University of Ibadan Journals
Not a member yet
794 research outputs found
Sort by
Numerical Solution of First Order Delay Differential Equation Using a Newly Developed Mathematical Expression for Evaluation of Delay Term
Get PDFThis study aims to numerically solve several first-order delay differential equations (DDEs) for step numbers k = 2, 3, and 4 by employing the Extrapolated Block Backward Differentiation Formulae Method (EBBDFM). This is accomplished by using a recently developed mathematical formula to evaluate its delay term. The continuous form of each step number was used to generate discrete schemes, which were then constructed using a matrix inversion technique and a linear multistep collocation approach. Applying this suggested method yielded results demonstrating the accuracy and efficiency of the step number incorporated with an extrapolated future point, which outperformed the other existing methods at Lower Computational Processing Unit Time (LCPUT), particularly when compared to step numbers of K = 3 and 2
Comparative Analysis of Eight Different Blockchain Technology Schemes and Their Implementations
Get PDFBlockchain is a digital ledger that allows a transparent links of increasing record which are connected together with the means of cryptographic algorithms. Blockchain technology has attracted more speculations in various sectors recently, due to its ability of decentralised, robust and secure data exchange amongst various application platforms. There are important key variations between each blockchain technology scheme in regards to their architecture, scalability, interoperability, security features, consensus mechanism, and application. This difference in the block chain technology scheme has brought about the need to comparatively analyse different block chain technology schemes in order to better comprehend their strengths and weaknesses, advantages and disadvantages, scope and limitations so as to be able to access and measure suitability for efficient implementation in different case scenarios. In this study, 16 different qualities are compared amongst eight of the most popular blockchain technology. It concludes with a synopsis of these technologies and suggestions for the most widely used ones
Detection of Banks' Customers Loyalty Using Naïve Bayes and Support Vector Machine Classifiers: A Machine Learning Approach
Get PDFThis research paper presents a machine learning approach for detecting and predicting customer loyalty in the banking sector. The study utilizes Naive Bayes and Support Vector Machine (SVM) classifiers to analyze customer data, including demographic information, transaction history, and customer feedback. The dataset is divided into training and testing sets for model development and evaluation. The Naive Bayes classifier leverages the assumption of feature independence, while the SVM classifier constructs optimal hyperplanes for class separation. Performance metrics such as accuracy, precision, recall, and F1-score are used to evaluate the models. Both classifiers demonstrate high accuracy in identifying loyal customers, indicating their potential for real-world application. The study also analyzes the influence of factors like age, income level, and transaction frequency on customer loyalty through feature importance analysis. The proposed machine learning approach offers valuable insights for banks to identify and target loyal customers, enabling effective customer relationship management and improved business performance. The research underscores the importance of feature engineering and model selection in developing ccurate customer loyalty prediction models. 
A Hybrid Approach to Developing a Stroke Prediction System
Get PDFThe development of a stroke prediction system using machine learning algorithms offers a novel approach to identifying individuals at risk for stroke. By analyzing large datasets, it is possible to identify patterns and predictors of stroke that may not be apparent to human clinicians. This system has the potential to improve early detection and treatment of stroke, leading to better patient outcomes and helping to identify at-risk individuals who may benefit from preventive measures. Although single techniques have been employed to improve the accuracy and robustness of stroke prediction models, this study performs a hybrid technique using logistic regression (LR), random forest (RF), and support vector machines (SVMs) to enhance the accuracy and robustness of the proposed model. All three algorithms performed well in terms of accuracy, with random forest achieving the highest accuracy. However, LR and SVM were more efficient regarding training time and complexity. The overall conclusion was that RF is the best-performing algorithm for this particular task, but other algorithms may be more suitable for different applications. In conclusion, developing a stroke prediction system using machine learning algorithms is a promising approach for improving stroke prediction and patient outcomes. This study shows that machine learning algorithms can effectively identify individuals at risk for stroke and may have advantages over traditional risk factors. However, more research is needed to fully understand the potential of machine learning in this field and to determine the most effective algorithms and training methods. 
