SeedlingNet: A colour-based segmentation approach towards classification of plant species seedlings Pushpa B R, Bhavya K R, Manohar N Methodsx, 2026 • Proposed a segmentation method for extracting plant parts from complex environments with low lighting conditions. • Compared the proposed segmentation model against other existing segmentation methods. • Different deep learning models are trained on segmented and non-segmented images for classifying various seedlings to accurately determine an effective transfer learning model with the best possible recognition rate. Early identification of plant species in uncontrolled conditions can be complex due to the complex background and morphological diversity of a plant's leaves. Agriculture plays an important role in our daily life to produce food, develop economies, international trade, research, and promote global sustainability. In this work, classification of plant species is performed based on a proposed segmentation method using a colour thresholding technique to separate the plant regions in images captured in low lighting and a complex background. The models include DenseNet121, NasNet Mobile, MobileNet, RegNet, and XceptionNet, trained on the proposed segmentation method and raw image samples, and compared for their effectiveness. The dataset, comprising 4,750 images of 12 different types of plants, their seedlings, and weeds, is sourced from Kaggle. The results demonstrate that the model's classification performance using the proposed segmentation method consistently outperformed with the non-segmented images, confirming the need for segmentation to improve model accuracy.
CISCS: Classification of inter-class similarity based medicinal plant species groups with machine learning N. Shobha Rani, Bhavya K R, I. Jeena Jacob, Pushpa B. R, Bipin Nair BJ, Akshatha Prabhu Methodsx, 2025 The reliable classification of medicinal plant species plays a vital role in ensuring their quality, authenticity, and safe use in healthcare. However, existing methods often face difficulties when species exhibit strong visual similarities or when datasets are imbalanced, which limits their effectiveness in practice. Although deep learning models such as ResNet18 and VGG16 have proven influential in image recognition tasks, our experiments showed that they tended to overfit, with validation losses reaching 42.99% and test accuracy falling to 73.99% in certain groups. To overcome these challenges, we introduce a multi-level fusion feature model that combines 3D normalized color histograms, extended uniform Local Binary Patterns (LBP with P=24, R=3), multi-orientation Gabor filters, and Histogram of Oriented Gradients (HOG). This approach captures a richer set of visual cues by bringing together global color statistics, detailed textures, frequency-domain patterns, and shape descriptors. We incorporate SMOTE-based synthetic augmentation to address further class imbalance, which helps balance feature distributions across categories. We employ a soft-voting ensemble of machine learning classifiers for classification and use cosine similarity metrics to capture inter-class relationships better. Tests on Indian medicinal plant datasets show that our model consistently outperforms deep learning baselines, reaching 100% accuracy in Group 1, 95.82% in Group 3, and over 90% in other groups. These results suggest that the proposed model offers a more robust and computationally efficient solution for plant species classification, particularly under conditions of high inter-class similarity and dataset imbalance. • The proposed domain-specific model can be applied explicitly to Indian plant species groups exhibiting high inter-class visual similarities through a novel feature fusion strategy. • The proposed multi-level feature fusion method's innovation integrates 3D normalized color histograms, extended uniform LBP (P=24, R=3), multi-orientation Gabor filters, and HOG features to capture the color, texture, and shape characteristics. • The proposed work offers a scalable ensemble framework for inter-class similarity analysis by combining SMOTE-based class balancing, feature normalization, and a soft-voting ensemble of diverse classifiers that support biodiversity and ecological studies.
