Department Of Computer Science

Permanent URI for this community

https://ir.unilag.edu.ng/handle/123456789/3381
The overall philosophy of Computer Sciences degree programmes in the Faculty of Science is to produce graduates with fully integrated science knowledge so that they can have a sound background required to fully understand the theoretical base of Computer Science.

Browse

Browsing Department Of Computer Science by Title

Now showing 1 - 20 of 97
  • Item
    Open Access
    A 3-D MODEL OF AN INSTITUTIONAL LOCATION NAVIGATION SYSTEM (NAVILOC) (A CASE STUDY OF COVENANT UNIVERSITY)
    (International Journal of Civil Engineering and Technology, 2019-01) Adebiyi, Marion; Oladeji, Florence; Onyido, Solomon; Ori, Daniel; Ogundokun, Roseline; Adeniyi, Emmanuel; Okesola, Olatunji
    Covenant University location navigation system (CU Naviloc) built on the Android platform is a mobile based system which can be easily accessed from an android mobile device across any location, downloadable on Google play store and deployable anywhere in the world. In this study,Computer-aided design as well as building Information modelling (CAD/BIM) system applications were introduced to the simulation of Covenant University, a smart and compact campus whose edifice elaborates the need for the development of a three dimensional (3D) virtual model of locations as an advancement over the existing 2D model representation of maps on the Google map and Google Earth platform. Therefore, this research work outlays the development of three dimensional models (CU NAViLoc Model) for details of information at Covenant University as well as the requirements for its development and implementation for cooperate representation of the institution. A three dimensional map of CU was packaged into a location navigation system and was implemented using Unreal Engine, Trimble SketchUp and Revit to effect a user friendly, smarter and multi-dimensional viewable user interface. CU Naviloc explore the advantage of the rich benefits of building information models and geographic information systems to build a free-roam navigator, based on a well-updated model of Covenant University location map. The benefits of this system is not limited to 3D capability, real time similarity, portability, no downtime on access, and progressive scalability with zero or little loss of data. The usage of the CU Naviloc system requires free download and installation of the app and internet presence.
  • Item
    Open Access
    Access Control Model for E-Health in a Cloud-Based Environment for HIV Patients in South Africa
    (IEEE, 2018) Azeez, N; Vyver, C.V
    Information about the rampant nature of Human Immunodeficiency Virus (HIV) in Africa, particularly South Africa is no more a news. There is a global awareness on this. In spite of the ubiquitous nature of this ailment, patients feel highly uncomfortable with the way and manner their sensitive and classified health information are being accessed and shared by different healthcare practitioners. HIV patients opined that information about them are vulnerable that people are using it against them. Although, the traditional security mechanisms have been adopted over the years to protect health data and patient information, researches have however shown that some of these approaches are suffering from several challenges such as platform dependency, isolation, cumbersomeness as well as inflexibility. Against these backdrops, this research aims at building a cloud-based access control model for sharing information across nine (9) provinces (The Eastern Cape, The Free State, Gauteng, KwaZulu-Natal, Limpopo, Mpumalanga, The Northern Cape, North West) in the Republic of South Africa among medical experts to ensure safety, security, reliability, dependability as well as flexile information sharing framework. This work is based on the adoption and usage of Role Based Access Control (RBAC) model, Access Control List (ACL) model and Motive Based Access Control (MBAC) model in a cloud-based environment. The implementation of the proposed framework will undoubtedly provide a unique and novel approach for achieving its primary aim and objectives.
