PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
December 5, 2025Concurrency and Computation Practice and Experience3 citations

CNNx : Optimizing Smart CNN Models for Efficient Banana Disease Detection and Severity Estimation

View Full Paper
HKHardeep KaurBPBhanu PriyaKSKuldeep Singh

Key Points

  • Classification accuracy reached 96.87% using the 5-layer Convolutional Neural Network model with SMOTE-ENN data enhancement.
  • F1 score was a key metric demonstrating improved sensitivity and specificity in the automated detection of banana diseases.
  • Assessment employed hybrid techniques for feature extraction from diseased leaf images to address dataset noise.
  • These advancements may enable timely interventions in banana farming and reduce reliance on excessive pesticide use.

Abstract

ABSTRACT Banana farming plays a crucial role in supporting the livelihoods of people in equatorial and tropical regions. Not only does it support local economies, but it also contributes significantly to food security. However, banana crops are frequently threatened by fungal infections, such as Cordana, Pestalotiopsis, and Sigatoka, which largely affect yield and quality. Intelligent computational methods that identify diseases at an early stage and evaluate severity can greatly enhance the timeliness and effectiveness of plant health interventions. In this context, the current study proposes an innovative integrated platform for automatic detection and estimation of the severity of banana diseases. A hybrid sampling technique, SMOTE‐ENN, is applied for the first time to address class disparity of specimens while removing noisy and potentially mislabeled datasets. Four different Convolutional Neural Network (CNN) architectures have been proposed, labeled CNN1 through CNN4, with varying layer depths and hyperparameters to extract distinctive features from diseased leaf images. Following classification, color thresholding has been used, which uses both HSV and Lab color spaces to measure disease‐specific severity; lesion regions are accurately segmented. The empirical evaluation demonstrated that the 5‐layer CNN2 architecture obtained the best classification accuracy of 96.87%, outperforming the other CNN variants in multiple parameters, including sensitivity, specificity, precision, and F 1 score. Furthermore, the time and space complexities of the models have been analyzed and compared to modern baselines to assess computational efficiency. Following established agricultural norms, the severity percentage is then used to assign a severity grade of the disease and suggest suitable fungicides. The proposed CNN‐based integrated framework facilitates timely interventions, reduces excessive pesticide use, and supports sustainable banana cultivation.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Kaur et al. (2025) studied this question.

synapsesocial.com/papers/693231308e51979591dce994https://doi.org/10.1002/cpe.70475
Ask AI
Helpful
Bookmark
Share
View Full Paper