University of Ibadan Journals
Not a member yet
794 research outputs found
Sort by
Performance Analysis of Fuzzified Machine Learning Algorithm for Flood Risk Assessment
Get PDFPluvial flooding is a type of flood that occurs when high-force precipitation surpasses the limit of drainage framework which has become a threat to human life and the global economy, thus this study proposes a fuzzified Machine Learning (ML) applications that can be used to reduce this risk. However, less attention has been paid to the use of a fuzzy rule-based classification to appraise the performance of ML applications, based on pluvial flood Conditioning Variables (CVs) for training a classifier. This research proposes a fuzzified classifier models and a performance analysis of the five ML algorithms namely K-Nearest Neighbours (KNN), Random Forest (RF), Classification and Regression Trees (CART), Naïve Bayes (NB) and Artificial Neural Network (ANN) algorithms to detect and predict pluvial flood risk. The performance analysis was evaluated using the 10-fold cross-validation and hold-out techniques, based on accuracy, sensitivity, specificity, precision and Area Under Receiver Operating Characteristics (AUROC) metrics. The performance evaluation results for each algorithm, using hold-out techniques in respect of accuracy, sensitivity, specificity, precision, and AUROC for KNN were 95.3%, 95.3%, 92.7%, 93.8% and 92.2% respectively; for RF, 72.8%, 73.0%, 73.2%, 73.0% and 83.6% respectively; for NB, 71.0%, 77.0%, 73.7%, 84.7% and 72.7% respectively; for CART, 98.4%, 98.4%, 98.3%, 98.4% and 98.6% respectively; and for ANN, 83.6%, 84.0%, 96.9%, 74.0% and 87.9% respectively. In addition, results obtained for using 10-fold cross-validation method for KNN were 96.4%, 96.4%, 94.1%, 96.6% and 93.7% respectively; for RF, 95.2%, 95.2%, 93.7%, 94.3% and 94.6% respectively; for NB, 77.3%, 77.3%, 74.7%, 84.3% and 89.5% respectively; for CART, 95.5%, 99.5%, 99.4%, 99.5% and 97.6% respectively; and for ANN, 89.5%, 89.5%, 89.7%, 89.1% and 89.9% respectively. Thus, this study shows that the fuzzified ML application can be used in detecting and predicting pluvial floods. Consequently, CART which had the best results, when compared to the rest of the classifier models, is recommended for use by experts
Impact of Construction Productivity Factors on Wall Tiling Labour Output in Abuja and Kaduna, Nigeria
Get PDFProductivity is one of the important elements in construction planning and scheduling. However, construction industries in Nigeria are currently lacking in data with regard to productivity of the building’s construction activities especially in tiling works. The focus of the study was to use work study approach to empirically establish relationship between the influential factors and productivity in wall tiles labour output in Nigeria Construction Company. A total of 46 gang sizes of tillers for wall tiles 400mm x 300mm x 5mm, width > 300mm long side horizontal, 32 gang sizes of tillers for wall skirting 400mm x 50mm high and Riser 400mm x 150mm high were observed within Kaduna state and Abuja. Physical observations and measurement of work outputs were conducted through work study approach. The difference in mean labour outputs of two groups and multiple groups was tested using independent t-test and analysis of variance (ANOVA) respectively. The mode of employment of tradesmen observed had a significant effect on the output for wall tiling 400mm X 300mm X 5mm, plain width >300mm, tiles with long side horizontal with backing. Those on daily paid term produced more on site in their outputs. Regarding the labour output for Wall Skirting, 400mm X 50mm High, Ceramic Tile 5mm Thick, the weather condition significantly affected the output. The study recommends that stakeholders in the construction industry should consider the use of daily paid workers for wall tilting on building sites to enhance project performance
An Optimal Detection for Leukaemia Cancer Based On RNS-Metaheuristic Technique in Micro Array Dataset
Get PDFThis paper addresses the critical challenge of leukaemia cancer detection through the integration of Residue Number System (RNS) and Convolutional Neural Network (CNN) Deep Learning Framework using a Microarray dataset. Leveraging a dataset obtained from the Kaggle machine learning repository, the study employs a comprehensive image processing pipeline, encompassing grayscale conversion, data augmentation, contrast enhancement, geometry normalization, and OTSU segmentation. The subsequent stages involve feature extraction using Histogram of Gradient (HOG) and comparative feature selection through Ant Colony Optimization (ACO) and an optimized ACO+RNS approaches. Results indicates that incorporating ACO+RNS outperforms the ACO-only in terms of classification accuracy, sensitivity, specificity, precision, and F1-score. Notably, the ACO+RNS model achieves a lower error rate and reduced training time, emphasizing the efficiency of incorporating Residue Number System encoding in feature selection
FUTACOVNET: A Deep CNN Network for Detection of Corona Virus (Covid-19) using Chest X-ray Images
