https://ajesa.com.ng/index.php/AJESA <p>ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS (AJESA) is an academic/technical Journal of engineering and applied sciences published by the Nigerian Institute of Electrical and Electronic Engineers (NIEEE) Awka Chapter covering all fields of Engineering and Engineering Sciences such as Mechanical Engineering, Safety and Fire Engineering, Civil Engineering, Electrical and Electronic Engineering, Computer Engineering, Communication Engineering, Computer Science, Software Engineering, Cybersecurity, Information Technology, Entrepreneurship Studies, Chemical Engineering, Petrochemical Engineering, Water Engineering, Highway Engineering, Materials and Metallurgical engineering, current trends in Artificial Intelligence, Robotics and Machine Learning, Polymer Engineering, etc.</p> <p>The Journal is an open-access online journal publishing double-blind peer-reviewed research papers in every area of engineering and scientific applications related to engineering and engineering sciences and sub-fields. It is published every month within two-months interval, but paper submission is open every month.</p> The Nigerian Institute of Electrical and Electronic Engineering (NIEEE) Awka Chapter, Nigeria en-US ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://ajesa.com.ng/index.php/AJESA/article/view/59 The California Bearing Ratio (CBR) test is a penetration test used to evaluate the subgrade strength of roads and pavements. Results from the CBR test are used with empirical curves to determine the thickness of pavement layers, and the test remains the most widely used method for the design of flexible pavements. Under normal conditions, obtaining the result of a soaked CBR test takes between four and five days, a duration that can be impractical in emergency situations. During the COVID-19 pandemic, for example, pressure to deliver infrastructure quickly led to the construction of a 1,000-bed Huoshenshan Hospital in Wuhan, China, in ten days (24 January to 2 February 2020); achieving comparable feats depends on faster means of estimating soil strength. This study therefore explores an indirect, regression-based approach to predicting CBR. Geotechnical test results for 84 soil samples were collected, and a multiple regression analysis was carried out with the soaked CBR value as the dependent variable and existing moisture content (EMC), liquid limit (LL), plastic limit (PL), plasticity index (PI), particle size distribution, optimum moisture content (OMC), and maximum dry density (MDD) as independent variables. The analysis produced the relationship Y = −0.57359169X₁ + 0.677530201X₂ – 0.64691219X₃ – 0.59578021X₄ + 0.004879034X₅ – 0.01717437X₆ + 0.13710102X₇ – 0.266139X₈ – 0.10248341X₉ + 0.118277058X₁₀ – 0.10766766X₁₁ + 0.25140518X₁₂ – 0.16878082X₁₃ + 7.543637025X₁₄ – 0.20878597X₁₅ + 5.381442462X₁₆ + 10.18311796, where Y is the predicted soaked CBR value and X₁ through X₁₆ are the corresponding independent variables. The equation was used to predict CBR values for the remaining samples, achieving an accuracy of approximately 92%. A reliability analysis was subsequently carried out on each independent variable; the percentage passing sieve No. 200 and the maximum dry density returned R² values of 0.9872 and 0.9691, respectively, against the coefficient of variation. T. Aleyemi J. E. Sani S. A. A. Jibril V. M. Ishaku Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-08-14 2026-08-14 4 1 1 13 https://ajesa.com.ng/index.php/AJESA/article/view/60 Wheel alignment is a critical aspect of vehicle maintenance that significantly influences road safety, steering stability, fuel efficiency, tire longevity, and overall vehicle performance. Conventional wheel alignment technologies, including mechanical, laser-based, Charge-Coupled Device (CCD), and three-dimensional (3D) camera systems, provide reliable measurements but are often expensive, require specialized hardware, frequent calibration, and skilled technicians. These limitations reduce their accessibility, particularly for small and medium-sized automotive workshops and educational institutions. This study proposes the design and implementation of a deep learning-based vision system for automated vehicle wheel alignment using computer vision and artificial intelligence techniques. The proposed framework integrates digital image acquisition, camera calibration, image preprocessing, object detection, feature extraction, and geometric measurement algorithms to estimate principal wheel alignment parameters, including camber, caster, and toe angles, without the need for wheel-mounted sensors or reflective targets. An experimental research design was adopted, comprising system development and performance evaluation phases. Vehicle wheel images were collected from multiple passenger vehicles under varying lighting conditions, camera viewpoints, and workshop environments. The dataset underwent preprocessing through image resizing, normalization, augmentation, and annotation before training a deep learning object detection model. Camera calibration techniques were employed to correct lens distortion and establish accurate geometric relationships between image coordinates and real-world measurements. The trained model detected wheel features, extracted rim centers and reference points, and estimated alignment angles, which were subsequently compared with measurements obtained from a commercial wheel alignment machine. The system also achieved real-time processing capability, requiring approximately 100 ms per image and operating at about 30 frames per second on a GPU-enabled platform, while maintaining moderate computational resource utilization. Performance evaluation under varying lighting