Aim/Purpose: Electronic examinations have some inherent problems. Students have expressed negative opinions about electronic examinations (e-examinations) due to a fear of, or unfamiliarity with, the technology of assessment, and a lack of knowledge about the methods of e-examinations. Background: Electronic examinations are now a viable alternative method of assessing student learning. They provide freedom of choice, in terms of the location of the examination, and can provide immediate feedback; students and institutions can be assured of the integrity of knowledge testing. This in turn motivates students to strive for deeper learning and better results, in a higher quality and more rigorous educational process. Methodology : This paper compares an e-examination system at FUT Minna Nigeria with one in Australia, at the University of Tasmania, using case study analysis. The functions supported, or inhibited, by each of the two e-examination systems, with different approaches to question types, cohort size, technology used, and security features, are compared. Contribution: The researchers’ aim is to assist stakeholders (including lecturers, invigilators, candidates, computer instructors, and server operators) to identify ways of improving the process. The relative convenience for students, administrators, and lecturer/assessors and the reliability and security of the two systems are considered. Challenges in conducting e-examinations in both countries are revealed by juxtaposing the systems. The authors propose ways of developing more effective e-examination systems. Findings: The comparison of the two institutions in Nigeria and Australia shows e-examinations have been implemented for the purpose of selecting students for university courses, and for their assessment once enrolled. In Nigeria, there is widespread systemic adoption for university entrance merit selection. In Australia this has been limited to one subject in one state, rather than being adopted nationally. Within undergraduate courses, the Nigerian scenario is quite extensive; in Australia this adoption has been slower, but has penetrated a wide variety of disciplines. Recommendations for Practitioners: Assessment integrity and equipment reliability were common issues across the two case studies, although the delivery of e-examinations is different in each country. As with any procedural process, a particular solution is only as good as its weakest attribute. Technical differences highlight the link between e-examination system approaches and pedagogical implications. It is clear that social, cultural, and environmental factors affect the success of e-examinations. For example, an interrupted electrical power supply and limited technical know-how are two of the challenges affecting the conduct of e-examinations in Nigeria. In Tasmania, the challenge with the “bring your own device” (BYOD) is to make the system operate on an increasing variety of user equipment, including tablets. Recommendation for Researchers: The comparisons between the two universities indicate there will be a productive convergence of the approaches in future. One key proposal, which arose from the analysis of the existing e-examination systems in Nigeria and Australia, is to design a form of “live” operating system that is deployable over the Internet. This method would use public key cryptography for lecturers to encrypt their questions online. Impact on Society : If institutions are to transition to e-examinations, one way of facilitating this move is by using computers to imitate other assessment techniques. However, higher order thinking is usually demonstrated through open-ended or creative tasks. In this respect the Australian system shows promise by providing the same full operating system and software application suite to all candidates, thereby supporting assessment of such creative higher order thinking. The two cases illustrate the potential tension between “online” or networked reticulation of questions and answers, as opposed to “offline” methods. Future Research: A future design proposition is a web-based strategy for a virtual machine, which is launched into candidates’ computers at the start of each e-examination. The new system is a form of BYOD externally booted e-examination (as in Australia) that is deployable over the Internet with encryption and decryption features using public key cryptography (Nigeria). This will allow lecturers to encrypt their questions and post them online while the questions are decrypted by the administrator or students are given the key. The system will support both objective and open-ended questions (possibly essays and creative design tasks). The authors believe this can re-define e-examinations as the “gold standard” of assessment.

Email has continued to be an integral part of our lives and as a means for successful communication on the internet. The problem of spam mails occupying a huge amount of space and bandwidth, and the weaknesses of spam filtering techniques which includes misclassification of genuine emails as spam (false positives) are a growing challenge to the internet world. This research work proposed the use of a metaheuristic optimization algorithm, the whale optimization algorithm (WOA), for the selection of salient features in the email corpus and rotation forest algorithm for classifying emails as spam and non-spam. The entire datasets were used, and the evaluation of the rotation forest algorithm was done before and after feature selection with WOA. The results obtained showed that the rotation forest algorithm after feature selection with WOA was able to classify the emails into spam and non-spam with a performance accuracy of 99.9% and a low FP rate of 0.0019. This shows that the proposed method had produced a remarkable improvement as compared with some previous methods.

The incessant destruction and harmful tendency of malware on mobile devices has made malware detection an indispensable continuous field of research. Different matching/mismatching approaches have been adopted in the detection of malware which includes anomaly detection technique, misuse detection, or hybrid detection technique. In order to improve the detection rate of malicious application on the Android platform, a novel knowledge-based database discovery model that improves apriori association rule mining of a priori algorithm with Particle Swarm Optimization (PSO) is proposed. Particle swarm optimization (PSO) is used to optimize the random generation of candidate detectors and parameters associated with apriori algorithm (AA) for features selection. In this method, the candidate detectors generated by particle swarm optimization form rules using apriori association rule. These rule models are used together with extraction algorithm to classify and detect malicious android application. Using a number of rule detectors, the true positive rate of detecting malicious code is maximized, while the false positive rate of wrongful detection is minimized. The results of the experiments show that the proposed a priori association rule with Particle Swarm Optimization model has remarkable improvement over the existing contemporary detection models.

Several machine learning techniques based on supervised learning have been adopted in the classification of malware. However, only supervised learning techniques have proofed insufficient for malware classification task. This paper presents a classification of android malware using candidate detectors generated from an unsupervised association rule of Apriori algorithm improved with particle swarm optimization to train three different supervised classifiers. In this method, features were extracted from Android applications byte-code through static code analysis, selected and were used to train supervised classifiers. Using a number of candidate detectors, the true positive rate of detecting malicious code is maximized, while the false positive rate of wrongful detection is minimized. The results of the experiments show that the proposed combined technique has remarkable benefits over the detection using only supervised or unsupervised learners.