LAUTECH Journal of Engineering and Technology (LAUJET)
Not a member yet
571 research outputs found
Sort by
PERFORMANCE ESTIMATION OF LONG-HAUL OPTICAL TRANSMISSION SYSTEM OVER A COHERENT SYSTEM USING GAUSSIAN NOISE MODEL
Get PDFThe demand for internet capacity is expected to increase exponentially owing to more implementation of the Internet of Things and 5G which requires high speed and data volume to be delivered to clients. To accommodate this internet demand in the future, fiber optics is the most viable alternative for delivering reliable high-speed Internet access with good quality of service. Optical Transmission systems (OTSs), however, suffer from signal impairments such as nonlinearities in optical fibre and Amplified Spontaneous Emission noise. Signal impairments due to fiber nonlinearities become more significant as the optical power, transmission distance, capacity and the number of channels in the fiber are increased. Hence, to maintain the quality of the transmission as the length of the transmission increases, the Gaussian Noise (GN) model, a reliable tool for performance prediction over a wide range of system scenarios, was used to check for signal distortion. Noise estimation and optical signal-to-noise ratio were used to measure the quality of transmission while the obtained results were also used to evaluate the performance of longer-distance OTS. This paper addresses the nonlinear issue and provides possible solutions to identified challenges
EVOLUTION OF A MODEL TO DETERMINE UNSECURED TRANSACTIONS
Get PDFThe widespread presence of fraudulent transactions in financial institutions is of significance in banking operations. Examples of financial instruments that are utilized include credit cards, smart cards, swipe cards, etc. These cards provide important information and enable small costs to be incurred by customers. These small amounts are removed from customer accounts. Banks need to discover the correctness of transactions, thus the introduction of the evaluation of models to determine unsecured transactions. The focus of this research is to contribute to the field of the application of machine learning to banking operations by introducing tools for predicting unsecured transactions in the banking sector. The research objectives include the examination of different methods utilized in machine learning for investigating unsecured transactions about the physical stealing of credit cards and the illegal collection of details on credit cards. To accomplish the aims of this research, information gathering is done using Kaggle. Kaggle is obtainable online. The major focus of this research is to examine cardholders' spending patterns. The method includes using a multilayer perceptron (MLP). This is utilized with training of 70% and testing of 30% subsets. The evaluation of the model is done using a confusion matrix technique. This research is implemented using the Python programming language. The model produces accuracy rates of 93% and 99% respectively. This research can leverage achievements recorded to improve security concerns in financial institutions
Optimization of mechanical and tribological properties of Al composites reinforced with selected agricultural waste ash for lightweight engineering applications
Get PDF Agricultural residues have been applied as reinforcements in metal matrix composites because of their low cost and the possibility of reducing environmental pollution. In most of these applications, the mixing ratios follow a parametric approach making optimization important for maximum deployment of agricultural residue. In this study, tribological and mechanical properties of Al composites reinforced with coconut shell ash (CSA), rice husk ash (RHA), and cassava peel ash (CPA) were optimized following a multi-objective optimization technique. Eleven samples were prepared in a two-step stair casting technique with the selected filler at 15wt.% and 85wt.% Al-powder as the matrix. The tensile strength, percentage elongation, wear rate, and elastic modulus of all synthesized samples were analyzed. The results show that the samples containing 5wt.%RHA + 5wt.%CSA + 5wt.%CPA + 85wt.%Al and 10wt.%RHA + 2.5wt.%CSA + 2.5wt.%CPA + 85wt.%Al gave optimum mechanical values (133.106 MPa, 8.175%, and 109.945 GPa) while samples with 2.5wt.%RHA + 10wt.%CSA + 2.5wt.%CPA + 85wt.%Al gave optimum wear rate (0.074Ml/Nm). Statistical analysis showed that the three fillers (RHA, CSA, and CPA) are significant implying that they are responsible for the variation in physicomechanical properties of the composites. The optimum physico-mechanical propeeties were 133.106 MPa, 8.175%, 109.945 GPa, and 0.074Ml/Nm and obtained at proportions of 5wt.%RHA + 5wt.%CSA + 5wt.%CPA + 85wt.%Al and 10wt.%RHA + 2.5wt.%CSA + 2.5wt.%CPA + 85wt.%Al and 2.5wt.%RHA + 10wt.%CSA + 2.5wt.%CPA + 85wt.%Al
Effects of magnetic field on removal of light non aqueous phase liquid from unsaturated zone using steam injection
No full textAbstract
Unsaturated zone is of great importance in providing water and nutrients that are vital to the biosphere and often the main factor controlling water movement from the land surface to the aquifer. Steam injection for remediation of porous media contaminated by NAPLs has been shown to be a potentially efficient technology. However, the need for its improvement in recovery efficiency using other methods has been a subject of continuous study. The aim of this study was to carry out the experiments to investigate the effect of magnetic field on the removal of NAPLs from unsaturated zone using Steam Injection An unsaturated zone of a sand box of interior dimensions 110 x 74 x 8.5 cm was polluted at different period with 200 mL of Toluene. Steam injection experiment with flow rate of 0.01 m3/s was performed to determine the recovery efficiencies of Toluene only in an unsaturated zone containing sand of porosity 0.42 and permeability of 0.001163779 cm/s with the introduction of varying magnetic field 1-3T in step of 1T. The results for the recovery efficiency of Toluene using steam injection only was 80.30% while that of steam injection and magnetic field at 1-3 T yielded 83.70-86.60 %. The results of recovery efficiency of steam injection with magnetic field were 4.23-7.85 % higher than the result of steam injection only for LNAPL (Toluene). A combined application of steam injection with magnetic field appreciably enhances the removal of Non Aqueous phase liquids from Unsaturated Zone.
