Open access Jurnal SINTA 2
Evaluasi Dan Optimalisasi Model CNN-Transformer Encoder dalam Deteksi Stres Melalui Sinyal Suara
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 13 No. 1 (2026) · pp. 189–198
- ISSN
- 2528-6579, 2355-7699
- Published
- 2026-02-26
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- id
Abstract
Bahasa Indonesia
Deteksi stres melalui sinyal suara masih menghadapi tantangan akurasi karena keterbatasan model konvensional dalam menangkap distribusi frekuensi spasial-temporal. Oleh karena itu, diperlukan pendekatan baru yang mampu mengekstraksi pola kompleks secara efektif. Artikel ini mengeksplorasi peningkatan performa deteksi stres melalui sinyal suara dengan mengintegrasikan model Convolutional Neural Network (CNN) dan Transformer Encoder. Kami mengevaluasi berbagai konfigurasi jumlah head pada self-attention dan nilai learning rate untuk model CNN-Transformer Encoder guna mengidentifikasi parameter optimal. Hasil eksperimen menunjukkan bahwa konfigurasi dengan 6 head pada Transformer Encoder dan learning rate 0,01 memberikan performa terbaik dengan nilai loss terendah sebesar 0,5034, akurasi tertinggi 78,37%, serta peningkatan pada precision, recall, dan F1-score. Selain itu, penggabungan model CNN dengan Transformer Encoder secara paralel secara signifikan meningkatkan akurasi deteksi stres dibandingkan dengan model baseline CNN dan DSCNN. Pengujian lebih lanjut menggunakan confusion matrix menunjukkan keunggulan model DSCNN-Transformer Encoder dalam mendeteksi kelas stres dengan akurasi tertinggi. Pengujian pada dataset yang berbeda juga menunjukkan bahwa model yang diusulkan memiliki kestabilan yang baik. Temuan ini menegaskan efektivitas integrasi Transformer Encoder dalam meningkatkan performa deteksi stres pada sinyal suara. Abstract Stress detection through speech signals still faces accuracy challenges due to the limitations of conventional models in capturing spatial-temporal frequency distributions. Therefore, new approaches are needed that can effectively extract complex patterns. This study explores enhancing stress detection performance through speech signals by integrating Convolutional Neural Network (CNN) and Transformer Encoder models. We evaluated various configurations of self-attention head counts and learning rates for the CNN-Transformer Encoder model to identify optimal parameters. Experimental results indicate that a configuration with 6 heads in the Transformer Encoder and a learning rate of 0.01 yields the best performance with the lowest loss of 0.5034, highest accuracy of 78.37%, and improvements in precision, recall, and F1-score. Furthermore, the parallel integration of CNN with Transformer Encoder significantly improves stress detection accuracy compared to baseline CNN and DSCNN models. Further analysis using confusion matrices highlights the superior performance of the DSCNN-Transformer Encoder model in detecting stress classes with the highest accuracy. These findings affirm the effectiveness of integrating Transformer Encoder in enhancing stress detection performance from voice signals.
