Enerst Edozie

Enerst Edozie

Auto-generated profile, based on publicly available information

Enerst Edozie

Department of Electrical, Telecommunication and Computer Engineering, Kampala International University, Kampala, Uganda

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
25 January 2025 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
EEEnerst Edozie
Enerst Edozie
ASAliyu Nuhu Shuaibu
Aliyu Nuhu Shuaibu
BSBashir Olaniyi Sadiq
Bashir Olaniyi Sadiq
UJUkagwu Kelechi John
Ukagwu Kelechi John
Telecommunication networks are becoming increasingly dynamic and complex due to the massive amounts of data they process. As a result, detecting abnormal events within these networks is essential for maintaining security and ensuring seamless operation. Traditional methods of anomaly detection, which rely on rule-based systems, are no longer effective in today’s fast-evolving telecom landscape. Thus, making AI useful in addressing these shortcomings. This review critically examines the role of Artificial Intelligence (AI), particularly deep learning, in modern anomaly detection systems for telecom networks. It explores the evolution from early strategies to current AI-driven approaches, discussing the challenges, the implementation of machine learning algorithms, and practical case studies. Additionally, emerging AI technologies such as Generative Adversarial Networks (GANs) and Reinforcement Learning (RL) are highlighted for their potential to enhance anomaly detection. This review provides AI’s transformative impact on telecom anomaly detection, addressing challenges while leveraging 5G/6G, edge computing, and the Internet of Things (IoT). It recommends hybrid models, advanced data preprocessing, and self-adaptive systems to enhance robustness and reliability, enabling telecom operators to proactively manage anomalies and optimize performance in a data driven environment.

12 June 2025 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
EEEnerst Edozie
Enerst Edozie
ASAliyu Nuhu Shuaibu
Aliyu Nuhu Shuaibu
UJUkagwu Kelechi John
Ukagwu Kelechi John
BSBashir Olaniyi Sadiq
Bashir Olaniyi Sadiq
This comprehensive review looks into the recent developments in visual object detection, focusing on the transformative effect of deep learning (DL) technologies. In object detection, computer vision is a basic issue. This involves object detection and location in the video and image frames, which has notable advantages in robotics, autonomous driving, medical imaging, and surveillance. This review, therefore, presents a thorough integration analysis in visual object detection of the latest developments, providing both the historical context and state-of-the-art analysis. This review categorizes current methods into one-stage and two-stage frameworks, studying their architectural innovations, detection accuracy, computational speed, and deployment readiness. This review further scrutinizes the performance measures, emphasizes the inevitability of large-scale annotated datasets, and provides a curated overview of the widely used datasets in the field. Notable features include a discussion of practical applications and current research trends, and a comprehensive comparative analysis that compares models based on accuracy, speed, and trade-offs. A unique addition of this work is a thorough comparative analysis table that benchmarks traditional and modern models in terms of mean Average Precision (mAP), frames per second (FPS), advantages, limitations, and the coverage of transformer-based models and real-time deployments. The review’s holistic approach provides significant insights for researchers and practitioners seeking to understand, benchmark, develop, or benchmark object detection systems.

17 September 2025 in IEEE Access
Verified
Journal Article
Open access
OCOgenyi Fabian Chukwudi
Ogenyi Fabian Chukwudi
MBMohammed Dahiru Buhari
Mohammed Dahiru Buhari
Bashir Olaniyi SadiqBashir Olaniyi Sadiq
Bashir Olaniyi Sadiq
EEEnerst Edozie
Enerst Edozie
Non-Orthogonal Multiple Access (NOMA) has emerged as a critical facilitator of downlink communications in next-generation wireless networks, where user connectivity and spectral efficiency are paramount. The present paper examines dynamic and energy-efficient power allocation in the NOMA systems with imperfect Channel State Information (CSI). To overcome the issues caused by CSI uncertainty and to ensure maximum performance of the system, an Adaptive Particle Swarm Optimization-Dynamic Power Allocation (APSO-DPA) algorithm is proposed. The algorithm has a multi-objective optimization framework that takes into account energy-efficiency (EE), user fairness and the reliability of Successive Interference Cancellation (SIC) decoding in a combined manner. Simulation results reveal that APSO-DPA has always shown better results in comparison with the conventional fixed and equal power allocation scheme at different signal-to-noise ratio (SNR) levels. Its maximum sum rate at 40 dB is 17.7367 bps/Hz, with an energy-efficiency of 0.00177 bits/joule and a Jain’s Fairness Index of 0.5971. Although EE is expected to decline with elevated SNR as more power is consumed, APSO-DPA keeps the balance between throughput and fairness very high. It also provides better SIC robustness and stable convergence to verify that it is resilient to CSI imperfections. In conclusion, the implementation of APSO-DPA in 5G and next-generation wireless communications is highly suitable as it provides a scalable, efficient, and robust power allocation approach.

