Johnson Adeleke Adeyiga

Johnson Adeleke Adeyiga

Auto-generated profile, based on publicly available information

Johnson Adeleke Adeyiga

Department of Computer Science and Information Technology, Bells University of Technology, Ota, Nigeria

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 July 2025 in American Journal of Networks and Communications
Verified
Journal Article
Open access
PDF file
OOOyinkansola Olagunju
Oyinkansola Olagunju
MAMichael Adegoke
Michael Adegoke
GIGabriel Iwasokun
Gabriel Iwasokun
AAAdeleke Adeyiga
Adeleke Adeyiga
SAStephen Aderibigbe
Stephen Aderibigbe
Intrusion Detection Systems (IDS) are essential for protecting wireless networks against an increasingly complex range of cyber threats. This study evaluates and compares the effectiveness of Naïve Bayes, Weighted Naïve Bayes, and Convolutional Neural Network (CNN) using the Network Security Laboratory-Knowledge Discovery and Data Mining (NSL-KDD) dataset. The Naïve Bayes model was used as a baseline due to its simplicity and computational efficiency, delivering consistent results across multiple iterations. The Weighted Naïve Bayes model, which incorporated a feature-weighting mechanism was used to improve precision and Receiver Operating Characteristics-Area Under Curve (ROC-AUC) scores while striking a balance between performance and interpretability. These qualities make it well-suited for real-time intrusion detection in wireless environments, where both transparency and resource efficiency are crucial. The Naïve Bayes model was used as a baseline for offering a straightforward and efficient classification approach with moderate overall performance while the Weighted Naïve Bayes model was used to enhance the standard version by introducing a feature-weighting mechanism, which improved precision and reduced false positives. The CNN model outperformed the Naïve Bayes-based approaches across all evaluation metrics, underscoring its ability to learn complex patterns in network traffic. The Weighted Naïve Bayes model was also used to strike a practical balance between accuracy and efficiency, making it especially suitable for wireless networks. The CNN model was used to deliver the highest scores across all evaluation metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, reflecting its ability to learn complex patterns in the data. Experimental results demonstrated the potential of the Weighted Naïve Bayes model to support online learning and dynamic feature weighting, which is necessary for boosting adaptability to new and evolving attacks while preserving simplicity and transparency.

6 November 2023 in Environmental Health Engineering and Management
Verified
Journal Article
Closed access
DIDesmond Eseoghene Ighravwe
Desmond Eseoghene Ighravwe
AAAkpevweoghene Solomon Abijah
Akpevweoghene Solomon Abijah
DADaniel Aikhuele
Daniel Aikhuele
SASunday Thomas Ajayi
Sunday Thomas Ajayi
JAJohnson Adeleke Adeyiga
Johnson Adeleke Adeyiga
Background: Several aquaculture industries in underdeveloped nations use fossil fuel-powered generators to produce electricity. This pattern has raised greenhouse gas emissions as well as the price of aquaculture products. Methods: To address this issue, this study contains a bi-objective model that optimizes the parametric settings of waste-to-energy (WTE) plants for aquaculture firms: Levelized cost of energy and power expenses for reverse logistics. The best values for these objectives were created using a genetic algorithm and goal programming. Results: Four planning periods were taken into account during implementation, and actual data were gathered from a Nigerian aquaculture company. The electricity costs from biodiesel ranged from N0.7541 per kW to N0.7628 per kW, respectively. Reverse logistics has energy costs ranging from N6 329 492.10 to N7 121 015.53. The proposed model produced average values for several WTE parametric parameters, including a 1.69 million kg hydrogen gas, a 59.16% hydrogen gas compression efficiency, and an 83.39% electricity conversion efficiency. Furthermore, the system had logistics’ minimum and maximum fractions of 0.18% and 21%, respectively. Conclusion: Our findings demonstrated how WTE parametric parameters impact the aquaculture industry’s electrical power unit.