  • Item
    Open Access
    Access Control Model for E-Health in a Cloud-Based Environment for HIV Patients in South Africa
    (IEEE, 2018) Azeez, N
    Information about the rampant nature of Human Immunodeficiency Virus (HIV) in Africa, particularly South Africa is no more a news. There is a global awareness on this. In spite of the ubiquitous nature of this ailment, patients feel highly uncomfortable with the way and manner their sensitive and classified health information are being accessed and shared by different healthcare practitioners. HIV patients opined that information about them are vulnerable that people are using it against them. Although, the traditional security mechanisms have been adopted over the years to protect health data and patient information, researches have however shown that some of these approaches are suffering from several challenges such as platform dependency, isolation, cumbersomeness as well as inflexibility. Against these backdrops, this research aims at building a cloud-based access control model for sharing information across nine (9) provinces (The Eastern Cape, The Free State, KwaZulu-Natal, Limpopo, Mpumalanga, The Northern Cape, North West) in the Republic of South Africa among medical experts to ensure safety, security, reliability, dependability as well as flexile information sharing framework. This work is based on the adoption and usage of Role Based Access Control (RBAC) model, Access Control List (ACL) model and Motive Based Access Control (MBAC) model in a cloud-based environment. The implementation of the proposed framework will undoubtedly provide a unique and novel approach for achieving its primary aim and objectives.
  • Item
    Open Access
    AI-Powered Plagiarism Detection: Leveraging Forensic Linguistics And Natural Language Processing
    (FUDMA Journal of Sciences, 2021) Nwohiri, Anthony; Joda, Opemipo; Ajayi, Olasupo
    Plagiarism of material from the Internet is nothing new to academia and it is particularly rampant. This challenge can range from borrowing a particularly apt phrase without attribution, to paraphrasing someone else’s original idea without citation, to wholesale contract cheating. Plagiarized content can infringe on copyright laws and could incur hefty fines on publishers and authors. Unintentional plagiarism mostly occurs due to inaccurate citation. Most plagiarism checkers ignore this fact. Moreover, plagiarizers are increasingly becoming negatively “smarter”. All these necessitate a plagiarism detector that would efficiently handle the challenges. Several plagiarism detectors have been developed but each with its own peculiar limitations. This paper aims at developing an AI-driven plagiarism detector that can crawl the web to index articles and documents, generate similarity score between two local documents, train users on how to properly format in-text citations, identify source code plagiarism and use natural language processing and forensic linguistics to properly analyse plagiarism index.
  • Item
    Open Access
    Analysis of Nigerian Stock Market Returns Volatility Using Skewed ARMA-GARCH Model
    (Journal of Nigerian Statistical Association, 2013) Adewole, A. P.; Isenah, M.G; Agwuegbo, S.O
    This study used ARMA-GARCH type volatility models for predicting future values of the Nigerian stock market's percentage nominal returns and volatility. The data used in the study are time series data of the monthly Nigerian Stock Exchange All-Share-Index for the period of January 1990 to December 2012. The data was further segmented into in-sample and out-sample data sets for model building and out-of-sample forecast comparisons. Three ARMA(1,2)-GARCH(1, 1) models with skewed normal distribution (SNORM), skewed Student-t distribution (SSTD) and skewed generalized error distribution (SGED) were fitted. In-sample model selections were based on the Akaike Information Criterion (AIC), Bayes Information Criterion ( BIC), Schwarz Information Criterion ( SIC) and the Hannan - Quinn Information Criterion ( HQIC), while out-sample forecast evaluations were based on the Forecast Root Mean Square Error (FRMSE) and Forecast Mean Absolute Error (FMAE) metrics. The results of the study revealed the asymmetry) inherent in the stock market returns distribution with kurtosis that exceeds that of normal distribution. The ARMA (1,2)-GARCH (1,1) model with skewed normal error distribution slightly outperformed the other models in the out-sample forecast evaluations, but for short-run forecasts the three models are quite adequate.
  • Item
    Open Access
    ANALYSIS OF TWO-PHASED APPROACHES TO LOAD BALANCING IN CLOUD COMPUTING
    (IEEE, 2015) Ajayi, O.O.; Oladeji, F.A.; Uwadia, C.O.
