Julius Olaniyan

Dr. Julius Olaniyan

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 December 2025 in Algorithms
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
DODeborah Olaniyan
Deborah Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
Madison N NgafeesonMadison N Ngafeeson
Madison N Ngafeeson
Detection of financial fraud remains a constant challenge due to the dynamic and highly imbalanced nature of transaction data. This paper proposes the Graph-Temporal Contrastive Transformer (GTCT) framework for modeling both structural dependencies between accounts and temporal evolution in transactional behaviors. We propose a model that combines three components: a graph encoder for modeling relationships between accounts, a temporal encoder for learning sequential patterns in transactions, and a contrastive learning objective that enhances the robustness of representations when supervision is limited. To assess the contribution of each component individually, we systematically remove one module at a time. As shown, an exclusion of the contrastive loss resulted in reduced recall and AUC from 0.867 and 0.982 to 0.805 and 0.948, respectively, indicating the importance of self-supervised learning of representations in fraud detection. Similarly, removing the graph encoder decreased the F1-score from 0.876 to 0.786, which confirmed that modeling transaction structures between accounts is crucial for the identification of complex fraud rings. The exclusion of the temporal encoder led to a more drastic drop in recall (0.743) and AUC (0.905), indicating that capturing the temporal dynamics of transactions is relevant. By comparing all variants, the full GTCT model attained the highest accuracy (0.975) and AUC (0.982), thus showing superior robustness in the detection of sophisticated and evolving financial fraud patterns.

4 November 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
DODeborah Olaniyan
Deborah Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
MOMatthew Odighi
Matthew Odighi
This paper presents a transformative explainable convolutional neural network (CNN) framework for cataract detection, utilizing a hybrid deep learning model combining Siamese networks with VGG16. By leveraging a learning rate scheduler and Grad-CAM (Gradient-weighted Class Activation Mapping) for explainability, the proposed model not only achieves high accuracy in identifying cataract-infected images but also provides interpretable visual explanations of its predictions. Performance evaluation metrics such as accuracy, precision, recall, and F1 score demonstrate the model’s robustness, with a perfect accuracy of 100%. Grad-CAM visualizations highlight the key image regions—primarily around the iris and pupil—that contribute most to the model’s decision-making, making the system more transparent for clinical use. Additionally, novel statistical analysis methods, including saliency map evaluation metrics like AUC (Area Under the Curve) and the Pointing Game, were employed to quantify the quality of the model’s explanations. These metrics enhance the interpretability of the model and support its practical applicability in medical image analysis. This approach advances the integration of deep learning with explainable AI, offering a robust, accurate, and interpretable solution for cataract detection with the potential for broader adoption in ocular disease diagnosis and medical decision support systems.

11 November 2024 in Electronics
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
DODeborah Olaniyan
Deborah Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
AAAyodele A. Adebiyi
Ayodele A. Adebiyi
OBOlorunfemi Paul Bernard
Olorunfemi Paul Bernard
Financial forecasting plays a critical role in decision-making across various economic sectors, aiming to predict market dynamics and economic indicators through the analysis of historical data. This study addresses the challenges posed by traditional forecasting methods, which often struggle to capture the complexities of financial data, leading to suboptimal predictions. To overcome these limitations, this research proposes a hybrid forecasting model that integrates Bayesian optimization with Long Short-Term Memory (LSTM) networks. The primary objective is to enhance the accuracy of market trend and asset price predictions while improving the robustness of forecasts for economic indicators, which are essential for strategic positioning, risk management, and policy formulation. The methodology involves leveraging the strengths of both Bayesian optimization and LSTM networks, allowing for more effective pattern recognition and forecasting in volatile market conditions. Key contributions of this work include the development of a novel hybrid framework that demonstrates superior performance with significantly reduced forecasting errors compared to traditional methods. Experimental results highlight the model’s potential to support informed decision-making amidst market uncertainty, ultimately contributing to improved market efficiency and stability.

