Early disease Classification will help reduce crop loss as well as increase agricultural productivity. A rapid and accurate deep learning-based framework to identify different diseases in eggplant on the marketplace level has been proposed in the research. Implementation and Training of an End-to-End Object Classification Based on YOLOv8. To train a custom multi-class data set, six target classes: Healthy Leaf, White Mold Disease, Leaf Spot Disease, Wilt Disease, Mosaic Virus Disease, and Insect Pest Disease. Initial work was done in developing the object detectors. We used standard metrics like accuracy, precision, recall, and F1-score to evaluate the performance of the model. When it came to finding Plant Leaf Disease (PLD), traceable configurations were revealed from configuration tuning among the combinations of hyperparameters, which converged at equal measurement intervals on a curve between Classification accuracy and computation efficiency from screened candidate architectures along ranges determined by performance metrics defined for detecting plant diseases using only above-ground debris as input sources. With stable convergence during the training phase, the model YOLOv8m had an accuracy of 96.84%, a precision of 96.85%, a recall of 96.84%, and an F1 score of 96.84%. The model that has been trained was deployed with the help of a web application named Streamlit, so that it could be used in practical procedures where disease can be detected if we upload an image. That means the system is robust and operates effectively in the wild as opposed to ideal test conditions, which lends itself well to agricultural usage. The present work provides an integrated, optimized deep learning detector with a user interface beneficial for precision farming that can help in the early identification of diseases on eggplants, resulting in increased yield.
Sujatha Krishna, O. I. Khalaf· International Journal of Dat...· 0 citations
The security landscape is increasingly at risk from phishing attackers; individuals engaging in this type of attack successfully persuade users to divulge sensitive data such as identity information or financial resources. Existing blacklist-based solutions and other approaches have proved ineffective because the adversaries are able to adjust to current bottleneck detectors and because machine learning models are based on hand-crafted behavior patterns. Deep learning brings the inductive bias of generalization to the fore while explicitly constraining the architectures to only hold local representations and to limit their capacity to express long-range relationships in data. We present a model based on CapsNet for phishing website detection in this paper. In the framework of CapsNets, dynamic routing is used to fortify the relationship between spatial and hierarchical features in a model that is built upon these orders between features. This approach is mostly to enable the model to gain complex relationships in a URL string and HTML structure. As a result of this property, the architecture is resistant to various types of adversarial perturbations like character replacement, subdomain mimicry, and misphrasing in phishing URLs. The model is evaluated the model using datasets from PhishTank, OpenPhish, and a benign domain list sourced from the Tranco list. Experimental results show that the proposed method is superior to the state-of-the-art deep learning methods and traditional classifiers in terms of accuracy, precision, recall, and ROC-AUC and reduces the false positive rate. The results confirm that CapsNet is a stable and flexible method for phishing classification that can be used for designing and implementing secure reliable web protection systems.
Sujatha Krishna, Krishna Chandra M, Rajesh Natarajan et al.· 2026 4th International Confe...· 0 citations