Afe Babalola University Based Journals
Not a member yet
992 research outputs found
Sort by
Predictive Modeling for Cardiovascular Disease in Patients Based on Demographic and Biometric Data
Get PDFCardiovascular disease (CVD) remains the leading global cause of death, highlighting the urgent need for accurate risk assessment and prediction tools. Machine learning (ML) has emerged as a promising approach for CVD risk prediction, offering the potential to capture complex relationships between clinical and biometric data and patient outcomes. This study explores the application of support vector machines (SVMs), ensemble learning, and artificial neural networks (NNs) for predictive modeling of CVD in patients. The study utilizes a comprehensive dataset comprising demographic and biometric data of patients, including age, gender, blood pressure, cholesterol levels, and body mass index, features. SVMs, ensemble learning, and NNs are employed to construct predictive models based on these data. The performance of each model is evaluated using metrics such as accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC). The results demonstrate that all three models achieve accuracy performance in predicting CVD events, with AUC values ranging from 0.85 to 0.92. Ensemble learning exhibits the highest overall accuracy, while SVM and ANN demonstrate strengths in specific aspects of prediction. The study concludes that Machine learning algorithms, particularly ensemble learning, hold significant promise for improving CVD risk assessment. The integration of ML-based predictive models into demographic practice can facilitate early intervention, personalized treatment strategies, and improved patient outcomes
Evaluation of Effective Interfacial Area in a Rotating Packed Bed Equipped with Dual Gas Inlets
No full textThis study investigates the effective interfacial area in a novel rotating packed bed (RPB) equipped with dual gas inlets instead of the conventional single-gas-inlet RPB. The aim is to enhance the mass transfer efficiency of gas-liquid contacting processes in RPBs by increasing the number of gas inlets to improve the spread of gas supply into the packing. The RPB is a promising gas-liquid contactor configuration known for its intensified mass transfer characteristics. However, the impact of additional gas inlets on the effective interfacial area of the packing remains unexplored. An experimental method assessed the interfacial area under varying operational conditions which include a liquid flow rate of 0.30-0.60 m3/h, a gas flow rate of 100-300 Nm3/h, and a rotation speed of 600-1000 rpm. At operating conditions covering the maximum rotation speed of 1400 rpm, gas flow and liquid flow rates of 300 Nm3/h and 0.60 m3/h respectively, the results showed that on average, 55 to 97% of the 2400m2/m3 specific packing area can be effectively utilized for gas-liquid mass transfer during separation operations using the RPB. Compared to results reported for single-gas-inlet RPBs using similar packings, the RPB with double gas inlet proved to provide higher utilization of the packing. By simply doubling the number of gas inlets, the findings provide valuable insights into optimizing RPB designs and operations which could enhance mass transfer efficiency for various chemical and environmental applications
Cost-Efficient Automated Intrusion Detection and Reporting System for Homes in Nigeria
Get PDFSubstantial investments are made to mitigate the persistent threat to lives and assets posed by various forms of intrusion. Automated security systems have emerged as crucial tools for safeguarding homes against intrusions in recent times. A major advantage of this is its independent ability to report human activities around homes without direct observation. However, the cost of implementing the system is not pocket-friendly to an average Nigerian given the prevailing economic situation. This research therefore seeks to develop and implement an intrusion detection and reporting system using low cost materials while maintaining a balance between quality and cost at the same time. The system architecture employs the passive infrared sensor (PIR) for motion detection, the ultrasonic sensor measures intruders’ location from the home entrance while the NodeMCU ESP8266 microcontroller is responsible for coordinating the reception and relaying of signals within the system. The system was implemented with varying distances of human presence from the security device. Reports of potential intrusion alerts were obtained within reasonable time frames (between 11 seconds and 49 seconds) on the homeowner’s mobile phone via the Blynk application. This performance demonstrates the reliability of the system for home security. The system is equally cost-efficient relative to most similar state-of-the art IoT based home security systems considered in this work. Our work therefore contributes to knowledge by proposing an affordable home security solution for a low budget Nigerian user.  
