Browsing by Author "Oladele, Tinuke Omolewa"

Now showing 1 - 20 of 30
  • Item
    ADABOOST Ensemble Algorithms for Breast Cancer Classification
    (Journal of Advances in Computer Research, 2019) Hambali, A. H.; Yakub, K. S.; Oladele, Tinuke Omolewa; Gbolagade, M. D.
    With advances in technologies, different tumor features have been collected for Breast Cancer (BC) diagnosis. The process of dealing with large data set suffers some challenges which include high storage capacity and time required for accessing and processing. The objective of this paper is to classify BC based on the extracted tumor features and to develop an ADABOOST ensemble Model to extract useful information and diagnose the tumor. In this research work, both homogeneous and heterogeneous ensemble classifiers (combining two different classifiers together) were implemented, and Synthetic Minority Over-Sampling Technique (SMOTE) data mining pre-processing is used to deal with the class imbalance problem and noise in the dataset. In this paper, the proposed method involve two steps. The first step employs SMOTE to reduce the effect of data imbalance in the dataset. The second step involves classifying using decision algorithms (ADTree, CART, REPTree and Random Forest), Naïve Bayes and their Ensembles. The experiment was implemented on WEKA Explore (Weka 3.6). Experimental results show that ADABOOST-Random forest classifies better than other classification algorithms with 82.52% accuracy, followed by Random Forest- CART with 72.73% accuracy while Naïve Bayes classification is the lowest with 35.70% accuracy.
  • Item
    Application of Data Mining Algorithms for Feature Selection and Prediction of Diabetic Retinopathy
    (Computational Science and Its Applications – ICCSA 2019, 2019) Oladele, Tinuke Omolewa; Ogundokun, R. O.; Kayode, A. A.; Adegun, A. A.; Adebiyi, M. O.
    Diabetes Retinopathy is a disease which results from a prolonged case of diabetes mellitus and it is the most common cause of loss of vision in man. Data mining algorithms are used in medical and computer fields to find effective ways of forecasting a particular disease. This research was aimed at determining the effect of using feature selection in predicting Diabetes Retinopathy. The dataset used for this study was gotten from diabetes retinopathy Debrecen dataset from the University of California in a form suitable for mining. Feature selection was executed on diabetes retinopathy data then the Imple mentation of k-Nearest Neighbour, C4.5 decision tree, Multi-layer Perceptron (MLP) and Support Vector Machines was conducted on diabetes retinopathy data with and without feature selection. There was access to the algorithms in terms of accuracy and sensitivity. It is observed from the results that, making use of feature selection on algorithms increases the accuracy as well as the sensitivity of the algorithms considered and it is mostly reflected in the support vector machine algorithm. Making use of feature selection for classification also increases the time taken for the prediction of diabetes retinopathy.
  • Item
    Archival System for Projects Using Association Approach
    (International Journal of Information Processing and Communication (IJIPC), 2017) Oladele, Tinuke Omolewa; Ojeh, A.; Afolayan, I.
  • Item
    Coactive Neuro-Fuzzy Expert System: A Framework for Diagnosis of Malaria
    (African Journal of Computing & ICTs (AJOCICT), 2014) Oladele, Tinuke Omolewa; Sadiku, J. S.; Oladele, R. O.;
  • Item
    Comparative Analysis of Association Rule Mining Techniques for Monitoring Behavioural Patterns of Customers in a Grocery Store
    (African Journal of Computing & ICTs (AJOCICT), 2015) Adeniji, I. A.; Saheed, Y. K.; Oladele, Tinuke Omolewa; Braimah, J. O.
    The amount of data being generated and stored is growing exponentially, due to the continuing advances in computer technology. This presents tremendous opportunities for those who can unlock the information embedded within this data, but also introduces new challenges. The primary challenge is how to discover the hidden knowledge or pattern from the large sets of data in order to be able to make intelligent decisions that would shape the future of the store and also to determine the best tool to use in mining. This study proposed to use two different algorithms in association rule mining. The main motivation for carrying out this study is to compare the two algorithms and determine the time complexity of the two algorithms in mining association rules. In this paper, association rule techniques were compared and analyzed for monitoring behavioural pattern of customers in a grocery store. The FP-growth Algorithm and Apriori Algorithm were applied on sixty three (63) datasets from a grocery store. The time complexity of the two algorithms were considered and it was observed that FP-growth Algorithm is more efficient within the resource constraints than Apriori Algorithm. The comparison and analysis were implemented using Weka tool. The results revealed that FP-growth Algorithm is currently one of the fastest approaches for frequent data item set mining.
