Ife Journal of Information and Communication Technology

The Development of Sign Language Converter

2025-08-21T19:03:52+00:00

This paper presents the development of a wearable glove that converts sign languages based on hand gesture protocol to text and speech. Sign language, a human communication protocol of speech impaired people, can also leverage on the convergence of computers and communication technology to expand the use of the language and ensure more integration and inclusion of speech impaired people into the main stream of socio-economic life. Existing works majorly proffer solutions based on image processing, however, this work presents the integration of flex sensors, accelerometer, Bluetooth connectivity and an android application to achieve smart glove prototype which basically converts hand gestures to speech and text in order to promote seamless sign language representation and translation. The device was tested and representation of 5 separate phrases was achieved. Hence, it proved to be a concept that can be realized and improved with increased build complexity.

In-depth Insights into Utilization of Microsoft Excel Matrix Functions Technique for Adsorption Equilibrium Models

2025-08-21T19:10:45+00:00

Adsorption equilibrium models are commonly utilised to analyse the mechanism of adsorption characteristics in a set system and establish the mass-transfer saturation mechanisms. Previous studies were mainly focused on the description and utilization of the adsorption equilibrium models, evaluation of the appropriate quality, estimation of the model’s parameters and practical application of adsorption process in the environmental pollution control systems such as water and wastewater treatment. However, insights into utilization of Microsoft Excel Matrix Functions Technique for adsorption equilibrium models and their mathematical relations were rarely revealed in the literature. This paper provided step by step techniques required in the utilization of Microsoft Excel Matrix Functions in the determination of adsorption equilibrium parameters. Adsorption equilibrium data were obtained from our previous and published articles. Unknown engineering design parameters in the commonly utilized 2-parameters adsorption equilibrium models were determined using matrix functions and Microsoft Excel Solver in Microsoft Excel. Efficacies of these techniques were evaluated statistically using Analysis of Variance, Coefficient of Determination (CD) and correlation coefficient (R). and compared with experimental adsorption equilibrium. The study revealed that there was no significant difference between the adsorption capacities obtained using the two techniques at a 95 % confidence level. It was concluded that the CD and R between experimental adsorption equilibria, Microsoft Excel Solver and matrix simulated adsorption equilibria were between 0.6916 and 0.9535; 0.0492 and 0.9535; and 0.8318 and 0.9765, and 0.2218 and 0.9765, respectively. The paper established that matrix functions and Microsoft Excel Solver in Microsoft Excel are essential tools in the determination of engineering parameters in adsorption process.

Secure Text embedding using hybrid encryption algorithms

2025-08-21T19:19:26+00:00

Data and information Security in this modern world of digital communication are dominant looking at the rapid growing priory and dependency for interchanging confidential information across data networks. This paper emphasized to look into this and come up with an enhancement of image Steganoraphy approach known as Most Significant Bit (MSB) using Secure Text embedding (STE). This research comprises of advance encryption System and Blow-fish algorithm to protect cover image and embed encryption Keys within Stego-image as Key images to improves the security of encrypted data by applying a robust pixel random function. In this respect a greater complexity is introduced without impacting the execution time significantly. The results of experiment indicate that this method’s security is far better compared to other steganographic techniques, good distortion measurement computed having Mean Square error of 0.00043 and Peak Signal to noise ratio of 90.27 values guaranteeing excellent quality of image, very short Run time of 0.52ms for encryption and 0.90ms for decryption, which is correlated to security. Additional evaluations indicate the robustness of the proposed method making it the right solution for protected information concealment in digital images.

