University of Ibadan Journals
Not a member yet
794 research outputs found
Sort by
Enhancing Intermediate System Network Routing Mechanism for Wireless Sensor Networks through Swarm Intelligence Algorithms Techniques
Get PDFWireless Sensor Networks (WSNs) consist of nodes equipped with limited energy resources. These microsensors collect and relay data to a central node, but they often encounter challenges related to energy efficiency. This study examines WSNs' architecture, uses, and energy issues, and introduces Particle Swarm Optimization (PSO) and Firefly Optimization (FFO) to refine routing protocols. The focus is on enhancing the Intermediate System Routing Protocol (ISRP) by addressing energy use, transmission delays, and packet delivery. The method includes node placement, coverage, link stability, and optimization via PSO/FFO. Performance is assessed through metrics such as energy consumption, delay, packet delivery ratio, and network lifetime Performance is assessed through energy consumption, delay, packet delivery ratio, and network lifetime. These research shows that optimizing ISRP with PSO and FFO leads to significant improvements: energy use decreases from 0.235J to 0.14J, delay reduces by 0.5974s, packet delivery rises from 87% to 96%, and network lifespan extends from 370s to 576s. This work enhances WSN efficiency and longevity, offering insights for future studies
The Use of Wood Composites as Building Materials for Sustainable Development
Get PDFThe escalating environmental and human impact of indiscriminate wood waste disposal from the wood industry necessitates sustainable solutions. This study explores the utilization of wood cement composites as building materials to address this issue. Recycling wood waste into value-added composites offers the potential to alleviate pressure on diminishing forest resources, mitigate environmental pollution, and foster economic growth. The production of environmentally friendly wood composites for low-cost building components is investigated, emphasizing their applications in housing infrastructure, interior decoration, furniture manufacturing, and industrial needs. However, the challenge lies in the substantial binder requirement, constituting a significant portion of manufacturing costs. To address this, various binders, both organic and inorganic, have been employed, with a focus on reducing the use of formaldehyde due to its hazardous nature. This study particularly explores the incorporation of polystyrene-based resin as an alternative binder, derived from discarded polystyrene packaging materials, aiming to enhance composite properties while reducing toxic emissions. The research examines the strength and sorption properties of wood composites from specific Nigerian wood species, namely Albizia zygia and Cordia millenii, comparing conventional water-based resin and polystyrene as bonding agents. Results indicate distinctive characteristics in composites bonded with polystyrene, suggesting improved interfacial bonding and potential benefits in terms of strength and moisture resistance
Comparative Performance Evaluation of Random Forest on Web-based Attacks
Get PDFThe majority of typical online attack methods are thoroughly researched and documented. Countries,corporations, people, and vital infrastructures that depend on information technology for daily operations havesuffered financial losses, the loss of personal information, and economic harm as a result of web-based intrusion. However, foreseeing an attack before it happens can aid in its prevention. This research proposes a predictive model for web-based attacks and a performance comparison of random forest with and without feature selection to secure the availability, integrity, and secrecy of networks, computer systems, and their data. The CIC-Bell-IDS2017 dataset, which includes typical and contemporary intrusion attacks, served as the raw data source for the proposed model. A python-based programming environment and interface for Anaconda Navigator, Jupyter Notebook, was used to create the predictive models. Performance evaluation andcomparative analysis were conducted, and the results demonstrate that, once big data analytics (feature scaling and feature selection) were applied to the dataset, the models' prediction accuracies improved, creating a potential intrusion detection system. The outcome yielded excellent accuracy and model development times in both cases, with 97% and 98% precision for both sets and model development times of 35 seconds for the raw set and 15 seconds for the reduced set, which is an important factor when deploying machine learning models in a real-time setting. Random Forest is more computationally expensive than Correlation feature Selection-based classifiers, but having higher predictive accuracy, according to a comparison. Both of these methods work well and each has advantages and disadvantages. The use of big data analytics (PySpark) was found to help machine learning models perform better, resulting in better intrusion detection system. 
