LAUTECH Journal of Engineering and Technology

DEVELOPMENT OF CREDIT CARDS FRAUD DETECTION MODEL

Sat, 08 Jul 2023 00:00:00 +0000

The evaluation of fraud is of significant importance A credit card contains a compact, thin plastic card that carries information about the individual, such as a photograph or signature, and allows the person make charges on products and services connected to his account, which is deducted regularly. Financial institutions analyzes whether or not transactions are genuine in the future. This research develops a model for fraud detection. As a result of the importance of this study, the goal of this study is to develop a machine learning technique for predicting credit card fraud in the financial sector. The objectives of this research are to investigate machine learning techniques for detecting and analyzing online transactions and investigate credit card fraud cases involving the stealing of physical cards or fraudulently acquiring a victim's card information. The methods applied in this paper include collecting data from Kaggle, an online data collection tool. The Kaggle application programming interface was used in importing the dataset. In this study, cardholders spending behavior are input into the multilayer perceptron and used to train and test the system. This was determined on the training dataset (70%) and evaluated on the testing dataset (30%). The model is developed using a multilayer perceptron (MLP), together with an algorithm. The confusion matrix technique is used for evaluation. The evaluation of results is done by comparing its performance with the classifier using accuracy metrics. The model implementation was done using the python programming language. The data was passed into MLP with an algorithm classifier and the results were obtained with an accuracy of 93% and 99% respectively. This work is advantageous to the banking sector in predicting fraudulent transactions. The model is developed to improve the solution to fraud issues in the financial institutions sector

COMBINING TEXT CLASSIFICATION WITH MACHINE LEARNING

Sat, 08 Jul 2023 00:00:00 +0000

The internet community is a medium of conveying information for various individuals. Enterprises need to have an insight into their various products and services. For the time being, not automatically reading and classifying plenty of text data could be overwhelming. As a result, this research appropriates the Data scraping method in which datasets are collected via a code written in python programming. Machine learning models were evolved using Random Forest and Naïve Bayes algorithms which are trained with extracted data for text classification. Consequently, texts are classified as positive, negative, slightly negative, slightly positive, or neutral comments utilizing classifiers, in which the experimental outputs indicate that the Random Forest classifier produces more preferable results in terms of reliability with 76.5% above the Naïve Bayes with 70.01%.

DEVELOPMENT OF AN OPTIMIZED INTELLIGENT MACHINE LEARNING APPROACH IN FOREX TRADING USING MOVING AVERAGE INDICATORS

O. E. Aru, C. C. Okechukwu — Sat, 08 Jul 2023 00:00:00 +0000

This research presents the development of an optimized intelligent machine learning approach in Forex trading using two variants of Moving Average indicators. The main aim of the Expert Advisor (EA) development is to introduce a new intelligent model for automated execution of trades in the Forex market, reducing potential losses due to human errors and sentimental factors in trading Forex. In developing this trading model, Momentum strategy was used since it takes advantage of market swings, along with Machine Learning - Genetic algorithm, being a type of supervised learning used in training the past historical data based on selected trading parameters in a Meta Trader 4 (MT4) platform. The new Expert Advisor –Exponential Moving Average (ESMA) was built using the MQL4 language which is based on C++ for programming specific trading strategies and easily facilitates automated trading. The result is an optimized intelligent trading system that implements the intersection of the two moving averages at various periods, to execute trades autonomously with a profit pass rate of 75% visible from the Optimization chart of the MetaTrader 4 (MT4) platform