Design and Implementation of a PLC- Based Disinfecting Doorway

2025-08-21T19:24:58+00:00

Extensive scientific research has demonstrated that the maintenance of proper hygiene plays a crucial role in the prevention of diseases. In particular, the process of disinfection has become increasingly important in the context of highly transmissible and contagious illnesses. The task of disinfecting an individual’s entire body and personal belongings can be labor-intensive and exhausting. To address this challenge, an automated disinfection model based on a Programmable Logic Controller (PLC) has been developed and implemented, enhancing the efficiency and ease of full-body disinfection compared to traditional manual methods. This model has been installed at the entrance of the Robotics and Automation Laboratory within the Mechatronics Engineering building at the Federal University of Agriculture, Abeokuta (FUNAAB). It operates by spraying a disinfectant solution, stored in a tank, through an array of misting nozzles directed at detected objects for a duration of five seconds. The system utilizes a Relay type PLC, programmed with GX Developer software, which activates upon receiving a signal from a mounted photoelectric sensor that detects an individual approaching the entrance. This triggers the diaphragm pump to dispense the disinfectant from a 5-liter storage tank through a hose to the overhead misting nozzle array for the predetermined time. This disinfection model minimizes the need for human involvement, streamlining the disinfection process while ensuring the appropriate quantity of disinfectant is applied.

A Hybrid Learning-based Model for Predicting Diabetes using Tabular Network

2025-08-21T19:27:52+00:00

Diabetes mellitus, a metabolic disorder characterized by hyperglycemia, poses a significant global health burden. Early and accurate diagnosis of diabetes subtypes is crucial for effective management and prevention of complications. This research addresses the challenge of multi-class diabetes type prediction using a local dataset. A deep learning approach, specifically Tabular Network, is employed to classify patients into different diabetes types. Tabular Network unique sequential attention mechanism dynamically selects relevant features at each decision step, enhancing model performance. Experimental results demonstrated the superiority of Tabular Network over other machine learning algorithms like Artificial Neural Network (ANN), Boosting and logistic regression. This research contributes to the advancement of diabetes diagnosis and offers a promising tool for healthcare professionals to make informed clinical decisions.

An Enhanced Application of Microsoft Excel Matrix Functions Technique for Adsorption Kinetics Models

2025-08-21T19:36:58+00:00

Adsorption kinetics and equilibrium models are generally utilised to analyse the mechanism of adsorption characteristics in a set system and establish the mass-transfer saturation mechanisms. Previous studies were mainly focused on the description and utilization of the adsorption equilibrium models, evaluation of the appropriate quality, estimation of the model’s parameters and practical application of adsorption process in the environmental pollution control such as water and wastewater treatment. However, insights into utilization of Microsoft Excel Matrix Functions Technique for Adsorption kinetics Models and their mathematical relations were rarely revealed in the literature. This paper provided step by step techniques required in the utilization of Microsoft Excel Matrix Functions in determination of adsorption kinetics parameters. Adsorption kinetics data were obtained from our previous and published articles. Unknown engineering design parameters in the commonly utilized adsorption kinetics models were determined using matrix functions and Microsoft Excel Solver in Microsoft Excel. Efficacies of these techniques were evaluated statistically using Analysis of Variance, Coefficient of Determination (CD) and correlation coefficient (R). and compared with experimental adsorption kinetics. The study revealed that adsorption treatment time and initial concentration of the pollutants are significant factors that influence adsorption kinetics at a 95 % confidence level (F11, 33= 2.478; p = 0.022 and F3,33 = 65.997, p = 4. 96 x 10-14, which less than 0.05). It was concluded that the CD and R between experimental adsorption kinetics and simulated adsorption kinetics were 0.7692 and 0.8770, and 0.7975 and 0.8930 for Microsoft Excel solver and matrix techniques, respectively and Microsoft Excel are essential tools in the determination of engineering parameters in adsorption kinetics.