Crop Recommendation Analysis and Validation in Nigeria Using Machine Learning Algorithms
Get PDFCrop recommendation systems are crucial for optimizing agriculture by suggesting crops based on environmental and soil conditions. Failure in selecting suitable crops can result in low yields and resource wastage. This study builds an improved recommendation system for Nigerian farmers. Data from various sources, including the Nigeria Metrological Agency, the Agronomy Department University of Ibadan, Ahmadu Bello University Zaria, and Federal University Wukari, were preprocessed using numpy and pandas. The climate parameters used were Rainfall, Temperature and Humidity while the soil parameters were Nitrogen (N), Phosphorus (P), Potassium (K), Calcium (C) and Magnesium (Mg). The pH was used to measure the soil acidity or alkalinity. The 18 crops considered were Bambara Nut, Cassava, Cocoyam, Tomato, Yam, Acha, Cocoa, Beans, Groundnut, Beniseed, Maiza, Rice, Oil Palm, Cashew, Sugar cane, Sweet Potato, Pepper and Coconut. After preprocessing, the dataset was partitioned into training, validation, and testing sets in the ratio 80:10:10. Four Machine learning algorithms which are Random Forest, Naïve Bayes, K Nearest Neighbor, and Support Vector Machine (SVM) were employed, with Random Forest outperforming others in accuracy, precision, recall, and F1 score. Naïve Bayes ranked second, followed by K Nearest Neighbor, and Support Vector Machine performed as the poorest. The models effectively recommended crops for specific climates and soils, with SVM being the least effective. Hence, this study demonstrates the importance of accurate crop recommendations in maximizing agricultural productivity
Food Components Recognition from Still Images Using Multi-Label Learning
Get PDFFood recognition, a recent research area in image processing, helps identify food items to keep track of the food consumed, thereby maintaining a healthy diet. However, the task of food recognition is challenging due to the deformable nature of food items. Usually, there are more than one food item in a meal making the task more challenging. Therefore, the aim of this work is to develop a deep learning model to detect and enumerate visual food components present in a meal. In the multi-label learning approach, food images were collected to build a food image dataset, which comprised 2150 images. The images were pre-processed. Contrast Limited Adaptive Histogram Equalization was then applied followed by scaling to fit as input into the model for training/testing. Thereafter, Deep (VGG-16) and Dense (DenseNet50) models were used to extract deep features. The final layer of the model was applied with a multi-label technique to train on the selected features. The multi-label model was tested using appropriate metrics in which VGG-16 performed better than DenseNet50 with an accuracy of 91.90%, hamming loss of 8.10%, loss of 0.26%, precision of 73.49%. An independent test set was used on the model which showed impressive results. It was observed from this study that the proposed approach performed excellently well in predicting Nigerian Food components. It is recommended that this work be applied in real world this work in real world scenario such as dietary tracking to monitor food intake. Human-Computer Interaction with automatic purchasing systems at restaurants can be used to speed up services
Sentiment Analysis of Low-Resource Yorùbá Tweets Using Fine-Tuned Bert Models
Get PDFSentiment analysis in low-resource languages poses a notable challenge because of the scarcity of labelled data and language-specific models. This study addresses this challenge of Yorùbá sentiment analysis using fine-tuned variants of Bidirectional Encoder Representations from Transformers (BERT) model. Yorùbá, being a low-resource language, lacks effective sentiment analysis tools for detecting the sentiment polarity of content written in the language. Solving this problem is important for understanding beliefs of the public, cultural sentiment, and enhancing communication analytics in Yorùbá-speaking communities. The paper employs transfer learning techniques to adjust pretrained models to the unique linguistic properties of Yorùbá. The chosen models include Bert Base (Uncased), African Bidirectional Encoder Representations from Transformers (AfriBERTa), Multilingual version of BERT (mBERT), and multilingual version of RoBERTa (XLM-RoBERTa). AfriBERTa model demonstrates a superior performance in capturing sentiment nuances specific to Yorùbá language tweets after comparative analysis was done on the performance of the four models on two different datasets
Appraisal of Internally Generated Revenue and School Plant Development in Osun State Public Secondary Schools