HerbSimNet: Deep Learning -Based Classification of Indian Medicinal Plants with High Inter-Class Similarities N. Shobha Rani, Bhavya K R, Pushpa B.R., Ragavendra M. Devadas Procedia Computer Science, 2025 Medicinal plant species recognition is important across diverse sectors such as Ayurveda, agriculture, environment conservation and botanical research. Specific groups of plants in Indian medicinal plant ecosystem exhibit significant inter-class similarities due to varying abundance and ecological factors. To address the challenges involved in the process of classifying these species in this work a deep learning model Herb-SimNet is proposed. The Herb-SimNet analyzes similarity of plant species over other plant species using vision based deep learning and machine learning techniques. The proposed model works based on the combination of wavelet features and convolutional features extracted using three sequential convolution layers to extract the prominent features that distinguish variations among the inter class similarity plant species. To perform experiments, a dataset is created by capturing medicinal plant leaf images using box model in plain background and uniform lighting. A smart phone captured twelve Indian medicinal plant species comprising of about 1400+ samples that belongs different plant species but similar morphological structure is collected. Baseline experiments are carried out between Herb-SimNet and other state-of-the-art deep learning models for classification based on the proposed dataset. The outcomes demonstrate that Herb_SimNet provides clear interpretation one plant variety with others and achieves superior accuracy in prediction than that of state-of-the-art approaches. Furthermore, the model demonstrates better generalization towards the other inter-class similarity groups considered for testing. In conclusion, the proposed dataset and Herb-SimNet plays a a crucial role in advancement of research concerning Indian medicinal plant species classification resulting into enhancement of AI-based technology for biodiversity conservation and ethnobotanical studies.
FeaFusion-PomoNet: A Feature Fusion Driven Regression Framework for Non-Destruction Weight Estimation of Pomegranates K. R. Bhavya, Raghavendra M. Devadas, N. Shobha Rani, Manjunath Varchagall, Akshatha Prabhu, Renuka R. Herakal Patil IEEE Access, 2025 Non-destructive fruit weight estimation plays a critical role in precision agriculture, particularly for yield forecasting, grading, and logistics optimization. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FeaFusion-PomoNet</i>, a feature fusion-based regression framework, is proposed for estimating the weight of fruits using a self-collected image dataset comprising samples captured from multiple orientations. Handcrafted features—including texture, shape, geometric attributes, and pixel density—are extracted and optimized via the Boruta feature selection algorithm. Multiple regression models are evaluated, with Multiple Linear Regression (MLR) achieving the best performance, yielding R² scores of 0.97 and 0.92 on 80-20 and 70-30 train-test splits, respectively. Validation through Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) produces average relative error rates of 7.6% and 8.3%, indicating high predictive accuracy. A Pearson correlation coefficient of 0.99 confirms the robustness of the model. The method also supports orientation-independent image acquisition, making it adaptable to irregularly shaped fruits. Future work will focus on scaling the dataset, incorporating field-captured images, and improving robustness under real-world conditions, contributing to automated, cost-effective post-harvest systems.
A Novel Curriculum Learning Training Strategy for Pomegranate Growth Stage Classification Using YOLO Models on Multi-Source Datasets for Precision Agriculture N. Shobha Rani, K. R. Bhavya, A. Vadivel, T. Vasudev, Raghavendra M. Devadas, Vani Hiremani IEEE Access, 2025 Pomegranates are among the many vital crops generally believed to offer health quality and economically impact agriculture. Accurate detection and classification of the pomegranate growth stages enables fruit harvesting robots, resulting in yield optimization, supply chain, and market readiness. In this study, we propose that the YOLO object detection models adopt a novel curriculum learning approach to detect the growth stages of pomegranates using multi-source datasets. A combined dataset of 5700+ images is considered for categorizing pomegranates into bud, flowering, early-fruit, mid-growth, and maturity stages. In the present study, we have experimented with two deep learning-based object detection models, YOLOv5 and YOLOv7, to perform training using a multi-level curriculum learning approach. The proposed training strategy proves to show improvement over state-of-the-art work Zhao et al. [2] in achieving higher detection accuracies towards all five classes. The efficiency of the curriculum learning strategy with YOLOv7 and YOLOv5 models achieved a mAP score of 92.2% with a precision of 90.1%, recall of 82.3%, and F1 score of 86.1%. By comparing the performance proposed curriculum learning-based YOLO object detection models with traditional learning-based YOLO models, it was revealed that the YOLOv5 model with curriculum learning shows a consistent improvement over another model. It is inferred that the proposed training strategy is valuable in increasing the efficacy of pomegranate fruit detection and enhancing precision agriculture activities.