  • Item
    Concept of strings and Trees in Bioinformatics
    (ABACUS. Published by Mathematics Association of Nigeria., 2008) Oladele, Tinuke Omolewa; Bamigbola, O. M.; Gbadeyan, J. A.
    Strings have been found to be the most general medium for the representation of information. Considering the large amount of data stored in data dictionaries, databases or the massive data in genomic databases, text remains the main form of exchanging information. The representation of information from real-world problem may involve the use of many interlinked data structures. In this paper, the suffix tree data structure was used to solve the Pattern Matching problem. We present the suffix tree as an efficient data structure that provides efficient access to all substrings of a string. It is able to rapidly align sequences containing millions of nucleotides and give sufficient biological information.
  • Item
    Development of an inventory management system using association rule
    (Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), 2021) Oladele, Tinuke Omolewa; Ogundokun, R. O.; Adegun, A. A.; Adeniyi, A. E.; Ajanaku, A. T.
    Stores today still make use of manual approaches to keeping inventory which could be cumbersome. Having a computerized inventory system would make inventory management more efficient and effective. In this chapter, an Inventory Management System using Association Rule was developed which will ensure proper record keeping and keep items in stocks updated. ANGULARJS, a JavaScript framework, was used for the implementation of the system, PHP (hypertext pre-processor) was used for the backend of the system development as well as the database management, HTML was used alongside CSS for the system interface design and NoSQL database was the database used for this research. In conclusion, a computerized inventory system that had been improved using the association rule method was the resulting product useful for creating transactions, updating items in stock, record keeping, generating reports for decision making, and lastly, the system will make the stores more effective.
  • Item
    Diagmal: A Malaria Coactive Neuro-Fuzzy Expert System
    (Computational Science and Its Applications – ICCSA 2020, 2020) Oladele, Tinuke Omolewa; Ogundokun, R. O.; Awotunde, J. B.; Adebiyi, M. O.; Adeniyi, J. K.
    In the process of clarifying whether a patient or patients is suffering from a disease or not, diagnosis plays a significant role. The procedure is quite slow and cumbersome, and some patients may not be able to pursue the final test results and diagnosis. The method in this paper comprises many fact-finding and data-mining methods. Artificial Intelligence techniques such as Neural Networks and Fuzzy Logic were fussed together in emerging the Coactive Neuro-Fuzzy Expert System diagnostic tool. The authors conducted oral interviews with the medical practitioners whose knowledge were captured into the knowledge based of the Fuzzy Expert System. Neuro-Fuzzy expert system diagnostic software was implemented with Microsoft Visual C# (C Sharp) programming language and Microsoft SQL Server 2012 to manage the database. Questionnaires were administered to the patients and filled by the medical practitioners on behalf of the patients to capture the prevailing symptoms. The study demonstrated the practical application of neuro-fuzzy method in diagnosis of malaria. The hybrid learning rule has greatly enhanced the proposed system performance when compared with existing systems where only the back-propagation learning rule were used for implementation. It was concluded that the diagnostic expert system developed is as accurate as that of the medical experts in decision making. DIAGMAL is hereby recommended to medical practitioners as a diagnostic tool for malaria.
  • Item
    Discriminating Features for Characterization of Human Skin
    (Nigeria Computer Society, 2018) Emmanuel, J. A.; Akinola, K. G.; Oladele, Tinuke Omolewa
  • Item
    Drug Target Selection for Malaria: Molecular Basis for the Drug Discovery Process
    (Centrepoint Journal (Science Edition), 2012) Oladele, Tinuke Omolewa; Bewaji, C. O.; Sadiku, J. S.
  • Item
    An Empirical Investigation of the Prevalence of Osteoarthritis in South West Nigeria: A Population- Based Study
    (International Journal of Online and Biomedical Engineering (iJOE), 2020) Kayode, A. A.; Akande, N. O.; Jabaru, S. O.; Oladele, Tinuke Omolewa
    Today, Osteoarthritis remains the most prevalent chronic joint disease and a potentially incapacitating joint illness. It is an enduring health problem which cannot be cure though it can be managed. Osteoarthritis remains a serious public health problem because its burden is high, people who live with it have a greater risk of developing anxiety / or depression and if it is not properly managed, it can bring about disability as well as impairing quality of life. This paper presents a statistical correlation between the reported risk factors of Osteoarthritis and its prevalence in Nigeria. Statistical tests were performed to investigate if there is enough evidence for inferring that the risk factors for Osteoarthritis are true for the whole of Nigerian population.