conditions, camera distances, wheel sizes, and vehicle categories confirmed the robustness and generalization capability of the proposed approach. The study demonstrates that deep learning and computer vision can provide an accurate, low-cost, and automated alternative to conventional wheel alignment systems. By reducing dependence on proprietary hardware and minimizing human intervention, the proposed system offers improved accessibility, diagnostic consistency, and operational efficiency. Samuel Goodliffe Dickson Madubuezi Christian Okoronkwo Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-08-15 2026-08-15 4 1 14 34 https://ajesa.com.ng/index.php/AJESA/article/view/61 Enterprise Resource Planning (ERP) systems consolidate core operational functions of business processes on a single database, thereby making them prime targets for insider threats. Thus, insider threats remain among the most consequential yet least detectable risks, because the individuals responsible for most anomalous activity already hold legitimate, and often extensive, system’s privileges. Traditional insider threat controls rely on operating access rules and retrospective audit trails that register violations only after damage has occurred. This study proposes a machine learning-based predictive framework for the early detection of insider threats within ERP systems environments. The framework integrates sequential deep learning architectures, primarily the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks with ensemble learning methods of Random Forest (RF) and Gradient Boosting (GB) to model the temporal evolution of user behavior across authentication, file-access, email, and enterprise transaction logs. The methodology addresses data imbalance through the Synthetic Minority Over-sampling Technique (SMOTE), employs temporally aware cross-validation to avoid information leakage, and evaluates candidate models using precision, recall, F1-score, and the Area Under the Receiver Operating Characteristic Curve (AUC-ROC). Five conceptual diagrams operationalized the framework. A structured synthesis of benchmark outcomes reported across comparable insider threat studies indicated recurrent architectures consistently improved the detection of temporally patterned insider behavior relative to static classifiers, while ensemble methods retained advantages in interpretability, training efficiency, and auditability. The study closes with ethical deployment guidelines and a concrete roadmap for empirically validating the framework on live ERP telemetry. Joseph Osahon Idemudia Dr. Princewill Aigbe Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-07 2026-09-07 4 1 35 42 https://ajesa.com.ng/index.php/AJESA/article/view/62 Energy resources technology is very vital to the economic, social; and political development of any county. Energy is needed both for domestic and industrial purpose and most developing countries such as Nigeria are blessed with abundant energy resources (renewable and/or non-renewable) but the basic problem lies in the lack of technological capability to extract and process these resources to their own benefit, grouped among renewable resources include solar, hydropower, hydro tidal energy, geothermal and biomass, while the non-renewable (depletable) energy, resources include the fossil fuels (coal, crude oil and natural gas nuclear fuels, uranium core or thorium ) and for an energy resource to be economically feasible and viable it must satisfy these techno-economic criteria i. Time frame; ii. Breadth of application; iii. Fuel supply; iv. Environmental effect; v. Safety factor; vi. Social customs; vii. Political factors. J.N Ndive E.N Ikezue Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-12 2026-09-12 4 1 43 45 https://ajesa.com.ng/index.php/AJESA/article/view/63 The increasing volume, variety, and velocity of healthcare data have created significant opportunities for data-driven decision-making while simultaneously exposing limitations in conventional Business Intelligence (BI) systems. Healthcare organizations often rely on fragmented information systems, delayed reporting processes, and historical data, which can limit the ability of healthcare professionals and managers to respond promptly to emerging clinical, operational, and administrative situations. This study proposes the development of a hybrid model for real-time Business Intelligence decision-making in the healthcare sector. The proposed model integrates real-time data acquisition, data integration, business intelligence, predictive analytics, and decision-support mechanisms to provide timely and actionable insights to healthcare decision-makers. The hybrid architecture is designed to integrate data from diverse sources, including electronic health records, hospital information systems, laboratory systems, administrative databases, and healthcare monitoring devices. A Design Science Research approach is adopted to guide the requirements analysis, model design, prototype development, implementation, and evaluation of the proposed framework. The model combines descriptive and predictive analytics with real-time processing and visualization to support faster, evidence-based decision-making. The proposed approach is expected to improve decision-making speed, information availability, predictive capability, resource utilization, and operational efficiency within healthcare organizations. The study contributes a structured framework for integrating real-time Business Intelligence and advanced analytics into healthcare decision-support processes and provides a foundation for developing more responsive and data-driven healthcare management systems. Onyebuchi Evidence Chukwudi Beloved Obinnaya Omankwu Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-21 