No full textThis study appraised internally generated revenue and school plant development in public secondary schools in Osun State. The descriptive survey research design was adopted for the study. The population of the study comprised all teachers in public secondary schools in Osun State from where 270 teachers were selected using simple random sampling technique. A self-designed questionnaire tagged “Appraisal of Internally Generated Revenue and School Plant Development (AIGRSPD)” and a Checklist were used to collect data for the study. Four research questions were raised and answered using percentages and frequency tables. Two research hypotheses were formulated and tested using Pearson Product Moment Correlation (PPMC) at 0.05 level of significance. Findings, among others, revealed that secondary schools in Osun State generated revenue through various methods to complement government’s subvention for school plant development. It was concluded among others that government should increase the funds allocated to education sector in its budget and that secondary school administrators should be more proactive in getting revenue to supplement what government is providing through budget
Perception of Users on Indoor Air Quality of Lecture Theatres Located in the Federal University of Technology, Akure, Nigeria
Get PDFSatisfaction with odour, indoor temperature, indoor relative humidity, fresh/stuffy air and indoor air speed is widely regarded as universal way of assessing the perception of indoor air quality (IAQ). The aim of this paper was to evaluate the perception of students on the IAQ of lecture theatres within the Federal University of Technology, Akure, Nigeria towards expansion of the database of indoor environmental quality aspects of educational buildings in Nigeria. The two-stage survey was carried out using a structured questionnaire in September 2021 and February 2022. The population of the study was the undergraduate population in the University (17,772) and the sample was 377 students. Results from the rank sum analysis indicated that the prevalence of “dust” has the potential to affect indoor air quality within the research area. Additionally, Satisfaction with breakaway factors of indoor air quality for both dry and wet seasons was less than ASHRAE’s benchmark of 80% satisfaction votes for IAQ in the study area. Results of the Spearman rank correlation coefficient analysis between pollution factors and indoor air quality breakaway factors point out that there was an inverse relationship between them, although, it was only significant in the dry season. The design challenge is that architectural projects such as lecture theatres should have the capacity to satisfy the comfort of users in both the dry and wet seasons
High Level Noise Impact on Image Data of Yagi Antenna Smart TV Transmitting at 18- 24 Ghz
Get PDFNoise had been known to have great impact on the quality of service (QoS) in digital Television transmission network and in wireless communication systems during data communication. This is because noise reduces Signal to Noise ratio (SNR) in Wi-Fi and cellular networks, and in television and radio broadcasting systems. Yagi antenna had been in use on Television network and in wireless systems, because it provides focused coverage and minimize interference especially in location where signal strength is weak. The effect of high impact noise at very close range on microwave signal have not been investigated to include non-convectional sources of noise such as a high-noise source (?80 dB). The measurement of high level noise impact on digital TV transmission at microwave frequency with Yagi antenna transmission at microwave frequency up links (18 -24 GHz) and downlink (474 to 842 MHz) band was taken using Digital Transmission Television (DST) equipment, a GOTV decoder, a Yagi antenna, a high-noise source (?80 dB), a power source, a smart television monitor, and a sound meter. Twenty stations within the microwave frequency range were selected for the study. The results indicated that signal loss caused by excessive environmental noise adversely affected signal quality on the Smart TV. It was concluded that high noise level greater than 80 dB may have detrimental effect leading to decrease in signal quality (loss of picture) during evening hours and on rainy days
Fault Prediction in Power Transformer Using Ensemble Models
Get PDFOne of the highly important elements of electrical system networks is the power transformer. There is an increasing amount of research being done on early warning systems and faults detection because the failure of these elements can ground economic activities. More so, using dissolved gas analysis (DGA) as one of the mostly used conventional techniques is deficient in locating these incipient faults as this may be caused by a variety of factors which includes but not limited to imbalance problem, inadequate and overlap in the DGA datasets, thereby restricts its capacity to obtain precise diagnosis. Therefore, this paper proposed an ensemble machine learning methods for incipient faults prediction using DGA datasets comprising 166 samples and eight variables. This research compares the accuracies of four ensemble machine learning methods: Bagging, Adaboost, Stacking, and Voting methods using multilayer perceptron and support vector machines respectively. The results obtained ranges from 90.50% to 100% with the Adaboost (MLP) achieving the highest accuracy, whilst the misclassification percentage ranges from 1.62% - 18.06% with Stacking method as the least performing. In the end, our findings highlighted the importance of the use of ensemble methods and has future prospects for further advancemen