No abstract

No abstract

Mobile learning (m-learning) adoption has increased and shall be demonstrated superior performance by implementing related computing paradigms, such as IoT, edge, mobile edge, fog, AI, and 5G. Mobile cloud architectures (MCAs) enable m-learning with several benefits and face limitations while executing real-time applications. This study investigates the state-of-the-art m-learning architectures, determines a layered m-learning-MCA obtaining numerous benefits of related computing paradigms, and expands m-learning functional structure. It evaluates m-learning performance across the four physical layer’s MCAs—distance cloud, cloudlet, operator-centric cloud, ad hoc cloud, and emerging computing architectures. Surprisingly, only distance-cloud MCA is adopted for developing m-learning systems by ignoring the other three. Performance evaluation shows m-learning gets terrific benefits and users QoE in related computing paradigms. Mobile edge computing offers ultralow latency, whereas the current architecture improves task execution time (1.87, 2.01, 2.63, and 3.97) for the resource-intensive application (i.e., 4.2 MB). Fog using AI algorithms is exceptional for more complex learning objects, IoT is superior for intelligent learning tools, and 5G ultrawideband services are more significant for intelligent video analytics. These findings help learners, educators, and institutions adopt an appropriate model for achieving their academic objectives across educational disciplines. The presented approach enables future research to design innovative architectures considering resource-intensive m-learning application execution requirements, such as video content analytics and virtual reality learning models.

Abstract. Thanks to the major evolutions in the communication technologies and in order to deal with a continuous increase in systems complexity, current applications have to cooperate to achieve a common goal. Modeling such cooperatives applications should stress regular context evolutions and increasingly users requirements. Therefore, we look for a model based solution suitable to cooperative application that can react in response to several unpredictable changes. Driven by the cooperative application structure, we propose, in this paper, an UML extension named "DM profile" ensuring a high-level description for modeling the deployment and its management in distributed application. The proposed contribution is validated through a "Follow Me" case study and implemented through an Eclipse plug-in.

This study aims to assess and measure students' performances using course-key performance indicators (course-KPIs) in an academic course at a Saudi university. The approach includes three aspects of assessment (i) integrating course components and correlating course learning objectives with the program learning domain, (ii) course evaluation using rubrics, and (iii) performance mesurement using a scientific method. Moreover, it presents a novel approach for performance measurement of the course learning skills. In this study, a course has been taken to demonstrate how the KPIs are measured for evaluating students' performances. This approach relies on several specific documents that are developed for the course delivery by following the National Qualification Framework (NQF) in Saudi Arabia and the guidelines of the Accreditation Board for Engineering and Technology (ABET). The performance evaluation outcomes are useful indicators that guide the teachers to improve course learning skills. It also helps the teachers in the quality delivery of the courses and ensures continuous improvement in learning and teaching. This study concludes with an emphasis on the measuring performance using course-KPIs which can be adopted for quality improvement for any academic course in higher education irrespective of data size.

The traditional way of diagnosing malaria takes time, as physicians have to check about 5000 cells to produce the final report. The accuracy of the final report also depends on the physician’s expertise. In the event of a malaria epidemic, a shortage of qualified physicians can become a problem. In the manual method, the parasites are identified by visual identification; this technique can be automated with the use of new algorithms. There are numerous publicly available image datasets containing the intricate structure of parasites, and deep learning algorithms can recognize these complicated patterns in the images. This study aims to identify and localize malaria parasites in the photograph of blood cells using the YOLOv5 model. In this research, a publicly available malaria trophozoite dataset is utilized which contains 1182 data samples. YOLOv5, with the novel technique of weight ensemble and traditional transfer learning, is trained using this dataset, and the results were compared with the other object detection models—for instance, Faster RCNN, SSD net, and the hybrid model. It was observed that YOLOv5 with the ensemble weights yields better results in terms of precision, recall, and mAP values: 0.76, 0.78, and 0.79, respectively. The mAP score closer to 1 signifies a higher confidence in localizing the parasites. This study is the first implementation of ensemble YOLOv5 in the malaria parasite detection field. The proposed ensemble model can detect the presence of malaria parasites and localize them with bounding boxes better than previously used models.

No abstract

Mobile learning (m-learning) adoption has incredibly increased with the implementation of related computing paradigms. The mobile cloud architectures (MCAs) enable m-learning with several benefits and face limitations with m-learning actors’ changing requirements. IoT, edge, mobile edge, fog, AI, and 5G, bring numerous features and increase m-learning efficiency across educational disciplines. This study investigates the state-of-the-art m-learning architectures, determines a unified m-learning MCA, and explores the related computing paradigms’ characteristics to expand m-learning provision. Also, it evaluates m-learning performance across the MCAs and the emerging computing architectures. It finds the four physical layer’s MCAs and several application layer’s m-learning architectures. Only distance-cloud MCA does explore, and the other three MCAs do ignore by experts. Besides, the performance evaluation in related computing paradigms gives terrific benefits and QoE. MEC offers ultra-low latency for resource-intensive m-learning applications, fog using AI algorithms is exceptional for more complex learning objects, IoT is superior for intelligent learning tools, and 5G Ultra-Wideband services are more significant for intelligent video analytics. Eventually, it identifies the challenges, limitations, presents implications, and raises the future research directions to improve m-learning performance efficiency. The study’s findings help m-learning actors, institutions, and potential stakeholders by following their needs.