Department of Computer Science;

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 20 of 40
  • Item
    Hybridized Dimensionality Reduction Model for Blurred Text Detection in Natural Scene Images
    (Lead City University, Ibadan, 2023-12) Chinonyelum Vivian NWUFOH
    Scene Text Recognition (STR) is synonymous with text recognition in the wild scene, and it is a difficult task since it necessitates getting rid of text strokes and their fuzzy borders, such as embossing, shading, and flare, from an image and then sharpen the latent text. STR has become widely researched because of application areas that cover most everyday activities for both humans and their technological advancement (such as self-driven vehicles and Artificial intelligence gadgets). Existing approaches must fully address the complex problems that arise in the wild regarding text recognition and detection, such as blurred images, which is an aspect of the task for this study. Again, research has recommended using Dimensionality Reduction (DR) and Genetic Algorithm (GA) to instantiate text recognition. Hence, it has given rise to using GA for DR as recommended. Here, we develop two major DR models: the DR model using ICA for pre-processing of the dataset and the DR model using an Independent Component Analysis (ICA) – Enhanced Genetic Algorithm using the Bird Approach (BA-GA), making the ICA-BA-GA model for text deblurring in the wild, coupled with SVM, K-NN, and Ensemble for evaluating the models. The study uses Large-Scale Street View 2019 ICDAR Text (LSVT19), which has 20,000 test photos, 30,000 annotated training images, and 400,000 unlabeled or partially labeled training images. Evaluation parameters such as accuracy, precision, and f1-scores were used for benchmarking. For accuracy compared to the state of the art, ICA-BA-GA gives an impressive 99%. For the improved model (ICA-BA-GA) using the classifiers - with the ensemble, we get the best result (99.30%): K-NN 98.65% and SVM 94.01%. Further research could investigate a hybrid using Neural Networks. A different dataset, preferably one curated by scholars with various categories of blurriness, can be used. Keywords: Scene Text Recognition, Independent Component Analysis, ICDAR Text (LSVT19), Deblurring Text, Pattern Recognition Word Count: 291
  • Item
    An Improved Call Quality for Call Drop Minimization during Handover in Mobile Communication
    (Lead City University, Ibadan, 2023-12) Temilola Adedamola JOHN-DEWOLE
    Mobile devices have become essential and significant aspects of everyone's life in the modern technology. Call drops are significant problems for telecommunications network providers. Users’ call quality being negatively affected by mobile call drops, have also lowers revenue generation for telecom service providers. From the literature, the call quality for a group of calls could be predicted based on combination of calls’ successful factors. This study aims at developing an improved call quality for call drop minimization during handover in mobile communication. In order to address the call drop, a model of neural network to enhance call performance and effectiveness was created. Top-performing Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) models were selected and their predictions were combined using a weighted average ensemble approach. The Ensemble Models machine learning approach was employed using Python software. The features used were signal strength, call drop rate, data usage, call types, congestion level, call setup success rate and traffic control congestion rate. The study utilized a dataset with a total of 3000 data points across 30 cell towers and with each cell running for 5 minutes. The performance is evaluated using accuracy, precision, recall, f-score measures and auc-roc. Results of the research gave an accuracy of 97.18 %, 96.64 % precision, 96.58 % recall, 96.11 % f-score measures and auc-roc of 98.79 % for call drop quality. This strongly correlate with existing results of 90 % accuracy, 93 % precision, 92 % recall, 90 % f-score measures but no auc- roc. Another research showed overall accuracy of 95 %. It is therefore recommended that telecommunications companies should implement deep learning techniques on cellular network data to reduce and fix call drops so that consumers will have a higher call quality in the future; providing continuous communications. Keywords: call drop, call quality, call setup success rate, LSTM, CNN, ensemble models, deep learning, telecommunication providers. Word Count: 295
  • Item
    PERFORMANCE EVALUATION OF HOMOGENOUS BOOSTING TECHNIQUE FOR INTRUSION DETECTION IN ONLINE BANKING
    (Lead City University, Ibadan, 2023-12) JIBOKU, Folahan Joseph
    In recent times, it has been observed that a lot of users have been migrating to online banking. However, security in online banking has been a matter of great concern for most users. This thesis presents a performance evaluation of a homogeneous boosting technique for online banking network intrusion detection. The study aims to determine the effectiveness of the boosting technique in improving the detection of network intrusion attempts in online banking systems. The research methodology includes applying fuzzy logic feature selection technique on the dataset to determine the objectivity of the homogenous boosting ensemble machine learning algorithms. The experimental results of the study showed that the homogenous boosting technique performed well on the datasets, achieving high levels of accuracy and recall. The study also shows that the homogeneous boosting technique has a relatively low false-positive rate, indicating a high level of precision in detecting network intrusion attempts. Furthermore, the study evaluates the impact of various feature selection techniques on the performance of the boosting technique. The results demonstrate that the boosting technique performed better with selected feature subsets, which implies that the technique can be optimized for different online banking network intrusion detection scenarios. In conclusion, this thesis demonstrates the effectiveness of the homogeneous boosting technique for online banking network intrusion detection. The study provides valuable insights into the use of boosting techniques and feature selection for improving the detection of network intrusion attempts in online banking systems. The findings of this study could help enhance the security of online banking systems and improve the overall trust of customers in online banking. Keywords: Online Banking, Intrusion Detection, Fuzzy Logic, Homogenous boosting. Word Count:263.
