Abstract
Natural disasters not only cause death and property destruction around the world but the severity of these disasters is also reflected in many other forms like the economic loss, loss of lives, and the ability of populations to rebuild. This paper focuses on using machine learning, deep learning, and computer vision to detect natural disasters. Previously, many attempts have been made to detect natural disasters using different techniques including the use of sensors, satellites, drones, crowdsourcing, and basic ML models and reducing the severity of these disasters. But natural disaster detection still faces challenges due to the limitations of the above techniques like high cost of equipment and training time, lower accuracy, etc. Therefore, in order to combat these issues, transfer learning models are being used, namely a few architectures from VGG, ResNet, and EfficientNet. Many different values for epochs and dataset sizes were experimented with, as well as different configurations for the hidden layers and optimizers to improve the classification accuracy. From the results obtained after training the models, ResNet50 gave the best results with an accuracy of 96.35%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sushma L, Lakshmi KP (2020) An analysis of convolution neural networks for image classification using different models. Int J Eng Res Technol (IJERT) 9(10)
Havas C, Resch B, Francalanci C, Pernici B, Scalia G, Fernandez-Marquez JL, Van Achte T, Zeug G, Mondardini MR, Grandoni D, Kirsch B (2017) E2mc: improving emergency management service practice through social media and crowdsourcing analysis in near real time. Sensors 17(12):2766
National Institutes of Health (2017) National Library of Medicine, National Center for Biotechnology Information, The United States of America, Accessed 2 Nov 2022. https://www.ncbi.nlm.nih.gov
Zhang Z, He N, Li D, Gao H, Gao T, Zhou C (2022) Federated transfer learning for disaster classification in social computing networks. J Saf Sci Resilience 3(1):15–23
Mythili S, Shalini E (2016) A comparative study of smart phone emergency applications for disaster management. Int Res J Eng Technol (IRJET) 3(11):392–395
Ghazal M, Ali S, Al Halabi M, Ali N, Al Khalil Y (2016) Smart mobile-based emergency management and notification system. In: 2016 IEEE 4th International conference on future Internet of Things and cloud workshops (FiCloudW). IEEE, pp 282–287
Sahin YG, Ince T (2009) Early forest fire detection using radio-acoustic sounding system. Sensors 9(3):1485–1498
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the Harvard IEEE conference on computer vision and pattern recognition, pp 4700–4708
Desai C (2021) Image classification using transfer learning and deep learning. Int J Eng Comput Sci 10(9)
Tripathi M (2021) Analysis of convolutional neural network based image classification techniques. J Innov Image Process (JIIP) 3(02):100–117
Lin Q, Ci T, Wang L, Mondal SK, Yin H, Wang Y (2022) Transfer learning for improving seismic building damage assessment. Remote Sens 14(1):201
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Mahmudul Hassan SK, Maji AK, Jasinski M, Leonowicz Z, Jasinska E (2021) Identification of plant-leaf diseases using CNN and transfer-learning approach. Electronics 10(12):1388
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bosco, J., Yavagal, L., Srinivas, L.T., Katabatthina, M.K., Kasturi, N. (2023). Detection of Natural Disasters Using Machine Learning and Computer Vision by Replacing the Need of Sensors. In: Ranganathan, G., Papakostas, G.A., Rocha, Á. (eds) Inventive Communication and Computational Technologies. ICICCT 2023. Lecture Notes in Networks and Systems, vol 757. Springer, Singapore. https://doi.org/10.1007/978-981-99-5166-6_50
Download citation
DOI: https://doi.org/10.1007/978-981-99-5166-6_50
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5165-9
Online ISBN: 978-981-99-5166-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)