Volume 7 Issue 4 October-December 2019
Design and study of Automotive Chassis bracket using structural Finite Element Analysis [pp 01-06]
Mohammad Faraz Rayeen, Arun Singh Patel
Abstract: Producing better quality, reducing the manufacturing cost and delivering the product quickly, have now become the major targets for manufacturing industry. FE simulation can play an important role in the integration of design and manufacture during the development of automobile…
Design & Simulation of Dynamic Voltage Restorer for Power Quality Improvement
[pp 07-12]
Balwant Barkhaniya, Madhu Upadhyay
Abstract: Producing better quality, reducing the manufacturing cost and delivering the product quickly, have now become the major targets for manufacturing industry. FE simulation can play an important role in the integration of design and manufacture during the development of automobile…
Surveying Advanced Deep Learning Techniques for Unmanned Aerial Vehicle Detection: An In-Depth Exploration
[pp 13-17]
Doi – 10.55083/irjeas.2019.v07i04006
Dr. Sajeeda Parveen Shaik
Abstract: Remote sensing, a crucial tool for Earth observation, has witnessed a paradigm shift with the integration of deep learning methodologies. This comprehensive review explores recent advancements in the application of deep learning to remote sensing data, encompassing key architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and attention mechanisms. The study delves into multi-sensor fusion and multimodal approaches, elucidating their role in enhancing accuracy and robustness. Transfer learning and domain adaptation strategies are examined, providing insights into their effectiveness in overcoming data limitations and domain shifts. Through a detailed analysis of applications, including land cover classification, change detection, and object detection, the review showcases the transformative impact of deep learning across diverse remote sensing scenarios. While acknowledging successes, the paper critically evaluates challenges, such as interpretability and computational requirements, and outlines potential future directions, including explainable AI and the integration of emerging technologies. This review provides a comprehensive understanding of the current landscape, aiming to guide researchers and practitioners in advancing the field of deep learning for remote sensing applications.