College of Engineering

Permanent URI for this communityhttp://itsupport.cu.edu.ng:4000/handle/123456789/28755

Welcome to the page of the College of Engineering.

Browse

Subject: search.filters.subject.Deep Learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Bridging the Artificial Intelligence Knowledge and Skill Gaps in Africa: a Case of the 3rd Google Tensorflow Bootcamp and FEDGEN Mini-Workshop
    (2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals, 2024) Adetiba Emmanue; Wejin John S.; Oshin Oluwadamilola; Ifijeh Ayodele H.; LAWAL, Comfort Oluwaseyi; Thakur Surendra Colin; Awelewa Ayokunle A.; Kala Raymond Jules; Ajayi Priscilla O.; Akanle Matthew B.; Sweetwiliams Faith O.; Nnaji Uche; Owolabi Emmanuel; Idowu-Bismark Olabode; Sobola Gabriel
    In transiting from one civilization to another, technology has played a vital and positive role. In the 21st century, one of the digital developments that is paving ways for human life improvement is machine-assisted technology using Artificial Intelligence (AI). Artificial Intelligence has successfully enhanced man’s capacity in solving complex problems and processes. However, as developed nations continue to reap from the adoption of AI in various fields of human endeavors, the continent of Africa has remained behind, especially in AI-based skills and research. Various governments in developing nations have encouraged the adoption of AI, especially in institutions of learning. However, theoretical adoption without practical experience has remained an ineffective way of bridging the digital divide. In this paper we present the outcome of a practical approach to bridging the AI divide among students and researchers in Africa through funding support from the Google TensorFlow College Outreach Award. A 3-day hybrid bootcamp was organized (11th to 13th December, 2023) using the Google funding in order to equip postgraduate students and researchers with AI and collaborative research skills. A pre-survey method was employed to ascertain the knowledge level of the bootcamp participants. From the pre-surveyed feedback, training sessions on various AI domains were presented, and participant equipped with practical AI skills using a deployed AI-based cloud programming platform running on the private Federated Genomic Cloud (FEDGEN) infrastructure at Covenant University. A post-survey feedback was used to ascertain the effectiveness of this approach. A comparative analysis of the pre-survey and post-survey reveals a 70% improvement of AI skills among participants. This shows that having continuous training session for students and researchers is an effective method in closing the AI skills gap between developed and developing nations.
  • No Thumbnail Available
    Item
    DEVELOPMENT OF A HIERARCHICAL ANOMALY DETECTION MODEL IN A FEDERATED CLOUD INFRASTRUCTURE USING ENHANCED GRAPH SAMPLING AND AGGREGATION
    (Covenant University Ota, 2025-08) LAWAL, Comfort Oluwaseyi; Covenant University Dissertation
    Modern distributed computing systems generate massive volumes of log data, making manual analysis infeasible. Existing methods treat log entries as independent events, failing to leverage structural dependencies and temporal correlations. This limitation is critical in federated cloud infrastructures where anomalies propagate across interconnected services. This research developed a hierarchical anomaly detection model that employs Federated Hierarchical Graph Sampling and Aggregation (Fed-HiGraphSAGE) techniques to enable multi-level anomaly classification in distributed cloud environments while preserving data privacy. FedHiGraphSAGE was built on an Enhanced Hierarchical GraphSAGE architecture, incorporating node features, edge attributes, and hierarchical structure to classify anomalies across five semantic levels: Anomaly, Anomaly-Type, Cloud Component, Application-Type and Specific-cloud-module. The model employs federated learning capabilities, dynamic graph management, hierarchical diagnostic capabilities, adaptive thresholding, and memory-efficient training. It also implemented a HierarchicalStratifiedBalancer to address class imbalance. The model was trained and evaluated using federated learning across three data-contributing regions: Afe Babalola University, Landmark University, and DRC_Congo, with Covenant University serving as the federated learning coordinator. A total of 54,919 system logs were processed from these three regions to simulate real-world federated deployment. The model demonstrated exceptional performance with region-specific accuracies of 91.97% (Afe Babalola), 98.27% (Landmark), and 98.76% (DRC_Congo). Hierarchical metrics confirmed effective multi-level classification with h-precision ranging from 91.82% to 98.99%, h-recall from 90.60% to 98.53%, and h-f1 from 89.95% to 98.66%. The model generated detailed hierarchical anomaly classifications and demonstrated significant performance adaptability across regions while maintaining global model coherence, with federated training reducing the global client’s loss from approximately 0.47 to 0.02 over 15 rounds. This research advances automated system monitoring by demonstrating that federated learning with graph-based representations and hierarchical classification significantly improves anomaly detection performance while enabling cross-regional knowledge sharing. The model’s ability to maintain exceptional performance across multiple classification levels while providing explainable results establishes a new benchmark for automated log analysis in complex distributed systems