http://laujci.lautech.edu.ng/index.php/laujci/issue/feedLAUTECH JOURNAL OF COMPUTING AND INFORMATICS 2023-08-31T15:15:13+00:00Professor Justice O. Emuoyibofarhe eojustice@gmail.comOpen Journal Systems<p><strong>Aim and Scope</strong></p> <p>The Lautech Journal of Computing and Informatics (LAUJCI) ISSN: 2714-4194 is an institutional based peer-reviewed research publishing journal with the aim of promoting and publishing original high quality research outputs in all areas of Computing and Informatics. All technical or research papers and research results submitted to LAUJCI should be original in nature, never previously published in any journal or presented in a conference or undergoing such process across the globe. All the submission will be peer-reviewed by the panel of experts associated with particular fields. Submitted papers should meet the internationally accepted criteria and manuscripts should follow the journal format which is available in the journal website for the purpose of both reviewing and editing.</p> <p>Some of the topics and subject areas of LAUJCI include but not limited to:</p> <ul> <li>Computer Science & Computer Engineering</li> <li>Information Security, Cyber Security & Computer Forensics</li> <li>Cloud, Cluster & Green Computing</li> <li>Signal & Image Processing</li> <li>Artificial Intelligence (includes pattern recognition, evolutionary computation, logic, etc.)</li> <li>Human-Computer Interaction</li> <li>Mobile Technologies & Mobile Web Services</li> <li>Remote Sensing</li> <li>IP mobility protocols</li> <li>Communications software and services</li> </ul> <ul> <li>Applied ICT, including but not limited to: <ul> <li>ICTs in Industrialization & Manufacturing</li> <li>ICT applications in Energy (Renewable, Oil, Hydro, Clean Coal & Nuclear)</li> <li>Internet applications</li> <li>Virtual environments and social networks</li> <li>ICT applications in education & training, including eLearning, Distance Education &</li> </ul> </li> </ul> <p>Innovative Educational Platforms</p> <ul> <li>E-government, e-governance & e-skills for development</li> <li>eHealth & mHealth</li> <li>Remote tracking, logistics & monitoring technologies</li> <li>Wireless Sensor Networks</li> <li>ICT for creative industries & technology innovations</li> <li>Electrical & Electronic Engineering, including but not limited to:</li> <li>Electronics Design</li> <li>Smart Utility Systems</li> <li>Power line communications and their applications</li> <li>Biomedical engineering</li> <li>Consumer electronics and components</li> <li>Measurements and modelling of signal propagation</li> <li>Communications, including but not limited to:</li> </ul> <ul> <li> <ul> <li>Green communications</li> <li>Telecommunications</li> <li>Wireless and fibre networks</li> <li>Satellite communications</li> <li>Software-Defined and Cognitive Radios</li> <li>Long term evolution networks</li> <li>Computer Networking</li> <li>Other Related Areas</li> </ul> </li> </ul> <p> </p>http://laujci.lautech.edu.ng/index.php/laujci/article/view/60AN IMAGE BASED PARKINSON’S DISEASE DETECTION SYSTEM USING MACHINE LEARNING APPROACH2023-08-31T12:14:20+00:00D.O Olanloye odun.olanloye@unimed.edu.ngO.A Halleluyahaworinde.hallelyah@unimed.edu.ngAyodeji Ibitoyeayodeji.ibitoye@bowen.edu.ngO. N. Emuoyibofarheozichi.emuoyibofarhe@bowen.edu.ngOloyede Johnjohn.oloyede@bowen.edu.ng<p><span class="fontstyle0">Quite several people have been sent to untimely grave and some with part of their body system paralyzed resulting from Parkinson Disease (PD). PD is a neurodegenerative disorder that affect neuron in the brain called substantial nigra with central movement. In this research work, an attempt is being made to design and implement a system for early detection of (PD) making use of relevant data (drawing of waves) from patient of PD and non-patient of the disease. Machine Learning models which include random forest (RF), Decision Tree (DT) and K- Nearest Neighbor (KNN), Dummy Classifier, Support Vector Machine (SVM), Convolutional Neural Network (CNN) were used to develop the model and the model in turn were used to develop the system. Machine Learning (ML)<br>models helped in predicting whether the patient have PD or not using both spiral and wave drawing and hence, displays the result.<br>Performance metrics such as Precision, recall and f1-score were used to determine the accuracy of the model result. Confusion matrix on the various algorithms were also displayed. Random Forest Classifier is discovered to be the most accurate machine learning algorithm for both the wave and spiral classification with an accuracy of 100% and a precision score for healthy (100%) and Parkinson’s (100%) after the extracted features were trained for wave classification, and an accuracy of 80% with a precision score for healthy (75%) and Parkinson’s (86%) after the extracted features were trained for spiral classification. Logistic Regression and Dummy Classifier had the worst accuracy with wave classification with an accuracy of 47%. Logistic Regression produced the worst accuracy (47%) in term of spiral classification. The best model (Random Forest) with 100% accuracy was used to develop the system and hence, the system was found to be highly efficient and far better than the existing methods or techniques.