@article{N. P._Umair Bagali_N._2023, title={BBCNN: Bounding Box Convolution Neural Network for Cyclone Prediction and Monitoring}, volume={11}, url={https://ijisae.org/index.php/IJISAE/article/view/2596}, abstractNote={<p>The correct identification of tropical cyclones is essential for the prevention and preparation for catastrophic events that they cause. The prediction of a cyclone’s surge, as well as the monitoring of its severity, is an important part of the predictive model. Despite the significant efforts made each year, a significant number of individuals still lose their lives as a consequence of cyclones. More appropriate predictive methods need to be developed to reduce the severity of this harm. Deep learning techniques provide perks in detecting challenges since they can increase the prediction algorithm’s stability and efficiency. The method discussed here uses artificial neural networks to analyse MOSDAC satellite imagery. With the help of satellite data, a several-layer neural-net model was trained to predict cyclones, much like biological visual perception. The findings suggest that the method has the potential to be further refined into an efficient instrument for cyclone track predictions by making use of a variety of different kinds of remote sensing imagery and information.</p>}, number={2}, journal={International Journal of Intelligent Systems and Applications in Engineering}, author={N. P., Mamatha and Umair Bagali, Mohmad and N., Thangadurai}, year={2023}, month={Feb.}, pages={64–73} }