Get PDFIn December 2019, WHO declared COVID-19 as morbidity and mortality rates continue to soar high with a global cumulative case of 460,280,168 and cumulative mortality of 6,050,018. The standard clinical golden tool mostly used for the diagnosis of COVID-19 is the Reverse transcription polymerase chain reaction (RT-PCR). It is adjudged to be very expensive, less-sensitive, not readily available in hospitals and most significantly, requires the services of a specialized medical expert. X-ray imaging is an easily accessible tool that can be an excellent alternative tool in COVID-19 diagnosis. This paper proposed a technique to automatically predict the presence of COVID-19 pneumonia from digital chest X-ray images using deep learning. Any technological tool that can help in the effective screening of the COVID-19 infection with high level of accuracy is highly required. In this research, the use of transfer learning approach in the rapid and accurate diagnosis of COVID-19 from chest X-ray images is carried out. A new CNN architecture that is trainable optimally while maximizing the detection accuracy is developed. A database was created by combining several public databases and also by collecting images from National Hospital, Abuja. The database contains a mixture of 3616 COVID-19 and 10,192 normal chest X-ray images. The X-ray images were used to train and validate the deep ConvolutionalNeural Network (CNN) model. The trained network was then used to classify the normal and COVID-19 patients. The proposed CNN classification accuracy, precision, recall and F1-Score of the model are 96.5%, 96%, 96% and 96% respectively. The model was then compared with the state-of-the-art CNN models and it outperformed all of them. The high accuracy of this model can significantly improve the speed and accuracy of COVID-19 diagnosis in our local hospitals. This would be extremely valuable during an outbreak of pandemicrelated diseases when there are limited facilities and human resources for early diagnosis and management. 
A Review of Open-Source Fully Homomorphic Encryption Libraries: Zama.ai Concrete Compiler, Applications and Vulnerability
Get PDFFully Homomorphic Encryption (FHE) is an advanced cryptographic technique that enables computational operations to be performed on encrypted data without the need for decryption. In other words, FHE allows operations to be conducted directly on ciphertexts, producing encrypted results that, when decrypted, correspond to the output of the operations performed on the plaintext data. This revolutionary capability ensures data privacy and security throughout the entire computation process, as the data remains encrypted at all times, even during computation. FHE schemes typically involve complex mathematical operations and algorithms, often based on lattice-based cryptography or other mathematical structures, to enable secure and efficient computation on encrypted data. Substantial progress has been achieved in the realm of FHE and its application since 2015, yielding enhanced efficacy, heightened security, and augmented feasibility. This review paper discusses and reviews diverse FHE schemes/libraries, and the extent of progress attained hitherto and how the possibilities of adoption of the scheme in industry is being propagated, using research questions as a guide, we endeavor to utilize searches across various academic databases and industry repositories for peer-reviewed papers, articles, and books. While some of the examined papers suggested new techniques to improve the security of transferred data, several of the publications provided novel schemes for FHE to maximize efficiency and minimize noise. Special emphasis is placed on the open-source tools and libraries implementing FHE scheme, notably Concrete (developed using TFHE Scheme), an innovation by Zama.ai, a preeminent research establishment specializing in FHE research and development. Since writing FHE programs can be difficult, Concrete, based on LLVM, makes this process easier for developers with the ability to compile Python functions (that may include NumPy) to their FHE equivalents, to operate on encrypted data. The applications of the library are examined, encompassing accomplishments, limitations, and vulnerabilities. Conclusively, prospective avenues for advancement are underscored, deliberated upon, and illuminated
Deep Learning Algorithms for Multiple Cyberattacks Detection
Get PDFData is pervasive and accessible through the internet. The proliferation of smart devices worldwide, such as computers and mobile phones, has led to a significant increase in internet usage. Consequently, this surge has also given rise to a corresponding increase in cyberattacks, which are a prevalent issue faced by internet users. To address this problem, it is crucial to have an effective cyberattack detection mechanism in place to safeguard computer networks, systems, and data. While intrusion detection systems (IDS) play a significant role in this regard, they do have their limitations. Therefore, in this research, two deep learning algorithms, namely Multilayer Perceptrons (MLPs) and Recurrent Neural Networks (RNN), have been proposed. The NSL-KDD and CIC-IDS-2017 datasets were utilized for this project. When using the NSL-KDD dataset, the MLP algorithm achieved an accuracy of 99.44% with a false positive rate of 0.52%, whereas the RNN algorithm achieved an accuracy of 98.02% with a false positive rate of 2.21%. On the other hand, when employing the CIC-IDS-2017 dataset, the MLP algorithm achieved an accuracy of 99.98% with a false positive rate of 2.06%, while the RNN algorithm achieved an accuracy of 99.09% with a false positive rate of 39.65%. Furthermore, various metrics such as precision, recall, F1-score, error rate, and others were calculated and compared for both models. The obtained results clearly indicate that the MLP algorithm outperformed the RNN algorithm in terms of performance when applied to both datasets  
