Kolawole John Adebayo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kolawole John Adebayo has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Joseph Damilola Akinyemi
University of York
2 shared publications Abeer Rashad Mirdad
1 shared publicationAmjad Rehman
1 shared publication- Ayesha Khaliq
Iqra University, Karachi, Pakistan
1 shared publication - Ebtihal Ismail Enfes
Computer Engineering Department, Eastern Mediterranean University, Famagusta, Trkiye
1 shared publication Faten S. Alamri
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Elsevier in Egyptian Informatics Journal
- Vol. 34
Ensemble of graph neural networks with Transformer fusion for diabetic retinopathy severity classification
- 12 April 2026
- Published by Elsevier in Egyptian Informatics Journal
- Vol. 34
Open AccessEnsemble of graph neural networks with Transformer fusion for diabetic retinopathy severity classification
- Open Access
- 27 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 48182-48197
Cross-Dialectal Transfer Learning for Offensive Language Detection in Arabic
Automated offensive language detection (OLD) is essential for online safety, yet remains particularly challenging for under-resourced languages and their dialectal variations. This paper addresses these challenges by evaluating OLD across three low-resource Arabic dialects: Egyptian, Libyan, and Levantine, using newly collected dialect-specific datasets and a novel parallel corpus for controlled cross-dialect analysis.We benchmark a wide range of models, including encoder-only, encoder–decoder, and decoder-only Large Language Models (LLMs), alongside traditional machine learning baselines (XGBoost, LightGBM), under zero-shot, few-shot, and fine-tuned settings. Our experiments reveal that task-specific fine-tuning consistently delivers the highest performance, especially for models pre-trained on Arabic corpora such as AraBERT, while few-shot learning yields modest and sometimes unstable gains. Surprisingly, classical models leveraging AraBERT embeddings remain competitive in zero-shot settings. Cross-dialect evaluations further highlight substantial performance variability driven by dialectal distance, lexical ambiguity, and contextual offensiveness. These findings offer a comprehensive benchmark for OLD in dialectal Arabic and provide practical guidance for developing robust moderation systems in linguistically diverse, low-resource environments.
- 27 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 48182-48197
Open AccessCross-Dialectal Transfer Learning for Offensive Language Detection in Arabic
Automated offensive language detection (OLD) is essential for online safety, yet remains particularly challenging for under-resourced languages and their dialectal variations. This paper addresses these challenges by evaluating OLD across three low-resource Arabic dialects: Egyptian, Libyan, and Levantine, using newly collected dialect-specific datasets and a novel parallel corpus for controlled cross-dialect analysis.We benchmark a wide range of models, including encoder-only, encoder–decoder, and decoder-only Large Language Models (LLMs), alongside traditional machine learning baselines (XGBoost, LightGBM), under zero-shot, few-shot, and fine-tuned settings. Our experiments reveal that task-specific fine-tuning consistently delivers the highest performance, especially for models pre-trained on Arabic corpora such as AraBERT, while few-shot learning yields modest and sometimes unstable gains. Surprisingly, classical models leveraging AraBERT embeddings remain competitive in zero-shot settings. Cross-dialect evaluations further highlight substantial performance variability driven by dialectal distance, lexical ambiguity, and contextual offensiveness. These findings offer a comprehensive benchmark for OLD in dialectal Arabic and provide practical guidance for developing robust moderation systems in linguistically diverse, low-resource environments.
