Evaluating Hybrid Model Performance in Predicting the Impact of Lockdown on Controlling Covid-19 Cases Progression in Middle Income Settings
A Method for the Identification of Denial of Service (DoS) Attack in Network Traffic using Machine Learning Techniques
Agriculture Management System
Unveiling Sentiment Analysis: A Comparative Study of LSTM and Logistic Regression Models with XAI Insights
Resume Screener System
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
Integrated Atlas Based Localisation Features in Lungs Images
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
A Computer Based Test (CBT) Local Area Network (LAN) security center was developed using XAMPP (Cross-Platform Apache MariaDB PHP and Perl) integrated net-base application and JAVA object-oriented programming language, using a backend Oracle database (JBuilder and NetBeans) where the Media Access Control (MAC) address of the users will be saved and using hard to spoof measure that is correlated to location of LAN to prevent MAC address spoof. This security system is controlled through the network via the server and controls all clients that choose to use the resources like e-exam platform, e-library, etc. It also views the activities of the users in the network (surveillance system). The security system also keeps history/records of all detection sensor/ MAC address of users, to track any activities carried with the resources. The performance under test was found to be satisfactory, as all unauthorized users are blocked and appropriate warning messages are sent to the client's system by the server when the user attempts to login. This eliminates external users from gaining access to the examination platform.
Phishing is a cybercrime that is described as an art of cloning a web page of a legitimate company with the aim of obtaining confidential data of unsuspecting internet users. Recent researches indicate that a number of phishing detection algorithms have been introduced into the cyber space, however, most of them depend on an existing blacklist or whitelist classification. Therefore, when a new phishing web page is introduced, the detection algorithms find it difficult to correctly classify it as phishing. This paper puts forward a soft computing approach called Artificial Neural Network (ANN) algorithm with confusion matrix analysis for the detection of e-banking phishing websites. The proposed ANN algorithm produces a remarkable percentage of accuracy and reduced false positive rate during detection. This shows that, the ANN algorithm with confusion matrix analysis can produce competitive results that is suitable for detecting phishing in e-banking websites.
User authentication is one of the most important security characteristics of any system given today's globalized digital life style. The safety and security of sensitive data, privacy and also critical infrastructure relies primarily on authentication. Amongst all authentication schemes, text-based passwords are the most deployed across various platforms, thus the importance of evaluating user password management practice cannot be overemphasized. This research, via, a case study aimed at establishing the theoretical password knowledge in comparison to actual password management practice of staff and students from Information Technology (IT) inclined departments of the Federal University of Technology, Minna. Results from the survey reveal that the target respondents are knowledgeable on good password management policies. However, actual password practice results by the respondents showed that they do not comply and effectively implement the theoretical password knowledge they possess. Thus it can be concluded that there is a significant difference between what respondents know compared to their actual practice. Numerous implications abound when this is the case as it makes users more vulnerable to security risks of unauthorized access by unauthorized users.
Personnel recruitment operation which involves selecting the right person for the right job is an essential human resource operation of an organization due to the fact that organizations’ performance depends on its personnel performance. However, personnel selection for recruitment operation of human resource management has various operational behaviors, and when carrying out the operation the operational behaviors should be considered. Due to this consideration, carrying out personnel selection for recruitment operation is complex. To minimize the complexity, various research works developed personnel selection expert systems to carry out personnel selection for recruitment operation considering some of its operational behaviors. However, the behavioral change of personnel selection operation was not considered during the development of their respective proposed expert systems. This study identified an adaptive personnel selection model developed in a research work and the behavioral change feature of personnel selection for recruitment operation was considered. The adaptive personnel selection model was developed using a C4.5 decision tree and frequent and non-frequent patter analysis of data mining. However, the adaptive feature of the adaptive personnel selection model was improved and then implemented as this study proposed adaptive personnel selection expert system.
A phishing URL is a web address created with the intent of deceiving users into releasing their personal and private data or downloading malware into the users' systems without their knowledge. Increase in the adoption of the Internet has led to corresponding increase in the number of phishing sites globally. Many classification techniques have been developed for detecting phishing URLs. This paper seeks to evaluate the performances of existing techniques. With dataset obtained from UCI Machine Learning Repository, the algorithms were assessed in terms of Accuracy, Precision, Recall, F-Measure, Receiver Operating Characteristic (ROC) area and Root Mean Squared Error (RMSE). From analysis and comparison with results from related literature, the Random Forest was found to perform best.
CAPTCHA is a piece of program designed to distinguish human beings from bots. These are computer generated tests which can be solved by humans but will be difficult to be solved by computers. Bots smuggled CAPTCHAs are gradually on the increase in order to deceive unsuspecting users and inadvertently infect systems. From the available literature reviewed so far, there is no model to detect or predict CAPTCHA smuggling attack. The aim of this work is to come up with a model capable of predicting this attack. The approach used was based on deep supervised neural network approach. In order to achieve the aim, framework based on hyperparameter specification was developed. The model was evaluated on the available CAPTCHA smuggling dataset. The accuracy of prediction achieved in this work is 77.89% at consistency of 0.1543. The sensitivity and specificity of the model are 78.11% and 78.2%, respectively.
