“…Since the entire profile construction is an information retrieval process, calculating the profile accuracy is also based on the metrics used when evaluating information retrieval systems [21].…”
Personalized Web Applications aim to improve the user's browsing experience by offering customized products and services based on his preferences and needs. A key feature of a successful personalization system is building profiles that accurately express the real interests and needs of each user. In this work, we focus on creating accurate, complete and dynamic profiles by capturing and tracking the users’ browsing activities. Moreover, we implement techniques to increase the accuracy of the retrieved user profiles by collecting more browsing data, identifying the most important concepts and removing irrelevant ones, and the number of levels from the concept hierarchy in the reference ontology that we should use to efficiently represent the users’ reel interests and needs. The result is a complete, dynamic, and accurate user profile that can be used to give users better-personalized browsing experience.
“…Since the entire profile construction is an information retrieval process, calculating the profile accuracy is also based on the metrics used when evaluating information retrieval systems [21].…”
Personalized Web Applications aim to improve the user's browsing experience by offering customized products and services based on his preferences and needs. A key feature of a successful personalization system is building profiles that accurately express the real interests and needs of each user. In this work, we focus on creating accurate, complete and dynamic profiles by capturing and tracking the users’ browsing activities. Moreover, we implement techniques to increase the accuracy of the retrieved user profiles by collecting more browsing data, identifying the most important concepts and removing irrelevant ones, and the number of levels from the concept hierarchy in the reference ontology that we should use to efficiently represent the users’ reel interests and needs. The result is a complete, dynamic, and accurate user profile that can be used to give users better-personalized browsing experience.
“…As part of the second phase, the segmented data are sent to a front-desk (FD) component (4), which will then seek for a legacy version or else a compatible AR model based on a semantic-based search [36]. If the FD finds a legacy version, the legacy version is assigned with a teacher role (5a); otherwise the model builder (MB) component builds the AR model upon any labelled data available at this step (5d).…”
Transfer learning is a growing field that can address the variability of activity recognition problems by reusing the knowledge from previous experiences to recognise activities from different conditions, resulting in the leveraging of resources such as training and labelling efforts. Although integrating ubiquitous sensing technology and transfer learning seem promising, there are some research opportunities that, if addressed, could accelerate the development of activity recognition. This paper presents TL-FmRADLs; a framework that converges the feature fusion strategy with a teacher/learner approach over the active learning technique to automatise the self-training process of the learner models. Evaluation TL-FmRADLs is conducted over InSync; an open access dataset introduced for the first time in this paper. Results show promising effects towards mitigating the insufficiency of labelled data available by enabling the learner model to outperform the teacher’s performance.
“…Ontologies provide a powerful framework for representing this conceptual metadata layer as they provide the necessary flexibility to define relationships between concepts across the heterogeneous data sources. The search backend can then leverage these relationships that embody the background knowledge built into the ontology (Ramkumar & Poorna, 2014).…”
A large overhead in the analytics process is the time required to find relevant data. We present an ontology-driven data discovery application, implemented over IBM’s Cognitive Enterprise Data Platform (CEDP). CEDP contains a large collection of heterogeneous data assets from enterprise-wide data sources. The application accelerates the time required for data consumers to search and find data relevant for their analytics applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.