A Statistical Learning Model for Number Plate Recognition for Vehicular Security
Get PDFConventional security protocols at organizational gates that depend on human monitoring of vehicle traffic frequently fall short because of data inconsistencies and errors. This research makes use of computer vision techniques to suggest a statistical image processing system for tracking vehicle movements within businesses. It focuses specifically on the University of Ibadan in Nigeria's innovative Vehicle License Plate Recognition (VLPR) system for tracking automobiles. The Tesseract OCR engine and YOLOv5 were utilized by the system to attain 89% detection accuracy and 93% recognition accuracy. This resulted in a reliable solution that can improve security, traffic monitoring, and decision-making. The present study addresses a significant void in the Nigerian setting by providing a beneficial framework for the effective surveillance and management of vehicles
Educational Resources and Proficiency of Job Skills among Students of Government Technical Colleges, in Oyo State, Nigeria
No full textAchieving high proficiency of job skills among students of Government Technical Colleges (GTCs) might depend on the availability of appropriate educational resources. This study, therefore, investigated educational resources and proficiency of job skills among students of GTCs in Oyo State. The descriptive survey research design was adopted. Three out of the five GTCs, seven departments, three principals, 58 tutors and 331 students were randomly selected. Two research questions were formulated. Data were collected and content analysed using frequency counts, percentages and mean. The findings of the study showed that the level of proficiency of job skills among the students was high (x = 3.10). The level of educational resources for human, physicals, material and financial resources were low: x = 2.99. The study concluded that needed educational resources are crucial for high proficiency of job skills. The study recommended that there should be adequate budget appropriation for funding technical education activities
Social Class Factors and Academic Well-Being among Public Secondary School Students in Ekiti North Senatorial District, Nigeria
No full textThis study investigated the relationship between social class factors (parent education, occupation, and wealth) and academic well-being among public secondary school students in Ekiti North Senatorial District, Nigeria. A quantitative research design was employed, and a questionnaire was administered on a sample of 324 students. The average academic well-being score indicated a high level (mean=3.29). The majority of parents fell within the middle class across education, occupation and wealth. However, findings revealed no significant relationship between parental social class and student academic wellbeing. Also, the joint contribution of parent education, occupation and wealth was not significant in predicting student academic well-being (F(3,320)=0.308, p>0.05), suggesting that other factors may play a more significant role in determining academic well-being of public-school students in Ekiti North, Nigeria. The study therefore recommended that educators and school administrators should prioritize creating supportive learning environments that foster academic well-being for all students, regardless of social class background
A Web Based Chatbot for Mental Health Support
Get PDFThis study explores the development of a web-based chatbot designed to provide personalized mental health therapy, addressing the challenge of accessing timely mental health interventions. The chatbot, developed using a dataset of mental health-related FAQs, employs lemmatization, lowercasing, and duplication removal to prepare data for analysis. Utilizing neural networks, particularly LSTM architecture, the machine learning model shows a negative correlation between training epochs and loss magnitude, indicating improved performance over time. The findings reveal the chatbot's high proficiency in delivering individualized care, quick response, and relevant therapy recommendations. The study underscores the efficacy of chatbots in mental health care, enhancing resource availability and addressing societal stigma, limited resources, and geographical isolation issues. It recommends continuous updates to the chatbot’s knowledge base, therapy suggestions, and conversational skills, ensuring its relevance and effectiveness in providing personalized mental health care. This highlights the potential of advanced chatbots in revolutionizing mental health interventions and suppor