 
Development of an intrusion detection system using mayfly feature selection and artificial neural network algorithms
Get PDFProtecting the privacy and confidentiality of information and devices in computer networks requires reliable methods of intrusion detection. However, effective intrusion detection is made more difficult by the enormous dimensions of data available in computer networks. To boost intrusion detection classification performance in computer networks, this study developed a feature selection mode for the classification task. The proposed model utilized the Mayfly feature selection algorithm and ANN as the classifiers. The model was also tested without a mayfly algorithm. The model's efficacy was determined through a comparison of its accuracy, specificity, precision, sensitivity, and F1 score. The experimental outcomes revealed that the proposed model is more efficient than existing models based on the performance evaluation and the CIC-IDS 2017 dataset employed in this research. Accuracy scores of 99.94% (using Data+mayfly+ANN) and 90.17% (using Data+ANN) were attained after experimentation. In comparison to existing models, the proposed model yielded better results in terms of accuracy, sensitivity, specificity, and F1-score metrics. The model's sturdiness can be attributed to the use of mayfly techniques, which harness the strength in PSO, GA and FA for selecting optimal feature subsets. The results of this research provide a reliable dimensionality reduction model that may be used in the field of computer networks for intrusion detection and enhancement of security in computer networking environments
Iron oxide Green synthesized nanoparticles for improved performance in Monolithic Dye Sensitized Solar Cells
Get PDFIn order to improve photovoltaic efficiency in Monolithic Dye-Sensitized Solar Cells (MDSSCs), this study examined the effects of incorporating green produced iron oxide nanoparticles to a nanoporous carbon counter electrode. An extract from the leaves of Ocimum gratissimum was effectively used to synthesize iron oxide nanoparticles. The development of iron oxide nanoparticles was verified by optical absorption in the 350–450 nm range. With an average crystallite size of 47.9 nm, XRD patterns demonstrated the crystalline nature of the Iron oxide nanoparticles. Chemical bonds that may responsible for the nanoparticle production were found using FTIR investigations. An impressive 135.3% boost in efficiency was recorded for cell containing the Iron oxide nanoparticles, according to the MDSSC performance evaluation where DSSC without nanoparticles had a lower solar-to-electric power conversion efficiency of 1.7%, an open circuit voltage of 0.2625 V, a short-circuit current of 0.0723 mA/cm2, and a fill factor of 0.3630. The FeO CEs cell had an open-circuit voltage of 0.4274 V, a short-circuit current of 0.1042 mA/cm2, and a fill factor of 0.46. Their solar-to-electric power conversion efficiency was 4.0%. The potential of incorporating green-synthesised iron oxide nanoparticles into MDSSC counter electrode was shown by their great biocompatibility and even dispersion
Analysis of dimensionality reduction on ransomware detection using machine learning techniques
Get PDFRansomware attacks continue to evolve as a pervasive threat to cybersecurity such as data loss, financial losses, and potential disruption of critical services which have prompted the need for robust detection mechanisms. Leveraging on machine learning techniques for ransomware detection has gained recognition; however, the high-dimensional nature of feature spaces has posed some challenges in model efficiency and effectiveness. This research therefore explores the impact of two well-known dimensionality reduction methods that may enhance ransomware detection using five popularly used machine learning algorithms which are K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM) and Naive Bayes (NB). Through comprehensive analysis and experimentation, two well-known dimensionality reduction techniques, Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) were examined on the selected machine learning algorithms using a Ransomware PE Header Feature Dataset (publicly available on online data repository) with 1028 features. Metrics such as Accuracy, Recall, Precision and F1-Score were used to evaluate the classifiers. The comparative analysis of LDA and PCA reveals a discernible preference for one classifier over another. From the results, it is observed that the performance of classifiers with PCA is better than that of with LDA. Also, Decision Tree and Random Forest classifiers outperform the other three algorithms without using dimensionality reduction as well as with both PCA and LDA
ASSESSMENT OF PHYSICAL AND CHEMICAL PROPERTIES OF SOILS IN KWARA STATE POLYTECHNIC FOREST RESERVES
