Aim/Purpose: The digital ecosystem has contributed to the acceleration of digital and mobile educational tools across institutions worldwide. The research displays educators’ perspectives on web applications on mobile devices that can be used to engage and challenge students while impacting their learning. Background: Explored are elements of technology in education and challenges and successes reported by instructors to shift learning from static to dynamic. Methodology: Insights for this study were gained through questionnaires and focus groups with university educators in the United Arab Emirates. Key questions addressed are (1) challenges/benefits, (2) types of mobile technology applications used by educators, and (3) strategies educators use to support student learning through apps. The research is assisted by focus groups and a sample of 42 completed questionnaires. Contribution: The work contributes to web/mobile strategic considerations in the classroom that can support student learning and outcomes. Findings: The results reported showcase apps that were successfully implemented in classrooms and provide a perspective for today’s learning environment that could be useful for instructors, course developers, or any educational institutions. Recommendations for Practitioners: Academics can integrate suggested tools and explore engagement and positive associations with tools and technologies. Recommendation for Researchers: Researchers can consider new learning applications, mobile devices, course design, learning strategies, and student engagement practices for future studies. Impact on Society: Digitization and global trends are changing how educators teach, and students learn; therefore, gaps need to be continually filled to keep up with the pace of ever-evolving digital technologies that can engage student learning. Future Research: Future research may focus on interactive approaches toward mobile devices in higher education learning and shorter learning activities to engage students.

Aim/Purpose: This exploratory qualitative case study examines the perceptions of high-school learners of English regarding a pedagogical intervention involving progressive reduction of captions (full, sentence-level, keyword captions, and no-captions) in enhancing language learning. Background: Recognizing the limitations of caption usage in fostering independent listening comprehension in non-captioned environments, this research builds upon and extends the foundational work of Vanderplank (2016), who highlighted the necessity of a comprehensive blend of tasks, strategies, focused viewing, and the need to actively engage language learners in watching captioned materials. Methodology: Using a qualitative research design, the participants were exposed to authentic video texts in a five-week listening course. Participants completed an entry survey, and upon interaction with each captioning type, they wrote individual reflections and participated in focus group sessions. This methodological approach allowed for an in-depth exploration of learners’ experiences across different captioning scenarios, providing a nuanced understanding of the pedagogical intervention’s impact on their perceived language development process. Contribution: By bridging the research-practice gap, our study offers valuable insights into designing pedagogical interventions that reduce caption dependence, thereby preparing language learners for success in real-world, caption-free listening scenarios. Findings: Our findings show that learners not only appreciate the varied captioning approaches for their role in supporting text comprehension, vocabulary acquisition, pronunciation, and on-task focus but also for facilitating the integration of new linguistic knowledge with existing background knowledge. Crucially, our study uncovers a positive reception towards the gradual shift from fully captioned to uncaptioned materials, highlighting a stepwise reduction of caption dependence as instrumental in boosting learners’ confidence and sense of achievement in mastering L2 listening skills. Recommendations for Practitioners: The implications of our findings are threefold: addressing input selection, task design orchestration, and reflective practices. We advocate for a deliberate selection of input that resonates with learners’ interests and contextual realities alongside task designs that progressively reduce caption reliance and encourage active learner engagement and collaborative learning opportunities. Furthermore, our study underscores the importance of reflective practices in enabling learners to articulate their learning preferences and strategies, thereby fostering a more personalized and effective language learning experience. Recommendation for Researchers: Listening comprehension is a complex process that can be clearly influenced by the input, the task, and/or the learner characteristics. Comparative studies may struggle to control and account for all these variables, making it challenging to attribute observed differences solely to caption reduction. Impact on Society: This research responds to the call for innovative teaching practices in language education. It sets the stage for future inquiries into the nuanced dynamics of caption usage in language learning, advocating for a more learner-centered and adaptive approach. Future Research: Longitudinal quantitative studies that measure comprehension as captions support is gradually reduced (full, partial, and keyword) are strongly needed. Other studies could examine a range of individual differences (working memory capacity, age, levels of engagement, and language background) when reducing caption support. Future research could also examine captions with students with learning difficulties and/or disabilities.

