Wellspring University

Driver drowsiness is a major cause of road accidents worldwide, leading to thousands of fatalities and billions in economic losses each year. This study presents a real-time drowsiness detection framework based on a hybrid Vision Transformer Convolutional Neural Network (ViT-CNN) architecture enhanced with multi-task learning and temporal attention. Unlike traditional sensor-based or reactive vehicle behavior methods, the proposed vision-based approach provides a non-intrusive, scalable solution capable of detecting early fatigue indicators such as eye closure, yawning, and head pose. The model leverages self-supervised pretraining on over 1.2 M unlabeled driving videos and is optimized for embedded deployment using INT8 quantization and TensorRT, achieving 99.27% accuracy, F1 = 0.98, and AUC = 0.998 while sustaining 42 FPS at 42 ms latency on the NVIDIA Jetson AGX Xavier. Explainability tools (Grad-CAM + + and Bayesian uncertainty estimation) ensure transparency in safety-critical contexts. Evaluation across six datasets demonstrates strong generalization, and the framework is adaptable to other fatigue-sensitive domains such as aviation and industrial safety.

Blockchain technology is increasingly recognised for its ability to enhance transparency, reliability, and accuracy in supply chain operations. This study examined the influence of blockchain adoption on data accuracy within the supply chain management system of the Nigerian National Petroleum Company Exploration & Production Limited (NEPL), Benin City. Four blockchain constructs data integrity, transaction accuracy, error rate reduction, and data security were assessed as predictors of data accuracy. Data accuracy was measured using seven Likert-scale items evaluating the correctness, uniformity, and reliability of supply chain records. A descriptive survey research design was adopted, and a sample of 138 respondents was determined using the Taro Yamane formula. Data were collected through a structured questionnaire and analysed using descriptive statistics, reliability tests, and multiple regression analysis. Findings revealed that data integrity (β = 0.322, p < .001), transaction accuracy (β = 0.276, p = .002), error rate reduction (β = 0.241, p = .007), and data security (β = 0.295, p = .001) each significantly enhanced data accuracy. Collectively, the predictors explained 70.8% of the variance in data accuracy. The study concludes that blockchain adoption substantially improves data accuracy in NEPL’s supply chain operations. It recommends institutionalising blockchain systems, building staff capacity, and strengthening regulatory support.

This study investigates the effect of employee engagement on turnover intentions in the banking industry in Warri, Delta State, Nigeria. High employee turnover has become a critical challenge in the sector, disrupting operations and increasing recruitment and training costs. Drawing on the behavioral, emotional, and cognitive dimensions of employee engagement, the study examines how each dimension influences employees’ intentions to leave their organizations. A quantitative research design was employed, using structured questionnaires administered to 316 bank employees selected through stratified random sampling. Data were analyzed using descriptive statistics and multiple regression analysis. The findings revealed that behavioral engagement (β = 2.030, p < 0.01), emotional commitment (β = 2.043, p < 0.01), and cognitive engagement (β = 2.034, p < 0.01) each had a significant negative effect on turnover intentions. The model demonstrated strong explanatory power, with an R² value of 0.66, indicating that 66% of the variation in turnover intentions could be attributed to these engagement factors. The results suggest that employees who are behaviorally active, emotionally connected, and cognitively involved are less likely to consider leaving their jobs. The study concludes that fostering comprehensive engagement strategies—encompassing emotional attachment, active participation, and intellectual involvement—can effectively reduce turnover intentions and enhance workforce stability. It recommends that bank management in Nigeria’s banking sector prioritize initiatives that build loyalty, promote involvement in decision-making, and encourage continuous professional development to strengthen employee retention and organizational performance.