Botnet Attack Detection in Internet of Things Using Selected Learning Algorithms
Get PDFThe Internet of Things (IoT) refers to a network of everyday devices, such as smartphones and industrial sensors, all connected to the Internet, allowing them to communicate and share data. IoT networks comprise various devices with different functions, communication protocols, and computational capabilities. This heterogeneity complicates the development of a one-size-fits-all solution for botnet detection. Developing effective botnet detection systems for IoT environments is challenging due to the diversity of devices, each with unique characteristics and behaviors. This study focuses on creating a robust model to identify botnet attacks across various IoT devices. Using the NB-IoT-23 datasets, which include data from five distinct devices, supervised machine learning techniques, namely Logistic Regression, Linear Regression, Artificial Neural Network (ANN), K-nearest neighbours (KNN), and Bagging, were employed to identify the most accurate and efficient method. The research highlights the Bagging ensemble technique as particularly effective. The Bagging model demonstrated remarkable performance, achieving an accuracy of 99.96%, precision of 99.93%, recall of 99.98%, an F1 score of 99.96%, and a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) score of 99.96%, all within a training time of 27.59 seconds. These results suggest that the Bagging model is highly effective and very efficient, making it a strong candidate for real-world IoT botnet detection. The model's high accuracy and low computational overhead make it a viable solution for real-world applications of Botnet detection, contributing significantly to the ongoing efforts of stakeholders in securing IoT networks against botnet threats
Secondary Education and E-Learning Programme during Pandemic: Challenges and Way Forward In Nigeria
No full textOver the years, education is being acquired in the traditional way but the innovation of information and communication technology, which is widely employed in the education sector at all levels in most developed countries had made it possible for developed countries to bridge the gap that would have occurred during the pandemic period. The outbreak of Corona virus (COVID 19) pandemic has resulted into total closure of all institutions of learning all over the world, and this has led to great set back in educational sector especially secondary education in Nigeria. In order to keep students busy during lockdown and also to prevent further deterioration in the system, E-learning programme was introduced in the education system. There are several challenges observed during the pandemic such as financial constraint, epileptic power supply that hindered the achievement of qualitative education through this programme. Government should provide adequate funding among others and government intervention in the E-learning process are possible solutions and recommendations suggested in this paper. This paper therefore discusses the challenges of E-learning during Coronavirus pandemic and proffers possible solutions and recommendations
Quality Assurance Measures and Students’ Academic Performance in Public Colleges of Education in Southwest, Nigeria
No full textThe study investigated the influence of quality assurance measures on students’ academic performance in public Colleges of Education in Southwest, Nigeria. The population of the study consisted of 3 federal and 3 state including heads of quality assurance departments in the public Colleges of Education Southwest. The research adopted the survey research design and used purposive sampling technique for selecting a sample of four Public Colleges of Education from a population of six Public Colleges of Education in Southwest. Three hypotheses were formulated for the study. Two instruments tagged “Quality Assurance Measures Questionnaire” (QAMQ) and “Final Year Students’ Academic Performance Data Collection” (FYAPDC) were designed for the study. Data collected were analyzed using inferential statistics such as Pearson Product Moment Correlation and regression analysis at 0.05 level of significance. The finding showed a significant relationship between quality assurance measures and students’ academic performance. There was significant composite influence of quality assurance measures on students’ academic performance. The study also found that among the quality assurance measures, staff motivation contributed most to students’ academic performance in Public Colleges of Education in the Southwest, Nigeria. The nexus between quality assurance measures and students’ academic performance would be more pronounced if the management, staff and students of the institutions will perform and discharge their duties ethically and work towards realizing the mission and vision for the establishment of Colleges of Education. It was therefore recommended that management should constantly supervise staff and discipline any erring staff and students that work contrary to the vision, mission and ethics of the institution in the discharge of their duties
School Supervision, Inspection and Quality of Secondary Education in Ibadan North Local Government Area, Oyo State
No full textEffective school supervision and inspection have been identified as key mechanisms for improving educational outcomes. However, research specifically focusing on their influence on secondary education quality in the context of Ibadan North Local Government remains limited. This study adopted descriptive survey research design. Four hypotheses were formulated and tested at 0.05 level of significance. The population of the study comprised all the teachers’ and principals in Ibadan North Local Government Area of Oyo State, while 391 teachers and principals were sampled through multistage sampling technique A self-structured questionnaire titled “Influence of School Supervision and Inspection on Quality of Secondary Education (ISSIQS)” containing 18 items with 0.85 reliability coefficient was used for data collection. The data collected was analysed using Pearson Product Moment correlation and multiple regression at 0.05 level of significance. The study found that school supervision has positive and significant relationship with quality education (r=0.049, p= 0.033) & (r = 0.706, p = 0.000) for both teachers and principals respectively. Also, school inspection has positive and (no) significant relationship with quality secondary education (r=0.266, p=0.243) & (r=0.753, p=0.000) for both teachers and principals respectively. There was found to be a relative and joint contribution of school supervision and inspection on the quality secondary education. The study concluded that school supervision and inspection have positive and significant relationship with quality secondary education. It was therefore recommended that school supervision and inspection should be given more attention to further enhance quality of secondary education.