19 July 2025 in International Journal of Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
GIGabriel Iwasokun
Gabriel Iwasokun
OSOluwaseyi Segun
Oluwaseyi Segun
SOSamuel Ogunlana
Samuel Ogunlana
MAMichael Adegoke
Michael Adegoke
JAJohnson Adeyiga
Johnson Adeyiga
OAOjo Aderibigbe
Ojo Aderibigbe
The integration of Internet of Things (IoT) devices into modern payment systems has introduced innovative functionalities, but also significant security and performance challenges. IoT devices, such as smart sensors, wearables, and automated vending machines, are typically resource-constrained yet handle sensitive financial transactions that demand robust security mechanisms. Conventional cryptographic solutions are often unsuitable for these environments due to their high computational and memory requirements. This paper presents the design of a lightweight blockchain-based model to secure IoT payment systems by leveraging the Ethereum blockchain and AES-128 encryption. The blockchain token is encrypted with AES-128 to add layer of security before being stored in a database. The model is designed to employ a decentralised digital ledger to record and validate transactions without a central authority, and the transaction is grouped into a block and linked to the preceding block through cryptographic hashes. The chain of blocks forms an immutable record that enhances transparency and security, and the distributed nature of blockchain networks, wherein multiple participants validate each transaction, minimises the risk of fraudulent activities while ensuring consensus is achieved through predefined protocols. Analysis of results from the implementation established the minimization of computational overhead and robust security measures, and was particularly beneficial where the scalability of decentralized systems is required alongside heightened security protocols.

26 July 2026 in Science Journal of Circuits, Systems and Signal Processing
Verified
Journal Article
Open access
PDF file
GIGabriel Iwasokun
Gabriel Iwasokun
DADayo Alowolodu
Dayo Alowolodu
RARaphael Akinyede
Raphael Akinyede
BRBlossom Remi-Ofakunrin
Blossom Remi-Ofakunrin
MAMichael Adegoke
Michael Adegoke
MAMoses Achas
Moses Achas
The creation of platforms for systematic control of electric power switches based on the hands-on application of Artificial Intelligence in day-to-day life lessens the prospect of unintended switch initiation. It can enhance security by ensuring that only authorized users receive responses. Physically challenged individuals also need systems bereft of point-point contacts or interactions with electrical or power switches. Some of the known methods for achieving these objectives include smart objects, the Internet of Things, and biometric technologies, each with its strengths and weaknesses. This paper proposed a voice signal model for remote control of electrical switches. The model uses a voice recorder connected to an Arduino microcontroller to boost the audio or voice signal from the user, while a voice sensor is also linked to a power switch relay to acquire the voice signal for registration, training, verification, and processing. The Arduino microcontroller sensor runs TinyML and TensorFlow Lite environment sensors while operating at an adjustable voltage. A switch relay was required for limiting the voltage to a required level based on synergy with the Arduino microcontrollers. A Wi-Fi module was also used for launching the microcontroller and the TCP/IP connections based on Hayes-style commands. The system runs with an electromechanical device designed for the flow of electric current to open or close the electrical circuit. The user voice recognition leverages Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks to guarantee effective capturing of temporal dependencies in sequential data typical of audio signals. The implementation of the framework on specialized hardware and software has established its ability to effectively classify spoken commands as either ON or OFF independent of the speaker’s identity, based on comparison of the input features. Performance evaluation based on the confusion matrix established that a very high percentage of the input commands were correctly recognized with an accuracy of 90%.

28 July 2026 in American Journal of Networks and Communications
Verified
Journal Article
Open access
PDF file
GIGabriel Iwasokun
Gabriel Iwasokun
AOAhmed Ojodu
Ahmed Ojodu
JAJohnson Adeyiga
Johnson Adeyiga
OOOludare Olaleye
Oludare Olaleye
MOMojisola Ogunseye
Mojisola Ogunseye
DADavid Adewole
David Adewole
The existing communication networks are currently encompassed with various malicious activities that aim to compromise the confidentiality, integrity, and availability of data and systems. The activities include malware, phishing, ransomware, Distributed Denial of Service (DDoS) attacks, and insider attacks. The rapid evolution of these threats necessitates the development of advanced and adaptable intrusion detection systems (IDS) capable of operating across diverse network environments. This paper presents the design of a cross-domain network intrusion detection system that leverages a convolutional neural network and principal components analysis to enhance network intrusion detection accuracy and generalisation. The design integrates GloVe (Global Vectors for Word Representation) embeddings to transform network traffic data into a meaningful feature space, utilises Principal Component Analysis (PCA) for dimensionality reduction, and employs a one-dimensional Convolutional Neural Network (1D-CNN) for efficient classification of network activities. The design also considered preprocessing of multiple intrusion detection data from various network domains, and each data is subjected to GloVe-based feature extraction to generate dense vector representations, which are subsequently concatenated to form a unified embedding layer. The PCA component is required for mitigating the issues with dimensionality and enhancing computational efficiency. It will also be used to extract some significant features before the 1D-CNN-enabled intrusion classification. The experimental study of the system established its practical function and suitability for a very high, accurate, and reliable detection of intrusions in multi-domain networks.