Browsing by Author "Aro, Taye Oladele"

Now showing 1 - 8 of 8
  • Item
    A 2- Dimensional Gabor-Filters for Face Recognition System: A Survey
    (Faculty of Computers and Applied Computer Science, "Tibiscus" University of Timişoara, Romania., 2017) Aro, Taye Oladele; Oluwade, Bamidele A; Abikoye, Oluwakemi Christiana; Bajeh, Amos Orenyi
    An efficient recognition algorithm for human face is a technique discovered to be based on good facial feature representation. A two-dimensional Gabor represents a group of wavelets which capture optimally frequency information and local orientation from a digital image. Gabor filters have been employed greatly and highly considered to be one of the best performing techniques for feature extraction in face recognition owing to its invariant against local distortion initiated by changes in expression, lighting and pose. This paper discusses some reviews on 2-Dimensional Gabor-based facial recognition techniques. The huge feature dimensionality problem associated with Gabor feature is stated and several techniques to reduce this problem are suggested.
  • Item
    Adaptive Neuro-Fuzzy Inference System for HIV/AIDS Diagnosis, Clinical Staging And Regimen Prescription
    (Published by Georgian Technical University and St. Andrew the First Called Georgian University of The Patriarchy of Georgia, 2017) Abikoye, Oluwakemi Christiana; Popoola, Eunice Oluwadamilola; Aro, Taye Oladele; Popoola, Victor Oluwatobi
    HIV/AIDS is one of the life threaten diseases in the society today, which has resulted into loss of many lives in the world. Despite the deadly nature of the disease and the availability of effective treatment, most people still do not know their HIV status, largely because of lack of privacy, stigmatization and discrimination that exist in the community. To bridge these gaps identified, an adaptive neuro-fuzzy Inference system is efficiently developed to diagnose and manage patients by placing them into appropriate clinical stages as recommended by the World Health organization (WHO) and prescribing to them the life-saving Antiretroviral drugs through a standardized set of rules that will enable efficient use of scarce resources, encourage testing and lead to overall better treatment outcome for patients.
  • Item
    Binary Text Classification Using An Ensemble of Naïve Bayes and Support Vector Machines
    (Georgian Technical University and St. Andrew the First Called Georgian University of The Patriarchy of Georgia, 2017) Abikoye, Oluwakemi Christiana; Omokanye, Samuel Oladeji; Aro, Taye Oladele
    Text classification is being done by classifiers over the years, combining classifiers together can result in better classification and thus Naïve Bayes algorithm is combined with Support vector machine through stacking and the results shows that the ensemble results in an increase in the classification accuracy though at the expense of the time taken by the ensemble to build its classification model
  • Item
    Comprehensive Evaluation of Appearance-Based Techniques for Palmprint Features Extraction Using Probabilistic Neural Network, Cosine Measures and Euclidean Distance Classifiers
    (Editura Universitatii din Pitesti, 2018) Akande, Noah Oluwatobi; Abikoye, Oluwakemi Christiana; Adeyemo, I.A; Ogundokun, Roseline Oluwaseun; Aro, Taye Oladele
    Most biometric systems work by comparing features extracted from a query biometric trait with those extracted from a stored biometric trait. Therefore, to a great extent, the accuracy of any biometric system is dependent on the effectiveness of its features extraction stage. With an intention to establish a suitable appearance based features extraction technique, an independent comparative study of Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) algorithms for palmprint features extraction is reported in this article. Euclidean distance, Probabilistic Neural Network (PNN) and cosine measures were used as classifiers. Results obtained revealed that cosine metrics is preferable for ICA features extraction while PNN is preferable for LDA features extraction. Both PNN and Euclidean distance yielded a better recognition rate for PCA. However, ICA yielded the best recognition rate in terms of FAR and FRR followed by LDA then PCA.