- Open Access
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 22318-22334
DKC-LLM: Dynamic Knowledge Caching for Large Language Models in Business Applications
Large Language Models (LLMs) often face severe latency and computational cost constraints which hinder their adoption in real-time enterprise applications. Retrieval-Augmented Generation (RAG) frameworks, while improving factual accuracy, further increase inference delays owing to additional retrieval and context integration steps. To address these challenges, we propose Dynamic Knowledge Caching for Large Language Models (DKC-LLM), a novel framework that integrates dynamic semantic caching with an adaptive cache management strategy, which detects and compensates for semantic drift to accelerate response generation while ensuring accuracy and freshness. We evaluate DKC-LLM on two distinct question-answering benchmarks: BankFAQs, a domain-specific dataset with 5,000 selected queries and HotpotQA, an open-domain dataset with 5,000 selected queries, totaling 10,000 evaluation queries. Experimental results demonstrate that DKC-LLM achieves 20-30% lower latency, i.e., 5.3–6.8 ms vs. RAG’s 8–10 ms, a 63-70.5% cache hit rate, and a 60% reduction in LLM compute overhead, while maintaining 83-90% response accuracy. Additionally, DKC-LLM reduced hallucination rates by 75%, outperforming baseline RAG by up to 15 percentage points. These findings posit that DKC-LLM is a cost-efficient, low-latency, and high-accuracy solution for real-time, high-frequency business scenarios such as customer support and enterprise information retrieval.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 22318-22334
Open AccessDKC-LLM: Dynamic Knowledge Caching for Large Language Models in Business Applications
Large Language Models (LLMs) often face severe latency and computational cost constraints which hinder their adoption in real-time enterprise applications. Retrieval-Augmented Generation (RAG) frameworks, while improving factual accuracy, further increase inference delays owing to additional retrieval and context integration steps. To address these challenges, we propose Dynamic Knowledge Caching for Large Language Models (DKC-LLM), a novel framework that integrates dynamic semantic caching with an adaptive cache management strategy, which detects and compensates for semantic drift to accelerate response generation while ensuring accuracy and freshness. We evaluate DKC-LLM on two distinct question-answering benchmarks: BankFAQs, a domain-specific dataset with 5,000 selected queries and HotpotQA, an open-domain dataset with 5,000 selected queries, totaling 10,000 evaluation queries. Experimental results demonstrate that DKC-LLM achieves 20-30% lower latency, i.e., 5.3–6.8 ms vs. RAG’s 8–10 ms, a 63-70.5% cache hit rate, and a 60% reduction in LLM compute overhead, while maintaining 83-90% response accuracy. Additionally, DKC-LLM reduced hallucination rates by 75%, outperforming baseline RAG by up to 15 percentage points. These findings posit that DKC-LLM is a cost-efficient, low-latency, and high-accuracy solution for real-time, high-frequency business scenarios such as customer support and enterprise information retrieval.
- Open Access
The PV-ALE Dataset: Enhancing Apple Leaf Disease Classification Through Transfer Learning with Convolutional Neural Networks
As the global food security landscape continues to evolve, the need for accurate and reliable crop disease diagnosis has never been more pressing. To address global food security concerns, we extend the widely used PlantVillage dataset with additional apple leaf disease classes, enhancing diversity and complexity. Experimental evaluations on both original and extended datasets reveal that existing models struggle with the new additions, highlighting the need for more robust and generalizable computer vision models. Test F1 scores of 99.63% and 97.87% were obtained on the original and extended datasets, respectively. Our study provides a more challenging and diverse benchmark, paving the way for the development of accurate and reliable models for identifying apple leaf diseases under varying imaging conditions. The expanded dataset is available at https://www.kaggle.com/datasets/akinyemijoseph/apple-leaf-disease-dataset-6-classes-v2 enabling future research to build upon our findings.
Open AccessThe PV-ALE Dataset: Enhancing Apple Leaf Disease Classification Through Transfer Learning with Convolutional Neural Networks
As the global food security landscape continues to evolve, the need for accurate and reliable crop disease diagnosis has never been more pressing. To address global food security concerns, we extend the widely used PlantVillage dataset with additional apple leaf disease classes, enhancing diversity and complexity. Experimental evaluations on both original and extended datasets reveal that existing models struggle with the new additions, highlighting the need for more robust and generalizable computer vision models. Test F1 scores of 99.63% and 97.87% were obtained on the original and extended datasets, respectively. Our study provides a more challenging and diverse benchmark, paving the way for the development of accurate and reliable models for identifying apple leaf diseases under varying imaging conditions. The expanded dataset is available at https://www.kaggle.com/datasets/akinyemijoseph/apple-leaf-disease-dataset-6-classes-v2 enabling future research to build upon our findings.