  • Item
    Advanced Surveillance Technology Multicast Using Optical Wireless Transceiver in Smart Environment
    (Lead City University, Ibadan, 2023-12) Israel Oluwagbejamija FAKUNLE
    Security practice is crucial peaceful living. In the old times, before the advancement of technology, security was a major concern due to invasions, robbery, and wars. According to history, security personnel in those days known as vigilante also served as police. The security responsibilities then require 100% human effort, having to go over an assign geographical area, restlessly and sleeplessly, to secure lives and properties. But today with technological advancements, people are able to live in security without the need for protection. The advancement in technology as relieved human a whole lot of security threats and stress. This study aims to develop a real-time surveillance system that utilizes multicast technology to prevent and detect crime in an enclosed geographical location. The objective is to empower residents to work together and contribute to the security of their environment, lives, and properties. Real-time surveillance multicast is faced with numerous challenges, such as; lags / interruption in transmission, due to error from the framework or internet connections, high internet data consumption, due to enormous data transmission and limited number of users allowed. A Close-Circuit Television system will be designed using an analogue camera and digital video recorder with a hard drive for data capturing and storage allowing decentralization of the system using a wireless video transceiver through integration. Overall, this study aims to develop a surveillance system that empowers residents to work together and contribute to the security of their community. The system will leverage advanced technologies such as wireless video transceivers and multicast technology to improve the efficiency and effectiveness of surveillance. Keywords: Technological Advancement, Security Threats, need for protection, real-time surveillance, multicast, lags in transmission, empower residents. Word Count: 260
  • Item
    A Web Based Chatbot for Mental Health Support
    (Lead City University, Ibadan, 2023-12) Samuel Ejomafuvwe LUCKY
    Despite the significance attributed to mental health, a considerable number of individuals have difficulties in accessing prompt and tailored mental health interventions. This predicament can be attributed to various factors, including societal stigmatisation, limited availability of resources, and residing in geographically isolated areas. This study addresses the persistent challenge of providing timely and individualized mental health treatment through the development of a web-based chatbot for personalized therapy. The study comprises the utilisation of a dataset containing frequently asked questions (FAQs) related to mental health. Preprocessing techniques, including lemmatization, lowercasing, and duplication removal, are employed in order to prepare the data for analysis. The machine learning model, which utilises neural networks, undergoes training and has a negative association between epochs and loss magnitude, suggesting enhanced performance as the training progresses. The findings indicated that the developed chatbot demonstrated a high level of proficiency in delivering personalised mental health care that is relevant to the individual, providing fast responses, and offering appropriate recommendations for therapy. Additionally, the user feedback received during the performance evaluation highlights a high level of satisfaction and a strong inclination to utilise the chatbot again in the future. The study highlights the potential of chatbots, particularly those based on LSTM architecture in effectively addressing mental health issues and enhancing the availability of resources. The study therefore recommends that continuous improvement refining and enhancing the chatbot's capabilities by regularly updating the chatbot's knowledge base, therapy recommendations, and conversational abilities to ensure it remains relevant and effective. Keywords: Epochs, Frequently asked questions (FAQs), Lemmatization, Lowercasing, LSTM architecture, Machine learning model, Mental health, Personalized therapy Word Count: 247 Words
  • Item
    Predicting the Severity of Vehicle Accidents Based on Traffic Accident Attributes Using Machine Learning
    (Lead City University, Ibadan, 2023-12) Segun Abayomi Sofoluwe