Forensic document forgery investigations have elevated the need for source identification for printed documents during the past few years. It is necessary to create a reliable and acceptable safety testing instrument to determine the credibility of printed materials. The proposed system in this study uses a neural network to detect the original printer used in forensic document forgery investigations. The study uses a deep neural network method, which relies on the quality, texture, and accuracy of images printed by various models of Canon and HP printers. The datasets were trained and tested to predict the accuracy using logical function, with the goal of creating a reliable and acceptable safety testing instrument for determining the credibility of printed materials. The technique classified the model with 95.1% accuracy. The proposed method for identifying the source of the printer is a non-destructive technique.

Currently, Android is a booming technology that has occupied the major parts of the market share. However, as Android is an open-source operating system there are possibilities of attacks on the users, there are various types of attacks but one of the most common attacks found was malware. Malware with machine learning (ML) techniques has proven as an impressive result and a useful method for malware detection. Here in this paper, we have focused on the analysis of malware attacks by collecting the dataset for the various types of malware and we trained the model with multiple ML and deep learning (DL) algorithms. We have gathered all the previous knowledge related to malware with its limitations. The machine learning algorithms were having various accuracy levels and the maximum accuracy observed is 99.68%. It also shows which type of algorithm is preferred depending on the dataset. The knowledge from this paper may also guide and act as a reference for future research related to malware detection. We intend to make use of Static Android Activity to analyse malware to mitigate security risks.

To assess a country's economic outlook and achieve higher economic growth, econometric models and prediction techniques are significant tools. Policymakers are always concerned with the correct future estimates of economic variables to take the right economic decisions, design better policies and effectively implement them. Therefore, there is a need to improve the predictive accuracy of the existing models and to use more sophisticated and superior algorithms for accurate forecasting. Deep learning models like recurrent neural networks are considered superior for forecasting as they provide better predictive results as compared to many of the econometric models. Against this backdrop, this paper presents the feasibility of using different deep-learning neural network architectures for trade forecasting. It predicts export trade using different recurrent neural architectures such as 'vanilla recurrent neural network (VRNN)', 'bi-directional long short-term memory network (Bi-LSTM)', 'bi-directional gated recurrent unit (Bi-GRU)' and a hybrid 'bi-directional LSTM and GRU neural network'. The performances of these models are evaluated and compared using different performance metrics such as Mean Square Error (MSE), Mean Absolute Error (MAE) Root Mean Squared Error (RMSE), Root Mean Squared Logarithmic Error (RMSLE) and coefficient of determination <em>R</em>-squared (<em>R</em>²). The results validated the effective export prediction for India.

To better explore the application of unsupervised learning neural networks in psychological interventions for college students, this study investigates the relationships among latent psychological variables from the perspective of neural networks. Firstly, college students' psychological crisis and intervention systems are analysed, identifying several shortcomings in traditional psychological interventions, such as a lack of knowledge dissemination and imperfect management systems. Secondly, employing the Human-Computer Interaction (HCI) approach, a structural equation model is constructed for unsupervised learning neural networks. Finally, this study further confirms the effectiveness of unsupervised learning neural networks in psychological interventions for college students. The results indicate that in psychological intervention for college students. Additionally, the weightings of the indicators at the criterion level are calculated to be 0.35, 0.27, 0.19, 0.11 and 0.1. Based on the results of HCI, an emergency response system for college students' psychological crises is established, and several intervention measures are proposed.

This article presents a case study that outlines the potential of DigiBot technology, an interactive automated response program, in mobile open learning (MOL) for business subjects. The study, which draws on a project implemented in Sub-Saharan Africa, demonstrates the applications of DigiBots delivered via WhatsApp to over 650,000 learners. Employing a mixed-methods approach, the article reports on live event tracking, qualitative observations from facilitators and learning technologists, and a learner survey (<i>N</i> = 304,000). The research offers practical recommendations and proposes a model for scalable DigiBot learning. Findings reveal that in this case, DigiBot MOL had the potential to effectively address two key obstacles in open learning: accessibility and scalability. Leveraging mobile platforms such as WhatsApp mitigates accessibility restrictions, particularly in resource-constrained contexts, while tailored micro-learning enhances scalability.

