IMPLEMENTASI BROAD LEARNING SYSTEM (BLS)  UNTUK IDENTIFIKASI PENYAKIT DAUN TANAMAN TOMAT BERDASARKAN CITRA DIGITAL

Elien Marnes Kusmina; Rudi Kurniawan; Armanto Armanto; Tri Hasanah Bimastari  Aviani

doi:10.31539/qsba4219

Authors

Elien Marnes Kusmina Universitas Bina Insan
Rudi Kurniawan Universitas Bina Insan
Armanto Armanto Universitas Bina Insan
Tri Hasanah Bimastari Aviani Universitas Bina Insan

DOI:

https://doi.org/10.31539/qsba4219

Abstract

Penyakit daun pada tanaman tomat dapat menurunkan produktivitas sehingga diperlukan metode identifikasi berbasis karakteristik visual citra. Penelitian ini bertujuan menerapkan Broad Learning System (BLS) sebagai classifier untuk klasifikasi penyakit daun tomat dengan MobileNetV2 sebagai feature extractor. Dataset yang digunakan berasal dari PlantVillage dan terdiri atas 18.160 citra dalam 10 kelas. Tahapan penelitian meliputi preprocessing, augmentasi citra, ekstraksi fitur menggunakan MobileNetV2, L2 normalization, reduksi dimensi menggunakan Principal Component Analysis (PCA), klasifikasi menggunakan BLS, dan evaluasi model. Hasil pengujian terhadap data testing menunjukkan accuracy sebesar 78%, dengan macro precision 0,78, macro recall 0,78, dan macro F1-score 0,77. Confusion matrix menunjukkan bahwa sebagian besar data dapat diklasifikasikan dengan benar, meskipun masih terdapat kesalahan pada beberapa kelas dengan karakteristik visual yang serupa. Hasil penelitian menunjukkan bahwa kombinasi MobileNetV2 dan BLS dapat digunakan sebagai salah satu pendekatan untuk klasifikasi penyakit daun tomat berbasis citra digital.

Kata kunci: Broad Learning System, MobileNetV2, penyakit daun tomat, PlantVillage.

References

[1] S. P. Mohanty, D. P. Hughes, dan M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Front. Plant Sci., vol. 7, hlm. 1419, Sep 2016, doi: 10.3389/fpls.2016.01419.

[2] J. Boulent, S. Foucher, J. Théau, dan P.-L. St-Charles, “Convolutional Neural Networks for the Automatic Identification of Plant Diseases,” Front. Plant Sci., vol. 10, hlm. 941, Jul 2019, doi: 10.3389/fpls.2019.00941.

[3] L. Tan, J. Lu, dan H. Jiang, “Tomato Leaf Diseases Classification Based on Leaf Images: A Comparison between Classical Machine Learning and Deep Learning Methods,” AgriEngineering, vol. 3, no. 3, hlm. 542–558, Jul 2021, doi: 10.3390/agriengineering3030035.

[4] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, dan L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” dalam 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT: IEEE, Jun 2018, hlm. 4510–4520. doi: 10.1109/CVPR.2018.00474.

[5] S. Z. M. Zaki, M. Asyraf Zulkifley, M. Mohd Stofa, N. A. M. Kamari, dan N. Ayuni Mohamed, “Classification of tomato leaf diseases using MobileNet v2,” IJ-AI, vol. 9, no. 2, hlm. 290, Jun 2020, doi: 10.11591/ijai.v9.i2.pp290-296.

[6] S. Ahmed, Md. B. Hasan, T. Ahmed, Md. R. K. Sony, dan Md. H. Kabir, “Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification,” IEEE Access, vol. 10, hlm. 68868–68884, 2022, doi: 10.1109/ACCESS.2022.3187203.

[7] M. S. A. M. Al‐gaashani, F. Shang, M. S. A. Muthanna, M. Khayyat, dan A. A. Abd El‐Latif, “Tomato leaf disease classification by exploiting transfer learning and feature concatenation,” IET Image Processing, vol. 16, no. 3, hlm. 913–925, Feb 2022, doi: 10.1049/ipr2.12397.

[8] O. Attallah, “Tomato Leaf Disease Classification via Compact Convolutional Neural Networks with Transfer Learning and Feature Selection,” Horticulturae, vol. 9, no. 2, hlm. 149, Jan 2023, doi: 10.3390/horticulturae9020149.

[9] V. Maeda-Gutiérrez dkk., “Comparison of Convolutional Neural Network Architectures for Classification of Tomato Plant Diseases,” Applied Sciences, vol. 10, no. 4, hlm. 1245, Feb 2020, doi: 10.3390/app10041245.

[10] B. Khan dkk., “Bayesian optimized multimodal deep hybrid learning approach for tomato leaf disease classification,” Sci Rep, vol. 14, no. 1, hlm. 21525, Sep 2024, doi: 10.1038/s41598-024-72237-x.

[11] M. Jelali, “Deep learning networks-based tomato disease and pest detection: a first review of research studies using real field datasets,” Front. Plant Sci., vol. 15, hlm. 1493322, Okt 2024, doi: 10.3389/fpls.2024.1493322.

[12] C. L. P. Chen dan Z. Liu, “Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture,” IEEE Trans. Neural Netw. Learning Syst., vol. 29, no. 1, hlm. 10–24, Jan 2018, doi: 10.1109/TNNLS.2017.2716952.

[13] J. Jin, Z. Qin, D. Yu, Y. Li, J. Liang, dan C. L. P. Chen, “Regularized discriminative broad learning system for image classification,” Knowledge-Based Systems, vol. 251, hlm. 109306, Sep 2022, doi: 10.1016/j.knosys.2022.109306.

[14] B. Krawczyk, “Learning from imbalanced data: open challenges and future directions,” Prog Artif Intell, vol. 5, no. 4, hlm. 221–232, Nov 2016, doi: 10.1007/s13748-016-0094-0.

[15] Haibo He dan E. A. Garcia, “Learning from Imbalanced Data,” IEEE Trans. Knowl. Data Eng., vol. 21, no. 9, hlm. 1263–1284, Sep 2009, doi: 10.1109/TKDE.2008.239.

[16] X. Zhe, S. Chen, dan H. Yan, “Directional statistics-based deep metric learning for image classification and retrieval,” Pattern Recognition, vol. 93, hlm. 113–123, Sep 2019, doi: 10.1016/j.patcog.2019.04.005.

[17] S. C. Ng, “Principal component analysis to reduce dimension on digital image,” Procedia Computer Science, vol. 111, hlm. 113–119, 2017, doi: 10.1016/j.procs.2017.06.017.