    The occurrence of accidents on global road networks results in a considerable loss of human life on a yearly basis, hence underscoring the urgent matter of ensuring road safety. This research aims to predict the severity of road traffic accidents and enhance prediction performance by employing two machine learning algorithms; the Random Forest model and the Decision Tree Classifier model. The study employs a dataset obtained from Kaggle.com, which is subjected to comprehensive data mining, pre-processing, and exploratory data analysis. The dataset was divided into training and testing subsets for model development and evaluation. The evaluation of model performance involved the computation of key performance metrics such as precision, recall, and F1-score. The findings of the study revealed that the Random Forest (RF) model continuously exhibited better performance compared to the Decision Tree (DT) model across all evaluation metrics, including precision, recall, F1-score, and overall accuracy. The evaluations consistently exhibited higher values for RF across all accident severity classes, indicating its greater predictive capability in accurately determining accident severity. The RF algorithm was found to have a higher weighted-average F1-score, taking into account the presence of class imbalances within the dataset. Therefore, based on the findings of this study, it can be concluded that the Random Forest (RF) model demonstrates superior performance in accurately predicting accident severity across all categories, with an overall accuracy rate of 0.84. In comparison, the Decision Tree (DT) model achieves an accuracy rate of 0.73. It is therefore recommended that additional analysis can be done in order to gain a deeper understanding of the underlying causes for misclassifications, with the aim of enhancing the performance of the models for these particular classes. Additionally, optimizing the hyperparameters of the models can result in enhanced performance and utilization of cross- validation methodologies, such as k-fold cross-validation, to more accurately evaluate the models' performance and mitigate the potential for overfitting. Keywords: Accuracy, Accident severity, Algorithms, Data analysis, Exploratory data analysis, F1-score, Fine-tuning, Machine learning, Precision, Random Forest model, Severity prediction Word Count: 311 Words
  • Item
    Intrusion Detection Performance in Cloud Network Environment: A Hybrid of Deep Belief Network and Multilayer Perceptron
    (Lead City University, 2023-12) Simon Olufikayo AWODELE
    It is nearly impossible in the world of today to ponder the digital evolution of businesses, entertainment, organizations, and government without cloud computing. It is therefore not a surprise that many organizations and companies are increasing their investments in cybersecurity. Malicious attackers are increasingly focusing on unprotected web apps and systems connected to the Internet. This makes IT networks, systems, and the data they contain, more vulnerable to threats. attacks and intrusions that can harm business operations, inflict substantial costs, and damage a company's reputation. As a result, the cloud network security systems are essential, significant, and must not be compromised. Therefore, it is necessary to develop a network intrusion detection system using an anomaly detection approach for a cloud computing network that can identify as many intrusions as possible with better detection accuracy and reduce the false positive rate. In this research, a hybrid model has been developed for intrusion detection in a cloud network environment based on the use of UNSW-NB15 detection datasets. Multilayer Perceptron (MLP) and Deep Belief Network (DBN) algorithm techniques were used in a parallel integration pattern to form a single optimal model through the use of the voting classifier to achieve higher precision, lower inaccuracy, increased consistency, and reduce bias The experimental result showed that the hybrid model achieved a lower false positive rate, which makes it more promising for intrusion detection in cloud network environments while the MLP model, which is a conventional method, achieved better performance in terms of accuracy, recall, precision, and F1-score, furthermore the DBN model which is also a conventional model showed a lower performance in all categories of Implementation results. Keywords: Intrusion detection, Cloud computing, Deep learning, Voting Classifier, UNSW- NB15 Word Counts: 282 words.
