Browsing by Author "Sulaiman Olaniyi Abdulsalam"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    A Churn Prediction System for Telecommunication Company Using Random Forest and Convolution Neural Network Algorithms
    (EAI Endorsed Transactions on Moblie Communications and Applications, 2022-07-27) Sulaiman Olaniyi Abdulsalam; Jumoke Falilat Ajao; Bukola Fatimah Balogun; Micheal Olaolu Arowolo
    INTRODUCTION: Customer churn is a severe problem of migrating from one service provider to another. Due to the direct influence on the company's sales, companies are attempting to promote strategies to identify the churn of prospective consumers. Hence it is necessary to examine issues that influence customer churn to yield effective solutions to minimize churn. OBJECTIVES: The major purpose of this work is to create a model of churn prediction that assists telecom operatives to envisage clients that are more probably to be prone to churn. METHODS: The experimental strategy for this study leverages the machine learning techniques on the telecom churn dataset, employing an improved Relief-F feature selection algorithm to extract related features from the enormous dataset. RESULTS: The result demonstrates that CNN has a high prediction capability of 94 percent compared to the 91 percent Random Forest classifier. CONCLUSION: The results are of enormous relevance to the telecommunication business in improving churners and loyal clients.
  • Thumbnail Image
    Item
    A Hybrid Approach for Face Morphing Detection
    (KASU Journal of Computer Science, 2024) Saka Kayode Kamil; Abdulrauf Uthman Tosho; Aro Taye; Seriki Aliu Adebayo; Sulaiman Olaniyi Abdulsalam
    Background: In biometrics, one of the most popular study topics is the detection of face morphing attacks. However, because present methods are unable to capture significant feature changes, they are unable to strike the correct balance between accuracy and complexity. Survey investigation and analysis have shown that the existing method of face morphing detection take a bit longer time to detect the image attack due to the high computation required by facial feature extraction approaches. Conversely, further study is needed to develop a model to enhance the computational time and accuracy of the current face morphing recognition methods. The paper developed a hybrid model for face morphing detection. The FERET database was created to aid in the evaluation and development of algorithms. Local Binary Pattern (LBP) was used as feature extraction algorithm and Residue Number System (RNS) was introduced to reduce the lengthy computational time of LBP during the extraction of images. The classification accuracy of 98% was achieved for the FERET database, while an accuracy of 96% was achieved for the FRGCv2 database. An average training time of 0.0532seconds was recorded for the FERET database, while an average training time of 0.0582seconds was achieved for the FRGCv2 database. The study concluded that the high dimensionality of LBP was well reduced and optimized by the RNS algorithm, which improved the performance of face morphing recognition
  • Thumbnail Image
    Item
    An Enhanced Network Intrusion Detection System using Dimensionality Reduction Techniques
    (KASU Journal of Computer Science, 2024) Olufemi James Akinola; Sulaiman Olaniyi Abdulsalam; Michael Favour Edafeajiroke; Kazeem Alagbe Gbolagade
    Protecting the privacy and confidentiality of data in computer networks is crucial, necessitating reliable intrusion detection methods. The complexity and vast volume of data present challenges to effective intrusion detection, as traditional models struggle with high-dimensional data that reduce accuracy. This study addresses these challenges by integrating Mutual Information (MI) and Linear Discriminant Analysis (LDA) as feature selection and extraction techniques respectively, to enhance the classification performance of Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers. The Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CIC-IDS 2017) dataset was used to develop an Intrusion Detection System (IDS). The Results findings revealed that integrating MI+LDA with SVM yielded an accuracy of 98.84% while combining MI+LDA with KNN produced an accuracy of 90.17%. The result of the MI+LDA+SVM model based on accuracy, sensitivity, specificity, and F1-score matrixes, outperformed that of MI+LDA with KNN and other existing models. Therefore, the incorporation of MI and LDA dimensionality reduction techniques proved reliable for boosting the performance of an intrusion detection system in computer networks. Future research could apply the result of this study to other types of computer network benchmark datasets and other kinds of machine learning techniques.
  • Thumbnail Image
    Item
    Detection of Banks' Customers Loyalty Using Naive Bayes and Support Vector Machine Classifiers: A Machine Learning Approach
    (University of Ibadan Journal of Science and Logics in ICT Research, 2024) Sulaiman Olaniyi Abdulsalam; Ismaila Yusuf; Samson Olutunji Ojerinde; Abdullahi Yahaya
    This research paper presents a machine learning approach for detecting and predicting customer loyalty in the banking sector. The study utilizes Naive Bayes and Support Vector Machine (SVM) classifiers to analyze customer data, including demographic information, transaction history, and customer feedback. The dataset is divided into training and testing sets for model development and evaluation. The Naive Bayes classifier leverages the assumption of feature independence, while the SVM classifier constructs optimal hyperplanes for class separation. Performance metrics such as accuracy, precision, recall, and F1-score are used to evaluate the models. Both classifiers demonstrate high accuracy in identifying loyal customers, indicating their potential for real-world application. The study also analyzes the influence of factors like age, income level, and transaction frequency on customer loyalty through feature importance analysis. The proposed machine learning approach offers valuable insights for banks to identify and target loyal customers, enabling effective customer relationship management and improved business performance. The research underscores the importance of feature engineering and model selection in developing accurate customer loyalty prediction models.
