Model Ensemble Fusion–Stacking untuk Klasifikasi Varietas Salak Berbasis Deep Feature
- Bunga Intan Universitas Bina Insan, Indonesia
- Ahmad Taqwa Martadinata Universitas Bina Insan, Indonesia
-
Abdul Qodir
*
Mahasiswa s1,
Indonesia
Abstract
Visual classification of salak (snake fruit) varieties remains challenging due to similarities in texture, color, and morphological characteristics across classes. Manual identification is prone to subjectivity and inconsistency in determining varieties. This study proposes an ensemble model based on fusion and stacking applied to deep learning feature extraction in order to improve the accuracy of salak variety classification. Image features are extracted using two pre-trained Convolutional Neural Network architectures, namely VGG16 and ResNet50, as deep feature extractors. The resulting feature representations are subsequently classified using K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms. The output probabilities of both classifiers are then combined through a stacking ensemble approach with Logistic Regression as the meta-learner. The dataset consists of 584 images distributed across four salak varieties. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results indicate that the proposed fusion–stacking approach achieves an accuracy of 95%, outperforming single CNN-based models and conventional classification methods. These findings demonstrate that the integration of deep feature extraction and ensemble learning effectively enhances the discriminative capability of the model in agricultural image classification.
References
F. Aulia, “Computer Vision dan Pengolahan Citra Digital”.
David Shamoo Excel, “Computer Vision Promising Innovations,” World J. Adv. Res. Rev., vol. 23, no. 3, hlm. 610–619, Sep 2024, doi: 10.30574/wjarr.2024.23.3.2725.
L. Sharma dan M. Carpenter, Computer Vision and Internet of Things: Technologies and Applications, 1 ed. Boca Raton: Chapman and Hall/CRC, 2022. doi: 10.1201/9781003244165.
A. Betti, M. Gori, dan S. Melacci, Deep Learning to See: Towards New Foundations of Computer Vision. 2022. doi: 10.1007/978-3-030-90987-1.
Norbertus Tri Suswanto Saptadi, Hedie Kristiawan, Agung Yuliyanto Nugroho, Nina Rahayu, Suwarmiyati, dan Bayu Waseso, “Deep Learning: Teori, Algoritma, dan Aplikasi.” Diakses: 3 Maret 2026. [Daring]. Tersedia pada: https://www.researchgate.net/publication/389428653_Deep_Learning_Teori_Algoritma_dan_Aplikasi?utm_source=chatgpt.com
K. S. Babulal dan A. K. Das, “Deep Learning-Based Object Detection: An Investigation,” dalam Futuristic Trends in Networks and Computing Technologies, vol. 936, P. K. Singh, S. T. Wierzchoń, J. K. Chhabra, dan S. Tanwar, Ed., dalam Lecture Notes in Electrical Engineering, vol. 936. , Singapore: Springer Nature Singapore, 2022, hlm. 697–711. doi: 10.1007/978-981-19-5037-7_50.
F. X. Gaya-Morey, C. Manresa-Yee, dan J. M. Buades-Rubio, “Deep learning for computer vision based activity recognition and fall detection of the elderly: a systematic review,” Appl Intell, vol. 54, no. 19, hlm. 8982–9007, Okt 2024, doi: 10.1007/s10489-024-05645-1.
M. H. Mozaffari, “Deep Learning for Computer Vision Application,” Electronics, vol. 14, no. 14, hlm. 2874, Jul 2025, doi: 10.3390/electronics14142874.
A. Wang, H. Wu, dan Y. Iwahori, “Advances in Computer Vision and Deep Learning and Its Applications,” Electronics, vol. 14, no. 8, hlm. 1551, Apr 2025, doi: 10.3390/electronics14081551.
B. Liu, L. Yu, C. Che, Q. Lin, H. Hu, dan X. Zhao, “Integration and performance analysis of artificial intelligence and computer vision based on deep learning algorithms,” ACE, vol. 64, no. 1, hlm. 36–41, Mei 2024, doi: 10.54254/2755-2721/64/20241374.
Z. Cao, S. Sun, dan X. Bao, “A Review of Computer Vision and Deep Learning Applications in Crop Growth Management,” Applied Sciences, vol. 15, no. 15, hlm. 8438, Jul 2025, doi: 10.3390/app15158438.
D. Patil, N. L. Rane, P. Desai, dan J. Rane, “Machine learning and deep learning: Methods, techniques, applications, challenges, and future research opportunities,” dalam Trustworthy Artificial Intelligence in Industry and Society, Deep Science Publishing, 2024. doi: 10.70593/978-81-981367-4-9_2.
G. Naskar, S. Mohiuddin, S. Malakar, E. Cuevas, dan R. Sarkar, “Deepfake detection using deep feature stacking and meta-learning,” Heliyon, vol. 10, no. 4, hlm. e25933, Feb 2024, doi: 10.1016/j.heliyon.2024.e25933.
E. Alalwany, B. Alsharif, Y. Alotaibi, A. Alfahaid, I. Mahgoub, dan M. Ilyas, “Stacking Ensemble Deep Learning for Real-Time Intrusion Detection in IoMT Environments,” Sensors, vol. 25, no. 3, hlm. 624, Jan 2025, doi: 10.3390/s25030624.
N. Mungoli, “Adaptive Ensemble Learning: Boosting Model Performance through Intelligent Feature Fusion in Deep Neural Networks,” 4 April 2023, arXiv: arXiv:2304.02653. doi: 10.48550/arXiv.2304.02653.
B. N. Jyothi dan M. A. Jabbar, “Enhanced Xception Model for Deepfake Detection: Integrating CBAM, Contrastive Learning, and a Stacking Classifier”.
M. Y. Kardawi, F. M. Saragih, L. Rahadianti, dan A. M. Arymurthy, “Indonesian Food Classification Using Deep Feature Extraction and Ensemble Learning for Dietary Assessment,” vol. 9, no. 5, 2009.
K. Panç dan S. Sekmen, “Multi-CNN Deep Feature Fusion and Stacking Ensemble Classifier for Breast Ultrasound Lesion Classification,” forbes, Jul 2025, doi: 10.4274/forbes.galenos.2025.02360.
A. Karim, I. Purnama, and A. Ernawati, “Peningkatan Pengarahan Beam dan Estimasi Sudut Kedatangan Berbasis CNN untuk Sistem Antena MIMO Cerdas,” Explorer (Hayward)., vol. 6, no. 1, pp. 63–72, Jan. 2026, doi: 10.47065/explorer.v6i1.2592.
A. Karim, B. Bangun, S. Prayetno, M. Afrendi, and K. Kunci, “Optimasi Prediksi Harga Sawit Menggunakan Teknik Stacking Algoritma Machine Learning dan Deep Learning dengan SMOTE,” Technology and Science (BITS), vol. 7, no. 1, 2025, doi: 10.47065/bits.v7i1.7239.
Copyright (c) 2026 Bunga Intan , Ahmad Taqwa Martadinata, Abdul Qodir
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
.png)
.png)