  • Item
    A Dual-Mode Radio-Frequency Identification and Facial Recognition System for Attendance Capturing
    (Lead City University, 2023-12) Yinka John ADEGOKE
    In today's rapidly evolving technological landscape, efficient and secure attendance tracking systems are essential for various organizations. This study introduces a novel solution that combines Radio-Frequency Identification (RFID) and Facial Recognition technologies to create a robust attendance management system. By leveraging the capabilities of both hardware and software components, this system offers a seamless and accurate approach to recording and managing attendance data. The hardware component of the system utilizes Arduino microcontrollers and RFID modules to provide individual identification through RFID cards or tags. Each user is assigned a unique RFID card that triggers the RFID module to record the attendance information. Simultaneously, the system captures facial images using a camera module for facial recognition. A Python program processes the data using Open CV, associating it with the respective user's profile and initiates the facial recognition process. The facial recognition system identifies users by comparing the captured facial features with the pre-stored templates in the database. The system offers several advantages, including high accuracy in attendance recording, enhanced security, and rapid processing of data. Moreover, the combined approach reduces the time spent on proxy attendance, ensuring the integrity of attendance records, and creating options for attendance. The system also provides real-time attendance tracking and generates comprehensive reports for administrative purposes. This research presents a step- by-step implementation guide for setting up the RFID and Facial Recognition Attendance System using Arduino and Python, making it accessible for educational institutions, businesses, and organizations looking to streamline attendance management. The system's effectiveness is demonstrated through extensive testing, highlighting its reliability and robustness. The system represents a cutting-edge solution for modern attendance management needs. By harnessing the capabilities of the technologies adopted, this system offers a secure, accurate, and efficient approach to attendance tracking, paving the way for improved organizational efficiency and data integrity. Keywords: Python , Facial Recognition , Arduino, A Dual-Mode Radio, Frequency Identification, System, Attendance Capturing Word Count: 299
  • Item
    Employee Attendance Tracking Using Facial Recognition System
    (Lead City University, 2023-12) Bukola Meka OWOLABI
    Traditional pen-and-notebook methods for employee attendance are often susceptible to inaccuracies and falsifications. Biometric systems, despite being more secure, confront issues such as high acquisition costs and inefficiencies in capturing fingerprints, especially when hands are unclean or injured. In this study, a cutting-edge Employee Attendance Tracking System using Facial Recognition is developed, addressing the shortcomings of conventional attendance methods and biometric systems. The proposed system employs an array of Python libraries including Django, face_recognition, OpenCV (cv2), numpy, and PCA. These libraries are utilized for their strengths in image processing, facial recognition, and efficient data management. The primary objective is to create a reliable, cost-effective, and efficient alternative for recording employee attendance, overcoming the limitations of existing methods.The system utilizes advanced image processing techniques to tackle common challenges in facial recognition, such as noise interference, varying lighting conditions, and physical obstructions like occlusions. This is achieved through innovative approaches like noise reduction, illumination normalization, and occlusion handling, significantly improving the accuracy of facial recognition under diverse environmental conditions. A key component of the system is the "Capture_Image" module, which establishes a reference database by capturing and storing employee images. Concurrently, the "Recognize" module employs machine learning algorithms for facial recognition, ensuring accurate and timely recording of attendance. The effectiveness of the system is demonstrated in its ability to adapt to a variety of environments, attributed to its advanced image processing capabilities and robust algorithmic framework. This innovative system is particularly advantageous for institutions, corporate offices, and industries seeking secure, precise, and efficient attendance tracking solutions. It marks a significant advancement in the field of attendance management, offering a blend of enhanced security, accuracy, and operational efficiency. The study recommends further enhancements, such as incorporating advanced algorithms to improve recognition accuracy in different lighting and noise conditions. Keywords: Accuracy, Biometric system, Employee Attendance Tracking, Facial recognition, Machine learning algorithm Word Count: 295 Words
  • Item
    Hybridized Model of an Improved Genetic Algorithm with Local Linear Embedding Algorithm for Feature Selection in Intrusion Detection Systems
    (Lead City University, 2023-12) Tolulope Olushola OLUFEMI