English
Deteksi stres melalui sinyal suara masih menghadapi tantangan akurasi karena keterbatasan model konvensional dalam menangkap distribusi frekuensi spasial-temporal. Oleh karena itu, diperlukan pendekatan baru yang mampu mengekstraksi pola kompleks secara efektif. Artikel ini mengeksplorasi peningkatan performa deteksi stres melalui sinyal suara dengan mengintegrasikan model Convolutional Neural Network (CNN) dan Transformer Encoder. Kami mengevaluasi berbagai konfigurasi jumlah head pada self-attention dan nilai learning rate untuk model CNN-Transformer Encoder guna mengidentifikasi parameter optimal. Hasil eksperimen menunjukkan bahwa konfigurasi dengan 6 head pada Transformer Encoder dan learning rate 0,01 memberikan performa terbaik dengan nilai loss terendah sebesar 0,5034, akurasi tertinggi 78,37%, serta peningkatan pada precision, recall, dan F1-score. Selain itu, penggabungan model CNN dengan Transformer Encoder secara paralel secara signifikan meningkatkan akurasi deteksi stres dibandingkan dengan model baseline CNN dan DSCNN. Pengujian lebih lanjut menggunakan confusion matrix menunjukkan keunggulan model DSCNN-Transformer Encoder dalam mendeteksi kelas stres dengan akurasi tertinggi. Pengujian pada dataset yang berbeda juga menunjukkan bahwa model yang diusulkan memiliki kestabilan yang baik. Temuan ini menegaskan efektivitas integrasi Transformer Encoder dalam meningkatkan performa deteksi stres pada sinyal suara. Abstract Stress detection through speech signals still faces accuracy challenges due to the limitations of conventional models in capturing spatial-temporal frequency distributions. Therefore, new approaches are needed that can effectively extract complex patterns. This study explores enhancing stress detection performance through speech signals by integrating Convolutional Neural Network (CNN) and Transformer Encoder models. We evaluated various configurations of self-attention head counts and learning rates for the CNN-Transformer Encoder model to identify optimal parameters. Experimental results indicate that a configuration with 6 heads in the Transformer Encoder and a learning rate of 0.01 yields the best performance with the lowest loss of 0.5034, highest accuracy of 78.37%, and improvements in precision, recall, and F1-score. Furthermore, the parallel integration of CNN with Transformer Encoder significantly improves stress detection accuracy compared to baseline CNN and DSCNN models. Further analysis using confusion matrices highlights the superior performance of the DSCNN-Transformer Encoder model in detecting stress classes with the highest accuracy. These findings affirm the effectiveness of integrating Transformer Encoder in enhancing stress detection performance from voice signals.
Keywords
Collaboration network of the authors
35 authors · 76 co-authorship links
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- Affiliation unknown
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Dahnial Syauqy | University of Brawijaya | 5 |
| Eko Setiawan | University of Brawijaya | 4 |
| Wijaya Kurniawan | University of Brawijaya | 2 |
| Mochammad Hannats Hanafi Ichsan | University of Brawijaya | 2 |
| Ryzaldi Ananda Fabiana | University of Brawijaya | 2 |
| Syahrul Chilmi | University of Brawijaya | 2 |
| Septiyo Budi Perkasa | University of Brawijaya | 2 |
| Rizal Maulana | University of Brawijaya | 2 |
| Hurriyatul Fitriyah | University of Brawijaya | 1 |
| Heru Nurwarsito | University of Brawijaya | 1 |
| Denny Sagita Rusdianto | University of Brawijaya | 1 |
| Lindhu Parang Kusuma | University of Brawijaya | 1 |
| Eko Setiawan | University of Brawijaya | 1 |
| Muhammad Fawwaz Dynoeputra Isnandar | University of Brawijaya | 1 |
| Dittha Ratanasari | University of Brawijaya | 1 |
| Agung Setia Budi | University of Brawijaya | 1 |
| Ragil Hadi Prasetyo | University of Brawijaya | 1 |
| Fakhrul Allaam | University of Brawijaya | 1 |
| Rekyan Regasari Mardi Putri | University of Brawijaya | 1 |
| Irfan Muzakky Nurrizqy | University of Brawijaya | 1 |
| Achmad Ghifari | University of Brawijaya | 1 |
| Rakhmadhany Primananda | University of Brawijaya | 1 |
| Arsal Wildan Naviaddin | University of Brawijaya | 1 |
| Jevandika | University of Brawijaya | 1 |
| Brylliano Maza Putra | University of Brawijaya | 1 |
| Gabriel Hizkia Marhata Simbolon | Affiliation unknown | 1 |
| Gabriel Hizkia Marhata Simbolon | Affiliation unknown | 1 |
| Teguh Surya Darma Santoso | Affiliation unknown | 1 |
| Muhammad Rava Athalla | Affiliation unknown | 1 |
| Raihan Adi Prakoso | Affiliation unknown | 1 |
| Ika Nurfarida | Affiliation unknown | 1 |
| Alifa Azwadina Fuad | Affiliation unknown | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.