Background. Contrast sensitivity (CS) is the innate ability of the eyes to discern any variation in luminance or brightness between an object and its background within a given space. CS is important for recognizing lane markers, road signs, and oncoming traffic while driving, especially in low contrast environments, such as at night or during foggy weather. This survey aimed to evaluate the risk factors and prevalence of CS impairment among drivers of commercial motor vehicles in Benin City, Edo State, Nigeria. Methods. This study employed an observational cross-sectional survey of 341 drivers of commercial motor vehicles aged 20-70 years (with the mean age of 48.09 years ± 11.21 years) in Benin City. The sample comprised 326 (96.6%) male drivers and 15 (4.4%) female drivers. The sample was selected using the purposive random sampling technique. The data was collected through the adjusted National Eye Institute Visual Functioning Questionnaire-25. Pelli-Robson test was performed to assess contrast sensitivity. Data was analysed using IBM-SPSS (version 29.0). Chi-square test was used to observe significant differences between CS and the associated risk factors. Results. The prevalence of impaired CS in this study was 21.7%. It increased with the increase in age from 7.9% among the age group 20-30 years to 48.0% among the age group > 60 years. Higher educational level was found to correlate with decreased CS impairment. Conclusion. The high prevalence of CS in this study could be a threat to safe driving, especially in low contrast environments, if appropriate measures are not put in place to identify drivers with CS impairment. Routine CS assessment of drivers is recommended preceding the issuance of driver’s license and relicensing.

Indoor positioning systems are crucial for public safety, healthcare, and IoT, but Wi-Fi fingerprinting faces challenges such as signal interference, multipath effects, and high computational costs. These issues reduce positioning accuracy and make real-time localization difficult.This paper introduces an Ant Colony Optimization (ACO)-based dual clustering method to enhance Wi-Fi fingerprinting accuracy and efficiency. ACO performs coarse clustering by optimizing initial data groupings, while K-means refines clusters for improved precision. The Weighted K-Nearest Neighbor (WKNN) algorithm is then applied for real-time positioning by selecting the most similar signal sub-bases.Experiments show that the proposed method achieves 100% accuracy in building classification and 91% accuracy in floor classification. For latitude and longitude prediction, Random Forest and SVC outperform XGBoost, achieving MSE values of 0.0048 (latitude) and 0.0055 (longitude). The approach also reduces computational overhead by 93.51%, improving efficiency.The study presents a robust, scalable solution for indoor positioning and introduces the Dual Clustering Wi-Fi Localization Dataset (DCWiLD) for future research. Future work will focus on dataset balancing, BLE/UWB integration, and energy optimization for IoT applications.

With an emphasis on Value Added Tax (VAT), Excise Tax (ET), and Import Tariffs (IT), this study examines how indirect taxes affect the price of consumer products in Nigeria. The survey aims at evaluating the influence of VAT rates, ET rates, and import tariffs on the prices of consumer goods in Nigeria. By analysing secondary data from government reports, industry reports, and previous studies, the research explores the extent to which these indirect taxes contribute to inflationary pressures and consumer prices in the country. Using a quantitative approach and regression analysis, the inquiry explores the interaction between tax rates and consumer prices. It concludes that there is a statistically significant positive correlation between VAT rates and the prices of consumer goods, with VAT having a greater effect than the other taxes. The effect of Excise Tax on prices is positive but weaker, while Import Tariffs also show a positive, though less pronounced, influence on prices. These findings suggest that VAT is the most significant contributor to higher consumer prices in Nigeria, while Excise Tax and Import Tariffs also contribute but to a lesser extent. The study recommends that policymakers carefully consider the impacts of indirect taxes on consumer prices and inflation when making tax policy decisions. In particular, VAT rates should be examined in relation to their impact on consumer affordability and economic stability. Further research is also recommended to determine the long-term implications of indirect taxation on the broader Nigerian economy and to explore potential strategies for mitigating negative effects on consumers.

The technological revolution is redefining several aspects of human life with several innovative solutions like smart farming, smart city, smart healthcare, industry 4.0 powered smart factory, and smart cars. In driving these technologically driven solutions, the 5th generation (5G) of wireless connectivity has a role to play because of its low latency, faster network connection, and unlimited bandwidth when compared with its predecessors. This work examines the role of 5G wireless technology in the provision of sustainable healthcare services at minimal cost and improved efficiency. A comprehensive examination of the evolution of wireless networks from 1G to 6G is presented with their strengths and weakness. Though 6G is not yet available, research progress in this regard is presented and the projected date of its release. Various applications of the 5G network in healthcare delivery are presented as well as some of the challenges that might impair its usage. The 5G wireless technology-powered healthcare centres can greatly improve access to medical experts and services remotely in real time.