China
Africa
Explore chapters and articles related to this topic
Impact of AI on Teaching Pedagogy and its Integration for Enhancing Teaching-Learning
Published in Prathamesh Churi, Shubham Joshi, Mohamed Elhoseny, Amina Omrane, Artificial Intelligence in Higher Education, 2023
Bhagwan Toksha, Trishul Kulkarni, Prashant Gupta
The overlapping areas of AI and educational data mining can be influential in the teaching-learning process. The three independent fields 1) pedagogies equipped with the ease of computational facilities, 2) support of learning analytics and 3) smart machines mimicking natural intelligence can overlap as shown in Figure 7.3. The educational institutions have already started embracing such approaches integrating the AI component in the Educational Data Mining (EDM) to “track” students’ behaviours, figuring out losses such as students’ dropping out, so that it will offer well-timed assists via the regular evaluation of facts and track records in the class, and timely compliance of assignments (Luckin et al., 2016). The EDM designs have evolved as predictive models with data mining platforms. EDM helps in better comprehension of the dataset and the context of collected data. A method involving machine learning algorithms enabling the analysis of educational data in an iterative process where the knowledge discovery and the accuracy of the predictive model is studied by Toivonen et al. (Toivonen et al., 2019). An increase in accuracy with time and possible knowledge discovery via the accumulated clustered data processed with Neural N-Tree models is reported in this article. The early alert mechanism is a smart intervention that educational institutes can incorporate for timely identification of at-risk learners (Atif et al., 2020). The significance of student early alert systems is that support could be offered to high-risk students while they are still enrolled in the unit and able to influence their learning achievements before the completion of the unit. The requirement from the instructor is only identifying the at-risk student and designing further teaching/learning activities in a way that would bring change in the learners’ behaviours and learning tendencies. The system will keep sending the formal timely interventions and alerts to the learners.
Efficient computation of comprehensive statistical information of large OWL datasets: a scalable approach
Published in Enterprise Information Systems, 2023
Heba Mohamed, Said Fathalla, Jens Lehmann, Hajira Jabeen
Enterprise data management (EDM) is a process that encompasses effectively collecting, managing, and analysing enterprise data with the objective of producing useful information that supports decision-making as well as the subsequent data usage to improve business efficiency. The structure of enterprise data nowadays is far from being static, which made it more difficult for an enterprise to efficiently manage, understand, and use their data (Wood 2010). The management and the understanding of enterprise data has been improved by using Semantic Web technologies such as the Resource Description Framework (RDF), RDF Schema, and the Web Ontology Language (OWL) (Ma et al. 2009). Over the past decade, we have observed an increasing volume of semantic data, belonging to various domains available on the Web (Fathalla et al. 2019; Fathalla et al. 2018), resulting in large-scale semantic datasets (either in RDF or OWL format). These datasets are produced based on the ontology to which they conform (Li and Sima 2015; Fathalla et al. 2019). Ontologies are particularly widespread in the life sciences, where several large biomedical ontologies have been developed, including the Biological Pathways Exchange (BioPAX) ontology,1 and the National Cancer Institute thesaurus,2 and enterprise data representation, including Zachman’s Enterprise Ontology (Kappelman and Zachman 2013). Ontologies are being used in application areas like Software Engineering (Wongthongtham, Pakdeetrakulwong, and Marzooq 2017; Pileggi, Lopez-Lorca, and Beydoun 2018), Bioinformatics (Facchiano 2017), Data Integration (De Giacomo et al. 2018), scholarly information (Fathalla et al. 2020) and Enterprise Data Management (Rajabi, Minaei, and Seyyedi 2013).