Early prediction of students’ learning performance and analysis of student behavior in a virtual learning environment (VLE) are crucial to minimize the high failure rate in online courses during the COVID-19 pandemic. Nevertheless, traditional machine learning models fail to predict student performance in the early weeks due to the lack of students’ activities’ data in a week-wise timely manner (i.e., spatiotemporal feature issues). Furthermore, the imbalanced data distribution in the VLE impacts the prediction model performance. Thus, there are severe challenges in handling spatiotemporal features, imbalanced data sets, and a lack of explainability for enhancing the confidence of the prediction system. Therefore, an intelligent framework for explainable student performance prediction (ESPP) is proposed in this study in order to provide the interpretability of the prediction results. First, this framework utilized a time-series weekly student activity data set and dealt with the VLE imbalanced data distribution using a hybrid data sampling method. Then, a combination of convolutional neural network (CNN) and long short-term memory (LSTM) was employed to extract the spatiotemporal features and develop the early prediction deep learning (DL) model. Finally, the DL model was explained by visualizing and analyzing typical predictions, students’ activities’ maps, and feature importance. The numerical results of cross-validation showed that the proposed new DL model (i.e., the combined CNN-LSTM and ConvLSTM), in the early prediction cases, performed better than the baseline models of LSTM, support vector machine (SVM), and logistic regression (LR) models.

For higher education institutions that encourage digital transformation, understanding the barriers are necessary for the digital transformation accomplishment. The purpose of this paper is to present a review of the literature on barriers to digital transformation in higher education. To get a wide overview in identifying the barriers to the implementation of digital transformation, a structured literature review was used to select the relevant studies published. Nine categories were identified based on the literature reviewed: vision, strategy and policy, resources, leadership, digital skill and knowledge, technology, adaptability, resistance to change, and government and economic. Our findings provided a fish-bone diagram that outlines twenty-two barriers to digital transformation in higher education. The main contribution of this study is a synthesis of the state of the art of barriers to digital transformation in higher education. We contribute to provide a common basic understanding of barriers to digital transformation in higher education to overcome barriers for improving the possibility of success. Moreover, we give an insight into future research on barriers exploration

Over the last decade, numerous research efforts have been dedicated to countering malicious mobile applications. Given its market share, Android OS has been the primary target for most of these apps. Researchers have devised numerous solutions to protect Android devices and their users, categorizing them into static and dynamic approaches. Each of these approaches has its own advantages and disadvantages. The hybrid approach aims to combine the benefits of both. This study closely examines the hybrid solutions proposed between 2012 and 2023, highlighting their strengths and limitations. The objective of this study is to provide a comprehensive review of existing research on Android malware detection using a hybrid approach. Our review identifies several issues related to hybrid detection approaches, including datasets, feature utilization and selection, working environments, detection order mechanisms, integrity of the detection step, detection algorithms, and the use of automated input generation. Key findings of this study include: (i) the majority of studies have not adequately addressed on-device detection and have overlooked the importance of system usability, (ii) many studies rely on outdated datasets that do not accurately represent the current threat landscape, (iii) there is a need for a methodology to detect zero-day attacks, and (iv) most research has not paid attention to the impact of automated input generation on malware behavior and code coverage. We also discuss some open issues and future directions on the aspect that will help to substantiate the hybrid approach study.

Learning management systems (LMSs) have been used massively due to the growing utilization of distance learning. This advancement has led to increased educational data that can be analyzed to improve the quality of the learning process. Learning analytics (LA) is one of the most important methods that can be used to analyze student performance. In this paper, we proposed an LA method based on deep learning, i.e., transformer encoder, to sequentially predict the student’s final performance based on log activities provided by an LMS. The objective is to predict at-risk students of failing so that they can be mitigated as soon as possible. The proposed model was evaluated on the Open University LA Dataset (OULAD) for daily or weekly prediction. The results show that the model could predict at the early stage with an accuracy of 83.17% on withdrawn versus pass-distinction classes. Meanwhile, for other tasks, i.e., withdrawn-fail versus pass-distinction and fail versus pass-distinction tasks, the accuracy was at least 76% at the early stage. The proposed model was compared to the LSTM model. We found that the transformer encoder performed better than the LSTM, with the average difference values from 1% to 3% in terms of accuracy and from 3% to 7% in terms of F1-score for all tasks, based on the statistical testing. Furthermore, the ablation study using positional encoding, different feature aggregation methods, and weighted loss function for the imbalanced class problem was done. In OULAD, we found that model without positional encoding was better in all cases. In contrast, weekly feature aggregation and the use of the weighted loss function performed better only for some cases.

6LoWPAN is one of the implementations of WSN that using IPv6 as sensor addressing. 6LoWPAN is categorized in the new technology and still being developed. This causes issues about the networks performance to create the communication path and collecting data. Routing Protocol for Low-power-loosy (RPL) is a routing protocol used in 6LoWPAN. In RPL, there are two kind of objective functions development. Objective function is path selection mechanism when formation of the networks. This research is focus on performance analysis in two objective functions RPL that are Minimum Rank with Hysteresis Objective Function (MRHOF) and Objective Function Zero (OFO). This research observed using COOJA as a WSN simulator. The parameter that observed in this research are: networks convergence time, power consumption, ETX, hop, Packet Delivery Ratio (PDR), latency, PDR in mobility node. Based on the simulation we concluded that MRHOF give better performance than OF0 in terms of network quality. The implementation of MRHOF is suitable for use in sensor network that require data delivery in the reliable network. While OF0 is suitable for use in sensor network that require fast formation network link and low power consumption.