A Payel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
A Payel has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ashis Roy Barman
Department of Plant Pathology, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur 741 252, West Bengal, India
1 shared publication - Dipashree Sadhukhan
Department of Plant Pathology, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur 741 252, West Bengal, India
1 shared publication - Krishnendu Kundu
Department of Plant Pathology, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur 741 252, West Bengal, India
1 shared publication - P Soumen
Department of Plant Pathology, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur 741 252, West Bengal, India
1 shared publication - Raju Das
Department of Plant Pathology, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur 741 252, West Bengal, India
1 shared publication - Sabyasachi Mukhopadhyay
Department of Plant Pathology, Bidhan Chandra Krishi Viswavidyalaya, Mohanpur 741 252, West Bengal, India
1 shared publication
Latest Publications
- Open Access
- 3 October 2026
- Published by Horizon E-Publishing Group in Plant Science Today
- Vol. 13 (sp9)
Evaluation of deep learning models for optimised accuracy-emission trade-offs in the early detection of grain discolouration disease in rice
Rice (Oryza sativa L.) constitutes a primary food source for a significant proportion of the global population and its grain quality directly influences market value and consumer acceptance. Grain discolouration (GD), largely attributable to seed-borne pathogens and occasionally to insect infestation, poses a critical challenge by compromising visual quality and reducing commercial grade. This study evaluated the performance of advanced deep learning models for automated detection and classification of discoloured rice grains, incorporating criteria related to predictive accuracy, computational requirements and environmental sustainability. Among the assessed architectures, DenseNet121 exhibited the highest accuracy (98 %), followed by MobileNet (96 %) and MobileNetV2 (92 %), each demonstrating strong precision, recall and F1 scores. In contrast, VGG19 recorded comparatively lower accuracy (84 %). Computational and energy analysis revealed that DenseNet121, MobileNet and Xception required shorter training durations and lower computational resources, whereas MobileNetV2 and InceptionV3 were comparatively resource-intensive. Notably, MobileNet demonstrated superior energy efficiency, consuming 19.03 watts and generating 0.00952 kg carbon dioxide (CO₂), whereas InceptionV3 consumed 377.27 watts and emitted 0.18864 kg CO₂. To facilitate comprehensive model prioritisation, the technique for order of preference by similarity to ideal solution (TOPSIS) was employed, identifying MobileNet as the optimal model when considering performance, efficiency and environmental impact. The findings highlight the potential applicability of lightweight deep learning architectures, particularly MobileNet and DenseNet121, in real-time rice grading and sorting systems, supporting sustainable post-harvest management, improving grain quality assurance and mitigating seed-borne pathogen dissemination.
- 3 October 2026
- Published by Horizon E-Publishing Group in Plant Science Today
- Vol. 13 (sp9)
Open AccessEvaluation of deep learning models for optimised accuracy-emission trade-offs in the early detection of grain discolouration disease in rice
Rice (Oryza sativa L.) constitutes a primary food source for a significant proportion of the global population and its grain quality directly influences market value and consumer acceptance. Grain discolouration (GD), largely attributable to seed-borne pathogens and occasionally to insect infestation, poses a critical challenge by compromising visual quality and reducing commercial grade. This study evaluated the performance of advanced deep learning models for automated detection and classification of discoloured rice grains, incorporating criteria related to predictive accuracy, computational requirements and environmental sustainability. Among the assessed architectures, DenseNet121 exhibited the highest accuracy (98 %), followed by MobileNet (96 %) and MobileNetV2 (92 %), each demonstrating strong precision, recall and F1 scores. In contrast, VGG19 recorded comparatively lower accuracy (84 %). Computational and energy analysis revealed that DenseNet121, MobileNet and Xception required shorter training durations and lower computational resources, whereas MobileNetV2 and InceptionV3 were comparatively resource-intensive. Notably, MobileNet demonstrated superior energy efficiency, consuming 19.03 watts and generating 0.00952 kg carbon dioxide (CO₂), whereas InceptionV3 consumed 377.27 watts and emitted 0.18864 kg CO₂. To facilitate comprehensive model prioritisation, the technique for order of preference by similarity to ideal solution (TOPSIS) was employed, identifying MobileNet as the optimal model when considering performance, efficiency and environmental impact. The findings highlight the potential applicability of lightweight deep learning architectures, particularly MobileNet and DenseNet121, in real-time rice grading and sorting systems, supporting sustainable post-harvest management, improving grain quality assurance and mitigating seed-borne pathogen dissemination.