Prediction of Urban House Rental Prices in Lagos - Nigeria: A Machine Learning Approach
Get PDFOften, prospective tenants need to know the rental price of an apartment, and homeowners need to know how best to price their apartments. This work aims to predict house rental prices in Lagos, Nigeria, using machine learning by examining the relationship between the rental price and features such as the number of bedrooms, bathrooms, toilets, location and house status(newly built, furnished, and/or serviced). Five machine learning models were trained and evaluated using mean absolute error (MAE), root mean squared error (RMSE) and r-square (R2); the random forest regression model outperformed the other four models with the lowest MAE, RMSE and the highest R2. This study also revealed that the number of bedrooms and the apartment's location are the most significant predictors, confirmed using the feature importance analysis. The developed model can be used to estimate the rental price of a property in Lagos, Nigeria
Characterization of Anopheles Mosquitoes Larvae Breeding habitats in Selected Six Local Government Areas in Ekiti State, South-West Nigeria
Get PDFThis study explored the spatial distribution and attributes of Anopheles mosquito larvae breeding sites in six local government areas of Ekiti State, Nigeria. It employed a cross-sectional design, randomly sampling larvae habitats across three distinct locations, resulting in the assessment of a total of 18 breeding sites. The assessment of habitat characteristics and physico-chemical parameters of larvae breeding water-bodies was conducted through visual inspection and laboratory procedures, adhering to the standard protocol outlined by the World Health Organization (WHO). The objective of this study is to characteriseAnopheles mosquito larvae breeding habitats in six selected local government areas in Ekiti State using WHO protocol.. Two local governments were selected each from the three senatorial districts in the state and a survey was conducted to identify dams, rivers, swamps, marshlands, and temporary water ponds within each zone for Anopheles mosquito larvae using WHO protocols. Measurements of water temperature and pH were conducted twice in a week using a multi-parameter meter (PHB500- ww portable ph meter).Anopheles mosquito larvae were collected across the eighteen breeding sites in the selected six LGA in Ekiti using standard dipper, pasteur pipettes and scooping techniques and reared to adult in the laboratory. Most of the larvae habitats encountered were stagnant water bodies 10(56%) with the mean of 122.2 ± 41.20 followed by Tyre track 4(22%) with the mean of 129.8 ± 41.20, slowly flowing 2(11%) with the mean of 186.0 ± 16.97 and gutter 2(11%) with the mean of 170.0 ± 98.9. Types of breeding site across the six study area were all temporary sites 18(100%), more than half 13 (72%) of the habitats origin of water were natural, 11(61%) of the breeding habitats’ specific water body were stagnant water bodies. Furthermore, majority 14(78%) of the water bodies were polluted, 16(89%) were exposed to sunlight and it was also discovered that the all the breeding habitats across the six study area were around settlements (houses). Therefore physicochemical characteristics such as Temperature (r=0.896, p=0.016), pH (r=0.865, p=0.026) and Electrical conductivity (r=0.865, p=0.045) were significantly associated with larvae abundant with a strong positive correlation while the physicochemical characteristics such as DO and TDS were not significantly associated with larvae abundance
Understanding the Role of Sports and Physical Activity in Promoting Inclusion and Quality of Life for Individuals with Intellectual Disability
No full textEvery child that is born with expectation of living and fulfilling life’s expectancy. The quality of life approach focuses on what is most important to every individual. However, each child is born with different challenges and peculiarity in the area of intellectual capacity. The condition could be present at birth as a congenital abnormality. An individual may be physically fit with no brain or body abnormalities and yet be mentally disabled. The terms mild, moderate, severe and profound are often used to classify intellectual disability. In view of this, it has been observed that poor motor control, high physical demand, fear of accident and social exclusion could limit the involvement of persons with intellectual disability in activities related to sport or physical activity. Therefore, it is needful to achieve social inclusion and quality of life for persons with intellectual disability through sports and physical activity
Mondia whitei fruit extract abates cadmium chloride-induced nephrotoxicity via the suppression of oxidative stress in rats