TopoGeoFusion: Integrating object topology based feature computation methods into geometrical feature analysis to enhance classification performance N. Shobha Rani, Keshav Shesha Sai, B.R. Pushpa, Arun Sri Krishna, M.A. Sangamesha, K.R. Bhavya, Raghavendra M. Devadas, Vani Hiremani Methodsx, 2024 This study used smartphone captured RGB images of gooseberries to automatically sort into standard, premium, or rejected categories based on topology. Main challenges addressed include, separation of touching or overlapping fruits into individual entities and new method called 'TopoGeoFusion' that combines basic geometrical features with topology aware features computed from the fruits to assess the grade or maturity. Quality assessment helps in grading the fruit to determine market suitability and intelligent camera applications. Computer Vision-based techniques have been applied to automatically grade the quality of gooseberries as standard, premium, or rejected according to fruit maturity. Smartphone-captured images of 1697 Indian Star Gooseberries are contributed to the study. This work acquired images consisting multiple fruits with overlapping and non-overlapping boundaries for concurrent quality assessment. Multiple classifiers such as Random Forest, SVM, Naive Bayes, Decision Tree, and KNN were applied to grade the gooseberry fruit. Random Forest classification with a fusion feature model resulted in an accuracy of 100 % towards reject, standard, and premium classes for test sets with four training strategies. The proposed segmentation model proves reliable in fruit detection & extraction with an average mAP of 0.56, resulting in an acceptable model for grade assessment.•The study highlights the effectiveness of TopoGeoFusion in automating the grading process of gooseberry fruits using topologically computed features.•The developed models exhibit high accuracy and reliability, even in challenging scenarios such as overlapping and touching fruits.•The method provides the technique to detect and extract the occluded objects and compute the features based on the partial object's topology.
Stochastic calculus-guided reinforcement learning: A probabilistic framework for optimal decision-making Raghavendra M. Devadas, Vani Hiremani, K.R. Bhavya, N. Shobha Rani Methodsx, 2024 Stochastic Calculus-guided Reinforcement learning (SCRL) is a new way to make decisions in situations where things are uncertain. It uses mathematical principles to make better choices and improve decision-making in complex situations. SCRL works better than traditional Stochastic Reinforcement Learning (SRL) methods. In tests, SCRL showed that it can adapt and perform well. It was better than the SRL methods. SCRL had a lower dispersion value of 63.49 compared to SRL's 65.96. This means SCRL had less variation in its results. SCRL also had lower risks than SRL in the short- and long-term. SCRL's short-term risk value was 0.64, and its long-term risk value was 0.78. SRL's short-term risk value was much higher at 18.64, and its long-term risk value was 10.41. Lower risk values are better because they mean less chance of something going wrong. Overall, SCRL is a better way to make decisions when things are uncertain. It uses math to make smarter choices and has less risk than other methods. Also, different metrics, viz training rewards, learning progress, and rolling averages between SRL and SCRL, were assessed, and the study found that SCRL outperforms well compared to SRL. This makes SCRL very useful for real-world situations where decisions must be made carefully.•By leveraging mathematical principles derived from stochastic calculus, SCRL offers a robust framework for making informed choices and enhancing performance in complex scenarios.•In comparison to traditional SRL methods, SCRL demonstrates superior adaptability and efficacy, as evidenced by empirical tests.
Fruit Quality Prediction using Deep Learning Strategies for Agriculture International Journal of Intelligent Systems and Applications in Engineering, 2023
SeedlingNet: A Colour-Based Segmentation Approach Towards Classification of Plant Species Seedlings BR Pushpa, KR Bhavya, N Manohar MethodsX, 103883 , 2026 2026.0