Interactive Learning on the Go: Managing Student-Centered Programming Education through Mobile Applications

2025-08-21T19:39:46+00:00

This study addresses the limitations of traditional programming education by developing a mobile application designed for undergraduate students learning programming languages. Conventional teaching methods often fail to engage students and meet the diverse learning needs of novice programmers. The project aims to create a mobile application that integrates interactive coding exercises, real-time feedback, video tutorials, and collaborative tools to improve engagement and learning outcomes. The research focuses on designing an educational technology application that offers personalized, interactive, and accessible learning experiences. A structured methodology was employed, including an extensive literature review, requirement analysis, and the development of the mobile application using Android Studio, Flutter, and Firebase. The application was tested for usability, engagement, and effectiveness through pilot studies and user feedback. The results demonstrate a significant improvement in student engagement, reduced learning difficulties, and better comprehension of programming concepts through real-time feedback and interactive modules. The flexible design of the application allows for updates and customization, making it adaptable to different educational settings and programming languages. This study contributes to educational technology by providing a practical solution to challenges in programming education. The mobile application offers a holistic approach to learning, integrating interactive features and personalized learning paths to enhance the overall student experience. The findings emphasize the potential of mobile learning in improving educational outcomes, particularly in fostering engagement and addressing the needs of diverse learners.

Data-Driven Lifestyle Therapy Model for Hypertension Management: A Comparative Analysis of Algorithms

2025-08-21T19:44:01+00:00

Primary hypertension in young adults in Nigeria is a significant health concern, with many having risk indicators well in advance of the disease's negative consequences. Preventive care is essential for mitigating the early start of the disease, rather than relying on pharmacological therapy. Lifestyle therapy, a preventative intervention, addresses related risk factors to treat, reverse, and avert chronic conditions like hypertension. This research examined risk factors, developed a predictive model for hypertension classification, and provided lifestyle advice based on these characteristics. The model was developed using three machine learning algorithms: extreme gradient (XG) boost, random forest, and support vector machine learning. Data from 303 individuals at the General Out-patient Department of General Hospital, Kubwa, FCT-Abuja was used to train and evaluate the model's performance. The results showed an accuracy of 93.4%, 92.6%, and 91.8% for the random forest, XG boost, and SVM models, respectively. The performance of the developed system showed that 294 participants (93.7%) out of the 303 participant data tested were accurately classified and given appropriate lifestyle therapy recommendations. The model performance indicates that a thorough analysis of risk variables associated with hypertension can yield effective lifestyle therapy suggestions for illness prevention and early management.

Design of a Hybrid Architecture for P2P Network

2025-08-21T19:46:41+00:00

Free rider detection plays a very important role in the stability of a P2P network. Free riders tend to utilize the benefits from the network by downloading files from it without giving back to the network. This has adverse effect on the quality and lifetime of the whole network. Various approaches have been developed for mitigating free-riding; most of them are suffering from some limitations with regard to having correctly represented behavior at the peers and preventing the distribution of fake or duplicate files. To overcome these shortcomings, this work proposes a dynamically assigned grace period and a content scanning mechanism to prevent free riders and stop peers from uploading repeated and fake files in the network. Prototype of the syste wasimplemented with C# programming language and tested on a simulated network. The result showed that the system achieved a free rider detection rate of up to 60%, a duplicate file detection rate of 66%, and a fake file detection rate of 33% at a network size of 2000 peers. These results reflect the efficiency of the hybrid architecture in solving significant questions of free riding and authenticity of content for the more stable and secure development of the P2P environment.

Analysis and Design of a Mobile Technology Solution for Emergency Management: The Case of The Button in Nigeria

2025-08-21T19:54:33+00:00

One critical nationwide problem is the life-threatening delay in response to emergency situations by emergency services. This delay may be attributed to either the inefficiencies inherent in the emergency services or to a general apathy among Nigerians towards seeking assistance from these services. This paper aims to address this problem through the utilization of mobile technology. The paper develops a platform that enables users to instantly and effectively alert kin who are most likely to provide assistance during an emergency. This would minimize the delay in response to emergency situations, which is the objective of this research. To achieve this objective, surveys were conducted to gather relevant information, and the system was designed using Unified Modeling Language (UML) tools and a User Interface Mockup. The designed system was then implemented into an Android-based mobile application called “The Button.” “The Button” is user-friendly and intuitive. It enables users to instantly call for help from pre-specified emergency contacts with the click of a button. “The Button” has been rigorously tested to demonstrate and confirm its ability to perform its functions as required. With the availability of such a platform to the general populace, reliable help can now be quickly summoned, and emergencies can be effectively managed — ultimately contributing to a safer Nigeria for all.

