Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
Item Forecasting the Fury: A Deep Learning Approach to Predicting Cyclone Intensity(Institute of Electrical and Electronics Engineers Inc., 2023) Kumar, S.; Lohiya, K.S.; Patil, N.Cyclones are considered one of the most catastrophic natural calamities that result in severe destruction and numerous casualties each year. To ensure prompt and efficient disaster management and response, it is imperative to estimate the intensity of cyclones with precision and timeliness. In this research article, a deep learning technique is suggested for cyclone intensity evaluation utilizing INSAT-3D IR imagery. Our proposed method uses a pre-trained convolutional neural network (CNN) such as ResNet-50 and Inception-V3 to learn features from INSAT-3D IR imagery and estimate the cyclone's intensity. We train the model on a dataset of cyclones with known intensities and evaluate its performance on a separate test set. To analyze the significance of various elements in our proposed approach, we perform an ablation study, including the CNN architecture and input image preprocessing. The results show how well our suggested strategy works and shed light on the mechanisms that underlie it. In our deep learning model, we have used CNN, Inception, and Resnet50. We have calculated the Mean Squared Error, Mean absolute error, R-squared score, and Root mean squared error. We have considered the RMSE value for results which are for CNN is 13.77, Inception_V3 is 15.77 and Resnet50 is 11.69. This indicates that Resnet50 is giving better results in comparison to Inception_V3 and CNN. Overall, our deep learning-based approach offers a promising solution for accurate and timely cyclone intensity estimation, which can aid in disaster management and response efforts. © 2023 IEEE.Item An Efficient Rainfall Prediction Model Using Deep Learning Method(Institute of Electrical and Electronics Engineers Inc., 2023) Verma, V.K.; Janagama, H.S.; Patil, N.Rainfall is a crucial aspect of the Earth's natural cycle and it is necessary for various activities such as agriculture, water supply and hydroelectric power generation. However excessive rainfall can lead to floods, landslides and other destructive consequences, while insufficient rainfall can cause droughts and water shortages. Therefore accurate estimation of rainfall is essential to manage and mitigate the impacts of rainfall. In this study, the dataset is collected from the NASA Power database [22] to predict the annual rainfall in Mangalore(Karnataka), India. The data is collected from January 1, 2003 to February 04, 2023 using NASA POWER API. The study used four models MLP[15], LSTM, BiLSTM, CNN to predict the daily average precipitation that contributes to the annual rainfall. The input parameters considered for the prediction are maximum monthly temperature, minimum monthly temperature, humidity, atmospheric pressure and wind speed[9]. The model's performance is measured using mean squared error (MSE) and mean absolute error (MAE) of the predicted values on training and testing ratio 80:20. CNN(Convolutional Neural Network) model outperforms and gives the MSE and MAE for the CNN(Convolutional Neural Network) model are 0.0041 and 0.0456 respectively. © 2023 IEEE.Item Comprehensive Deep Learning Approach for Identifying Plant Nutrient Deficiency, Diseases and Pests(Institute of Electrical and Electronics Engineers Inc., 2024) Bavishi, C.; Patil, N.The core of the Indian economy is agriculture, facilitating the expansion of the service or industrial sectors. The quantity and standard of agricultural goods are seriously threatened by plant diseases. For agricultural productivity, early symptom detection and precise illness classification are essential. This paper underscores the transition from traditional methods, such as image processing and deep learning due to their improved efficiency and accuracy. The primary focus lies in classifying plant diseases using various Deep Learning architectures to achieve higher accuracy. The study will also provide predicting plant disease along with Nutrient Deficiency and pests identification. The final goal will be detecting all these three outcome using single model with high accuracy so no need to execute multiple times. Dataset used in this research is OLID I(Open Leaf Image Dataset). Models are trained with augmented images as well as original dataset. It is found that EfficientNetV2B0 model outperforms some state-of-the-art convolutional neural networks that include EfficientNetV2B3, VGG16 and custom CNN model while running with augmented dataset. Which achieves accuracy with 85.38% and f1-score with 85.08. © 2024 IEEE.Item A Deep Learning Framework for Plant Disease Detection(Springer Science and Business Media Deutschland GmbH, 2025) Munda, K.K.; Patil, N.As a major source of nutritious food, the agriculture industry supports economies and feeds people. Yet, the production of food is severely hampered by plant diseases. Major crops like wheat (21.5%), rice (30.0%), maize (22.6%), potatoes (17.2%), and soybeans (21.4%) have significant annual output declines due to numerous diseases, according to recent studies. Since deep learning technologies have been developed, image categorization accuracy has increased dramatically. Using CNN and vision transformer models, we examine the Plant Village dataset in this study, which consists of 54,305 sample images that illustrate various plant disease species in 38 classifications. Using a focus on potato leaves and a total of 2151 samples, we evaluate the model’s performance in comparison to other models in terms of training and testing accuracy, and we obtained impressive results. The models’ respective training accuracy is 97.27% for the CNN and 94.7% for the ViT model, while their validation accuracy is 100% and 94.27%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.