    Cloud computing is an emerging trend in computing whereby computing resources are offered as a service to users. Providing resources to an increasing number of users and managing these resources is a major challenge in Cloud Computing. Numerous researchers have proposed diverse ways of addressing these issues, either with the aim of effectively allocating user workload to resources or redistribution / load balancing of workloads amongst resources for improved utilization. These approaches have broadly been categorized into single phased load balancing. In alternate works, authors have proposed a combination of these single phased approaches, such that allocation of workload is done in the first phase and an improvement on the allocation done in the second phase. This combined approach is referred to as the two-phased approaches to load balancing. This paper therefore analyses the various state-of-the-arts two-phased approaches to load balancing in cloud computing.
  • Item
    Open Access
    ANCAEE: A Novel Clustering Algorithm for Energy Efficiency in Wireless Sensor Networks
    (Wireless Sensor Network, 2011) AZEEZ, Nureni
    One of the major constraints of wireless sensor networks is limited energy available to sensor nodes because of the small size of the batteries they use as source of power. Clustering is one of the routing techniques that have been using to minimize sensor nodes’ energy consumption during operation. In this paper, A Novel Clustering Algorithm for Energy Efficiency in Wireless Sensor Networks (ANCAEE) has been proposed. The algorithm achieves good performance in terms of minimizing energy consumption during data transmis-sion and energy consumptions are distributed uniformly among all nodes. ANCAEE uses a new method of clusters formation and election of cluster heads. The algorithm ensures that a node transmits its data to the cluster head with a single hop transmission and cluster heads forward their data to the base station with multi-hop transmissions. Simulation results show that our approach consumes less energy and effectively extends network utilization.
  • Item
    Open Access
    Artificial Neural Network Model for Forecasting Foreign Exchange Rate
    (World of Computer Science and Information Technology Journal, 2011) Adewole, Adetunji Philip; Akinwale, Adio Taofiki; Akintomide, Ayo Bidemi
    The present statistical models used for forecasting cannot effectively handle uncertainty and instability nature of foreign exchange data. In this work, an artificial neural network foreign exchange rate forecasting model (AFERFM) was designed for foreign exchange rate forecasting to correct some of these problems. The design was divided into two phases, namely: training and forecasting. In the training phase, back propagation algorithm was used to train the foreign exchange rates and learn how to approximate input. Sigmoid Activation Function (SAF) was used to transform the input into a standard range [0, 1]. The learning weights were randomly assigned in the range [-0.1, 0.1] to obtain the output consistent with the training. SAF was depicted using a hyperbolic tangent in order to increase the learning rate and make learning efficient. Feed forward Network was used to improve the efficiency of the back propagation. Multilayer Perceptron Network was designed for forecasting. The datasets from oanda website were used as input in the back propagation for the evaluation and forecasting of foreign exchange rates. The design was implemented using matlab7.6 and visual studio because of their supports for implementing forecasting system. The system was tested using mean square error and standard deviation with learning rate of 0.10, an input layer, 3 hidden layers and an output layer. The best known related work, Hidden Markov foreign exchange rate forecasting model (HFERFM) showed an accuracy of 69.9% as against 81.2% accuracy of AFERFM. This shows that the new approach provided an improved technique for carrying out foreign exchange rate forecasting.
  • Item
    Open Access
    Artificial neural network-based learning analytics technique for employability and self-sustenance
    (The journal of computer science and its applications, 2018-12) Adewole, P.; Okewu, E.
    The growing global rate of unemployment buttresses the quest for functional and all-inclusive education as canvassed by the Sustainable Development Goal 4 (SDG 4). Employability of graduates and entrepreneurial skills for self-sustenance can be fostered through Learning Analytics (LA) - a pedagogical paradigm that inculcates data analytics and team work skills in learners. LA measures the learning process by collecting learning-related data, analyzing same, and reporting trends to stakeholders for adaptive learning solutions that improve learning experience and learning outcomes. Though there are many data science techniques for enhancing LA, artificial neural network stands out as a highly predictive data mining tool and machine learning technique. An Artificial Neural Network-based Learning Analytics (ANN-based LA) system uses regression analysis, pattern recognition, and predictive analytics to elicit robust information from learner’s data for informed decision making by education stakeholders. However, there are open issues confronting ANN-based LA systems such as system quality issues, prolonged time of training neural network, and the huge memory space requirements. This paper proposes an n-tier layered software architecture for tackling the quality indicator concerns while hoping that upcoming researchers will resolve the others. This way, ANN-based LA will be repositioned for delivering functional education that promotes graduate employment through the impartation of industry-relevant skills like data analytics and team work.