Get PDFThe different features of soil greatly affect the flora and vegetative diversity of a forest. The physical and chemical characteristics of soils in the Kwara State Polytechnic Forest Reserve were evaluated to assess the fertility and productivity status of the soils. Three composite soil samples were collected randomly from different locations at the depth of 0-20cm, 20-60cm, and 60-100cm using soil auger. The physical parameters evaluated include: soil texture using hydrometer, soil infiltration rates and capacity by double ring infiltrometer, soil temperature using soil thermometer, and available soil moisture content by digital soil moisture meter. Results of the soil particle size analysis revealed that soil in the study area is sandy loam, using textural classification triangle chart. This indicates that the soil is generally very light-textured with sand percentage averaging more than 80% and loam is 20%. The estimated average infiltration rate of the soil in the study area is 96.9mm/hr and the values of infiltration capacities (K) were generally high and varied from 0.00956cm/s to 0.0104cm/s. The results of moisture contents for the sampling location points (Point A, B, and C) around the study area are; 1.08 %, 1.05%, and 1.09%, respectively. Similarly, the observed soil temperatures are; 6.7oC, 5.4oC, and 7.8oC, respectively. Chemical analysis results revealed that the soil pH was moderately to slightly acidic and it ranged from 5.30 to 6.87. The average organic carbon ranged from 0.142-0.267% of the entire soil nutrients relating to soil fertility. The available phosphorous content of the soil is high which ranged from 20.276 to 28.342mg/l. The sodium status of the soil is generally low which ranged from 0.156 to 0.653me/l. The exchangeable sodium percentage (ESP) value of the soil ranged from 5.90 to 10.0%. The calcium status of the soil is generally moderate which ranged from 4.36 to6.22 me/l. Magnesium been the dominant cation ranged from 1.16 to2.26 me/l. The organic matter of the soil is moderate as the values obtained ranged from 0.133 - 0.165%. The cation exchange capacity (CEC) of the soil ranged from 4.76 to 5.52me/l. Therefore, soil physical and chemical properties were the dominant factors influencing the extent of decomposition process. Thus, the forest reserve serves as protection for the soil as well as promoting the fertility and productivity of the soils to support a flourishing vegetation types in the study area
PREDICTION OF MILLING MACHINE FAILURES USING MACHINE LEARNING MODEL,
Get PDFThis study developed a random forest machine learning model for predicting milling machine failure using five input parameters, which include air temperature, process temperature, rotational speed, torque, and tool wear. Deploying the model helps to know when failure is likely to occur and what measures can be taken before the machine fails, including pre-emptive investigation, maintenance schedule adjustments, and repairs. The performance evaluation of the developed random forest model revealed that it predicts milling machine failure with high precision and accuracy, as evidenced by the performance metrics obtained during the model testing via accuracy, precision, recall, and F1 values of 0.98533, 0.71287, 0.82758, and 0.76595, respectively. The confusion matrix analysis shows the model correctly predicted 2884 no machine failures as true positives (TP) and 15 no machine failures as false positives (FP) out of 2899 no machine failure targets. In addition, the model predicted 72 machine failure targets as true negatives (TN) out of 101 machine failure targets and 29 as false negatives (FN). The model design determines the condition of the machine and predict when maintenance is needed to avoid breaking down. This improves the efficiency and productivity of milling machine operations, enabling proactive maintenance and reducing unplanned downtime
Winding inductance predictions of a machine: WINDING INDUCTANCE PREDICTIONS
No full textThe winding inductances of a double stator machine are analyzed in this study. Finite element analysis is deployed using MAXWELL-ANSYS software. It is revealed that the machines that have even number of poles i.e. 10-pole and 14-pole, exhibited larger amount of both self and mutual inductance values. The 10-pole and 14-pole machine types have relatively larger direct-axis inductance compared to that of its 11-pole and 13-pole counterparts; nevertheless, with comparably lower quadrature-axis inductances. The machine types that have odd number of poles seem to possess lesser sensitivity to its inductance-current relation, unlike its equivalent even number of pole categories. Predicted peak magnetic axis force value on the rotor of 10-pole, 11-pole, 13-pole and 14-pole machine varieties at 30 W is: 0.18 N, 87.60 N, 10.95 N and 0.13 N, respectively