Technical Education, which is geared towards preparing people for technological development of a nation, is fast diminishing in terms of recognition and utilization. Consequently, there is serious reduction in production of skilled and competent personnel who drive the economy for sustainable development at craft level in Nigeria. This study therefore was carried out to examine sustaining National Development through Quality Technical Education in Nigeria. A descriptive survey research design was used. The study was conducted in the five Technical Colleges in Ondo state and purposive sampling was used in selecting 55 technical teachers. Three research questions were formulated and answered. A modified structured questionnaire called Sustaining National Development Through Quality Technical Education In Nigeria Questionnaire (SNDTQTEINQ) with a reliability coefficient of 0.82, was used to collect data for the study. The data were analyzed using descriptive statistics. The results revealed that teaching-learning facilities are grossly inadequate (x? = 1.68, SD = 1.24) most available facilities are obsolete (x? = 1.29, SD = 1.20), infrastructural materials for teaching-learning are rarely utilized (x? = 1.21, SD = 1.25), and there are acute shortage of Technical instructors (x? = 2.24, SD = 1.35; x? = 2.30, SD = 1.37), for effective training and teaching. These culminated to weakening the quality of technical education. Based on these findings, it was recommended that timely intervention is required in the area of providing adequate learning facilities, refurbishing old equipments, provision and utilization of technical infrastructures, and employment of more technical experts to all technical colleges should be given preference if the desired national sustainable development through quality technical education is to be achieved
Hybrid Encryption System with Initialization Vector for Secure Data Transmission
Get PDFA critical challenge facing various industries is how to ensure the security of sensitive data. To transmit sensitive data over insecure channels, secure key management of encryption keys and generating a well-secured ciphertext have become paramount. To address this challenge, this paper provides a Hybrid Encryption System that leverages the strengths of asymmetric and symmetric encryption in terms of key management, encryption speed, and overall usability. The initialization vector ensures the uniqueness of the ciphertext produced. During encryption, a recipient generates two RSA keys (public and private) and then proceeds to share the public key with the sender. A pseudo-random number generator (PRNG) is used to create the initialization vector (IV) that is used alongside the AES key to encrypt the data file. The AES key is then encrypted using the recipients’ public key and all these are done during one execution stage. At decryption, the recipient will receive three files namely; an encrypted data file, an encrypted AES key, and IV. The AES key is decrypted using the recipients’ private key before decrypting the data file and all these are also done at one execution stage. The Hybrid Encryption System was evaluated against the AES and RSA algorithms. According to the results obtained, the total execution time indicated that the proposed hybrid system was considerably faster than RSA while AES was faster than the proposed hybrid system. The hybrid system also provides the maximum level of data security due to the uniqueness of the ciphertext it produces
Machine Learning in Cyber Security Operations
Get PDFThe defense of computational devices as well as computer networks against information leaks, theft, and damage to their electronic data, software, hardware, or other components, as well as against interruption or misrepresenting the services they offer, is defined as cyber security by securitystudio.com. In recent years, there has been an unparalleled increase in public interest in machine learning (ML) research. People's learning and working styles are changing as the Internet and social life become more intertwined, yet this also exposes them to major security risks. Protecting confidential data, networks, and computer-connected systems against illegal cyberattacks is a difficult challenge. Effective cyber security is crucial for this. To solve this issue, recent technologies like machine learning and deep learning are combined with cyberattacks. The write-up covers machine learning technology in cyber security, explores the benefits and limitations of employing them, and offers recommendations for future research. The world of today is highly network-interconnected due to the prevalence of both small personal devices (like smartphones) and large computing devices or services (like cloud computing or online banking). As a result, millions of data bytes are generated, processed, exchanged, shared, and used every minute to produce results in specific applications. As a result, protecting user privacy, machine (device) security, and data in cyberspace has become a top priority for private citizens, corporate entities, and national governments. Machine learning (ML) has often been used in cybersecurity in recent years, including for biometric-based user authentication and intrusion or virus detection. But ML algorithms are vulnerable to intrusions during both the training and testing phases, which often lead to noticeable performance decreases and security vulnerabilities. Comparatively little studies have been conducted to ascertain the type, extent, and defense mechanisms of ML methods' vulnerabilities against security threats. Systematizing recent cybersecurity-related initiatives leveraging ML is vital to garner the interest of researchers, scientists, and engineers