  • Item
    Open Access
    Asymmetric Model for Modeling Skewed Data
    (Nasarawa State University, Keffi, 2023-07) Badmus, N.I; Ogundeji, R.K; Olufolabo, O.O
    In this article, we present a new asymmetric distribution called Topp-Leone modified Weighted Rayleigh (TLMWR) distribution from Topp-Leone distribution. We study and examine several properties of the propose distribution such as density, distribution, reliability, hazard rate function, moment, generating function, quantile function and order statistics. The estimation of model parameters is obtain using method of maximum likelihood estimates. Exploratory data analysis, diagnostic test, normality test and goodness of fit statistics are carry out on the data used for the direction of skewness andlevel of kurtosis. The fitness and effectiveness of the proposed distribution is tested using both simulation and real data set to compare with other existing and new distributions. Therefore, we conclude based on the results from the analysis and supported the validity of the proposed model than other distributions considered.
  • Item
    Open Access
    A Cloud-Based Access Regulatory Model for the People Living with HIV in South Africa
    (International Journal of Information Security, Privacy and Digital Forensics, 2020-06-13) Azeez, N.; Van der Vyver, C.; Yekinni, W.A.
    Information about the rampant nature of Human Immunodeficiency Virus (HIV) in Africa, particularly South Africa is no more a news. There is a global awareness on this. In spite of the ubiquitous nature of this ailment, patients feel highly uncomfortable with the way and manner their sensitive and classified health information are being accessed and shared by different healthcare practitioners. HIV patients opined that information about them are vulnerable that people are using it against them. Although, the traditional security mechanisms have been adopted over the years to protect health data and patient information, researches have however shown that some of these approaches are suffering from several challenges such as platform dependency, isolation, cumbersomeness as well as inflexibility. Against these backdrops, this research aims at building a cloud-based access control model for sharing information across nine (9) provinces (The Eastern Cape, The Free State, Gauteng, KwaZulu-Natal, Limpopo, Mpumalanga, The Northern Cape, North West) in the Republic of South Africa among medical experts to ensure safety, security, reliability, dependability as well as flexile information sharing framework. This work is based on the adoption and usage of Role Based Access Control (RBAC) model, Access Control List (ACL) model and Motive Based Access Control (MBAC) model in a cloud-based environment. The implementation of the proposed framework will undoubtedly provide a unique and novel approach for achieving its primary aim and objectives.
  • Item
    Open Access
    Clustering of large dataset using adaptive resonance theory 2 (Art 2)
    (Lautech Journal of engineering and Technology, 2014) Adewole, A.P.; Amuda, T.J.
    Each and every day we generate a vast amount of data from cloud, mobile and social technology, consequently, there is a need to make sense out of this data. However, mining of big data comes with its own problem the major problem being the difficulty in detecting patterns in evolving data. Clustering techniques can lead us to discover hidden information in these evolving data. Traditional data clustering models such as K-means do not scale well on large data set and are dependent on assumptions regarding cluster statistical properties (ie. Number of clusters, cluster shape), while unsupervised ANN algorithms (Adaptive Resonance Theory – ART networks) are recognized widely by their ability to discover hidden patterns, adapt to evolving large data and robustness to noise. Consequently, in this paper, Adaptive Resonance Theory 2(ART2) was used to address the problem of clustering large data set using a sensor stream data for the clustering experiments. The data was categorized into 40 categories or clusters close to the 54 class of the data with initial parameters of vigilance parameter = 0.9. The vigilance parameter was varied to study the evolution of the number of categories. The pattern match (clusters) gets finer when the vigilance parameter is closer to 1 and coarser when it is away from 1. The study revealed that the closer the value of the vigilance parameter to 1, the more number of clusters (categories) produced and the farther the value of the vigilance parameter the less the number of clusters.
