Autism Classification Using MobileNetV3 Feature Extraction and K-Nearest Neighbor Algorithm
DOI:
https://doi.org/10.35194/mji.v17i2.5934Keywords:
Autism Spectrum Disorder, MobileNetV3, Feature Extraction, K-Nearest Neighbor, Image ClassificationAbstract
Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and repetitive behaviors. Early detection of ASD is crucial; however, conventional diagnostic methods rely heavily on clinical observation and expert assessment, which can be time-consuming and resource-intensive. Along with the rapid development of artificial intelligence, especially in computer vision and machine learning, automated image-based approaches have gained attention as alternative tools for ASD screening. This study proposes a hybrid classification approach that integrates MobileNetV3 as a feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification using facial image data. Unlike previous CNN–KNN approaches, this study specifically explores the use of MobileNetV3’s lightweight architecture to generate compact and discriminative facial features, which are then classified using KNN to evaluate its effectiveness in low-complexity and resource-efficient settings. This design highlights the novelty of combining an optimized lightweight CNN with a distance-based classifier for autism detection from facial images. The dataset used in this research was obtained from Kaggle and consists of 2,940 labeled facial images of children categorized into Autism and non-Autism classes. This study proposes a hybrid classification approach that combines MobileNetV3 as a lightweight feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification. Experimental evaluations were conducted over multiple independent runs to improve statistical reliability, and model performance was assessed using accuracy, precision, recall, and F1-score. The results indicate that the proposed hybrid model achieves satisfactory and consistent performance while maintaining computational efficiency. These findings suggest that integrating lightweight deep learning models with classical machine learning algorithms can provide an effective and resource-efficient approach for autism classification, with potential applicability as a supportive tool for early ASD screening rather than a definitive clinical diagnosis.References
[1] A. Novianto dan M. D. Anasanti, “Autism Spectrum Disorder ( ASD ) Identification Using Feature-Based Machine Learning Classification Model,” vol. 17, no. 3, hal. 259–270, 2023.
[2] R. K. Reghunathan, P. Nanjagoundan, dan P. Venkidusamy, “Machine Learning-Based Classification of Autism Spectrum Disorder across Age Groups †,” 2024.
[3] F. M. Talaat, Z. H. Ali, R. R. Mostafa, dan N. El-rashidy, “Real-time facial emotion recognition model based on kernel autoencoder and convolutional neural network for autism children,” Soft Comput., vol. 28, no. 9, hal. 6695–6708, 2024, doi: 10.1007/s00500-023-09477-y.
[4] S. Srividhya dan D. Vidhya, “Detecting Autism Spectrum Disorder Using Machine Learning Techniques,” vol. 12, no. 03.
[5] H. Li, Y. Gu, J. Han, Y. Sun, H. Lei, dan C. Li, “Faster R-CNN-MobileNetV3 Based Micro Expression Detection for Autism Spectrum Disorder,” hal. 1–13, 2025.
[6] X. Wang, “Deep Learning Architectures for Alzheimer ’ s Diagnosis,” 2025.
[7] N. Zuzzaifa dan R. Rianto, “Convolutional Neural Network Untuk Perbandingan Optimizer Pada Citra Batang Pohon,” J. Sist. Cerdas, vol. 6, no. 3, hal. 179–188, 2023, doi: 10.37396/jsc.v6i3.268.
[8] N. P. Novani, D. R. Salsabila, R. Aisuwarya, L. Arief, dan N. Afriyeni, “Sistem Pendeteksi Gejala Awal Tantrum Pada Anak Autisme Melalui Ekspresi Wajah Dengan Convolutional Neural Network,” JITCE (Journal Inf. Technol. Comput. Eng., vol. 5, no. 02, hal. 93–106, 2021, doi: 10.25077/jitce.5.02.93-106.2021.
[9] K. R. R. Wardani, H. Suryalim, V. J. L. Engel, dan H. Christian, “Analisis Pemilihan Optimizer dalam Arsitektur Convolution Neural Network VGG16 dan Inception untuk Sistem Pengenalan Wajah,” J. Edukasi dan Penelit. Inform., vol. 9, no. 2, hal. 186, 2023, doi: 10.26418/jp.v9i2.60432.
[10] Y. C. Oktaviani dan Y. Wahyuningsih, “Face Expression Recognizer Dengan Convolutional Neural Network Untuk Membantu Penderita Autisme Mengenali Ekspresi Wajah Seseorang,” J. Inform. dan Tek. Elektro Terap., vol. 11, no. 3, 2023, doi: 10.23960/jitet.v11i3.3108.