  • Thumbnail Image
    Item
    Development of an Intrusion Detection System using Mayfly Feature Selection and Artificial Neural Network Algorithms
    (LAUTECH Journal of Engineering and Technology, 2024-06-24) Sulaiman Olaniyi Abdulsalam; Rasheed Abiodun Ayofe; Michael Favour Edafeajiroke; Jumoke Falilat Ajao; Ronke Seyi Babatunde
    Protecting the privacy and confidentiality of information and devices in computer networks requires reliable methods of detecting intrusion. However, effective intrusion detection is made more difficult by the enormous dimensions of data available in computer networks. To boost intrusion detection classification performance in computer networks, this study proposed a feature selection mode for the classification task. The proposed model utilized the Mayfly feature selection algorithm and ANN as the classifier. The model was also tested without a Mayfly Algorithm (MA). The efficiency of the model was determined through a comparison of its Accuracy, Specificity, Precision, Negative predictive value, False positive rate, False discovery rate, False negative rate, Sensitivity, and F1- score. The experimental outcomes revealed that the proposed model is more efficient than existing models when implemented on the Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CIC-IDS 2017) dataset. Accuracy of 99.94% (using Data+mayfly+ANN) and 90.17% (using Data+ANN) were attained after experimentation. The proposed model demonstrated superior accuracy compared to existing studies. Its robustness is due to employing mayfly techniques that combine the strengths of PSO, GA, and FA for optimal feature selection. This research presents a dependable dimensionality reduction model useful for intrusion detection and improving security in computer networks.
  • Thumbnail Image
    Item
    Optimized Convolution Neural Network-based Model for Detection and Classification of Pulmonary Diseases
    (LAUTECH Journal of Engineering and Technology, 2024-06-15) Anthony Taiwo Olajide; Ronke Seyi Babatunde; Sulaiman Olaniyi Abdulsalam; Jumoke Falilat Ajao; Rafiu Mope Isiaka; A. J. Kehinde
    Pelican Optimization Algorithm-based Convolutional Neural Network (POA-CNN) method for the automated identification of pulmonary disorders such as COVID-19 and pneumonia is proposed in this research. The study aims to enhance the efficiency of CNN models in diagnosing lung diseases by using the Pelican Optimization Algorithm (POA), and by addressing drawbacks like a lack of flexibility in hyperparameter modifications. The three primary phases of the model are feature extraction via POA-based hyperparameter optimization, image classification, and image pre-processing. This approach improves existing systems' performance in detecting pulmonary diseases, highlighting the potential of deep learning in identifying and categorizing human diseases. The study uses resizing, grayscale, and augmentation methods to optimize an existing CNN model. A Convolutional Neural Network (CNN) is then applied to classify Pneumonia and COVID-19 cases. The proposed model achieves an accuracy rate of 97.28% and 97.00%, outperforming existing models. This technique is effective in detecting and classifying other pulmonary diseases and can be used to automatically detect and classify these diseases. Higher accuracy findings show how successful the model is, making it a useful tool for pulmonary illness identification.
  • Thumbnail Image
    Item
    Use of White Shark Optimization for Improving the Performance of Convolution Neural Network in Classification of Infected Citrus
    (University of Ibadan Journal of Science and Logics in ICT Research, 2023) Ronke Seyi Babatunde; Abdulrafiu Mope Isiaka; Jumoke F. Ajao; Sulaiman Olaniyi Abdulsalam; Bukola Fatimah Balogun
    Citrus plant diseases are major causes of reduction in the production of citrus fruits and their usage. Early detection of the onset of the diseases is very important to curb and reduce its spread. A number of researches have been done on the detection and classification of the diseases, most of which have identified poor labelling of symptoms which result into improper classification. Some researchers have also experimented on the effectiveness of convolution neural network and other deep learning techniques, most of which results into a faster convergence but suffers from low accuracy, computational overhead and overfitting as fundamental issues. To reduce the effects of overfitting, this research developed a White Shark Optimization-Convolution Neural Network (WSO-CNN) technique to address the aforementioned problem by introducing a regularization strategy via feature selection which selects more useful and distinguishing features for classification. As a result, the developed technique was able to detect and classify various types of citrus fruit diseases and label them accordingly with low false positive rate, high sensitivity, specificity, increased accuracy and reduced recognition time, based on all the experiments performed with the dataset used in the research. Hence WSOCNN performed better than CNN in classifying citrus plant disease having a reduced FPR of 3.57%, 8.34%, 3.89% and 9.00% for black spot, greasy spot, canker and healthy/non healthy dataset respectively.