Utilization of Microsoft Excel Matrix Functions Technique for Adsorption Equilibrium Models of Arsenic unto Powdered Eggshells

2025-08-21T20:48:43+00:00

This paper utilized Microsoft Excel Matrix Functions in determination of adsorption equilibrium parameters. Adsorption equilibrium data were obtained from our previous and published articles. Unknown engineering design parameters in the frequently utilized 2-parameters adsorption equilibrium models were determined utilising matrix functions and Microsoft Excel Solver in Microsoft Excel. Efficacies of these techniques were evaluated statistically utilising Analysis of Variance, Coefficient of Determination (CD) and correlation coefficient (R). and compared with experimental adsorption equilibrium. The study revealed that there was no significant difference between the adsorption capacities obtained utilising the two techniques at a 95 % confidence level. It was concluded that the CD and R between linear experimental adsorption equilibria, linear Microsoft Excel Solver and matrix simulated adsorption equilibria were between 0.6916 and 0.9535; 0.0492 and 0.9535; and 0.8318 and 0.9765, and 0.2218 and 0.9765, respectively. The paper established that matrix functions and Microsoft Excel Solver in Microsoft Excel are essential tools in the determination of engineering parameters in the adsorption process.

Enhance Support Vector Machine Models for Cassava Leaf Disease Variants Identification and Classification

2025-08-21T20:51:19+00:00

Cassava is one of the two main staple crops grown and consumed in large quantities in Nigeria's humid, sub-humid, and semi-arid regions, especially in the Southwest. Despite its usefulness and benefits to mankind, cassava is susceptible to various diseases such as “cassava mosaic disease (CMD)”, “cassava green mottle disease (CGMD)”, “cassava bacterial blight disease (CBBD)”, and “cassava brown streak disease (CBSD)”. It is very tedious and inaccurate to identify cassava disease on its plant leaf physically and even farmers in Nigeria lack good knowledge of identifying these diseases physically. However, failure to detect the disease on the plant early can affect both the quality and quantity of the product. Though, many researchers have developed different classification models based on machine learning techniques, however, many of these models are easily influenced by imbalanced datasets, the selection of irrelevant features, inappropriate selection of training and testing datasets, and fine-tuning of the hyperparameters in the classifier. This study mitigates the aforementioned problems by using equal number of datasets for the diseased dataset, 10-fold-approach was used to split the dataset into training and testing datasets, and two optimization techniques (i.e., Binary Particle Swarm Optimization (BPSO) and Reptile Search Algorithm (RSA) were separately used and also combine to fine-tune hyperparameters in the SVM and select more discriminating features to avoid overfitting. The images of the cassava leaves were obtained from the Kaggle village datasets, scaled down and converted to grayscale pictures. Images were further enhanced and sharpened using bi-histogram equalization and morphological filtering before noise was removed using adaptive median filtering. The Sobel edge detection method was used to separate the lesion from the uninfected parts of the leaves. The colour moment methods and gray-level spatial dependence matrix with the haralicstatistical feature were used to extract colour and texture features, respectively. Three classification models (i.e., BPSO-SVM, RSA-SVM, and BPSO-RSA-SVM) were developed, trained and tested with the datasets. The results show that BPSO-RSA-SVM outperforms both BPSO-SVM and RSA-SVM models in terms of all the performance evaluation metrics. Extensive experimental results show that the proposed models can extract robust features from superfluous features extracted from datasets and accurately classify cassava leaf disease. However, this study only identified three diseases affecting cassava, and no preventative measures were proposed.