[11] M. A. Hossain, S. Sakib, H. M. Abdullah, dan S. E. Arman, “Deep learning for mango leaf disease identification: A vision transformer perspective,” Heliyon, vol. 10, no. 17, hal. e36361, 2024, doi: 10.1016/j.heliyon.2024.e36361.
[12] A. Howard dkk., “Searching for mobileNetV3,” Proc. IEEE Int. Conf. Comput. Vis., hal. 1314–1324, 2019, doi: 10.1109/ICCV.2019.00140.
[13] S. F. D. Wardhana dan A. Nugroho, “Perbandingan Arsitektur MobileNetV2 dan MobileNetV3 Dalam Klasifikasi Jenis Jeruk,” J. Ilmu Komput. dan Bisnis, vol. 16, no. 1, hal. 25–34, 2025, doi: 10.47927/jikb.v16i1.916.
[14] R. C. B. Rego, V. M. L. Silva, dan V. M. Fernandes, “Predicting Gender by First Name Using Character-level Machine Learning,” 2021.
[15] G. Litjens dkk., “A Survey on Deep Learning in Medical Imaage Analysis,” no. 1995, 1998.
[16] P. Wahyu Setiyo Aji, R. Dijaya, dan F. Sains dan Teknologi, “KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) Prediksi Penyakit Stroke Menggunakan Metode Random Forest,” J. Penerapan Sist. Inf., vol. 4, no. 4, hal. 916–924, 2023.
[17] C. Shorten dan T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, 2019, doi: 10.1186/s40537-019-0197-0.
[18] R. R. Chevuri, “The Role of GPUs in Accelerating Machine Learning Workloads,” vol. 11, no. 2, hal. 2676–2684, 2025.
[19] S. Alden dan B. N. Sari, “Implementasi Algoritma CNN Untuk Pemilahan Jenis Sampah Berbasis Android Dengan Metode CRISP-DM,” J. Inform., vol. 10, no. 1, hal. 62–71, 2023, doi: 10.31294/inf.v10i1.14985.
[20] R. D. Wicaksono dan G. F. Shidiq, “Comparison of KNN and CNN Algorithms for Gender Classification Based on Eye Images,” vol. 11, no. 4, hal. 915–924, 2024, doi: 10.15294/sji.v11i4.13529.
[21] D. Mazumder dan T. Islam, “Franklin Open Evaluating the efficacy and site-specific performance of machine learning approaches?: A comprehensive review of autism detection models,” Franklin Open, vol. 11, no. April, hal. 100275, 2025, doi: 10.1016/j.fraope.2025.100275.
[22] E. Prihatini dkk., “Facial Expression Detection of Autism Children Using ResNet-50 in Convolutional Neural Network Algorithm,” vol. 8, no. 3, hal. 765–775, 2025.
[23] Kadek Ninda Nandita Putri, “Penerapan Fine-Tuning Resnet50 Dan Support Vector Machine (Svm) Untuk Klasifikasi Autism Specturm Disorder (Asd) Berbasis Citra Wajah,” 2025, hal. 5–6, 2025.
[2] R. K. Reghunathan, P. Nanjagoundan, dan P. Venkidusamy, “Machine Learning-Based Classification of Autism Spectrum Disorder across Age Groups †,” 2024.
[3] F. M. Talaat, Z. H. Ali, R. R. Mostafa, dan N. El-rashidy, “Real-time facial emotion recognition model based on kernel autoencoder and convolutional neural network for autism children,” Soft Comput., vol. 28, no. 9, hal. 6695–6708, 2024, doi: 10.1007/s00500-023-09477-y.
[4] S. Srividhya dan D. Vidhya, “Detecting Autism Spectrum Disorder Using Machine Learning Techniques,” vol. 12, no. 03.
[5] H. Li, Y. Gu, J. Han, Y. Sun, H. Lei, dan C. Li, “Faster R-CNN-MobileNetV3 Based Micro Expression Detection for Autism Spectrum Disorder,” hal. 1–13, 2025.
[6] X. Wang, “Deep Learning Architectures for Alzheimer ’ s Diagnosis,” 2025.
[7] N. Zuzzaifa dan R. Rianto, “Convolutional Neural Network Untuk Perbandingan Optimizer Pada Citra Batang Pohon,” J. Sist. Cerdas, vol. 6, no. 3, hal. 179–188, 2023, doi: 10.37396/jsc.v6i3.268.