  • Item
    Open Access
  • Item
    Open Access
    Communication of Scientists through Scientific Publications: Math-Net.Ru as a Case Study.
    (CEUR Workshop Proceedings, 2020-09) Pechnikov, Andrey; Chebukov, Dmitry; Nwohiri, Anthony
    We present a study of two scientific collaboration graphs built using data drawn from Math-Net.Ru, an all-Russian mathematical portal. One of the graphs is a citation-based scientific collaboration graph. It is an oriented graph with no loops and multiple edges. Its vertices denote authors of papers, while the arcs connecting these vertices denote that the first author has, in at least one of his papers, cited the work of the second author. The second graph is a coauthor- ship-based graph. It is a non-oriented graph, where the vertices denote authors, while edges connecting two vertices indicates that the two authors have coauthored at least a paper. We conduct a traditional study of the main characteristics of both graphs, such as degrees of vertices, influence of vertices, diameter, mean distance, connected components and clustering. Both graphs are found to have a similar connectivity structure – both have a giant component and several small components. Using the two graphs, we split the set of Math-Net.Ru authors. In this set, it was revealed that more than 40% of authors who have co-authored a paper with someone have not ever cited their co-authors. This means there is no deliberate plan to cite each other’s work in the journals registered in Math-Net.Ru.
  • Item
    Open Access
    Comparative analysis of text categorization algorithms
    (The journal of computer science and its applications, Nigeria computer society, 2017) Adewole, A.P.; Omitiran, D.M.
    Text categorization (also known as text classification) is the task of automatically assigning documents to a category (or categories) from a pre-specified set. This task has several applications, including spam filtering, identification of document genre, automated indexing of scientific articles according to a predefined thesauri of technical terms, and even the automated extraction of metadata. The importance of text categorization cannot be overemphasized due to the fact that unstructured texts are the largest readily available source of data and manual organization of this data is infeasible due to the large number of documents involved as well as time constraints. The accuracy of modern text categorization machines rivals that of trained human professionals. This study experimentally compared four machine learning classifiers used in text categorization. These algorithms are; Naïve Bayes, Decision trees, k-Nearest Neighbour (kNN) and Support Vector Machines (SVM). These classifiers were developed using Python programming language. When run on the Reuters dataset, SVM significantly outperforms Naïve Bayes, kNN and Decision Trees. Decision trees performed worst of the four algorithms considered in this study. From observations made during the course of running these experiments, there seems to be a trade- off between simplicity and effectiveness. In conclusion, the results of this comparative analysis prove that SVM is the most effective of the classifiers considered in this study.
  • Item
    Open Access
    Comparative Analysis of the Performance of Selected Learning Algorithms for Verification of vulnerable and Compromised Uniform Resource Locators (URLs)
    (Int. Sci. Technol. J. Namibia, 2018) Azeez, N.A; Ajayi, A.D; Yinka-Banjo, C.O
    The fact that cybercriminals have caused serious havoc and unprecedented financial loss through internet activities is well acknowledged by internet users across the globe. Different nefarious activities of the internet fraudsters have undoubtedly resulted in monumental loss of life and property of immeasurable values. From available literatures, many people have become victims of their handiworks by giving feedback to fake and phony Uniform Resource Locators (URLs) sent to their electronic mails. In the recent works by researchers in the area of cybersecurity, it has been established that machine learning approaches have been proposed to identify various compromised and fake URLs in order to safeguard internet users from becoming victim. Consequently, discrepancies noted in some the available results give room for doubt and reliability of the results obtained in their experimentations. In an attempt, however to protect internet users from experiencing further loss and to establish the performances of these algorithms, the authors carried out a comparative analysis of three learning algorithms (Na¨ıve Bayes, Decision Tree and Logistics Regression Model) for verification of compromised, phony and fake URLs and determined which is the best of all the three based on the metrics (F-Measure, Precision and Recall) used for evaluation. After the experimentation, it was finally observed that the decision tree provides optimal and efficient solution of all the tree algorithms with full and absolute F-Measure when 0.6 is considered as boundary. With optimal solution provided by the decision tree, internet users can be given reliable information and consequently be guarded against further attacks.