</span> </p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/61ASSESSING THE CREDITWORTHINESS STATUS OF MOBILE PHONE USERS USING SUPPORT VECTOR MACHINE2023-08-31T12:32:22+00:00M. M. Rufai mohammed.rufai@yabatech.edu.ngM. T. Ajala mosud.ajala@yabatech.edu.ngL. O. Lawalolawal201315@gmail.comW. A. AlaoOlalekan.awoniran@bowen.edu.ng<p><span class="fontstyle0">Credit risk is a major concern to lenders, it is important for any lending company to be able to determine when to approve and when to decline a loan. Machine learning techniques have recently been adopted to help identify defaulting customers, and also help to speed up the decision-making process of approving a loan. In this study, relevant features that are related to customers' credit scoring are selected, and we made use of a support vector machine to build a model that could solve the underlying problems. From the test result, our developed model could predict a borrower's compliance status to loan payment. The model was able to attain a performance measure for Precision, recall, accuracy, and f1-score on test data with values of 97.2 %, 100.0 %, 99.1 %, and 98.6 % respectively. This indicates that the Support vector machine is an effective approach that could be used in credit scoring, and our developed model<br>can be classified as a good classification.</span> </p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/65DEVELOPMENT OF A FACE MASK DETECTION SYSTEM USING SINGLE SHORT ALGORITHM: A CASE STUDY OF ELIZADE UNIVERSITY2023-08-31T13:10:18+00:00Ogunniyi JuliusJulius.ogunniyi@elizadeuniversity.edu.ngOlowu Adekemiadekemi.olowu@elizadeuniversity.edu.ngShobowale Yusufyusuf.shobowale@elizadeuniversity.edu.ngOgidan Olugbengaolugbengaogidan@gmail.comAsaniyan Olufemiolugbengaogidan@gmail.com<p>This paper discusses the development of a Face Mask Detection System using a Single Short algorithm for the prevention of the<br>spread of COVID-19 in public places. Several works have been done in the detection of face masks; however, there is a need to <br>increase the detection speeds while maintaining their high accuracy for large datasets. The developed system consists of both <br>software and hardware components. The model of the system was developed with a Single Short algorithm with a total of Nine <br>Hundred and Two (902) datasets with the faces of people with and without face masks, which were collected from Elizade <br>University, Ilara-Mokin, Ondo State of Nigeria. The Single Short Detection MobileNetv2 Algorithm was used to develop a <br>predictive model and deployed on the Raspberry Pi 4 microcontroller. Percentage accuracy, F1 score, Recall, and Precision were <br>the performance evaluation metrics used for the work. Also, a questionnaire was distributed to fifty (50) participants, mostly <br>students and staff of Elizade University, Ilara-Mokin, who tested the system with and without wearing a face mask. The result of <br>the system‟s performance evaluation indicates an accuracy of 99.86%, an F1 score of 100%, a recall of 100%, and a precision of <br>100%. The developed system can be miniaturised and reproduced to make the entire system smaller and more affordable. With the availability of the system‟s prototype, the development of the system for access control in public places such as stadiums, <br>shopping malls, and schools is possible.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/66DEVELOPMENT OF A PREDICTIVE MODEL FOR PETROLEUM PRODUCTS DISTRIBUTION IN NIGERIA USING MACHINE LEARNING APPROACH2023-08-31T13:47:27+00:00R.F. Famitimirfamitimi@unimed.edu.ngO.N. Emuoyibofarheozichi.emuoyibofarhe@unimed.edu.ngS. Adebayosegun.adebayo@bowen.edu.ngA.A. Ademoyeadetoye.ademoye@bowen.edu.ngT.I. Awonirantemitayo.awoniran@bowen.edu.ng<p>Petroleum products are the major economy of Nigeria today. The country being a producer and an exporter of these products is having internal challenge of availability of the product periodically due to inappropriate distribution coupled with the incessant increase in pump prices. This challenge has been on for decades. With this background information this research used a set of previous data set obtained from Nigeria National Petroleum Corporation and National Population Census data to develop a predictive model for the distribution of the product with the use of machine learning approach. Python programming tools were used for establishing possible relationship between the data sets before the development and implementation of the model. The developed model was evaluated and the error level was found to be tolerable this research provided a realistic model that can be used for the distribution of the product by the stake holders so as to address this age long challenge.