In India, 70% of the Indian population is dependent on agriculture, yet agriculture generates only 13% of the country's gross domestic product. Several factors contribute to high levels of stress among farmers in India, such as increased input costs, draughts, and reduced revenues. The problem lies in the absence of an integrated farm advisory system. A farmer needs help to bridge this information gap, and they need it early in the crop's lifecycle to prevent it from being destroyed by pests or diseases. This research involves developing deep learning algorithms such as <i>ResNet18</i> and <i>DenseNet121</i> to help farmers diagnose crop diseases earlier and take corrective actions. By using deep learning techniques to detect these crop diseases with images farmers can scan or click with their smartphones, we can fill in the knowledge gap. To facilitate the use of the models by farmers, they are deployed in Android-based smartphones.

In order to improve recommendation coverage, a personalised recommendation method for English online learning resources based on improved collaborative filtering algorithm is studied to enhance the comprehensiveness of personalised recommendation for learning resources. Use matrix decomposition to decompose the user English online learning resource rating matrix. Cluster low dimensional English online learning resources by improving the K-means clustering algorithm. Based on the clustering results, calculate the backfill value of English online learning resources and backfill the information matrix of low dimensional English online learning resources. Using an improved collaborative filtering algorithm to calculate the predicted score of learning resources, personalised recommendation of English online learning resources for users based on the predicted score. Experimental results have shown that this method can effectively backfill English online learning resources, and the resource backfilling effect is excellent, and it has a high recommendation coverage rate.

The conventional methods for identifying English online course learning behaviours have the problems of low recognition accuracy and high time cost. Therefore, a multimodal data fusion-based method for identifying English online course learning behaviours is proposed. Firstly, the analytic hierarchy process is used for decision fusion of multimodal data of learning behaviour. Secondly, based on the fusion results of multimodal data, weight coefficients are set to minimise losses and extract learning behaviour features. Finally, based on the extracted learning behaviour characteristics, the optimal classification function is constructed to classify the learning behaviour of English online courses. Based on the transfer information of learning behaviour status, the identification of online course learning behaviour is completed. The experimental results show that the recognition accuracy of the proposed method is above 90%, and its recognition accuracy is and can shorten the recognition time of learning behaviour, with high practical application reliability.

This paper proposes a method for predicting college students' performance based on learning behaviour data mining. The method addresses the issue of limited sample size affecting prediction accuracy. It utilises the K-means clustering algorithm to mine learning behaviour data and employs a density-based approach to determine optimal clustering centres, which are then output as the results of the clustering process. These clustering results are used as input for an attention encoder-decoder model to extract features from the learning behaviour sequence, incorporating an attention mechanism, sequence feature generator, and decoder. The characteristics derived from the learning behaviour sequence are then used to establish a prediction model for college students' performance, employing support vector regression. Experimental results demonstrate that this method accurately predicts students' performance with a relative error of less than 4% by leveraging the results obtained from learning behaviour data mining.

The research goal is to solve the problems of low accuracy and long time existing in traditional teaching reform performance evaluation methods, a performance evaluation method of teaching reform based on hierarchical multi-task deep learning is proposed. Under the principle of constructing the evaluation index system, the evaluation indicator system should be constructed. The weight of the evaluation index is calculated through the analytic hierarchy process, and the calculation result of the evaluation weight is taken as the model input sample. A hierarchical multi-task deep learning model for teaching reform performance evaluation is built, and the final teaching reform performance score is obtained. Through relevant experiments, it is proved that compared with the experimental comparison method, this method has the advantages of high evaluation accuracy and short time, and can be further applied in relevant fields.

This paper analyses the adoption of learning analytics to predict at-risk students. A total of 233 research articles between 2004 and 2023 were collected from Scopus for this study. They were analysed in terms of the relevant types and sources of data, targets of prediction, learning analytics methods, and performance metrics. The results show that data related to students' academic performance, socio-demographics, and learning behaviours have been commonly collected. Most studies have addressed the identification of students who have a higher chance of poor academic performance or dropping out of their courses. Decision trees, random forests, and artificial neural networks are the most frequently used techniques for prediction, with ensemble methods gaining popularity in recent years. Classification accuracy, recall, sensitivity, and true positive rate are commonly used as performance metrics for evaluation. The results reveal the potential of learning analytics for informing timely and evidence-based support for at-risk students.