Faculty of Computing

Permanent URI for this communityhttps://repository.nileuniversity.edu.ng/handle/123456789/13

Browse

Has files: YesSubject: search.filters.subject.Deep Learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    GeoAI at the forefront of climate action
    (Global Journal of Engineering and Technology Advances, 2025-08-21) MAVISCLARA, OHAKA AMARACHI; Esekie, Jeffery Omozokpia; Atoyebi, Temitope Olufunmi; ATUMAH, Prayer Erumusele; Akadiri, Oluwatoyin Olawale; JIMOH, Rildwan Adekunle; IBRAHIM, ISIAKA OSHOBUGIE
    GeoAI, merging artificial intelligence with geospatial data, is transforming climate change mitigation and adaptation. This review synthesizes 2020–2025 advancements, focusing on deep learning models like convolutional neural networks (CNNs) and transformers, achieving 90–95% accuracy in flood prediction, carbon sequestration mapping, and urban heat mitigation. Key mitigation strategies include forest biomass estimation in the Amazon and renewable energy optimization in India, while adaptation efforts encompass real-time flood mapping in Bangladesh and coastal resilience modeling in the Pacific Islands. Despite successes, challenges persist, including data biases, computational costs, and ethical concerns like privacy in urban GeoAI applications. Public discourse on platforms like X highlights demand for equitable climate solutions, reflected in discussions on wildfires and Arctic rain. Future directions involve federated learning for privacy-preserving GeoAI and generative AI for climate scenario modeling. Aligning with Sustainable Development Goal 13, GeoAI offers transformative potential to enhance global climate resilience, necessitating investment in open-access tools and interdisciplinary collaboration to address research gaps and ensure inclusivity.
  • No Thumbnail Available
    Item
    Intrusion Detection System Using Initialization- based Few-shot Learning
    (International Conference on Multidisciplinary Engineering and Applied Science, 2023-02-02) Nurudeen M. Ibrahim; Moussa Mahamat Boukar
    An Intrusion Detection System (IDS) has become an essential means of ensuring the security of a network. It is a system that monitors the state of the traffic running in the network. Few-shot learning is a novel machine learning (ML) approach that has the ability of recognizing novel objects from very few examples. Conventional ML models require substantial amount of data in order to train the model whereas the IDS dataset is imbalanced and is lacking in various categories. In this research, we proposed and implemented a method of using initialization-based few-shot learning (IB-FSL) to improve the performance of the IDS by initializing the weights and by “learning to fine-tune” the data as it detects intrusion. To accomplish our set objectives, we implemented a ResNet-50 on the proposed IB-FSL which gave us a model that initializes the weights such that classifiers for novel classes could be learned from very few labeled examples and a minimal number of gradient descent steps before the application of fine-tuning. The experiment on UNSW-NB15 showed a good performance with an accuracy of 85.96% on less than 2% of the training dataset. We also obtained a precision of 96.18% and F1-score of 92% while other methods such as Decision Tree (DT), Logistic regression (LR), Naïve Bayes (NB) and Expectation Maximization (EM) clustering used 100% of the training dataset but achieved an accuracy of 85.56%, 83.15%, 82.07% and 78.47% respectively. This model could be used to detect abnormal data intrusions into the network traffic with low false alarm rate leading to improved network security