23 September 2024 in Computers
Verified
Journal Article
Open access
PDF file
DODeborah Olaniyan
Deborah Olaniyan
JOJulius Olaniyan
Julius Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
BEBukohwo Michael Esiefarienrhe
Bukohwo Michael Esiefarienrhe
OBOlorunfemi Paul Bernard
Olorunfemi Paul Bernard
This study presents the development and evaluation of a Multi-Task Long Short-Term Memory (LSTM) model with an attention mechanism for predicting students’ academic performance. The research is motivated by the need for efficient tools to enhance student assessment and support tailored educational interventions. The model tackles two tasks: predicting overall performance (total score) as a regression task and classifying performance levels (remarks) as a classification task. By handling both tasks simultaneously, it improves computational efficiency and resource utilization. The dataset includes metrics such as Continuous Assessment, Practical Skills, Presentation Quality, Attendance, and Participation. The model achieved strong results, with a Mean Absolute Error (MAE) of 0.0249, Mean Squared Error (MSE) of 0.0012, and Root Mean Squared Error (RMSE) of 0.0346 for the regression task. For the classification task, it achieved perfect scores with an accuracy, precision, recall, and F1 score of 1.0. The attention mechanism enhanced performance by focusing on the most relevant features. This study demonstrates the effectiveness of the Multi-Task LSTM model with an attention mechanism in educational data analysis, offering a reliable and efficient tool for predicting student performance.

26 March 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
SVSilas Verkijika
Silas Verkijika
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
Fine-grained image classification under few-shot learning conditions remains a significant challenge due to limited labeled data and high intra-class similarity. This paper proposes a novel cross-modal framework that integrates Contrastive Language-Image Pretraining (CLIP) embeddings within a Siamese similarity network to enable robust and label-efficient classification. By leveraging the semantic alignment between textual class descriptions and visual representations, the model forms hybrid similarity pairs of image-to-image and image-to-text within a shared latent space, facilitating discriminative learning under low-shot scenarios. The architecture employs a dual-branch CLIP encoder and a contrastive loss function to optimize intra-class compactness and inter-class separability. Experiments conducted on benchmark datasets including miniImageNet and CUB-200-2011 demonstrate substantial improvements over zero-shot and few-shot baselines, achieving 70.32% accuracy, 71.15% F1-score, and 68.47% mAP on 5-way 1-shot and 78.41% accuracy, 79.02% F1-score, and 76.83% mAP on 5-way 5-shot tasks (averaged over 600 episodes with 95% confidence intervals on the CUB-200-2011 dataset). Extended evaluations under 10-way settings show similarly strong performance. Ablation studies further validate the critical roles of contrastive learning, normalization, and cross-modal embeddings in enhancing generalization. This work presents a scalable and interpretable paradigm for fine-grained classification in data-scarce domains.

26 March 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
SVSilas Verkijika
Silas Verkijika
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
The increasing demand for scalable and fair assessment of open-form responses in digital education shows the need for intelligent grading systems capable of balancing syntactic precision with semantic understanding. This study proposes a hybrid semantic–syntactic NLP framework for automated grading of short-answer and cloze-type questions. The framework integrates a rule-based matcher for syntactic accuracy, MPNet (Masked and Permuted Pre-trained Network) embeddings for semantic similarity, and a fine-tuned DeBERTa (Decoding-enhanced Bidirectional Encoder Representations from Transformer with Disentangled Attention) regressor for continuous score prediction, while a T5-small model provides pedagogically aligned feedback generation. Evaluations were conducted using benchmark corpora, synthetic cloze datasets, and a domain-specific short-answer corpus. Results demonstrate that the hybrid system outperforms traditional baselines, achieving 91% accuracy, a 0.89 F1 score, a mean absolute error of 0.36, and strong inter-rater agreement (κ = 0.87), aligning closely with human graders. Qualitative analyses show that the framework successfully recognizes paraphrased responses, assigns partial credit, and generates meaningful feedback. Ablation studies further validate the necessity of each subsystem, with performance significantly declining when components were removed. The findings confirm that the proposed framework is both computationally robust and pedagogically valuable, establishing a foundation for scalable, interpretable, and fair automated grading in contemporary educational environments.