  • Item
    Hybridized Intrusion Detection System Using Genetic and Tabu Search Algorithm
    (Faculty of Computers and Applied Computer Science, "Tibiscus" University of Timişoara, Romania., 2017) Abikoye, Oluwakemi Christiana; Aro, Taye Oladele; Obisesan, Racheal Oyeranti; Babatunde, Akinbowale Nathaniel
    As transactions, data communication and information systems are drastically increasing in the society, so many people are connected through internet for e-commerce and other electronic activities. The introduction of internet technology in business brings about great relief in reaching the end users. Also this technology invites numerous security threats of misuses and intrusions. Intrusion detection systems are significant element for network security infrastructure which plays key role in the detection of several attacks along the network. They are several techniques being employed in intrusion detection, but these methods are not completely flawless. In quest for an efficient Intrusion Detection System (IDS), this study employs hybridization technique which involves the Genetic Algorithm and Tabu-search to produce a robust Intrusion Detection System. Evaluation of the system on KKD 99 intrusion database, shows that the performance of proposed hybridized IDS is better than that of Genetic algorithm or tabu search method alone which can significantly detect almost all anomaly data in the computer network.
  • Item
    Optimized Gabor Features For Facial Recognition System
    (Editura Universitatii din Pitesti, 2018) Aro, Taye Oladele; Abikoye, Oluwakemi Christiana; Bajeh, Amos Orenyi
    Feature extraction is a significant process in any pattern recognition, computer vision and image processing. Among several feature extraction techniques like Fisher Linear Discriminant Analysis (FLDA), Principal Component Analysis (PCA), Elastic Bunch Graph Matching (EBGM) and Local Binary Pattern (LBP), Gabor-filters possess the ability of obtaining multi-orientation features from a facial image at several scales with the derived information being of local nature. Its optimal functionality in facial recognition is linked to its biological importance (similarity to the receptive fields of simple cells in primary visual cortex) and computational properties (optimal for calculating local spatial frequencies). Despite all the outstanding properties of Gabor-filters, this technique suffers high feature dimensionality. This paper addresses the problem of high feature dimensionality by application of Ant Colony Optimization meta-heuristic algorithm for feature selection of relevant and optimal features. Two face image databases; Olivetti Research Laboratory (ORL) Database and Locally Acquired Face Image Database (LAFI) are used to evaluate the performance of the proposed facial recognition model. The final experimental results showed better performance.
  • Item
    Stop Words Removal on Textual Data Classification
    (Faculty of Communication and Information Sciences, University of Ilorin., 2019-05) Aro, Taye Oladele; Dada, Funmi; Balogun, Abdullateef Oluwagbemiga; Oluwasogo, Samuel Ayodeji
    Text data is highly voluminous and performing mining tasks on it can be daunting due to large memory usage, thus researchers have considered different techniques to reduce the data while still maintaining or increasing the level of accuracy. Stop word removal is one of the pre-processing techniques used in text data mining. This paper investigates the effect of stop words removal on the text data mining performance. The machine learning algorithms used are C4.5 Decision Tree and Multinomial Naïve Bayes (MNB) on two text datasets; Sentiment Analysis and SMS Spam dataset. Results revealed that the removal of stop words had no influence on the classification accuracy of text mining model, but actually reduced the level of confidence of the prediction
  • Item
    Text Classification Using Data Mining Techniques: A Review
    (School of Computing, Engineering and Physical Science, University of the West of Scotland, Paisley., 2018-05) Abikoye, Oluwakemi Christiana; Omokanye, Samuel Oladeji; Aro, Taye Oladele
    mining algorithms used for text classification and a review of works that have been performed on classifying texts. Design/Methodology/Approach: Data mining algorithms used for text classification were discussed and researches done on applying such algorithms in classifying texts were considered with more emphasis on comparative studies. Findings: No classifier can perform best in all situations as different datasets and conditions bring about different classification accuracies. Practical Implications: In applying data mining algorithms for classifying text documents, it should be noted that the conditions of the data will affect classification accuracy; therefore such data should be well presented. Researchers may also need to try different algorithms and conditions to get a desired level of accuracy. Originality/Value: A lot of work has been done in reviewing of data mining algorithms but this research has its specific emphasis on text and in addition to previous reviews, more recent journals were considered