The transformation of education norms from face-to-face teaching era to the Massive Open Online Courses (MOOCs) era has promoted the rise of the big data era in educational data. This situation has created an opportunity for an educator to utilize the available data from MOOCs to facilitate student learning and performance. Therefore, this research study aims to introduce three types of ensemble learning methods, which are stacking, boosting, and bagging, to predict student performance. These techniques combine the advantage of feature selection method and Synthetic Minority Oversampling Technique (SMOTE) algorithm as a method to balance the number of output features to build the ensemble learning model. As a result, the proposed AdaBoost type ensemble classifier has shown the highest prediction accuracy of more than 90% and Area Under the Curve (AUC) of approximately 0.90. Results by AdaBoost classifier have outperformed other ensemble classifiers, stacking and bagging as well as base classifiers.

No abstract

A key exchange protocol enables two parties to share a common key for encrypting a large amount of data. Authentication is an essential requirement prior to the key exchange process in order to prevent man-in-the-middle attack. It is important to understand the capabilities and performance of the existing key exchange protocols before employing the protocols in our applications. In this paper, we compare Secure Socket Layer, Secure Shell, and Identity-based key exchange protocols by quantifying the performance, complexity, and level of security of each protocol. Detailed experiments and observations are conducted to examine the protocols in terms of disk usage, computation time, and data transmission time. The analysis shows that the identity-based key exchange maintains similar security level as the other protocols, while conveying better performance.

Background – Recently, there have been attempts to develop mHealth applications for asthma self-management. However, there is a lack of applications that can offer accurate predictions of asthma exacerbation using the weather triggers and demographic characteristics to give tailored response to users. This paper proposes an optimised Deep Neural Network Regression (DNNR) model to predict asthma exacerbation based on personalised weather triggers. Methods – With the aim of integrating weather, demography, and asthma tracking, an mHealth application was developed where users conduct the Asthma Control Test (ACT) to identify the chances of their asthma exacerbation. The asthma dataset consists of panel data from 10 users that includes 1010 ACT scores as the target output. Moreover, the dataset contains 10 input features which include five weather features (temperature, humidity, air-pressure, UV-index, wind-speed) and five demography features (age, gender, outdoor-job, outdoor-activities, location). Results – Using the DNNR model on the asthma dataset, a score of 0.83 was achieved with Mean Absolute Error (MAE)=1.44 and Mean Squared Error (MSE)=3.62. It was recognised that, for effective asthma self-management, the prediction errors must be in the acceptable loss range (error<0.5). Therefore, an optimisation process was proposed to reduce the error rates and increase the accuracy by applying standardisation and fragmented-grid-search. Consequently, the optimised-DNNR model (with 2 hidden-layers and 50 hidden-nodes) using the Adam optimiser achieved a 94% accuracy with MAE=0.20 and MSE=0.09. Conclusions – This study is the first of its kind that recognises the potentials of DNNR to identify the correlation patterns among asthma, weather, and demographic variables. The optimised-DNNR model provides predictions with a significantly higher accuracy rate than the existing predictive models and using less computing time. Thus, the optimisation process is useful to build an enhanced model that can be integrated into the asthma self-management for mHealth application.

This research proposed an algorithm to enhance the software requirements prioritization activity, called the multiple perspective prioritization technique. This proposed technique (algorithm) attempts to represent three perspectives: the customer, business and technical perspectives. In addition, this technique is designed for a medium to large number of requirements. The effectiveness and efficiency of the proposed multiple perspective prioritization technique were investigated empirically, in order to show whether it is worthy to be adopted in the real working environment. For this reason, a controlled experiment was conducted among 159 participants, where they were asked to prioritize 42 requirements using the three techniques: our proposed technique (multiple perspective prioritization technique), analytical hierarchical process and Wiegers' technique. The aim of this experiment was to compare and evaluate the multiple perspective prioritization technique with two other techniques, which are among the most widely used prioritization techniques. By this comparison, we would like to show which of these techniques (multiple perspective prioritization technique, analytical hierarchical process and Wiegers) is more efficient, understandable, easy to use, more scalable and less timeconsuming by the participants in practice. This will help the software industry and associated experts to improve the quality of their software products. The experiment outcome reveals in general that the multiple perspective prioritization technique is more effective, understandable, less time-consuming, more scalable and easier for prioritizing requirements than the analytical hierarchical process and Wiegers' techniques. As a conclusion, the multiple perspective prioritization technique is worthy to be implemented in real environments. Our findings reflecting the three perspectives would provide valuable insights into the domain of prioritizing software requirements.