognam-daero, Sujeong-gu, Seongnam-si 1342, Republic of KoreaDepartment of Computer Engineering, Gachon University, Seognam-daero, Sujeong-gu, Seongnam-si 1342, Republic of KoreaDepartment of Information Systems and Technologies, Tashkent State University of Economics, Tashkent 100066, UzbekistanDepartment of Data Communication Networks and Systems, Tashkent University of Information Technologies, Tashkent 100084, UzbekistanDepartment of Data Communication Networks and Systems, Tashkent University of Information Technologies, Tashkent 100084, UzbekistanDepartment of Computer Engineering, Konkuk University, Chungju 05029, Republic of KoreaDepartment of Computer Engineering, Konkuk University, Chungju 05029, Republic of Korea<b>Background/Objectives</b>: The accurate identification of insect bites from images of skin is daunting due to the fine gradations among diverse bite types, variability in human skin response, and inconsistencies in image quality. <b>Methods</b>: For this work, we introduce DeepBiteNet, a new ensemble-based deep learning model designed to perform robust multiclass classification of insect bites from RGB images. Our model aggregates three semantically diverse convolutional neural networks—DenseNet121, EfficientNet-B0, and MobileNetV3-Small—using a stacked meta-classifier designed to aggregate their predicted outcomes into an integrated, discriminatively strong output. Our technique balances heterogeneous feature representation with suppression of individual model biases. Our model was trained and evaluated on a hand-collected set of 1932 labeled images representing eight classes, consisting of common bites such as mosquito, flea, and tick bites, and unaffected skin. Our domain-specific augmentation pipeline imputed practical variability in lighting, occlusion, and skin tone, thereby boosting generalizability. <b>Results</b>: Our model, DeepBiteNet, achieved a training accuracy of 89.7%, validation accuracy of 85.1%, and test accuracy of 84.6%, and surpassed fifteen benchmark CNN architectures on all key indicators, viz., precision (0.880), recall (0.870), and F1-score (0.875). Our model, optimized for mobile deployment with quantization and TensorFlow Lite, enables rapid on-client computation and eliminates reliance on cloud-based processing. <b>Conclusions</b>: Our work shows how ensemble learning, when carefully designed and combined with realistic data augmentation, can boost the reliability and usability of automatic insect bite diagnosis. Our model, DeepBiteNet, forms a promising foundation for future integration with mobile health (mHealth) solutions and may complement early diagnosis and triage in dermatologically underserved regions.https://www.mdpi.com/2075-4418/15/15/1841multiclass classificationensemble deep learninginsect bite recognitionstacked meta-classifierimage-based diagnosis |
| spellingShingle | Doston Khasanov Halimjon Khujamatov Muksimova Shakhnoza Mirjamol Abdullaev Temur Toshtemirov Shahzoda Anarova Cheolwon Lee Heung-Seok Jeon DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning Diagnostics multiclass classification ensemble deep learning insect bite recognition stacked meta-classifier image-based diagnosis |
| title | DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning |
| title_full | DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning |
| title_fullStr | DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning |
| title_full_unstemmed | DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning |
| title_short | DeepBiteNet: A Lightweight Ensemble Framework for Multiclass Bug Bite Classification Using Image-Based Deep Learning |
| title_sort | deepbitenet a lightweight ensemble framework for multiclass bug bite classification using image based deep learning |
| topic | multiclass classification ensemble deep learning insect bite recognition stacked meta-classifier image-based diagnosis |
| url | https://www.mdpi.com/2075-4418/15/15/1841 |
| work_keys_str_mv | AT dostonkhasanov deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT halimjonkhujamatov deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT muksimovashakhnoza deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT mirjamolabdullaev deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT temurtoshtemirov deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT shahzodaanarova deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT cheolwonlee deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning AT heungseokjeon deepbitenetalightweightensembleframeworkformulticlassbugbiteclassificationusingimagebaseddeeplearning |