Implementation of an Automated Drainage Cleaning System using IoT

2025-08-21T20:54:10+00:00

The drainage system in urban centers frequently encounter blockages caused by the accumulation of waste, which can result in flooding and pose significant health hazards. Conventional cleaning techniques tend to be both inefficient and labor-intensive. This initiative presents an automated drainage cleaning system based on Internet of Things (IoT) technology, which employs sensors to detect water presence and waste levels within the filter basket, subsequently issuing alerts for waste disposal. Upon identifying blockages, the system engages automated cleaning mechanisms, including a DC motor and metal jaws. Furthermore, the system is integrated with an IoT platform, facilitating remote monitoring and control via a web or mobile application. Maintenance personnel receive notifications when the waste basket reaches capacity, allowing for prompt intervention. This innovative solution minimizes manual labor, mitigates flooding risks, and enhances the efficiency of drainage maintenance, thereby providing a scalable strategy for improving urban infrastructure.

A Hybrid Machine Learning Model for Detecting Anomalies and Cyberattacks in IoT Networks

2025-08-21T20:57:56+00:00

The rapid expansion of IoT networks has increased their vulnerability to cyberattacks. Their complexity challenges traditional security methods, highlighting the need for advanced detection mechanisms. This study proposes a hybrid machine learning framework for anomaly and attack detection in IoT-enabled smart grids. We evaluate three algorithms—Random Forest (RF), k-Nearest Neighbours (KNN), and Logistic Regression (LR)—using the Canadian Institute for Cybersecurity (CIC) dataset, which includes benign traffic and various cyberattacks (e.g., DDoS, DoS, Mirai). RF was selected for deployment due to its superior accuracy and real-time detection efficiency. To enhance performance, digital twin technology was used for real-time attack simulation, and federated learning enabled decentralized, privacy-preserving anomaly detection. The model was deployed in a Streamlit-based web application for real-time monitoring and alerting. This research bridges the gap between theoretical advancements and practical security solutions for IoT networks

Development of an Intelligent Student Advisory Chat System

2025-08-21T21:03:47+00:00

Development of a Student Advisory (STAD) system, which is able to provide responses to students on questions that they would usually ask their academic advisers, is the research presented in this paper. A knowledge base was built into the system using Dialogflow - Google's Natural Language Understanding module, which allowed the system to be trained as an agent using phrases or sentences that students are likely to use when communicating with advisors for each context or category of conversation referred to as intent. Information used to build the knowledge base and train the system was gathered from online and offline sources, including the student handbook, students, advisors, and a questionnaire. The information was organized and categorized to determine different intents and possible parameters. Conversation design was carried out to simplify the process and make the system somewhat interactive and conversational using the gathered information. The system was implemented using the Python Django framework and was evaluated using alpha-beta testing. A student advisory system was developed in the form of a chatbot,which is easily accessible, accepting phrases or sentences. It provides most of the necessary information students need to have successful academic sessions on the campus, as though they were communicating with an active advisor.

Vdetekt: Synchronous Vulnerability Detection Plugin for Android Studio, a Step Towards a Secure Development Environment

2025-08-21T21:10:15+00:00

As mobile app development becomes increasingly reliant on open source and third-party libraries, the risk of introducing security vulnerabilities during development becomes a major concern, most especially in the Android Studio environment. While automated tools can help reduce these vulnerabilities, they often lack real-time detection capabilities, are not user-friendly, and fail to integrate into the developer’s workflows seamlessly. This paper presents a synchronous vulnerability detection system for Android Studio that enables real-time code analysis and security checks within the development environment. The plugin was implemented using Kotlin, IntelliJ Plugin Devkit, and Android Studio. The empirical evaluation shows a 100% success rate in detecting SQL injection, a 90% success rate for identifying hardcoded secrets, and a 72% detection rate for insecure data storage. This study contributes a practical and lightweight plugin that significantly enhances the overall security for Kotlin-based Android app development, reinforcing the need for early-stage vulnerability detection in the mobile application development lifecycle.