  • Item
    Explainable artificial intelligence (XAI) in medical decision systems (MDSSs): healthcare systems perspective
    (The Institute of Engineering Technology (IET), 2022) Ayoade, O. B.; Oladele, Tinuke Omolewa; Imoize, A. L.; Awotunde, J. B.; Adeloye, A. J.; Olorunyomi, S. O.; Idowu, A. O.
    The healthcare sector is very interested in machine learning (ML) and artificial intelligence (AI). Nevertheless, applying AI applications in scientific contexts is difficult due to explainability issues. Explainable AI (XAI) has been studied as a potential remedy for the problems with current AI methods. The usage of ML with XAI may be capable of both explaining models and making judgments, in contrast to AI techniques like deep learning. Computer applications called medical decision support systems (MDSS) affect the decisions doctors make regarding certain patients at a specific moment. MDSS has played a crucial role in systems’ attempts to improve patient safety and the standard of care, particularly for noncommunicable illnesses. They have moreover been a crucial prerequisite for effectively utilizing electronic healthcare (EHRs) data. This chapter offers a broad overview of the application of XAI in MDSS toward various infectious diseases, summarizes recent research on the use and effects of MDSS in healthcare with regard to non-communicable diseases, and offers suggestions for users to keep in mind as these systems are incorporated into healthcare systems and utilized outside of contexts for research and development.
  • Item
    Feature selection and computational optimization in high-dimensional microarray cancer datasets via InfoGain-modified bat algorithm
    (Multimedia Tools and Applications, 2022) Hambali, M. A.; Oladele, Tinuke Omolewa; Adewole, K. S.; Sangaiah, A. K.; Gao, W.
    Achieving a satisfactory cancer classification accuracy with the complete set of genes remains a great challenge, due to the high dimensions, small sample size, and presence of noise in gene expression data. Feature reduction is critical and sensitive in the classification task, most importantly in heterogeneous multimedia data. One of the major drawbacks in cancer study is recognizing informative genes from thousands of available genes in microarray data. Traditional feature selection algorithms have failed to scale on large space data like microarray data. Therefore, an effective feature selection algorithm is required to explore the most significant subset of genes by removing non-predictive genes from the dataset without compromising the accuracy of the classification algorithm. The study proposed an information Gain – Modified Bat Algorithm (InfoGain-MBA) features selection model for selecting relevant and informative features from high dimensional Microarray cancer datasets and evaluate the approach with four classifiers - C4.5, Decision Tree, Random Forest and classification and regression tree (CART). The results obtained show that the proposed approach is promising for the classification of microarray cancer data. The random forest has 100% accuracy with few genes in all seven datasets used. Further investigations were also conducted to determine the optimal threshold for each of the datasets.
  • Item
    Forged Signature Detection Using Artificial Neural Network
    (African Journal of Computing & ICTs (AJOCICT), 2014) Oladele, Tinuke Omolewa; Adewole, K. S.; Abiodun, T. N.; Oyelami, A. O.
  • Item
    Hand geometry recognition: an approach for closed and separated fingers
    (International Journal of Electrical and Computer Engineering (IJECE), 2022) Adeniyi, J. K.; Oladele, Tinuke Omolewa; Akande, O. N.; Adeniyi, T. T.
    Hand geometry has been a biometric trait that has attracted attention from several researchers. This stems from the fact that it is less intrusive and could be captured without contact with the acquisition device. Its application ranges from forensic examination to basic authentication use. However, restrictions in hand placement have proven to be one of its challenges. Users are either instructed to keep their fingers separate or closed during capture. Hence, this paper presents an approach to hand geometry using finger measurements that considers both closed and separate fingers. The system starts by cropping out the finger section of the hand and then resizing the cropped fingers. 20 distances were extracted from each finger in both separate and closed finger images. A comparison was made between Manhattan distance and Euclidean distance for features extraction. The support vector machine (SVM) was used for classification. The result showed a better result for Euclidean distance with a false acceptance ratio (FAR) of 0.6 and a false rejection ratio (FRR) of 1.2.
