Ayei Ibor

Dr. Ayei Ibor

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
18 April 2023 in Journal of the Nigerian Society of Physical Sciences
Verified
Journal Article
Open access
PDF file
AIAyei Ibor
Ayei Ibor
EEE. B. Edim
E. B. Edim
AOArnold Ojugo
Arnold Ojugo
This paper focuses on highlighting the problems that are associated with the absence of privacy and security of medical records in a healthcare system. It seeks to bridge the gap between the currently used security protocols in the management of health information, and encryption algorithms that should be used. Extant health information systems have always been developed with conventional databases. With all the privileges to read, write and execute assigned to the administrator, who has centralised control over all medical records, there is the likelihood of the misuse, distortion and loss of such records in the event that the administrator becomes compromised or inadvertent system failure. To solve this problem, the use of decentralised and distributed databases becomes paramount. Blockchain technology has recently received much attention due to its ability to permit a peer-to-peer network with distributed databases that can be stored locally on each node in the network. Subsequently, all updates on records in a database are communicated to all participating parties, hence addressing the problem of centralised control. In this paper, we propose a health information system on a blockchain to create a trust-free system for both health personnel and patients. From the results obtained, we achieved the decentralisation of the medical records’ database to enhance the security and privacy of data on the modeled peer-to-peer network.

15 August 2022 in Journal of the Nigerian Society of Physical Sciences
Verified
Journal Article
Open access
PDF file
CUChinedu L. Udeze
Chinedu L. Udeze
IEIdongesit E. Eteng
Idongesit E. Eteng
AIAyei Ibor
Ayei Ibor
The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets such that a weak model with 99% accuracy and faulty predictions may still be assessed as high-performing. To build optimal models, four techniques were used in this research to sample the datasets including the baseline train test split method, the class weighted hyperparameter approach, and the undersampling and oversampling techniques. Three machine learning algorithms were implemented for the development of the models including the Random Forest, XGBoost and TensorFlow Deep Neural Network (DNN). Our observation is that the DNN is more effcient than the other 2 algorithms in modelling the under-sampled dataset while overall, the three algorithms had a better performance in the oversampling technique than in the undersampling technique. However, the Random Forest performed better than the other algorithms in the baseline approach. After comparing our results with some existing state-of-the-art works, we achieved an improved performance using real-world datasets.

1 April 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
RYRume Elizabeth Yoro
Rume Elizabeth Yoro
FOFidelis ObukohwoAghware
Fidelis ObukohwoAghware
MAMaureen Ifeanyi Akazue
Maureen Ifeanyi Akazue
AIAyei Ibor
Ayei Ibor
Arnold Adimabua OjugoArnold Adimabua Ojugo
Arnold Adimabua Ojugo
Access ease, mobility, portability, and improved speed have continued to ease the adoption of computing devices; while, consequently proliferating phishing attacks. These, in turn, have created mixed feelings in increased adoption and nosedived users’ trust level of devices. The study recruited 480-students, who were exposed to socially-engineered attack directives. Attacks were designed to retrieve personal data and entice participants to access compromised links. We sought to determine the risks of cybercrimes among the undergraduates in selected Nigerian universities, observe students’ responses and explore their attitudes before/after each attack. Participants were primed to remain vigilant to all forms of scams as we sought to investigate attacks’ influence on gender, students’ status, and age to perceived safety on susceptibility to phishing. Results show that contrary to public beliefs, age, status, and gender were not among the factors associated with scam susceptibility and vulnerability rates of the participants. However, the study reports decreased user trust levels in the adoption of these new, mobile computing devices.

17 June 2020 in Cybersecurity
Verified
Journal Article
Open access
PDF file
AIAyei Ibor
Ayei Ibor
FOFlorence A. Oladeji
Florence A. Oladeji
OOOlusoji B. Okunoye
Olusoji B. Okunoye
OEObeten O. Ekabua
Obeten O. Ekabua
The state of the cyberspace portends uncertainty for the future Internet and its accelerated number of users. New paradigms add more concerns with big data collected through device sensors divulging large amounts of information, which can be used for targeted attacks. Though a plethora of extant approaches, models and algorithms have provided the basis for cyberattack predictions, there is the need to consider new models and algorithms, which are based on data representations other than task-specific techniques. Deep learning, which is underpinned by representation learning, has found widespread relevance in computer vision, speech recognition, natural language processing, audio recognition, and drug design. However, its non-linear information processing architecture can be adapted towards learning the different data representations of network traffic to classify benign and malicious network packets. In this paper, we model cyberattack prediction as a classification problem. Furthermore, the deep learning architecture was co-opted into a new model using rectified linear units (ReLU) as the activation function in the hidden layers of a deep feed forward neural network. Our approach achieves a greedy layer-by-layer learning process that best represents the features useful for predicting cyberattacks in a dataset of benign and malign traffic. The underlying algorithm of the model also performs feature selection, dimensionality reduction, and clustering at the initial stage, to generate a set of input vectors called hyper-features. The model is evaluated using CICIDS2017 and UNSW_NB15 datasets on a Python environment test bed. Results obtained from experimentation show that our model demonstrates superior performance over similar models.

3 January 2022 in Journal of Information Security and Applications
Verified
Journal Article
Closed access
AIAyei Ibor
Ayei Ibor
OOOlusoji B. Okunoye
Olusoji B. Okunoye
FOFlorence A. Oladeji
Florence A. Oladeji
KAKhadeejah A. Abdulsalam
Khadeejah A. Abdulsalam

1 December 2024 in Journal of Future Artificial Intelligence and Technologies
Verified
Journal Article
Open access
PDF file
COChristopher Chukwufunaya Odiakaose
Christopher Chukwufunaya Odiakaose
FAFidelis Obukohwo Aghware
Fidelis Obukohwo Aghware
MOMargaret Dumebi Okpor
Margaret Dumebi Okpor
AEAndrew Okonji Eboka
Andrew Okonji Eboka
ABAmaka Patience Binitie
Amaka Patience Binitie
TATabitha Chukwudi Aghaunor
Tabitha Chukwudi Aghaunor
High blood pressure (or hypertension) is a causative disorder to a plethora of other ailments – as it succinctly masks other ailments, making them difficult to diagnose and manage with a targeted treatment plan effectively. While some patients living with elevated high blood pressure can effectively manage their condition via adjusted lifestyle and monitoring with follow-up treatments, Others in self-denial leads to unreported instances, mishandled cases, and in now rampant cases – result in death. Even with the usage of machine learning schemes in medicine, two (2) significant issues abound, namely: (a) utilization of dataset in the construction of the model, which often yields non-perfect scores, and (b) the exploration of complex deep learning models have yielded improved accuracy, which often requires large dataset. To curb these issues, our study explores the tree-based stacking ensemble with Decision tree, Adaptive Boosting, and Random Forest (base learners) while we explore the XGBoost as a meta-learner. With the Kaggle dataset as retrieved, our stacking ensemble yields a prediction accuracy of 1.00 and an F1-score of 1.00 that effectively correctly classified all instances of the test dataset.