    The Internet has revolutionized various sectors, offering opportunities for innovation and advancement. However, it brings the risk of cyber-attacks. Intrusion Detection Systems (IDS) are vital in identifying and preventing such attacks. The quality of IDS models relies on selecting relevant features during the training process. This study proposes a hybrid optimization model for feature selection in IDS to enhance the efficiency and accuracy of the system, and the methodology incorporates an improved Genetic Algorithm (I-GA) and Local Linear Embedding (LLE) optimization techniques. It aims to identify the most relevant features for building an appropriate and effective IDS model. The Machine learning classifiers, including Support Vector Machine (SVM) and k-nearest Neighbors (KNN), use the reduced and highly relevant features obtained through the I-GA with LLE approach for training and testing purposes. The performance of these combinations is validated using various metrics, and the results demonstrate the effectiveness of the proposed approach. The accuracy achieved for I-GA-LLE-SVM, I-GA-LLE-KNN, the LLE-SVM, the LLE-KNN, the I-GA-SVM, I-GA-KNN are 94%, 99%,86%,98%,89% and 98% respectively. These results highlight the I-GA-LLE approach's superiority over the other combinations. The significant improvements in accuracy obtained through the I-GA-LLE-SVM and I-GA-LLE-KNN combinations emphasize the importance of integrating multiple optimization techniques for feature selection in IDS models. In conclusion, this study presents a hybrid optimization model that effectively selects relevant features for IDS. The combination demonstrates superior performance in terms of accuracy. The findings emphasize incorporating advanced optimization techniques and multiple classifiers for outstanding intrusion detection, which can significantly enhance cybersecurity measures and safeguard networks in the face of evolving cyber threats. Keywords: Intrusion Detection System, Support vector machine, k-nearest Neighbor, Machine Learning, Genetic Algorithm Word Count: 275
  • Item
    Hybridized Model of an Improved Genetic Algorithm with Local Linear Embedding Algorithm for Feature Selection in Intrusion Detection Systems
    (Lead City University, 2023-12) Tolulope Olushola OLUFEMI
    Abstract The Internet has revolutionized various sectors, offering opportunities for innovation and advancement. However, it brings the risk of cyber-attacks. Intrusion Detection Systems (IDS) are vital in identifying and preventing such attacks. The quality of IDS models relies on selecting relevant features during the training process. This study proposes a hybrid optimization model for feature selection in IDS to enhance the efficiency and accuracy of the system, and the methodology incorporates an improved Genetic Algorithm (I-GA) and Local Linear Embedding (LLE) optimization techniques. It aims to identify the most relevant features for building an appropriate and effective IDS model. The Machine learning classifiers, including Support Vector Machine (SVM) and k-nearest Neighbors (KNN), use the reduced and highly relevant features obtained through the I-GA with LLE approach for training and testing purposes. The performance of these combinations is validated using various metrics, and the results demonstrate the effectiveness of the proposed approach. The accuracy achieved for I-GA-LLE-SVM, I-GA-LLE-KNN, the LLE-SVM, the LLE-KNN, the I-GA-SVM, I-GA-KNN are 94%, 99%,86%,98%,89% and 98% respectively. These results highlight the I-GA-LLE approach's superiority over the other combinations. The significant improvements in accuracy obtained through the I-GA-LLE-SVM and I-GA-LLE-KNN combinations emphasize the importance of integrating multiple optimization techniques for feature selection in IDS models. In conclusion, this study presents a hybrid optimization model that effectively selects relevant features for IDS. The combination demonstrates superior performance in terms of accuracy. The findings emphasize incorporating advanced optimization techniques and multiple classifiers for outstanding intrusion detection, which can significantly enhance cybersecurity measures and safeguard networks in the face of evolving cyber threats. Keywords: Intrusion Detection System, Support vector machine, k-nearest Neighbor, Machine Learning, Genetic Algorithm Word Count: 275
  • Item
    Predictive Analytics of Image Descriptors for Students Biometric Authentication System
    (Lead City University, 2023-12) Babatunde Taiwo OLOMOLA
    Nowadays, our education as well as other sectors is in a verge where accuracy of its authentication process is vital so as to close door tightly against impostors and impersonators. This thesis therefore improved the effectiveness and accuracy of biometrics based authentication models already in use for students’ attendance. The authentication framework is a five-phase biometric-based student attendance verification system that combined iris and fingerprint recognition attributes for the purpose of training deep learning models. The first phase entails the image acquisition. The acquired image inputs were then subjected to the feature extraction phase where attributes were extracted from the image inputs in form of numeric image descriptors. Data resampling were done in order to ensure a balanced training set for the machine learning-based study, which were consequently deployed for the deep learning phase after which performance evaluation was carried out in phase five. Three learner algorithms of Decision Tree (DT), Support Vector Machine (SVM), and Sequential Minimal Optimization (SMO) were trained with numeric vectors extracted from both fingerprint and iris biometrics of students for a student attendance authentication system. The numeric vectors were extracted using the SqueezeNet, InceptionV3, VG16, VG19, and Painters image embedders to return five distinct databases. The performances of the three base learners’ algorithms were evaluated alongside the performance of a Vote ensemble model after the five databases are subjected to a synthetic minority oversampling. Experimental results returned the Vote ensemble as the best model for student authentication which is followed by the SMO. The F1 score of Vote ensemble outperforms other models across the five datasets, with accuracy score as high as 0.999. The synthetic minority oversampling of the training sets further improved the performance of the models through data resampling. Consequently, Vote ensemble machine learning is better deployed for student authentication systems with any of the five image embedders. Keywords: Ensemble Machine, Information Security, Biometric Authentication, Biometric Recognition, Database Management System Word Count: 273