FeaFusion-PomoNet: A Feature Fusion Driven Regression Framework for Non-Destruction Weight Estimation of Pomegranates RMD K. R. BHAVYA IEEE ACCESS 16, 213578-213598 , 2025 2025.0
TGNO-CAD: A Novel Approach to Detect Fake Accounts in Social Networks P Krishnadas, GM Reddy, S Ghattamaneni, K Bhavya, D LR 2025 10th International Conference on Communication and Electronics Systems … , 2025 2025.0
CISCS: Classification of inter-class similarity based medicinal plant species groups with machine learning NS Rani, KR Bhavya, IJ Jacob, BN BJ, A Prabhu MethodsX, 103652 , 2025 2025.0
Plant Region Detection from Infield Images with Unconstrained Backgrounds using U-Net NS Rani, B KR, IJ Jacob, PV Theerthagiri, SVN SR 2025 2nd International Conference on New Frontiers in Communication … , 2025 2025.0
A Novel Curriculum Learning Training Strategy for Pomegranate Growth Stage Classification Using YOLO Models on Multi-Source Datasets for Precision Agriculture NS Rani, KR Bhavya, A Vadivel, T Vasudev, RM Devadas, V Hiremani IEEE Access , 2025 2025.0 Citations: 4
Federated learning for crop yield prediction: A comprehensive review of techniques and applications V Hiremani, RM Devadas, R Sapna, T Sowmya, P Gujjar, NS Rani, ... MethodsX 14, 103408 , 2025 2025.0 Citations: 16
HerbSimNet: Deep Learning-Based Classification of Indian Medicinal Plants with High Inter-Class Similarities NS Rani, KR Bhavya, BR Pushpa, RM Devadas Procedia Computer Science 258, 765-774 , 2025 2025.0 Citations: 3
TopoGeoFusion: Integrating object topology based feature computation methods into geometrical feature analysis to enhance classification performance NS Rani, KS Sai, BR Pushpa, AS Krishna, MA Sangamesha, KR Bhavya, ... MethodsX 13, 102859 , 2024 2024.0 Citations: 2
Stochastic calculus-guided reinforcement learning: A probabilistic framework for optimal decision-making RM Devadas, V Hiremani, KR Bhavya, NS Rani MethodsX 12, 102790 , 2024 2024.0 Citations: 4
Fruit quality prediction using deep learning strategies for agriculture KR Bhavya, SP Raja Int. J. Intell. Syst. Appl. Eng 11 (2), 10-301 , 2023 2023.0 Citations: 14
Machine learning-based stock price prediction for business intelligence KR Bhavya, M Sudhakara, GR Reddy, M Sangeetha AI-Driven Intelligent Models for Business Excellence, 209-226 , 2023 2023.0 Citations: 2
Customer purchase prediction and potential customer identification for digital marketing using machine learning M Sudhakara, KR Bhavya, MR Kumar, N Badrinath, K Rangaswamy AI-Driven Intelligent Models for Business Excellence, 95-111 , 2023 2023.0 Citations: 1
An Efficient Machine Learning Approach for Apple Leaf Disease Detection KR Bhavya, S Pravinth Raja, B Sunil Kumar, SA Karthik, S Chavadaki Intelligent Computing and Applications: Proceedings of ICDIC 2020, 419-429 , 2022 2022.0 Citations: 2
The plant disease detection using cnn and deep learning techniques merged with the concepts of machine learning N Sajitha, S Nema, KR Bhavya, P Seethapathy, K Pant 2022 2nd International conference on advance computing and innovative … , 2022 2022.0 Citations: 21
Cross channel scripting attacks (xcs) in web applications R Shashidhara, V Kantharaj, KR Bhavya, SC Lingareddy International Conference on Innovative Computing and Communications … , 2021 2021.0 Citations: 2
Framework for Real-Time Detection and Identification of possible patients of COVID-19 at public places B Peddinti, A Shaikh, NK KC Biomedical Signal Processing and Control 68, 102605 , 2021 2021.0 Citations: 13
Federated learning for crop yield prediction: A comprehensive review of techniques and applications P Gujjar, NS Rani, KR Bhavya Citations: 1
Generalized Hypercomplex Neural Networks: Advancing Multi-Dimensional Feature Representation with Adaptive Quaternion-Based Architectures DV Hiremani, DRM Devadas, NS Rani, B KR, P Gujjar Available at SSRN 5084804 , 0
Enhancing Medicinal Plant Leaves Species Classification Through Ensemble Learning with Transfer Learning Integration B KR, NS Rani, DRM Devadas, DV Hiremani Available at SSRN 4804339 , 0 Citations: 1
MOST CITED SCHOLAR PUBLICATIONS