No full textCadmium (Cd) is an industrial heavy metal that causes toxic effects to several body organs including the kidney. Medicinal plants are used in managing various diseases caused by environmental toxicants. This study aimed to evaluate the protective ability of Mondia whitei fruit extract (MWE) against nephrotoxicity induced by CdCl₂ exposure in Wistar rats. Twenty-five male Wistar rats of 90 to 130 g body weight (b.w) were used in this study. The animals were indiscriminately assigned to five groups of five animals per group. The control group were rats in group I, whereas group II to V rats were orally administered CdCl₂ (5 mg/kg body weight (b.w)) for 5 days. Simultaneously, the rats in group III to V were co-treated with 70 mg/kg b.w of silymarin, 250 and 500 mg/kg b.w of MWE, respectively. The CdCl2 significantly (p < 0.05) increased the levels of serum renal biomarkers such as urea and creatinine, total protein and albumin. Furthermore, a substantial (p < 0.05) elevation in the nitric oxide (NO) and malondialdehyde (MDA) levels, and a concomitant (p < 0.05) reduction in the kidney activities of superoxide dismutase (SOD) and glutathione transferase (GST), and the level of reduced glutathione (GSH) were observed in the CdCl2-intoxicated rats. Alterations in the kidney's histology were also noted. Nonetheless, treatment with MWE markedly returned to normal the levels of serum kidney parameters and tissue NO and MDA. In addition, the MWE significantly (p < 0.05) elevated tissue antioxidant levels and restored the kidney histology. The result of this study suggest that MWE could potentially serve as an alternative therapy in managing CdCl2-induced nephrotoxicity
Recent Advances on the Adsorption of Pollutants from Aqueous Media Using Clay-Based Adsorbents
Get PDFThe sequestration of pollutants from wastewater remains an active research topic recently owing to persistent disposal of industrial wastewater to waterbodies without adequate management strategies available especially in the developing countries. Different technologies have been employed in which adsorption has found a wide range of application. Today, various low cost adsorbents have been developed and evaluated for the adsorption processes. Clay mineral is one of the low cost natural adsorbents requiring minimum modification to enhance its adsorptive capacities. To maintain a clean and safe environment the water bodies must be free of contaminants of emerging concern. The availability of potable water is a global effort, as two of the UN's seventeen Sustainable Development Goals (SDG) are centered on water which is not surprising. Goal 6 focuses on clean water and sanitation whereas Goal 14 focuses on life below the water. With this in view, the availability of potable water highlights the significance of this study, which analyzes the potential of clay minerals as a good precursor for water treatment. Therefore, this review focuses on the clay minerals, its availability in Nigeria, classification and modification of the clay adsorbent
Three-State Hidden Markov Model for Spectrum Prediction in Cognitive Radio Networks
No full textThe exponential growth and proliferation of wireless devices for different wireless applications have led to the emergence of cognitive radio network (CRN) for optimal utilization of scarce spectrum resources. However, these resources have grossly been under-utilized due to the inaccurate spectrum predictions. Existing spectrum occupancy and prediction techniques which rely on 2-state hidden Markov model (HMM) results in false alarm or missed detection caused by noisy or incomplete observable effects. In this paper, a 3-state HMM spectrum occupancy and prediction technique in CRNs is proposed. The transmission, emission and initial state probabilities of the proposed 3-state HMM parameters were derived based on the three canonical problems associated with HMM. The evaluation, decoding and learning problems were solved using Forward algorithm, Viterbi algorithm and the Baum-Welch algorithm, respectively. The performance of the proposed 3-state HMM spectrum prediction technique was evaluated using prediction accuracy, probability of detection and spectrum utilization efficiency. The simulation results obtained revealed that the 3-state HMM outperformed the 2-state HMM spectrum prediction technique by 24.1% in prediction accuracy
Mitigating the Causes of Teenagers’ Involvements in Money Ritual and Related Activities in Ogun State, Nigeria
Get PDFThis study assesses the mitigating causes of teenagers’ involvements in money rituals and related activities in Ogun State. The study sets out to assess the factors responsible for the pandemic of money ritual and suggests solutions to the upsurge of money ritual related killings among teenagers. The study employed a descriptive research design. The population for this study consists of all residences in Abeokuta South and Ado-Odo/Ota local government areas of Ogun state. Participants were selected using a purposive random sampling procedure. The main instrument for this study is a self-structured questionnaire tagged: “Teenager and Money Rituals Killings Questionnaire” (TMRKQ). (R =0.82). Data collected was coded and analysed using descriptive statistics of mean and standard deviation. The results show that factors such as greediness on the part of teenagers and peer group pressure contributed to teenagers' involvement in money rituals and factors such as promotion of hard work, good values system and conducts among the youths will reduce youth tendency of engaging in money rituals. Based on the findings, it is suggested that the government should punish offenders to serve as a deterrent to others and the government should improve on intelligent gathering techniques in reducing cases of money rituals killings in the country