A Comprehensive Review of Deep Learning and Sensor-based Approaches for Efficient Mango Disease Detection

View at publisher Summarise with VIRAT
Authors: Gaurav Kumar, Dipanshu Pant, Nikita
Cited by: 0
References: 20

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Mango is an important fruit crop that grown all over the world, but its production is severely challenged by for leaf and fruit diseases such as anthracnose, powdery mildew, bacterial canker, and stem rot. This review summarises the findings of 20 peer-reviewed research papers, systematically reviewed using the Preferred Reporting Items for Systematic Reviews and MetaAnalyses (PRISMA) framework. The emphasis is placed on Deep Learning (DL), Convolutional neural networks (CNN), Vision Transformers (ViT), and hybrid sensor assistance-based methods for disease detection and classification. Recent studies show that CNN variants such as VGG16, DenseNet, and EfficientNet have achieved accuracies greater than 95$\%$, while ensemble models and ConvNeXt-ViT hybrids have reported performance exceeding 95%. Hybrid CNNSVM models and IoT-enabled Systems provide real-time Monitoring and detection capabilities, improve production and enhance field applicability. Also, disease severity estimation models used on ResNet50 and a sensor-based image segmentation enable a mechanism to qualify infection stages, offering deeper agronomic insight. Despite these added efficiencies capability to support decision making at the management level, lightweight interpretable AI models, standardised datasets, and sensor-IoT frameworks into cost-effective solutions for scalable precision agriculture. Real-time detection using AI, Mobile applications, drones and sensors has the potential to minimise yield loss, improve farmer decision-making, as well as support sustainable mango cultivation.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Water Quality Monitoring Technologies

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
37–42
Publication date
21 January 2026
Language
EN