The plant disease detection using cnn and deep learning techniques merged with the concepts of machine learning N Sajitha, S Nema, KR Bhavya, P Seethapathy, K Pant 2022 2nd International conference on advance computing and innovative … , 2022 2022.0 Citations: 21
Federated learning for crop yield prediction: A comprehensive review of techniques and applications V Hiremani, RM Devadas, R Sapna, T Sowmya, P Gujjar, NS Rani, ... MethodsX 14, 103408 , 2025 2025.0 Citations: 16
Fruit quality prediction using deep learning strategies for agriculture KR Bhavya, SP Raja Int. J. Intell. Syst. Appl. Eng 11 (2), 10-301 , 2023 2023.0 Citations: 14
Framework for Real-Time Detection and Identification of possible patients of COVID-19 at public places B Peddinti, A Shaikh, NK KC Biomedical Signal Processing and Control 68, 102605 , 2021 2021.0 Citations: 13
A Novel Curriculum Learning Training Strategy for Pomegranate Growth Stage Classification Using YOLO Models on Multi-Source Datasets for Precision Agriculture NS Rani, KR Bhavya, A Vadivel, T Vasudev, RM Devadas, V Hiremani IEEE Access , 2025 2025.0 Citations: 4
Stochastic calculus-guided reinforcement learning: A probabilistic framework for optimal decision-making RM Devadas, V Hiremani, KR Bhavya, NS Rani MethodsX 12, 102790 , 2024 2024.0 Citations: 4
HerbSimNet: Deep Learning-Based Classification of Indian Medicinal Plants with High Inter-Class Similarities NS Rani, KR Bhavya, BR Pushpa, RM Devadas Procedia Computer Science 258, 765-774 , 2025 2025.0 Citations: 3
TopoGeoFusion: Integrating object topology based feature computation methods into geometrical feature analysis to enhance classification performance NS Rani, KS Sai, BR Pushpa, AS Krishna, MA Sangamesha, KR Bhavya, ... MethodsX 13, 102859 , 2024 2024.0 Citations: 2
Machine learning-based stock price prediction for business intelligence KR Bhavya, M Sudhakara, GR Reddy, M Sangeetha AI-Driven Intelligent Models for Business Excellence, 209-226 , 2023 2023.0 Citations: 2
An Efficient Machine Learning Approach for Apple Leaf Disease Detection KR Bhavya, S Pravinth Raja, B Sunil Kumar, SA Karthik, S Chavadaki Intelligent Computing and Applications: Proceedings of ICDIC 2020, 419-429 , 2022 2022.0 Citations: 2
Cross channel scripting attacks (xcs) in web applications R Shashidhara, V Kantharaj, KR Bhavya, SC Lingareddy International Conference on Innovative Computing and Communications … , 2021 2021.0 Citations: 2
Customer purchase prediction and potential customer identification for digital marketing using machine learning M Sudhakara, KR Bhavya, MR Kumar, N Badrinath, K Rangaswamy AI-Driven Intelligent Models for Business Excellence, 95-111 , 2023 2023.0 Citations: 1
Federated learning for crop yield prediction: A comprehensive review of techniques and applications P Gujjar, NS Rani, KR Bhavya Citations: 1
Enhancing Medicinal Plant Leaves Species Classification Through Ensemble Learning with Transfer Learning Integration B KR, NS Rani, DRM Devadas, DV Hiremani Available at SSRN 4804339 , 0 Citations: 1
SeedlingNet: A Colour-Based Segmentation Approach Towards Classification of Plant Species Seedlings BR Pushpa, KR Bhavya, N Manohar MethodsX, 103883 , 2026 2026.0
FeaFusion-PomoNet: A Feature Fusion Driven Regression Framework for Non-Destruction Weight Estimation of Pomegranates RMD K. R. BHAVYA IEEE ACCESS 16, 213578-213598 , 2025 2025.0
TGNO-CAD: A Novel Approach to Detect Fake Accounts in Social Networks P Krishnadas, GM Reddy, S Ghattamaneni, K Bhavya, D LR 2025 10th International Conference on Communication and Electronics Systems … , 2025 2025.0
CISCS: Classification of inter-class similarity based medicinal plant species groups with machine learning NS Rani, KR Bhavya, IJ Jacob, BN BJ, A Prabhu MethodsX, 103652 , 2025 2025.0
Plant Region Detection from Infield Images with Unconstrained Backgrounds using U-Net NS Rani, B KR, IJ Jacob, PV Theerthagiri, SVN SR 2025 2nd International Conference on New Frontiers in Communication … , 2025 2025.0
Generalized Hypercomplex Neural Networks: Advancing Multi-Dimensional Feature Representation with Adaptive Quaternion-Based Architectures DV Hiremani, DRM Devadas, NS Rani, B KR, P Gujjar Available at SSRN 5084804 , 0