  • Item
    Open Access
    Comparative Evaluation of Available Bandwidth Estimation Tools (PRTG and OAUENTMON) in a Campus-Wide Area Network.
    (The Pacific Journal of Science and Technology, Akamai University, USA, 2009) AZEEZ, Nureni
    In recent years, there has been a strong interest in measuring the available bandwidth of network paths. Several methods and techniques have been proposed and various measurement tools have been developed and evaluated. However, there have been few comparative studies with regard to the actual performance of these tools. This project presents a study of available bandwidth measurement techniques for both PRTG and OAUNETMON and undertakes a comparative analysis in terms of accuracy, intrusiveness and response time of active probing tools. Finally, measurement errors and uncertainty of the tools are analyzed and overall conclusions were made.
  • Item
    Open Access
    Comparative Evaluation of Machine Learning Algorithms for Network Intrusion Detection Using Weka
    (Springer, 2018) Azeez, N
    For the past few years, it has been seen that the computer intrusion attacks are becoming more sophisticated, and the volume, velocity, and variance of traffic data have greatly increased. Because the conventional methods and tools have become impotent in the detection of intrusion attacks, most intrusion detection systems now embrace the use of machine learning tools and algorithms for efficiency. This is because of their ability to process large volume, velocity, and very high variance data. This work reviews and analyzes the performance of three out of the most commonly used machine learning algorithms in network intrusion. In this work, the performance of Naïve Bayes, decision tree, and random forest algorithms were evaluated as they were being trained and tested with the KDD CUP 1999 dataset from DARPA using a big data and machine learning tool called Weka. These classification algorithms are evaluated based on their precision, sensitivity, and accuracy.
  • Item
    Open Access
    A Comparative Study of Simulated Annealing and Genetic Algorithm for Solving the Travelling Salesman Problem
    (International Journal of Applied Information Systems (IJAIS), 2012-10) Otubamowo, K.; Egunjobi, T.O.; Adewole, A.P.
    Metaheuristic algorithms have proved to be good solvers for the traveling salesman problem (TSP). All metaheuristics usually encounter problems on which they perform poorly so the programmer must gain experience on which optimizers work well in different classes of problems. However due to the unique functionality of each type of meta-heuristic, comparison of metaheuristics is in many ways more difficult than other algorithmic comparisons. In this paper, solution to the traveling salesman problem was implemented using genetic algorithm and simulated annealing. These algorithms were compared based on performance and results using several benchmarks. It was observed that Simulated Annealing runs faster than Genetic Algorithm and runtime of Genetic Algorithm increases exponentially with number of cities. However, in terms of solution quality Genetic Algorithm is better than Simulated Annealing.
  • Item
    Open Access
    COMPARISON OF NEURAL NETWORK AND MULTIVARIATE DISCRIMINANT ANALYSIS IN SELECTING NEW COWPEA VARIETY
    (International Journal of Computer Science and Information Security (IJCSIS), 2010-07) Adewole, Adetunji Philip; Sofoluwe, A. B.; Agwuegbo, Samuel Obi-Nnamdi
    In this study, neural networks (NN) algorithm and multivariate discriminant (MDA) based model were developed to classify ten (10) varieties of cowpea which were widely planted in Kano. . In order to demonstrate the validity of our model, we use the case study to build a neural network model using Multilayer Feedforward Neural Network, and compare its classification performance against the Multivariate discriminant analysis. Two groups of data (Spray and Nospray) were used. Twenty kernels were used as training data set and test data to classify cowpea seed varieties. The neural network classified the new cowpea seed varieties based on the information it is trained with. At the end both methods were compared for their strength and weakness. It is noted that NN performed better than MDA, so that NN could be considered as a support tool in the process of selection of new cowpea varieties.