  • Item
    A Hybridized Semi-Global Sequence Alignment Algorithm for Intrusion- Detection Systems
    (African Journal of Computing & ICTs (AFRJCICT), 2018) Oladele, Tinuke Omolewa; Adeola, O. O.; Emmanuel, J. A.
    In modern day computing, with persistent remote terminal access, transmissions and virtual networks, conventional methods find it difficult to provide adequate security for the data, information or the service. This challenge deserves new mechanisms to guarantee that the data or information being sent is well secured. A correct system will take into cognizance the protection of the data it processes and the information it stores and sends out at due time. This research work solves the problem of masquerade intrusion into data or information kept on the computer system by reducing the false positive alarm and false negative alarm which increases the true positive proportionately. The Semi - Global Alignment Algorithm which is a hybrid of Smith Waterman Alignment Algorithm is regarded as a dynamic and efficient technique in finding out the attacks. The reports of high false positive rate and false negative rate in the Semi-Global Algorithm have not been reduced to an acceptable level. This study therefore, proposes an improvement on the Semi - Global alignment Algorithm to develop a masquerade intrusion detection system. Experiment was conducted and the performance of the new algorithm was evaluated using Schonlau Et Al (SEA) dataset. The results give hit rate of about 90% and false positive, which show that the improvement on Semi - Global Alignment Algorithm yields increase in the percentage of hit rate of the matching and reduces the value of false positive rate as well as false negative of the alignment.
  • Item
    In Silico Characterization of some Hypothetical Proteins in the Proteome of Plasmodium Falciparum
    (Centrepoint Journal (Science Edition), 2011) Oladele, Tinuke Omolewa; Sadiku, J. S.; Bewaji, C. O.
  • Item
    Information and Communication Technology Approach to Antimalarial Drug Discovery
    (iSTEAMS and University of Ilorin., 2015) Oladele, Tinuke Omolewa; Williams, F. E.
  • Item
    A Joint Neuro-fuzzy Malaria Diagnosis System
    (Journal of Physics: Conference Series, 2021) Oladele, Tinuke Omolewa; Ogundokun, R. O.; Misra, S.; Adeniyi, J. K.; Jaglan, V.
    Diagnosis takes a definitive role in the course of determining about clarifying patients as either having or not having the disorder. This method is relatively sluggish and tedious. Various fact-finding and data-mining methods are part of the approach of this article. In the development of the Collaborative Neuro-Fuzzy Expert System diagnosis platform, Neural Networks and Fuzzy Logic, which are artificial intelligence methods, have been merged together. Oral interviews were conducted with medical professionals whose experience was caught in the Expertise Developed Fuzzy Proficient Scheme. With Microsoft Visual C # (C Sharp) Programming Language and Microsoft SQL (Structured Query Language) Server 2012 to handle the database, the Neuro-Fuzzy Expert Framework diagnostic software was introduced. To capture the predominant signs, questionnaires were administered to the patients and filled out by the doctors on behalf of the patients.
  • Item
    Malicious Uniform Resource Locator Detection Using Wolf Optimization Algorithm and Random Forest Classifier
    (Machine Learning and Data Mining for Emerging Trend in Cyber Dynamics: Theories and Applications, 2021) Adewole, K. S.; Raheem, M. O.; Abikoye, O. C.; Ajiboye, A. R.; Oladele, Tinuke Omolewa; Jimoh, M. K.; Aremu, D. R.
    Within the multitude of security challenges facing the online community, malicious websites play a critical role in today’s cybersecurity threats. Malicious URLs can be delivered to users via emails, textmessages, pop-ups or advertisements. To recognize these malicious websites, blacklisting services have been created by the web security community. This method has been proven to be inefficient. This chapter proposed meta-heuristic optimization method for malicious URLs detection based on genetic algorithm (GA) and wolf optimization algorithm (WOA). Support vector machine (SVM) as well as random forest (RF) were used for classification of phishingweb pages. Experimental results showthatWOAreduced model complexity with comparable classification results without feature subset selection. RF classifier outperforms SVM based on the evaluation conducted. RF model without feature selection produced accuracy and ROC of 0.972 and 0.993, respectively, while RF model that is based onWOA optimization algorithm produced accuracy of 0.944 and ROC of 0.987. Hence, in view of the experiments conducted using two well-known phishing datasets, this research shows that WOA can produce promising results for phishing URLs detection task.