INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Forest fires have serious consequences for ecology, public safety, and the economy. Vegetation degradation results in the loss of biodiversity and habitat for numerous species. Plant regeneration can be hampered by soil erosion and diminished fertility. Forest fires produce smoke, particulate matter, and poisonous compounds, all of which contribute to air pollution and health problems. Carbon dioxide emissions feed greenhouse gas emissions and limit trees' potential to function as carbon sinks. Forest fires harm lives, cause property damage, and pose health problems. They can have economic consequences, demanding costly resources for firefighting and disrupting businesses such as farming and tourism. Early identification of forest fires is critical for efficient firefighting and mitigation techniques, as it allows for quicker reactions, safety precautions, and resource allocation.
Previous studies investigated the use of convolutional neural networks (CNNs) for forest fire detection with good accuracy rates. The methodology necessitates the use of hardware (such as GPUs) and software (Python, TensorFlow, and Keras), as well as preprocessing techniques such as scaling, normalization, and data augmentation. The AlexNet architecture with ReLU activation function may be used to identify forest fires, utilizing transfer learning and ensemble approaches to increase model performance. The evaluation measures include accuracy and loss, and the training technique includes Adam optimizer optimization, learning rate modification, batch size definition, and a set number of epochs. The experiment may be run on sites like Kaggle, which has GPU accelerators for quicker training.
Keywords:
Forest fire detection, Convolutional neural networks, Data Science
Cite Article:
"Forest Fire Detection Using Convolutional Neural Networks", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 5, page no.e790-e803, May-2023, Available :http://www.ijnrd.org/papers/IJNRD2305496.pdf
Downloads:
000118749
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn