Sugarcane Diseases Detection Using Optimized Convolutional Neural Network with Enhanced Environmental Adaptation Method

Journal Title: International Journal of Experimental Research and Review - Year 2024, Vol 41, Issue 5

Abstract

This research aims to address the need for accurate and prompt identification of sugarcane diseases, which substantially impact the worldwide sugar industry and the livelihoods of numerous farmers. Conventional visual inspection methods are hindered by subjective interpretations and restricted availability, prompting the investigation of more sophisticated techniques. By harnessing deep learning capabilities, specifically Convolutional Neural Networks (CNNs), and further enhancing their performance using the Environmental Adaptation Method (EAM) optimization, this research demonstrates significant enhancements in disease detection accuracy, precision, recall, and F1-Score. Based on the macro values obtained from the different approaches, it has been observed that an accuracy of 89% was obtained for the CNN designed from EEAM in comparison to the other counter parts. Similarly, the precision of the proposed architecture of CNN is better in comparison to GA, PSO and DE. On the same lines the Recall and F1 score of the proposed approach is better in comparison to that of the three counterparts. Similarly, the ROC analysis for the analysis of AUC is done and it was identified that the AUC curve for the different CNN designed by various optimizer were good in identifying the different classes of the sugarcane diseases. The major limitation of this approach is that model has marginal accuracy with its counterpart algorithm, however, the algorithm suggested the use of simple CNN models that are easy to use. The rigorous methodology, encompassing data collection and model optimization, guarantees the reliability and applicability of the sugarcane disease detection system based on Convolutional Neural Networks (CNN). Future research directions focus on integrating hyperspectral imaging, unmanned aerial vehicles (UAVs), and user-friendly mobile applications. This integration aims to empower farmers, facilitate proactive disease management, and ensure the sustainability of the sugarcane industry. This advancement represents notable progress in precision agriculture and disease mitigation.

Authors and Affiliations

Davesh Kumar Sharma, Pushpendra Singh, Akash Punhani

Keywords

Related Articles

Plant regeneration through somatic embryogenesis of pseudostem callus culture response in In-vitro condition of palmarosa grass (Cymbopogon martinii) with special reference to hardening and pot culture

This study successfully achieved somatic embryogenesis and plant regeneration from callus culture of the plant Cymbopogon martinii (Palmarosa Grass). The ability of medicinally significant palmarosa grass to regenerate t...

Population dynamics on soil insects in Greater Kolkata, West Bengal: A review

Soil is the natural habitat for microorganisms, plants and animals. Insects are the most diverse groups of organisms on earth and have adapted a wide range of habitats. Soil is the weathered surface of the earth’s crust...

Trend of urbanization in Chakdaha urban area in preceding few decades

Urbanization has not been uniform all over the world. Different ages have witnessed localized growth. The dawn of modern age saw the spread of urbanization to almost all the parts of the world. With the spread of globali...

A Critical Review on the Advancements in Exploration and Production of Shale Gas

The exploration and production of shale gas have seen significant advancements in recent years, driven by the increasing global demand for clean energy sources. These advancements encompass the understanding of a wide ra...

Evaluation of Pulmonary Status of Post-Tuberculosis Patients with Spirometry and Chest X-Ray

In 2022, 7.5 million new cases of tuberculosis were reported worldwide. Mycobacterium tuberculosis results in tuberculosis, an infectious disease mostly affecting the lungs. However, many completely treated post-tubercul...

Download PDF file
  • EP ID EP741628
  • DOI 10.52756/ijerr.2024.v41spl.005
  • Views 20
  • Downloads 0

How To Cite

Davesh Kumar Sharma, Pushpendra Singh, Akash Punhani (2024). Sugarcane Diseases Detection Using Optimized Convolutional Neural Network with Enhanced Environmental Adaptation Method. International Journal of Experimental Research and Review, 41(5), -. https://europub.co.uk/articles/-A-741628