Department of Computer Sciences
Permanent URI for this collection
Browse
Recent Submissions
Now showing 1 - 5 of 134
- ItemEmerging Security and Privacy Schemes for Cyber-physical Systems(2025-04-02) Olorunfemi, Blessing O.The challenges and possibilities in security and privacy are unique due to the rapidly evolving cyber-physical systems (CPS) landscape. Their increasing integration into essential infrastructures like healthcare, transportation, and energy has made it imperative for them to be secure and their data to remain private. This chapter discusses how both CPS digital and physical elements relate, considering sophisticated cyberattacks with physical consequences. Specifically, this chapter analyzes the vulnerabilities resulting from the merger of evermore complex systems with extensive connectivity and cyber attack sophistication and its impact on privacy in a data-centric world. The chapter underlines the importance of improving security solutions in cyber space to protect against both present and future attacks. This also touches on advanced technological alternatives, including encryption algorithms for 289 290 Emerging Security and Privacy Schemes for Cyber-physical Systems secure data transformation, machine learning models for threat forecast ing and unusual activity detection, and strong user authentication systems that allow only genuine people to get into important machines. Moreover, it highlights how vital privacy-preserving technologies like differential pri vacy and federated learning are because they enable one to harness all advan tages associated with enormous datasets without compromising anybody’s confidentiality. This chapter proposes a research agenda that would focus on developing adaptable, integrated security frameworks that are reactive and proactive in identifying and neutralizing threats before they strike. It consists of an ongoing cycle of research, implementation, and refinement of security measures complemented by continuous monitoring of an improving threat landscape so that CPS can remain safe and dependable as the backbone of modern civilization
- ItemPROFESSOR(Journal of Computer Science and Information Technology, 2014-03) OGUNDE, ADEWALE OPEOLUWAThe desire of every organization is to extract hidden but useful knowledge from their data through data mining tools. Also, the recent decline in the standard of education in most developing countries has necessitated researches that will help proffer solutions to some of the problems. From the literature, different analysis has been carried out on university data, which includes student’s university entrance examination and Ordinary level results but the relationship between these entry results and students’ final graduation grades has been in isolation. Therefore, in this work, a new system that will predict students’ graduation grades based on entry results data using the Iterative Dichotomiser 3 (ID3) decision tree algorithm was developed. ID3 decision tree algorithm was used to train the data of the graduated sets. The knowledge represented by decision trees were extracted and presented in form of IF-THEN rules. The trained data were then used to develop a model for making future prediction of students’ graduation grades. The developed system could be very useful in predicting students’ final graduation grades even from the point of entry into the university. This will help management staff, academic planners to properly counsel students in order to improve their overall performance. Keywords: Data mining, Decision trees, Prediction, ID3 algorithm, Knowledge extraction
- ItemA partition enhanced mining algorithm for distributed association rule mining systems(Elsevier., 2015) OGUNDE, ADEWALE OPEOLUWAThe extraction of patterns and rules from large distributed databases through existing Distributed Association Rule Mining (DARM) systems is still faced with enormous challenges such as high response times, high communication costs and inability to adapt to the constantly changing databases. In this work, a Partition Enhanced Mining Algorithm (PEMA) is presented to address these problems. In PEMA, the Association Rule Mining Coordinating Agent receives a request and decides the appropriate data sites, partitioning strategy and mining agents to use. The mining process is divided into two stages. In the first stage, the data agents horizontally segment the databases with small average transaction length into relatively smaller partitions based on the number of available sites and the available memory. On the other hand, databases with relatively large average transaction length were vertically partitioned. After this, Mobile Agent-Based Association Rule Mining-Agents, which are the mining agents, carry out the discovery of the local frequent itemsets. At the second stage, the local frequent itemsets were incrementally integrated by the from one data site to another to get the global frequent itemsets. This reduced the response time and communication cost in the system. Results from experiments conducted on real datasets showed that the average response time of PEMA showed an improvement over existing algorithms. Similarly, PEMA incurred lower communication costs with average size of messages exchanged lower when compared with benchmark DARM systems. This result showed that PEMA could be efficiently deployed for efficient discovery of valuable knowledge in distributed databases.
- ItemA Knowledge Sharing Architectural Model for Inter State e-Governement in Nigeria(Nigeria Computer Society, 2010) OGUNDE, ADEWALE OPEOLUWA
- ItemA recommender system for selecting potential industrial training organizations(John Wiley & Sons Ltd., 2019) OGUNDE, ADEWALE OPEOLUWAThe difficulty in securing students industrial work experience scheme (SIWES) placements has negatively affected the final grades of some undergraduates. A recommender system is hereby proposed to solve this problem. This systemwill use past SIWES data to recommend potential organizations to future SIWES students. Research data collection was through an online questionnaire, with 200 respondents. The data was divided into a training data set (70%) and test data set (30%). Collaborative filtering recommendation approach was employed using the C4.5 algorithm to classify the data and generate a decision tree model from the training data set. The model generated was used to predict the class label of the test data set. Results from the data analysis carried out revealed that Kappa statistics was 0.7839, mean absolute error = 0.0058, and root mean squared error = 0.0586. In addition, true positive rate = 0.788, recall = 0.788, precision = 0.749, F-measure = 0.755,MCC = 0.760, ROC = 0.985, and PRC = 0.813. The high values obtained indicates that the model was predicting with a high level of accuracy, ie, 78.84% correctly classified instances. The developed model was used as a knowledge base to develop a very beneficial front-end web application, tagged “RecommendIT” where students can enter their preferences and view company recommendations.