Publisher

IOCSCIENCEIOCSCIENCE

Journal VertexVertex Abstract

Rice (Oryza sativa) is a major food staple, which is prone to multiple diseases that will dramatically decrease the harvest yield. Disease identification is time-consuming and is usually subject to subjective errors in a manual approach. This research seeks to increase the precision of automatic rice plant disease detection, namely Brown Spot, Hispa, and Leaf Blast. The suggested method combines the Gray Level Co-occurrence Matrix (GLCM) to extract texture features and the Extreme Gradient Boosting (XGBoost) classification algorithm. Furthermore, the Synthetic Minority Over-sampling Technique (SMOTE) is applied to address class imbalance within the dataset of 5,548 images. Experimental results demonstrate that the model trained on SMOTE-balanced data with optimized XGBoost parameters achieved a superior accuracy of 98%, outperforming the imbalanced scenario (97%) and previous studies. This research confirms that the combination of GLCM, SMOTE, and XGBoost constitutes a robust and high-precision method for rice disease identification.

Conclusion

This study has demonstrated that the quality of agricultural disease identification is heavily dependent on how class imbalance is managed.The proposed method successfully integrates Gray Level Co-occurrence Matrix (GLCM) feature extraction with Synthetic Minority Over-sampling Technique (SMOTE) and Extreme Gradient Boosting (XGBoost), achieving a superior accuracy of 98%.Conceptually, this research offers a critical update to data imbalance handling strategies in the smart agriculture domain by shifting the focus from image-level augmentation to feature-space interpolation.

Future Research

Penelitian lebih lanjut dapat dilakukan dengan menggabungkan GLCM dengan deep learning embeddings untuk meningkatkan akurasi deteksi penyakit padi. Selain itu, model ringan ini dapat diimplementasikan ke dalam sistem pemantauan berbasis IoT untuk memberikan peringatan dini kepada petani mengenai potensi serangan penyakit. Untuk memperluas cakupan penelitian, studi dapat difokuskan pada identifikasi penyakit padi yang lebih beragam, termasuk penyakit yang disebabkan oleh patogen baru atau kombinasi patogen yang kompleks. Hal ini akan membutuhkan pengumpulan dataset yang lebih besar dan representatif, serta pengembangan teknik ekstraksi fitur yang lebih canggih. Terakhir, penelitian dapat mengeksplorasi penggunaan teknik pembelajaran transfer untuk memanfaatkan pengetahuan dari dataset penyakit tanaman lain, sehingga mengurangi kebutuhan akan data pelatihan yang besar dan meningkatkan generalisasi model.

References

1. IoT Agri-Care Advisor Mobile Application for Monitoring Paddy Plant Health and Delivering Smart Farmer... doi.org/10.56294/saludcyt20251979IoT Agri Care Advisor Mobile Application for Monitoring Paddy Plant Health and Delivering Smart Farmer doi 10 56294 saludcyt20251979
2. International Journal of Research and Innovation in Social Science. journal research innovation social... rsisinternational.org/journals/ijrissInternational Journal of Research and Innovation in Social Science journal research innovation social rsisinternational journals ijriss
3. Browser Not SupportedAgriCare: An Android Application for Detection of Paddy Diseases | IEEE Conference... ieeexplore.ieee.org/document/9825038Browser Not SupportedAgriCare An Android Application for Detection of Paddy Diseases IEEE Conference ieeexplore ieee document 9825038

Metadata

File size	430.1 KB
Pages	6
DMCA	Report