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/67DEVELOPMENT OF AN ANDROID-BASED ATTENDANCE MONITORING SYSTEM2023-08-31T13:59:10+00:00Esan AdebimpeAdebimpe.esan@fuoye.edu.ngSobowale AdedayoAdebimpe.esan@fuoye.edu.ngAjayi SamuelAdebimpe.esan@fuoye.edu.ng<p>The traditional method of taking attendance is not only time consuming but insecure and unreliable, therefore, technology was<br>introduced to attendance management. This research developed an android based attendance management system using ReactNative framework for the frontend and Node JS for the backend. Questionnaires were administered to twenty-five Engineering lecturers and students of a higher institution in Nigeria to determine users’ perception of the developed system based on acceptability and level of satisfaction. Results show that the developed android-based attendance management system is acceptable by the users and they are satisfied with the features incorporated in the system. It is however recommended that future work employ machine learning techniques for attendance management systems’ design.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/68DEVELOPMENT OF AN AUTOMATED TIMETABLE GENERATOR USING GENETIC ALGORITHM2023-08-31T14:08:38+00:00Sobowale AdedayoAdedayo.sobowale@fuoye.edu.ngEsan AdebimpeAdebimpe.esan@fuoye.edu.ngAjayi SamuelAdedayo.sobowale@fuoye.edu.ng<p>Educational timetabling is a major administrative activity for a wide variety of institutions. The process involves scheduling a <br>sequence of lectures between lecturers and students in a prefixed period. However, conventional approach to timetable scheduling is very time consuming, therefore, this research addresses the issue by developing an automated timetable generator using genetic algorithm. The developed system satisfied both hard and soft constraints as well as generate a conflict free timetable with an accuracy of 98.5% and an average response time of 0.176 seconds. The results obtained for functionality, reliability, ease of use, efficiency and portability are: 95%, 65%, 80%, 80% and 85% respectively. The mutation and crossover rates are 0.01% and 0.95% respectively and the fitness value is 1 which shows that the developed timetable generator has zero number of clashes. Although, the developed system has achieved a certain level of accuracy, reliability, functionality and ease of use, however, future work should consider hybridizing GA with more advanced algorithms to obtain better results and reduce processing time.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/69EMPIRICAL ANALYSIS OF FACTORS AFFECTING THE PERFORMANCE OF MINIMUM SPANNING TREE ALGORITHMS USING PRINCIPAL COMPONENT2023-08-31T14:18:19+00:00O. T. Odebunmibusayotola@gmail.comA.O. Olabodeanthony2olabode@gmail.comY.S. Jeremiahteejabar5@gmail.comI.A. Adelekeadeleke_israel@yahoo.comM.O. Lawrencemorolake.lawrence@bazeuniversity.comS. O. Olabiyisi soolabiyisi@lautech.edu.ng<p>The Minimum Spanning Tree (MST) of a graph is the cheapest subset of edges that keeps the graph in one connected component. The significant impact of overall efficiency of a minimum spanning tree is hugely determined by the efficiency of some selected factors such as time taken, memory usage and number of edges visited. However, the level at which each factor affect the performance of the minimum spanning tree is yet to be investigated. The experimentation evaluation was performed on the MST algorithms (Borukva, Kruskal, Prim and Reverse-Delete) by varying the input routes of Lagos State and Federal Capital Territory Road line distances, such that data were generated. Seventy two data samples were obtained from the experiments. The MST algorithms studied were implemented using Java Programming Language. The performance analysis of Borukva, Kruskal, Prim and Reverse-Delete spanning techniques were evaluated based on time taken, memory usage and number of edges visited. Statistical analysis was further performed on the evaluation results using Factor analysis by principal component for the analysis of the generated data. The percentages of variance based on time taken, memory usage and number of edges visited for Borukva were 84.90%, 14.40% and 0.65%, respectively, while the corresponding values for Kruskal were 82.30%, 30.80% and 10.58%, respectively. Also, the percentages of variance based on time taken, memory usage and number of edges visited for Prim were 86.10%, 13.10% and 0.81% respectively, while the corresponding values for Reverse-Delete were 58.70%, 17.50% and 0.13%. The percentage of variance forms the basis for establishing the level of contribution of each factor towards the performance of the MST algorithms. The study revealed that main factor affecting the efficiency of minimum spanning tree algorithm was time taken.