Mayuri Arul Vinayakam Rajasimman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mayuri Arul Vinayakam Rajasimman has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
G. L. N. Murthy
Department of Electronics and Communication Engineering, Lakireddy Bali Reddy College of Engineering, Mylavaram, India
2 shared publications- K. Meena
Department of Computer Science and Engineering, GITAM School of Technology, GITAM University, Bengaluru Campus, India
2 shared publications - Kamaleshwar Thangavilou
Department of Computer Science and Engineering, Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology, Chennai, India
2 shared publications Kanika Garg
Department of Computer Science and Engineering, SRM Institute of Science and Technology, NCR Campus, Modinagar, India
2 shared publicationsM. Duraisamy
Department of Computer Science, Government Arts and Science College, Tamil Nadu, Tirupattur, India
2 shared publicationsM. Sangeetha
Department of Computer Science and Engineering, Panimalar Engineering College, Chennai, India
2 shared publications
Latest Publications
- Open Access
- 30 March 2026
- Published by National Research Mordovia State University MRSU in Engineering Technologies and Systems
- Vol. 36 (1) , 97-113
A Hybrid Explainable Deep Learning and Spectral-Texture Ensemble Approach for Tomato Leaf Disease Diagnosis
Introduction. Early and reliable detection of tomato leaf diseases is critical for reducing yield loss and enabling precision agriculture. Recent advances in deep learning have improved classification performance; however, challenges remain in interpretability and robustness under real-field conditions.Aim of the Study. This study aims to develop an accurate and explainable hybrid framework that integrates handcrafted spectral–texture descriptors with deep convolutional features to achieve high-performance multi-class classification of tomato leaf diseases across ten categories.Materials and Methods. A three-stage pipeline is proposed. Spectral features including Excess Green (ExG), Excess Red (ExR), HSV color channels, and vegetation indices are extracted from RGB images to simulate multispectral responses. Texture features derived from Gray Level Co-occurrence Matrix (GLCM), Tamura descriptors, and FFT-based energy and entropy capture lesion morphology and frequency-domain patterns. These features are classified using a Random Forest model. In parallel, an EfficientNetB0-based CNN is fine-tuned on augmented images to learn deep spatial representations. Model interpretability is achieved using SHAP for feature-level analysis and Grad-CAM for visual localization. A late-fusion ensemble strategy integrates both models.Results. The handcrafted feature-based Random Forest model achieves a baseline classification accuracy of 89.2%, while the fine-tuned EfficientNetB0 CNN attains 94% accuracy. The ensemble framework further improves overall performance to 96%, demonstrating enhanced robustness and generalization across all ten disease classes.Discussion and Conclusion. The proposed hybrid and explainable framework effectively combines domain-driven features with deep learning representations, delivering high accuracy and transparent decision-making. Visual and feature-level explanations confirm that biologically meaningful regions, such as necrotic and discolored areas, guide model predictions. This approach provides a scalable and reliable solution for automated tomato disease diagnosis, supporting real-world deployment in smart farming and precision agriculture systems.
- 30 March 2026
- Published by National Research Mordovia State University MRSU in Engineering Technologies and Systems
- Vol. 36 (1) , 97-113
Open AccessA Hybrid Explainable Deep Learning and Spectral-Texture Ensemble Approach for Tomato Leaf Disease Diagnosis
Introduction. Early and reliable detection of tomato leaf diseases is critical for reducing yield loss and enabling precision agriculture. Recent advances in deep learning have improved classification performance; however, challenges remain in interpretability and robustness under real-field conditions.Aim of the Study. This study aims to develop an accurate and explainable hybrid framework that integrates handcrafted spectral–texture descriptors with deep convolutional features to achieve high-performance multi-class classification of tomato leaf diseases across ten categories.Materials and Methods. A three-stage pipeline is proposed. Spectral features including Excess Green (ExG), Excess Red (ExR), HSV color channels, and vegetation indices are extracted from RGB images to simulate multispectral responses. Texture features derived from Gray Level Co-occurrence Matrix (GLCM), Tamura descriptors, and FFT-based energy and entropy capture lesion morphology and frequency-domain patterns. These features are classified using a Random Forest model. In parallel, an EfficientNetB0-based CNN is fine-tuned on augmented images to learn deep spatial representations. Model interpretability is achieved using SHAP for feature-level analysis and Grad-CAM for visual localization. A late-fusion ensemble strategy integrates both models.Results. The handcrafted feature-based Random Forest model achieves a baseline classification accuracy of 89.2%, while the fine-tuned EfficientNetB0 CNN attains 94% accuracy. The ensemble framework further improves overall performance to 96%, demonstrating enhanced robustness and generalization across all ten disease classes.Discussion and Conclusion. The proposed hybrid and explainable framework effectively combines domain-driven features with deep learning representations, delivering high accuracy and transparent decision-making. Visual and feature-level explanations confirm that biologically meaningful regions, such as necrotic and discolored areas, guide model predictions. This approach provides a scalable and reliable solution for automated tomato disease diagnosis, supporting real-world deployment in smart farming and precision agriculture systems.
