Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Early detection of autism spectrum disorder through hybrid deep learning and classical machine learning approaches

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 4 (2026) · hlm. 3305–3313

DOI
10.11591/eei.v15i4.10905
ISSN
2089-3191, 2302-9285
Terbit
2026-08-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Early detection of autism spectrum disorder (ASD) is essential for timely intervention. This study presents a hybrid artificial intelligence framework for non-invasive ASD pre-screening using children’s coloring, drawing, and handwriting activities. The proposed framework combines deep convolutional neural networks (VGG16, ResNet50, and EfficientNetB0) as feature extractors with a support vector machine (SVM) classifier to distinguish four diagnostic categories: non-ASD, mild ASD, moderate ASD, and severe ASD. Experimental results demonstrate task-specific performance across architectures. ResNet50–SVM achieved perfect classification for coloring tasks, with 100% accuracy, precision, recall, and F1-score. VGG16–SVM performed best for drawing, achieving 88% accuracy and recall, 89% precision, and an F1-score of 87%. EfficientNetB0–SVM produced the highest handwriting performance, achieving 96% across all evaluation metrics. These findings demonstrate the potential of computer vision-based analysis of children’s expressive activities as an effective, non-invasive ASD pre-screening tool. Future work will focus on expanding dataset diversity and integrating multimodal behavioral cues to improve model generalization and clinical applicability.

Kata kunci

Jaringan kolaborasi para penulis

28 penulis · 88 tautan kepenulisan bersama · 39 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universiti Teknikal Malaysia Melaka
  • National University of Malaysia
  • Diponegoro University
  • Sunan Gunung Djati State Islamic University Bandung
  • University of Technology Malaysia
  • Open University Malaysia
  • Universiti Teknologi Petronas
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Ummi Rabaah HashimUniversiti Teknikal Malaysia Melaka2
Mohd Hilmi HasanUniversiti Teknologi Petronas2
Dian Sa’adillah MaylawatiSunan Gunung Djati State Islamic University Bandung2
Muhammad Ali RamdhaniSunan Gunung Djati State Islamic University Bandung2
Anton Satria PrabuwonoKing Abdulaziz University1
Azizi AbdullahNational University of Malaysia1
Lizawati Binti SalahuddinUniversiti Teknikal Malaysia Melaka1
Teo Hong ChunUniversiti Teknikal Malaysia Melaka1
Ummi Raba’ah HashimAfiliasi tidak diketahui1
Sabrina AhmadUniversiti Teknikal Malaysia Melaka1
Kasturi KanchymalayUniversiti Teknikal Malaysia Melaka1
Asih Dwi MeilaniDiponegoro University1
Rahma Prafinta SariUniversitas Semarang1
Nur Diana Izzani MasdzarifUniversiti Teknikal Malaysia Melaka1
Siti Azirah AsmaiUniversiti Teknikal Malaysia Melaka1
Muhammad Hafidz Fazli Md FauadiUniversiti Teknikal Malaysia Melaka1
Chiah Chin LimUniversiti Teknikal Malaysia Melaka1
Yuen Chin WongUniversiti Teknikal Malaysia Melaka1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Early detection of autism spectrum disorder through hybrid deep learning and classical machine learning approaches</dc:title><dc:creator>Aina Khairina Ahmad Khair</dc:creator><dc:creator>Wan Mohd Yaakob Wan Bejuri</dc:creator><dc:creator>Mohd Murtadha Mohamad</dc:creator><dc:creator>Masne Kadar</dc:creator><dc:creator>Zulaikha Zulaikha</dc:creator><dc:creator>Hadrina Sh-Hussain</dc:creator><dc:creator>Deasy Wahyuni</dc:creator><dc:creator>Fauziah Binti Kasmin</dc:creator><dc:creator>Ngo Hea Choon</dc:creator><dc:creator>Yogan Jaya Kumar</dc:creator><dc:subject>autism spectrum disorder</dc:subject><dc:subject>early detection</dc:subject><dc:subject>children's drawings</dc:subject><dc:subject>children's coloring</dc:subject><dc:subject>handwriting analysis</dc:subject><dc:subject>convolutional neural networks</dc:subject><dc:subject>support vector machine</dc:subject><dc:subject>hybrid deep learning model</dc:subject><dc:subject>non-invasive screening</dc:subject><dc:subject>severity classification</dc:subject><dc:description xml:lang="en">Early detection of autism spectrum disorder (ASD) is essential for timely intervention. This study presents a hybrid artificial intelligence framework for non-invasive ASD pre-screening using children’s coloring, drawing, and handwriting activities. The proposed framework combines deep convolutional neural networks (VGG16, ResNet50, and EfficientNetB0) as feature extractors with a support vector machine (SVM) classifier to distinguish four diagnostic categories: non-ASD, mild ASD, moderate ASD, and severe ASD. Experimental results demonstrate task-specific performance across architectures. ResNet50–SVM achieved perfect classification for coloring tasks, with 100% accuracy, precision, recall, and F1-score. VGG16–SVM performed best for drawing, achieving 88% accuracy and recall, 89% precision, and an F1-score of 87%. EfficientNetB0–SVM produced the highest handwriting performance, achieving 96% across all evaluation metrics. These findings demonstrate the potential of computer vision-based analysis of children’s expressive activities as an effective, non-invasive ASD pre-screening tool. Future work will focus on expanding dataset diversity and integrating multimodal behavioral cues to improve model generalization and clinical applicability.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-08-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i4.10905</dc:identifier><dc:identifier>10.11591/eei.v15i4.10905</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 4 (2026); 3305-3313</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/10905/4892</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>