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/70DEVELOPMENT OF A MODEL FOR ONLINE STUDENTS COMPLAINT MANAGEMENT SYSTEM. A CASE STUDY OF BOWEN UNIVERSITY NIGERIA2023-08-31T14:45:19+00:00O.N. EmuoyibofarheOzichi.emuoyibofarhe@bowen.edu.ngR.F. Famitimirfamitimi@unimed.edu.ngD.O. Olanloyegbengaoti@rockmail.comO.M. AwoniranOlalekan.awoniran@bowen.edu.ngG.M. Otigbengaoti@bowen.edu.ng<p>Recent experiences show that deficiencies in a University’s complaint management system could have massive costs in time, money and damage to the individual careers and institutional reputations. This work investigated the complaint management system in Bowen University through the use of survey methodology on students to elicit information and evaluate them so as to justify the implementation of better model of the current system. The implemented model is to assist the management of Bowen University in carrying out her complaint management activities. The evaluation of the survey showed that 22 (12.1%) respondents did not prefer E-complain management system while 161 (87.9%) showed preference to an E-complain management system. On the response nature of the manual system, 8 (6.3%) confirmed that it was very fast, 18(14.1% syndicated that it was fast, 100 (78.1%) maintained it was slow while 2 (1.6%) indicated that they never used the system. The result of the evaluation of the current manual system necessitated the implementation of an online complaint management model for the University. The model was implemented using Hypertext Preprocessor (PHP), AJAX, JavaScript, Cascading Style Sheets (CSS) and Hypertext Markup Language (HTML) and MySQL. The implemented system will positively affect the management of students’ complaints if implemented.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/71RESOURCE ALLOCATION IN CLOUD COMPUTING USING A GENERALIZED KNAPSACK ALGORITHM2023-08-31T14:56:44+00:00Dayo Reuben Aremudraremu2006@gmail.comAbiodun K. Mosesabbeykmos@yahoo.comS.A. Oluwasogosamueloluwasogo@yahoo.com<p>Efficient allocation of resources in order to achieve optimal performance and cost-effectiveness is a critical challenge in cloud <br>computing. This paper presents the Generalized Knapsack Algorithm (GKA) in order to address the resource allocation problem in <br>cloud environments. The GKA aims to maximize the utilization of computing resources, memory, and bandwidth while considering <br>various constraints. The paper presents a comprehensive analysis of the GKA's performance using both simulated experiments and real-world cloud datasets. Results demonstrate that the GKA outperforms existing resource allocation methods in terms of efficiency and scalability. The proposed approach provides a promising solution for enhancing resource allocation strategies in cloud computing, enabling better resource utilization and improved service delivery for cloud users. The study contributes to the advancement of cloud computing optimization and has practical implications for cloud service providers and users, fostering more effective resource management in cloud environments.</p>2023-08-31T00:00:00+00:00Copyright (c) 2023 LAUJCIhttp://laujci.lautech.edu.ng/index.php/laujci/article/view/72SPAM EMAIL DETECTION SCHEME BASED ON RANDOM FOREST ALGORITHM2023-08-31T15:09:54+00:00A.M. Oyelakinamoyelakin@alhikim.edu.ngIbrahim T.T. Salau ttsalau@alhikim.edu.ngB.S. Ogidanbolaji.gidan@alhikim.edu.ngH.I. Olufadibolaji.gidan@alhikim.edu.ngS.A. Yusufamoyelakin@alhikim.gmail.com.ngI.A. Adeinjiherdeyni@gmail.com<p>Emails are used for communication purposes in different sectors of the economy such as education, health, businesses, manufacturing, agriculture. People with malicious intent have been using emails accounts for different spam email attacks. Spam email refers to as unsolicited bulk email. It is the practice of sending large frequent, unwanted e-mail messages with commercial content to indiscriminate set of recipients. Spam emails expose users to challenges such as time wastage, high usage of computing resources and stealing of valuable information. Machine learning approaches have been widely accepted to be better than traditional approaches for the identification of spam emails. For this reason, several machine learning techniques have been proposed in the literature for the classification of spams in emails. This paper proposed a Random Forest-based scheme for email spam detection. A fairly large spam email dataset named spam base was collected from UCI machine learning repository. The dataset was pre-processed based on the feature encoding. Then, promising features were selected using feature importance technique. The feature selection yielded 12-feature subsets that were arrived at based on the feature scores. The Random Forest (RF) spam email detection model that was built achieved 99.65% Accuracy, 99.21% Precision, 99.46% of Recall and F1-score of 99.33%. The study concluded that the RF-based spam email detection model performed better than some of the approaches in similar studies.</p>2023-08-01T00:00:00+00:00Copyright (c) 2023 LAUJCI