[8] N. P. Novani, D. R. Salsabila, R. Aisuwarya, L. Arief, dan N. Afriyeni, “Sistem Pendeteksi Gejala Awal Tantrum Pada Anak Autisme Melalui Ekspresi Wajah Dengan Convolutional Neural Network,” JITCE (Journal Inf. Technol. Comput. Eng., vol. 5, no. 02, hal. 93–106, 2021, doi: 10.25077/jitce.5.02.93-106.2021.
[9] K. R. R. Wardani, H. Suryalim, V. J. L. Engel, dan H. Christian, “Analisis Pemilihan Optimizer dalam Arsitektur Convolution Neural Network VGG16 dan Inception untuk Sistem Pengenalan Wajah,” J. Edukasi dan Penelit. Inform., vol. 9, no. 2, hal. 186, 2023, doi: 10.26418/jp.v9i2.60432.
[10] Y. C. Oktaviani dan Y. Wahyuningsih, “Face Expression Recognizer Dengan Convolutional Neural Network Untuk Membantu Penderita Autisme Mengenali Ekspresi Wajah Seseorang,” J. Inform. dan Tek. Elektro Terap., vol. 11, no. 3, 2023, doi: 10.23960/jitet.v11i3.3108.
[11] M. A. Hossain, S. Sakib, H. M. Abdullah, dan S. E. Arman, “Deep learning for mango leaf disease identification: A vision transformer perspective,” Heliyon, vol. 10, no. 17, hal. e36361, 2024, doi: 10.1016/j.heliyon.2024.e36361.
[12] A. Howard dkk., “Searching for mobileNetV3,” Proc. IEEE Int. Conf. Comput. Vis., hal. 1314–1324, 2019, doi: 10.1109/ICCV.2019.00140.
[13] S. F. D. Wardhana dan A. Nugroho, “Perbandingan Arsitektur MobileNetV2 dan MobileNetV3 Dalam Klasifikasi Jenis Jeruk,” J. Ilmu Komput. dan Bisnis, vol. 16, no. 1, hal. 25–34, 2025, doi: 10.47927/jikb.v16i1.916.
[14] R. C. B. Rego, V. M. L. Silva, dan V. M. Fernandes, “Predicting Gender by First Name Using Character-level Machine Learning,” 2021.
[15] G. Litjens dkk., “A Survey on Deep Learning in Medical Imaage Analysis,” no. 1995, 1998.
[16] P. Wahyu Setiyo Aji, R. Dijaya, dan F. Sains dan Teknologi, “KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) Prediksi Penyakit Stroke Menggunakan Metode Random Forest,” J. Penerapan Sist. Inf., vol. 4, no. 4, hal. 916–924, 2023.
[17] C. Shorten dan T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, 2019, doi: 10.1186/s40537-019-0197-0.
[18] R. R. Chevuri, “The Role of GPUs in Accelerating Machine Learning Workloads,” vol. 11, no. 2, hal. 2676–2684, 2025.
[19] S. Alden dan B. N. Sari, “Implementasi Algoritma CNN Untuk Pemilahan Jenis Sampah Berbasis Android Dengan Metode CRISP-DM,” J. Inform., vol. 10, no. 1, hal. 62–71, 2023, doi: 10.31294/inf.v10i1.14985.
[20] R. D. Wicaksono dan G. F. Shidiq, “Comparison of KNN and CNN Algorithms for Gender Classification Based on Eye Images,” vol. 11, no. 4, hal. 915–924, 2024, doi: 10.15294/sji.v11i4.13529.
[21] D. Mazumder dan T. Islam, “Franklin Open Evaluating the efficacy and site-specific performance of machine learning approaches?: A comprehensive review of autism detection models,” Franklin Open, vol. 11, no. April, hal. 100275, 2025, doi: 10.1016/j.fraope.2025.100275.
[22] E. Prihatini dkk., “Facial Expression Detection of Autism Children Using ResNet-50 in Convolutional Neural Network Algorithm,” vol. 8, no. 3, hal. 765–775, 2025.
[23] Kadek Ninda Nandita Putri, “Penerapan Fine-Tuning Resnet50 Dan Support Vector Machine (Svm) Untuk Klasifikasi Autism Specturm Disorder (Asd) Berbasis Citra Wajah,” 2025, hal. 5–6, 2025.
Downloads
Published
2025-12-31
Issue
Section
Articles