Optimizing E-Library Engagement with Hybrid Recommender System

2025-08-21T21:19:53+00:00

With growing reliance on digital libraries, personalized recommendation systems have become essential for enhancing user experience and resource accessibility. This study presents a hybrid recommender model designed to optimize e-library engagement among university students by providing tailored book suggestions based on user preferences and activity patterns. The model integrates Cosine Similarity and Term Frequency-Inverse Document Frequency (TF-IDF) to enhance the accuracy and relevance of recommendations. The system was developed using Python with Django framework for backend and JavaScript with the React framework for the frontend interface. To assess its effectiveness, a structured questionnaire was distributed via Google Forms to 120 randomly selected students, evaluating key performance indicators such as recommendation accuracy, usability, and overall user satisfaction. Experimental results indicate that the model achieved a 95% accuracy rate in recommendations, with participants expressing high satisfaction regarding its precision and ease of use. These findings underscore the significance of hybrid recommender systems in advancing e-library accessibility, promoting user engagement, and facilitating seamless knowledge discovery.

VLSI Design and Physical Layout of a Decade Counter Digital IC Using an Open-Source CAD Tool

2025-10-22T13:56:14+00:00

Integrated circuits (ICs) are the foundation of modern electronics, and developing the capability to design and implement ICs is crucial for technological advancement and security. This paper presents the full-custom design, simulation,
and physical layout of a decade counter (divide-by-10 counter) using an open-source VLSI CAD tool within the context of a
resource-constrained educational system. The decade counter is implemented with a CMOS logic architecture and targeted for
fabrication in the ON Semiconductor C5 0.5 µm CMOS process via the MOSIS service. The design flow spans initial specification
and behavioral modeling through circuit schematic, layout design, and final verification. The open-source Electric VLSI CAD system
is used for all design steps, including schematic capture, layout editing, design rule checking (DRC), and layout-versus-schematic
(LVS) verification. SPICE simulations (using Electric’s built-in LTspice engine) are performed at both the schematic and post-
layout levels to validate functionality and performance. The finalized layout (GDSII) was generated for mask fabrication, and
the design passes all DRC and LVS checks. Key results show that the counter meets its target specifications: it correctly cycles
through 10 states (0–9) with a measured propagation delay of 63 ns (vs. 60 ns target) and power dissipation of 16 µW (vs. 15 µW target) at 5 V supply. The core layout occupies approximately 1.5 mm × 3.2 mm, within the allotted area budget.
This work demonstrates a successful proof-of-concept IC design using affordable, open-source tools and discusses the
methodology, verification techniques, and iterative optimizations employed. It serves as a case study in building local VLSI design
capacity and lays a foundation for more complex chip design projects in academic and low-resource settings.

A Low-Cost EEG Sleep Monitoring System with YASA-Based Classification and LLM-Assisted Analysis

2025-12-22T08:33:32+00:00

Electroencephalography provides valuable information on sleep dynamics, but conventional polysomnography systems are still costly and difficult to access. This paper presents the design and evaluation of a low-cost, portable EEG sleep monitoring system priced under sixty dollars, using an ESP32 microcontroller, SD card, and AD8232 with MCP602 operational amplifier for additional signal filtering and amplification as the analog front-end. The device samples and records data at a frequency of 256 hertz to an SD card for offline processing, enabling reproducibility in research and educational settings. Data analysis is performed through NeuroNap, a Gradio-based interface that visualizes EEG waveforms, filtered signals, frequency spectra, and hypnograms, with downloadable graphs for each frequency band. Sleep staging is performed using the Yet Another Spindle Algorithm (YASA) toolbox, which automatically classifies five standard stages: Wake, Non-Rapid Eye Movement (NREM) Stage 1, Stage 2, Stage 3, and Rapid Eye Movement (REM). To improve usability, an integrated large language model with retrieval- augmented generation allows users to query their results and receive explanations of the recorded data and derived sleep statistics for better understanding. The system incorporates simple feedback indicators and initialization controls to support reliable operation, demonstrating feasibility for and research use. Future work will explore multichannel EEG recording, supervised machine learning approaches, extended Wi-Fi or cloud-based functionality, improved electrode stability, and automated motion artifact removal.