- Retraction
- 5 January 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (S1) , 639
Retraction Note: Deep neural network with reduced feature for classification of breast cancer mammogram
- 5 January 2026
- Published by Springer Nature in Soft Computing
- Vol. 30 (S1) , 639
RetractionRetraction Note: Deep neural network with reduced feature for classification of breast cancer mammogram
- 30 July 2025
- Published by Springer Nature in Evolving Systems
- Vol. 16 (3) , 1-21
TransDense121-UNet: a multi-scale transformer-based approach for accurate liver tumor segmentation
- 30 July 2025
- Published by Springer Nature in Evolving Systems
- Vol. 16 (3) , 1-21
TransDense121-UNet: a multi-scale transformer-based approach for accurate liver tumor segmentation
- 26 February 2025
- Published by Springer Nature
- p. 403-414
Early Diagnosis of Parkinson's Disease Using Optimized Hybrid Transfer Learning Model
- 26 February 2025
- Published by Springer Nature
- p. 403-414
Early Diagnosis of Parkinson's Disease Using Optimized Hybrid Transfer Learning Model
- 19 February 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (4) , 1-25
Self-attention-based 1DCNN model for multiclass EEG emotion classification
- 19 February 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (4) , 1-25
Self-attention-based 1DCNN model for multiclass EEG emotion classification
- Open Access
- 5 February 2025
- Published by Springer Nature in Research Square
Enhanced Tomato Leaf Disease Classification and Localization using Advanced Feature Extraction and Transfer Learning
Tomato plants are susceptible to various diseases that significantly impact crop yield and quality. Accurate and timely identification of these diseases is crucial for effective management and mitigation. This study presents a deep learning-based methodology for enhancing disease prediction, classification, and precise localization of affected areas within tomato leaves. The proposed approach leverages a combination of statistical, texture (Tamura and GLCM), geometry, and color features extracted from leaf images. To further enrich feature representation, wavelet analysis is employed. The model not only classifies ten prevalent tomato diseases but also estimates the proportion of affected leaf area, providing valuable insights for disease severity assessment. Evaluated on a dataset comprising 10,000 images, our model achieves remarkable accuracy of 99.50%. This robust performance underscores the efficacy of our approach in accurate disease diagnosis, benefitting farmers and researchers by enabling prompt intervention and efficient disease management strategies.
- 5 February 2025
- Published by Springer Nature in Research Square
Open AccessEnhanced Tomato Leaf Disease Classification and Localization using Advanced Feature Extraction and Transfer Learning
Tomato plants are susceptible to various diseases that significantly impact crop yield and quality. Accurate and timely identification of these diseases is crucial for effective management and mitigation. This study presents a deep learning-based methodology for enhancing disease prediction, classification, and precise localization of affected areas within tomato leaves. The proposed approach leverages a combination of statistical, texture (Tamura and GLCM), geometry, and color features extracted from leaf images. To further enrich feature representation, wavelet analysis is employed. The model not only classifies ten prevalent tomato diseases but also estimates the proportion of affected leaf area, providing valuable insights for disease severity assessment. Evaluated on a dataset comprising 10,000 images, our model achieves remarkable accuracy of 99.50%. This robust performance underscores the efficacy of our approach in accurate disease diagnosis, benefitting farmers and researchers by enabling prompt intervention and efficient disease management strategies.