PREDICTING COVID-19 FROM CHEST X-RAY IMAGES USING OPTIMIZED CONVOLUTION NEURAL NETWORK

Sat, 08 Jul 2023 00:00:00 +0000

Machine learning is emerging as a unique powerful method to improve the diagnosis and prognosis of several multifactorial diseases, including COVID-19. The COVID-19 pandemic is a major threat, and it has severe impact on the health and life of many people worldwide. The recent advances in computer vision made possible by various computational method has paved the way for computer assisted diagnosis in fighting COVID-19. Early detection of the COVID-19 through accurate diagnosis, may decrease the patient’s mortality rate. Chest X-ray images are crucial and mostly used for the diagnosis of this disease. Thus, this study used optimized Convolution Neural Network (OCNN) to support the diagnosis of COVID-19 using chest x-ray. Particle Swarm Optimization (PSO) was applied to optimize the network of CNN for improved performance. The dataset used in this study was acquired from Kaggle repository. The dataset contains the Chest X-Ray images of COVID-19 patients and normal patients. The model is created, and the results have been evaluated by using the various evaluation metrics, i.e., sensitivity, false positive rate, precision, accuracy, and prediction time. The approach adopted in this study enhances CNN by making it free from iterative adjustment of weights which increases the computational speed to a higher extent. The experimental results reveal that the proposed technique achieved an improved performance which indicates the very high accuracy of the proposed model.

DEVELOPMENT AND PERFORMANCE EVALUATION OF GREEN -VEGETABLES SLICING MACHINE

O. O. Alabi, O. A. Adeaga, G. O. Ogunsiji, S. A. Dada — Thu, 27 Jul 2023 00:00:00 +0000

Requirements of food processing units are sensitive and must be in conformity with hygiene and time requirement. Continuous work on the development of machines that are involved in the processing of edibles should be carried out. Traditionally, green-vegetables are plucked raw which often require time and also compromise hygiene. However, the several works done on green-vegetable slicing equipment have added improvement to ways by processing and or consumption. This article attempted the development of green-vegetable slicing machine and also evaluated the performance of same. Existing vegetable slicing machines were studied through literature and process design for development was carried out. Cutting capacity of 1.5 kg and 25 g of uniform slicing were used to evaluate the performance of the developed green-vegetable slicing machine. The shortcomings in the existing slicing machines reduced while reducing loss of sliced and also with uniform slices. Existing vegetable machines has experienced loss and associated time. The developed machine has a significantly improved efficiency to 96%.

AGGREGATE SIZES AND LAND USE TYPES INFLUENCE THE SOIL AGGREGATE STABILITY OF THE HUMID TROPICAL SOIL ENVIRONMENT

K. S. Are, O. J. Idowu, G. A. Oluwatosin — Thu, 27 Jul 2023 00:00:00 +0000

The impacts of the land use pattern and its management techniques on the size and stability of soil aggregates are still poorly understood. Thus, this study investigated the best aggregate size class suitable for testing soil aggregate stability under different land use types in a humid southwestern Nigeria. Surface soil samples (0–15 cm) were collected under five land use types: continuous arable maize, pasture, coconut, cacao and cassava plantations. The sizes of the tested aggregates were 2–5, 5–10, 10–13, and 13–15 mm. The soil aggregate size classes from the different land use types were subjected to a 5-min. simulated rainfall of 150 mm h^-1. Two sieves with varying aperture sizes (1.0 and 0.5 mm) were used to test these aggregates under the rainfall simulator. The stability of soil aggregates tested on the 0.5 mm sieve did not significantly vary among aggregate size classes, regardless of land use types. However, there were significant variations in the stability of the soil aggregates evaluated on the 1.0 mm sieve between different land use types and aggregate size classes. The order of aggregate stability for soil under pasture (80.4%) > coconut (77.8%) > cocoa (65.9%) > cassava (51.1%) > maize (33.1%). The amount of soil organic carbon in the soils is directly correlated with this trend. The aggregate size classes of 5–10, 10–13 and 13–5 mm did not significantly differ in stability while the 2–5 mm class had significantly lower stability than the other classes. Due to significant high correlations of stability with soil organic carbon, aggregate size classes of 5–10 and 13–15 mm appear to be the best suitable for routine determination of aggregate stability in the study environment.