  • Item
    IMPROVEMENT ON CYBERSECURITY TECHNIQUES AND RISK MITIGATION OF INFORMATION SYSTEMS USED IN INTERNET BANKING AND MOBILE BANKING
    (Lead City University, 2023-12) Samuel Adetunji OLADEJO
    Cybercrime committed on financial institutions are rapidly and steadily becoming more sophisticated and more widespread. The rise in occurrence and extent of cyber-attacks can be linked to a number of factors, such as ineffective risk management systems within banking sectors, ICT technological infrastructure and staff competency and awareness about cybercrimes attacks. As a result of the vulnerabilities in the systems, organized criminals take advantage to breach financial institution’s systems to steal money. This study makes an effort to look into ways to improve improved multi-tier threat and risk management system for internet and mobile banking. The completion of this project marks a significant milestone in the development of a modern banking management application system. The Banking Management Application System, integrated with Flutter, DRF, and MySQL, demonstrates the capabilities of these technologies in building cross- platform mobile applications with an intuitive and visually appealing user interface, robust backend API, and efficient database management. By implementing essential banking functionalities, the system aims to enhance the banking experience for customers, providing convenience, security, and efficiency in managing their accounts and conducting transactions. The successful implementation of the Banking Management Application System with DRF and MySQL confirms the feasibility and effectiveness of this technology stack. The system's architecture, database design, user interface design, and the powerful features of DRF and MySQL contribute to its overall functionality and user satisfaction. Through this project, we have gained valuable insights into software design, system implementation, and the utilization of the Dart-Flutter-DRF-MySQL stack for developing a comprehensive and feature-rich banking management application system. Keywords: Multi-Tier Threat, Risk Management System Internet Banking, Mobile Banking Word count: 254
  • Item
    Enhancing Messaging Security Using Image Steganography Technique
    (Lead City University, 2023-12) Kayode Mathias MADEWA
    The introduction of steganography has brought plenty of improvement to information security, but not really employed in Information banks and this is often as a results of the protection issues that come together with the employment of Information security. Security issues is taken into account a significant concern which is why every individual still opt to follow the normal way of addressing sensitive information. The aim of this study is to enhance end to end messaging security using image steganography technique. End to End SMS has always been dealing with security missues as there are no security measures being put in place to improve the Confidentiality of the context of the SMS. The Methodology used in this study implore the use of mathematical expression as the first step is to convert the secret message into binary and thus obtain a bitstream as the result of this step. then divide the obtained bitstream into a set of groups with three bits in each group. To this end, from the least significant bit, grouping is then done to every three continuous bits in a group. The result of this study is presented as a software solution, as it is implemented and tested for use. This study uses evaluation parameters like Mean square error and Peak Signal to Noise Ratio to measure the performance of the images that are used in the cause of this study, the images that are evaluated is the stego-image with text of different word-lengths embedded in it. Keywords: Encryption , Algorithm, Red2 algorithm
  • Item
    A Hybrid Swarm Intelligence Convolution Neural Network for Object Detection and Tracking
    (Lead City University, 2023-12) Afiss Emiola KAREEM
    In recent years, analysis and interpretation of video sequences to detect and track objects of interest had become an active research field in computer vision and image processing. Despite significant efforts in object detection and tracking, an efficient method which provides high computational efficiency has not been developed. Hence, in this work a Hybrid Particle Swarm Optimization Convolution Neural Network (CNN-HPSO) technique was developed to improve computational efficiency in object detection and tracking. The video datasets (MP4 and AVi video formats) used in this work were obtained from a conventional online database and on a real-time basis from YouTube. Multiple frames sampled from the video clips were pre-processed and then segmented. An Enhanced Particle Swarm Optimization (HPSO) was formulated from standard PSO and was applied to Convolution Neural Network (CNN). CNN- HPSO technique was used for edge detection and extraction of the boundary of the image and the object tracking was finally carried out. The work was implemented using MatLab R2016 software. The average results of CNN-HPSO, CNN-PSO and CNN on the videos with MP4 format yielded processing time, accuracy, precision, FPR, sensitivity and specificity of 165.89s, 97.08%, 98.41%, 7.75%, 97.82%, and 92.25%; 179.52s, 94.25%, 96.99%, 10.37%, 95.23% and 89.62%; and 189.19s, 89.95%, 93.64%, 15.56%, 91.95.33% and 84.44% respectively. For the videos in AVi format, CNN-HPSO, CNN-PSO and CNN produced similar average results with processing time, accuracy, precision, FPR, sensitivity, and specificity of 185.09s, 96.62%, 98.23%, 7.80%, 97.34% and 92.19%; 198.24s, 94.83%, 97.62%, 8.56%, 95.46% and 91.43%; and 216.59s, 91.30%, 93.98%, 15.09%, 93.67% and 84.91% respectively. In this research, a CNN-HPSO with associated high computational efficiency was developed. The developed technique can be used for solving other related optimization problems. Keywords: Deep Learning Algorithms, Computer Vision, Moving Objects, Video Frame, Object Segmentation Word Count: 293