1 July 2025 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
FOFabian Chukwudi Ogenyi
Fabian Chukwudi Ogenyi
DMDahiru Buhari Mohammed
Dahiru Buhari Mohammed
Bashir Olaniyi SadiqBashir Olaniyi Sadiq
Bashir Olaniyi Sadiq
EEEnerst Edozie
Enerst Edozie
KUKelechi John Ukagwu
Kelechi John Ukagwu

5 November 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
EEEnerst Edozie
Enerst Edozie
ASAliyu Nuhu Shuaibu
Aliyu Nuhu Shuaibu
UJUkagwu Kelechi John
Ukagwu Kelechi John
BSBashir Olaniyi Sadiq
Bashir Olaniyi Sadiq
This study explores the deployment of YOLOv8s for detecting anomalies in fiber optic cables mounted on poles, with a focus on climbing activities and environmental impediments. To address the lack of climbing-related annotations in current datasets, a custom dataset was generated, covering a variety of scenarios to enhance model adaptability. During training, various augmentation approaches were used, which greatly enhanced model performance and reduced overfitting. The proposed model was trained and tested over many epochs, with detection performance progressively improving: mAP@0.5 increased from 78.9% at 20 epochs to 87.5% at 50 epochs and 97.3% at 100 epochs, after which further increases plateaued. In comparison, the trained YOLOv8s-modified model outperformed the other models on all key metrics. It achieved a mAP@50 of 97.3% and a mAP@50:95 of 71.5%, outperforming YOLOv8-original at 89.6% and 59.0%, respectively. Additionally, it achieved higher precision (96.9%) and recall (86.6%), demonstrating superior detection accuracy, dependability, and robustness in detecting complex anomalies. These improvements due to model backbone optimizations and the usage of a well-balanced, scenario-rich dataset. This study shows that YOLOv8s is a highly accurate and efficient method for detecting anomalies in fiber optic infrastructure, making it appropriate for real-time deployment in operational field environments.

29 September 2026 in F1000Research
Verified
Journal Article
Open access
PDF file
PAPaul Akampurira
Paul Akampurira
EEEnerst Edozie
Enerst Edozie
Bashir Olaniyi SadiqBashir Olaniyi Sadiq
Bashir Olaniyi Sadiq
MBMohammed Dahiru Buhari
Mohammed Dahiru Buhari
As cyber threats evolve, traditional rule-based systems struggle to detect complex and dynamic malicious behaviors, and the vulnerability of organizations to insider threats has drastically increased. Individuals entrusted with access or knowledge of the organization have become a significant concern. This review explores deep learning-based User Behavior Analytics and the integration of context-aware deep learning models for insider threat detection. Also, we investigate the use of hybrid models, including attention-based Long Short-Term Memory (LSTM) networks, which combine sequential modeling with attention mechanisms to enhance context-awareness and improve threat detection and proactive risk management. Furthermore, this paper highlights proactive risk management and dynamic interventions grounded on personalized risk profiling and user micro-segmentation. We further explore studies that give a deeper understanding of how these deep machine learning models align with ISO/IEC 27001:2022 standards, and how they can be integrated into existing frameworks to bolster proactive risk management efforts. By delivering insights into the future of AI-driven cybersecurity, this paper highlights the need to adapt to evolving threats and bolster the resilience of digital infrastructures through intelligent and adaptive security solutions.