- 25 September 2024
- Published by Springer Nature
- p. 90-101
A Comparative Analysis of Transfer Learning Based Models for Early Detection of Parkinson’s Disease
- 25 September 2024
- Published by Springer Nature
- p. 90-101
A Comparative Analysis of Transfer Learning Based Models for Early Detection of Parkinson’s Disease
- 26 April 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (S1) , 731-746
Recognize and classify illnesses on tomato leaves using EfficientNet's transfer learning approach with different size dataset
- 26 April 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (S1) , 731-746
Recognize and classify illnesses on tomato leaves using EfficientNet's transfer learning approach with different size dataset
- 13 May 2023
- Published by Wiley in Expert Systems
- Vol. 41 (6)
Faster Region‐based Convolutional Neural Networks with You Only Look Once multi‐stage caries lesion from oral panoramic X‐ray images
Neural networks and artificial intelligence find more applications in dentistry. It treats dental caries, the most prevalent type of dental illness worldwide. Even though dental caries can be prevented and treated, they typically cause dental discomfort and tooth loss. For dental caries to be treated quickly and effectively, comprehensive detection may be needed, a combination of techniques that include eye inspection, probing, using a dental probe, and using a hand‐held mirror, and the individual application of each of these techniques, can quickly identify large caries cavities. Long‐established caries detection techniques help to locate only partially hidden but still accessible holes. Deep learning (DL) techniques have produced remarkable diagnostic results in radiology. This study aimed to classify various radiographic extensions on panoramic films using DL techniques, identify caries lesions using these techniques, and compare the results to those of dentists with extensive training. Faster region‐based convolutional neural networks (R‐CNN) is a newly discovered field of medical research that is rapidly expanding and has produced outstanding results in diagnosing and prognosis of pathology and radiology conditions. In this study, dental cavities were detected and analysed using periapical radiographs to evaluate the accuracy of the Faster R‐CNN algorithm. Because these three caries were derived from the oral panoramic images, we designed You Only Look Once Version 3 (YOLOv3) as a U‐shaped network with a large‐scale axial attention module. We also compare the effectiveness of YOLOv3's segmentation to that of other industrial standards. Experiments show that our proposed method, Fast R‐CNN–YOLOv3, achieves higher accuracy in segmenting the three distinct caries level. The proposed model (R‐CNN–YOLOv3) achieved an effective result with a precision of 97.183%.
- 13 May 2023
- Published by Wiley in Expert Systems
- Vol. 41 (6)
Faster Region‐based Convolutional Neural Networks with You Only Look Once multi‐stage caries lesion from oral panoramic X‐ray images
Neural networks and artificial intelligence find more applications in dentistry. It treats dental caries, the most prevalent type of dental illness worldwide. Even though dental caries can be prevented and treated, they typically cause dental discomfort and tooth loss. For dental caries to be treated quickly and effectively, comprehensive detection may be needed, a combination of techniques that include eye inspection, probing, using a dental probe, and using a hand‐held mirror, and the individual application of each of these techniques, can quickly identify large caries cavities. Long‐established caries detection techniques help to locate only partially hidden but still accessible holes. Deep learning (DL) techniques have produced remarkable diagnostic results in radiology. This study aimed to classify various radiographic extensions on panoramic films using DL techniques, identify caries lesions using these techniques, and compare the results to those of dentists with extensive training. Faster region‐based convolutional neural networks (R‐CNN) is a newly discovered field of medical research that is rapidly expanding and has produced outstanding results in diagnosing and prognosis of pathology and radiology conditions. In this study, dental cavities were detected and analysed using periapical radiographs to evaluate the accuracy of the Faster R‐CNN algorithm. Because these three caries were derived from the oral panoramic images, we designed You Only Look Once Version 3 (YOLOv3) as a U‐shaped network with a large‐scale axial attention module. We also compare the effectiveness of YOLOv3's segmentation to that of other industrial standards. Experiments show that our proposed method, Fast R‐CNN–YOLOv3, achieves higher accuracy in segmenting the three distinct caries level. The proposed model (R‐CNN–YOLOv3) achieved an effective result with a precision of 97.183%.