ABSTRACT

Due to tremendous reception on digital learning platforms, many online users tend to register for online courses in MOOC offered by many prestigious universities all over the world and gain a lot on cutting edge technologies in niche courses. As the reception of online courses is increasing on one side, there have been huge dropouts of participants in the online courses causing serious problems for the course owners and other MOOC administrators. Hence, it is deemed necessary to find out the root causes of course dropouts and need to prepare a workable solution to prevent that outcome in the future. In this connection, the authors made use of three machine learning algorithms such as support vector machine, random forest, and conditional random fields. The huge samples of datasets were downloaded from the Open University of China, that is, almost 7K student profiles were extracted for the empirical analysis. The datasets were loaded into a confusion matrix and analyzed for the accuracy, precision, recall, and f-score of the model.

The lack of semantic descriptions for "web service properties" makes it difficult to find suitable web services. Current solutions are mostly based on broker/mediator agent systems. However, these techniques are syntactical, rather than semantics oriented. This article presents a semantic matching approach for discovering Semantic Web services through a broker-based semantic agent (BSA). The BSA includes knowledge-bases and several processing steps. The BSA's knowledge-bases are concept, task, and process ontologies built to describe both functional and non-functional parameters of services. The BSA executes semantic-based matching algorithms to discover similar services through the semantic matching step, process equivalence task, and matching of quality of service parameters. Relevant services are ranked by client preferences utilizing the semantic descriptions of available services. Other matchmaker studies are reviewed and compared with the BSA. Performance of the BSA algorithm is compared with SAM using published data and an experimental setup. The results indicate that our approach is better and more effective in some respects. Keywords Semantic Web, Semantic Web services, broker web applications, ontologies, semantic agents Citation Ç ELİK D, ELÇİ A. A broker-based semantic agent for discovering Semantic Web services through process similarity matching and equivalence considering quality of service.

No abstract

Health 3.0 is a health‐related extension of the Web 3.0 concept. It is based on the semantic Web which provides for semantically organizing electronic health records of individuals. Health 3.0 is rapidly gaining ground as a new research topic in many academic and industrial disciplines. Due to the recent rapid spread of wearable sensors and smart devices with access to social media, migrating health services from the traditional centre‐based health system to personal health care is inevitable. In this current era of greater personalization, treating patients' health problems according to their profile and medical data gathered is possible using the latest information technologies. Consequently, personalized health recommender systems have gained importance. Empowering the utility of advanced Web technology in personalized health systems is still challenging due to pressing issues, such as lack of low cost and accurate smart medical sensors and wearable devices, existing investment in legacy Web system architecture in health sector, heterogeneity of medical data gathered by myriad health care institutions and isolated health services, and interoperability issues as well as multi‐dimensionality of medical data. By tracing recent developments, this paper offers a systematic review through recent research on semantic Web‐enabled personalized health systems, namely, semanticized personalized health recommender systems with the key enabling technologies, major applications, and successful case studies. Critical questions derived from the research studies were discussed, and main directions of open issues were identified leading to recommendations for future study in the field of personalized health recommender systems.

No abstract

No abstract

No abstract