  • Item
    based Predictive Model for Keylogging Attack Mitigation
    (Lead City University, 2023-12) Mariam Ayobami GBADEGESIN
    In the ever-evolving landscape of cybersecurity, the relentless progression of cyber threats presents an ongoing challenge to the integrity of sensitive data and user credentials. Among these threats, keylogging malware has emerged as a particularly insidious vector, adept at covertly infiltrating systems, stealing login credentials, and exfiltrating valuable information. This research is driven by the imperative need to confront this menacing adversary. By delving into the subtle intricacies of human keystroke dynamics, we have engineered a groundbreaking and intelligent predictive model aimed at the early and reliable detection of keylogging attacks. The innovative character of this model stems from its amalgamation of two powerful techniques: adaptive neural networks and fuzzy logic inference. This research develops a Neuro-fuzzy predictive model using keystroke dynamics to reliably detect and mitigate ongoing keylogging threats. The model’s training process was conducted using a diverse dataset comprising over three hundred thousand keystroke samples, sourced from both simulated users and actual keyloggers. Impressively, baseline neural networks exhibited a detection accuracy rate of 99.1%. Building upon this solid foundation, the specialized Neuro-fuzzy model further elevated precision, achieving a remarkable 99.62% accuracy. This enhancement primarily stemmed from the model’s ability to distinguish between human and automated keystroke patterns, significantly reducing false positives. These results demonstrate that an adaptive Neuro-fuzzy model can reliably predict keylogging attacks in real-time based on anomalous keystroke dynamics before significant credentials or data are exfiltrated. The adaptive model provides a robust predictive solution to a rapidly evolving risk that continues to bypass traditional reactive defenses. Keywords: Neuro-fuzzy, Neuro-fuzzy model, keylogging, keylogging threats Total word count: 250 words
  • Item
    Automated Customer Support System (Chatbot) to Enhance Web-based Financial Application Services using Artificial Intelligence
    (Lead City University, 2023-12) Roqib Akintunde AKINYEMI
    Customer support is perhaps one of the main aspects of the user experience for online services. However, with the rise of natural language processing techniques, the industry is looking at automated chatbot solutions to provide quality services to an ever-growing user base. In view of this, the chatbot was developed using Artificial Intelligence Markup Language (AIML) java interpreter library Program AB (an experimental platform for the development of new features and serves as the reference implementation) which helps match input and output predefined in the AIML file. AIML was used to preprocess and train the bot using ready-made AIML file for Frequently Asked Questions. Also, vaadin was used to build a web user interface to interact with the trained AIML bot. Finally, a google script was written to translate from any language to English for the bot to understand and send the response in the preferred language of the user. Findings showed that the response time of the bot is dependent of the network, as the design gave a score of 70%, 80%, and 90% for load testing, stability, reliability testing and usability testing, respectively. Also, the bot is compatible with different operating systems, both for forward compatibility and backward compatibility having a score of 95%. The bot was able to answer customer questions, enquiries and complaints and the response time of the bot depends on the strength of the network since it is web based. Hence, the system provided a simple, cheaper, and durable customer financial and payment application service. It is therefore recommended that any company incorporating a chatbot should make sure that the chatbot is highly secure due to attacks and routine queries. It should also be standardised to deliver a high level of performance since chatbots will not be able to solve all queries. Keywords: Chatbot, Customer Support, Google Script, Online Service, Testing Word Count: 298 Words
  • Item
    Comparative Performance Evaluation of Random Forest on Web-based Attacks
    (Lead City University, 2023-12) Oluwaseye Abayomi ADEYEMI