2026-09-21 4 1 46 70 https://ajesa.com.ng/index.php/AJESA/article/view/64 The long-term performance of highway embankments constructed on compressible soils is significantly influenced by consolidation settlement and deformation characteristics of the underlying foundation soils. Conventional analytical approaches such as Terzaghi’s one-dimensional consolidation theory are widely used for settlement prediction; however, these methods are limited in representing complex subsurface conditions and realistic field behavior. This study therefore assessed embankment consolidation behavior using both Terzaghi’s analytical method and the Finite Element Method (FEM) implemented in PLAXIS 2D within the Ewu Hill section of the Benin–Auchi Expressway. Representative geotechnical datasets comprising moisture content, Atterberg limits, permeability, compression index, coefficient of consolidation, cohesion, and friction angle were obtained from published geotechnical investigations and documented embankment studies within humid tropical environments of Southern Nigeria. Terzaghi’s analytical consolidation procedure was applied to estimate settlement magnitude and consolidation rate, while FEM simulation was conducted using coupled hydro-mechanical analysis in PLAXIS 2D to evaluate stress redistribution, pore water pressure dissipation, deformation behavior, and long-term embankment performance. The results revealed that settlement increased progressively with time due to gradual dissipation of excess pore water pressure within the embankment foundation soils. The FEM simulation predicted higher and more realistic settlement values compared to the analytical method due to incorporation of layered soil conditions, nonlinear soil behavior, multidirectional drainage, and realistic stress interaction. The study further established that moisture content, permeability, compressibility, and shear strength parameters significantly influenced embankment performance and long-term settlement susceptibility. The FEM analysis also demonstrated that maximum settlement occurred beneath the embankment centerline where stress concentration was highest. The study concluded that FEM implemented in PLAXIS 2D provides more comprehensive and reliable assessment of embankment consolidation behavior under complex geotechnical conditions compared to simplified analytical approaches. The findings contribute to improved highway embankment design, settlement prediction, and long-term geotechnical performance evaluation within humid tropical environments. Taiye Victor Dosunmu Olugbenga Oludolapo Amu Ademola Bolarinwa Olaoluwa Richard Olowookere Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-16 2026-09-16 4 1 71 85 https://ajesa.com.ng/index.php/AJESA/article/view/65 Poultry farming is an important component of agricultural production and food security; however, effective management of poultry houses requires continuous monitoring of environmental and production conditions. Conventional monitoring practices often depend on manual observation and record keeping, which can result in delayed identification of abnormal conditions, inconsistent records, and slow responses to potentially harmful environmental changes. This study presents the design and development of an IoT-oriented framework for environmental monitoring and risk assessment in poultry farm management. The study adopted a hybrid Object-Oriented Analysis and Design (OOAD) and iterative prototyping methodology to develop a functional web-based poultry farm monitoring system. The proposed system was structured into four layers: data acquisition, communication and data storage, processing, and application/presentation. The system provides facilities for poultry-house registration, batch management, sensor-reading entry, configurable threshold management, environmental risk assessment, dashboard visualization, historical record management, role-based access control, and automated alert generation. Eight poultry-related indicators are considered, including temperature, humidity, ammonia level, light intensity, feed level, water level, mortality count, and bird-weight sample. A centralized MySQL relational database was implemented to store monitoring records, while a rule-based risk assessment engine evaluates environmental readings against administrator-configured threshold values and classifies conditions as Normal, Warning, or Critical. Where abnormal conditions are detected, corresponding alert records are generated and email notification is attempted. System testing covered critical environmental readings, invalid batch selection, dynamic batch retrieval, threshold reconfiguration, duplicate user registration, and role-restricted access. The test results showed that the major functional components operated as expected after identified implementation defects were corrected. In particular, a test temperature reading of 40°C and humidity reading of 75% successfully triggered Critical and Warning classifications respectively, demonstrating the effectiveness of the implemented threshold-based assessment mechanism. The study demonstrates that the proposed framework can provide a structured digital approach to poultry farm monitoring, improve data organization, support consistent environmental risk classification, and facilitate timely notification of abnormal conditions. However, the current implementation uses simulated sensor inputs and a rule-based assessment mechanism rather than physically deployed IoT sensors and a trained machine-learning model. The developed framework therefore provides a practical foundation for future integration of physical sensing devices, machine-learning algorithms, predictive analytics, automated actuators, and mobile-based remote monitoring for intelligent poultry farm management. Njoku Glory Onyinye Ugwoke F.N. Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-16 2026-09-16 4 1 86 93 https://ajesa.com.ng/index.php/AJESA/article/view/66 The California Bearing Ratio (CBR) test is the most widely used method for evaluating subgrade strength and for the design of flexible pavements, but the standard soaked CBR procedure typically requires between four and five days to complete, a duration that can be a challenge when infrastructure must be delivered quickly. This study presents a Python-based machine learning approach for the indirect prediction of soaked CBR from index and compaction properties routinely measured in geotechnical practice. Geotechnical laboratory data comprising existing moisture content, liquid limit, plastic limit, plasticity index, percentage passing standard sieve sizes, optimum moisture content, maximum dry density, and specific gravity were compiled for 1,000 soil samples. The dataset was imported into Python using the pandas library and split into training (80%) and testing (20%) subsets. A random forest regression model was then trained to predict soaked CBR values from the remaining variables. On the test set, the model achieved a coefficient of determination (R²) of 0.957, a mean absolute error of 2.43, and a root mean square error of 3.255, indicating strong predictive performance. These results demonstrate that random-forest-based machine learning models can reliably estimate soaked CBR values without the time and material costs of conventional laboratory soaking, offering a practical complement to standard testing, particularly for time-constrained construction projects. T. Aleyemi V. M. Ishaku J.V. Madaki Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-22 2026-09-22 4 1 94 104 https://ajesa.com.ng/index.php/AJESA/article/view/67 Radio Frequency Identification (RFID) turnstile systems have become a common ingress-control mechanism for large-capacity football stadiums, offering fast, contactless verification of ticket tokens. However, token-only verification cannot distinguish between the rightful ticket holder and a third party who possesses the same wristband or a cloned tag, leaving such systems structurally exposed to ticket-passing and proxy-attendance fraud. This paper proposes and evaluates a multi-factor authentication (MFA) architecture that augments an existing RC522/ESP32-based RFID stadium access control system with a fingerprint biometric verification stage, combined through a decision-gated, weighted score-level fusion rule. A Monte Carlo simulation (100,000 genuine and 100,000 fraudulent trials) was used to characterise the trade-off between security and throughput. At the Equal Error Rate (EER) operating point, the proposed system achieves a False Acceptance Rate (FAR) of 1.205% against pass-back/proxy fraud, compared with a 100% FAR for the same attack under the RFID-only baseline, since a valid token is, by design, always accepted by a token-only reader. The added biometric step increases per-spectator gate service time from 1.2 s to between 1.45 s and 2.05 s depending on sensor choice, which is shown, through a Pollaczek-Khinchine queueing approximation, to remain operationally acceptable when lane count is increased modestly. The paper reports the complete simulation methodology, all governing equations, and an explicit discussion of the synthetic nature of the biometric score model, consistent with a system-level feasibility study rather than a hardware-validated deployment. Results indicate that decision-gated biometric fusion is a practical, low-cost mitigation for the proxy-attendance vulnerability identified in prior RFID-only stadium access control work. Odesa Edward Ogaga Nwaubani Supreme Onyenkachi Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-09-28 2026-09-28 4 1 105 114 https://ajesa.com.ng/index.php/AJESA/article/view/68 Poor drainage is an important factor associated with pavement deterioration in urban road networks. This study evaluated drainage condition and its relationship with pavement deterioration along five selected road corridors in Ilorin, Kwara State, Nigeria. Field assessment covered drainage geometry, slope, blockage, structural condition and flow behaviour, together with pavement distress, chainage and hydraulic performance. Drainage Condition Index (DCI) and Pavement Deterioration Index (PDI) were used for comparative assessment, while estimated runoff was compared with drainage conveyance capacity. DCI ranged from 25 to 78 and PDI from 25 to 85. Akerebiata–Sobi recorded the poorest drainage condition (DCI = 25), highest deterioration (PDI = 85) and about 60% affected pavement area. Fate Roundabout–Sango recorded the best drainage condition (DCI = 78), lowest deterioration (PDI = 25) and about 15% affected area. Potholes and cracking accounted for 25% and 20% of observed distress types, respectively, while poor maintenance and siltation/sediment deposition represented 25% and 20% of identified drainage deficiencies. Hydraulic comparison showed inadequate capacity on Sango–Kwara Polytechnic Gate, Royal Valley–Akerebiata, Akerebiata–Sobi and Maraba–Fate Roundabout roads; Fate Roundabout–Sango was adequate. The findings indicate an association between poorer drainage and greater pavement deterioration, but drainage is not the sole cause of failure. Integrated drainage rehabilitation, routine desilting, hydraulic upgrading, culvert/outfall maintenance and chainage-based monitoring are recommended. Tijani Aliyu B.A Ibitoye S.O Subair Umar Lateef Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS https://creativecommons.org/licenses/by-nc/4.0 2026-10-04 2026-10-04 4 1 115 122