    As human resources try to break into networks, control systems, and steal information with the help of expanding data communication paths and protocols, cyber intrusions are currently on the rise. The majority of typical online attack methods are thoroughly researched and documented. Countries, corporations, people, and vital infrastructures that depend on information technology for daily operations have suffered financial losses, the loss of personal information, and economic harm as a result of web-based intrusion. However, foreseeing an attack before it happens can aid in its prevention. This research proposes a predictive model for web-based attacks and a performance comparison of random forest with and without feature selection to secure the availability, integrity, and secrecy of networks, computer systems, and their data. The CIC-Bell-IDS2017 dataset, which includes typical and contemporary intrusion attacks, served as the raw data source for the proposed model. A python-based programming environment and interface for Anaconda Navigator, Jupyter Notebook, was used to create the predictive models. Performance evaluation and comparative analysis were conducted, and the results demonstrate that, once big data analytics (feature scaling and feature selection) were applied to the dataset, the models' prediction accuracies improved, creating a potential intrusion detection system. The outcome yielded excellent accuracy and model development times in both cases, with 97% and 98% precision for both sets and model development times of 35 seconds for the raw set and 15 seconds for the reduced set, which is an important factor when deploying machine learning models in a real-time setting. Random Forest is more computationally expensive than Correlation feature Selection-based classifiers, but having higher predictive accuracy, according to a comparison. Both of these methods work well and each has advantages and disadvantages. The use of big data analytics (PySpark) was found to help machine learning models perform better, resulting in better intrusion detection system. Keywords: Web Based Attacks, Random Forest, Correlation Feature Selection, Word Count: 300
  • Item
    An Optimized Low-Level Interaction Glastopf Honeypot for Accurate Detection of Fake Honeypot using OMNET++ Simulation
    (Lead City University, 2023-12) Abimbola Basiru OWOLABI
    Securing cloud-based information has become the most critical aspect in computing, owing to different methods adopted by attackers to steal vital information. Most system developers focus their information security on defensive mechanisms against attackers, this has proven to be inactive as attackers continuously explore ways to gain unauthorized access to cyberspace information, which has necessitated more effective, robust, and efficient models to mitigate threats posed by Cyber criminals. Hence, the design of an optimized web-based low-interaction Glastopf honeypot for the accurate gathering of Attackers' intelligence information and detection of fake honeypot systems using the OMNET++ Simulation tool. This study aims to assess the effectiveness of the Glastopf honeypot in collecting relevant intelligence on attackers, detecting fake honeypot systems, analyses the honeypot's ability to capture and record attackers' actions, including their exploitation methods, tools used, and payloads deployed. It also evaluates the honeypot's ability to provide valuable insights into attackers' motivations, intentions, and potential targets. An extensive experiment was conducted by setting up a virtual system with OMNET++ simulation running on Ubuntu web-server on the back end while on the front end was windows operating system where Glastopf honeypot was configured in a controlled environment. The study injects Hornet 40 data sets of attacks collected from six different cloud servers into the server to test Glastopf honeypot. Multiple attack scenarios were simulated, involving various types of attackers and attack vectors. The honeypot's logs, network traffic captures, and other relevant data are collected and analyzed using automated techniques. The results of the experiment provide insights into the Glastopf honeypot’s effectiveness in gathering intelligence information and make Glastopf honeypot a good cyber security tool, but would perform better when deployed with IDS and firewalls, thereby recommended for organizations but would not be suitable for individuals due to the installation technicality involved. Keywords: Deception Technology, Honeypot, IDS, OMNET++, Glastopf, Web Application Word Count: 298 words
  • Item
    Web-base System for Motherless Homes Service Providers in Oyo State, Ibadan, Oyo State, Nigeria
    (Lead City University, 2022-12) Makinde Olukemi Funlola
    There is a need for an effective web based system for motherless homes service providers to decrease challenges in social sectors, to achieve this there is a need to design and implement a database, develop a web application and also test a design database. The methodology is achieved by studying and reviewing other literature relating to my study to improve the efficiency of the system as a means of filling the gap in the literature. The system makes use of designing software which makes use of two programming language, content management system (CMS), PHP and Javacript. Google Map API was also integrated in the system to enable GPS location sharing of the Motherless Homes service providers address and location. A developed system which hosted on Github International web host service for test verification and implemented. Agithub is a web based hosting service version control using Git. The hardware device that was made use are personal computer, uninterrupted power. Waterfall model is the methodology adopted. The Architectural design improves three levels structure 1, client server, middle tier, and back end. The entity diagram is a logical and graphical representation of the overall structure of the data base. The flowchart is concerned about splitting of high level functions into sub functions, establishing definite relationships among specified functions. The results are partitioned into three parts which are programming language used, Admin Dashboard and user interface. A data design and architectural design and a procedural design are all included in the design process. Keywords: Web-base, Design, NGO, Application. Word Count: 298