Context-Aware Reasoning Framework for Multi-user Recommendations in Smart Home
TL;DR: A context-aware reasoning framework that adapts to the needs and preferences of inhabitants continuously to provide contextually relevant recommendations to the group of users in a smart home environment is introduced.
Abstract: This paper introduces a context-aware reasoning framework that adapts to the needs and preferences of inhabitants continuously to provide contextually relevant recommendations to the group of users in a smart home environment. User’s activity and mobility plays a crucial role in defining various contexts in and around the home. The observation data acquired from disparate sensors, called user’s context, is interpreted semantically to implicitly disambiguate the users that are being recommended to. The recommendations are provided based on the relationship that exist among multiple users and the decision is made as per the preference or priority. The proposed approach makes extensive use of multimedia ontology in the life cycle of situation recognition to explicitly model and represent user’s context in smart home. Further, dynamic reasoning is exploited to facilitate context-aware situation tracking and intelligently recommending appropriate actions which suit the situation. We illustrate use of the proposed framework for Smart Home use-case.
••29 Nov 2016
TL;DR: This work proposes to improve the accuracy of probabilistic inference systems by including context information, and proves the suitability of such an approach in the application scenario of user activity recognition in a smart home environment.
Abstract: Multi-sensor data fusion is extensively used to merge data collected by heterogeneous sensors deployed in smart environments. However, data coming from sensors are often noisy and inaccurate, and thus probabilistic techniques, such as Dynamic Bayesian Networks, are often adopted to explicitly model the noise and uncertainty of data. This work proposes to improve the accuracy of probabilistic inference systems by including context information, and proves the suitability of such an approach in the application scenario of user activity recognition in a smart home environment. However, the selection of the most convenient set of context information to be considered is not a trivial task. To this end, we carried out an extensive experimental evaluation which shows that choosing the right combination of context information is fundamental to maximize the inference accuracy.
••14 Dec 2015
TL;DR: A novel context-aware situation-tracking framework that makes use of Dynamic Bayesian networks to predict and track the dynamically changing situations and uses Multimedia Web Ontology Language (MOWL) to represents the ontology.
Abstract: Ubiquitous intelligent devices have enabled provision of smart services to people in seamless way. Context-awareness helps understand current state-of-affairs or the situation in which presently the system is. This understanding helps the IoT application provide more relevant and smarter services based on situations that change over a period of time. In this paper, we propose a novel context-aware situation-tracking framework that makes use of an ontology. The ontology represents the conceptual model of a dynamic world, where situations evolve over time in changing contexts. The ontology provides the reasoning framework to infer about a situation based on the input context data as well as the past information of earlier situations. Future situations can be predicted with some belief based on current situation and incoming context data. The context data is acquired from sensor devices and external inputs. For every recognized situation, system recommends some actions to provide context-aware service. We use Multimedia Web Ontology Language (MOWL) to represents the ontology. MOWL proposes a probabilistic framework for reasoning with uncertainties linked with observation of context. It makes use of Dynamic Bayesian networks to predict and track the dynamically changing situations. We illustrate use of this framework for Smart Mirror use case.
26 Jun 2015
TL;DR: The book presents a unified approach to recent advances in multimedia and explains how a multimedia ontology can fill the semantic gap between concepts and the media world, and describes the limitations of existing ontology techniques in semantic multimedia data processing.
Abstract: The result of more than 15 years of collective research, Multimedia Ontology: Representation and Applications provides a theoretical foundation for understanding the nature of media data and the principles involved in its interpretation. The book presents a unified approach to recent advances in multimedia and explains how a multimedia ontology can fill the semantic gap between concepts and the media world. It relays real-life examples of implementations in different domains to illustrate how this gap can be filled. The book contains information that helps with building semantic, content-based search and retrieval engines and also with developing vertical application-specific search applications. It guides you in designing multimedia tools that aid in logical and conceptual organization of large amounts of multimedia data. As a practical demonstration, it showcases multimedia applications in cultural heritage preservation efforts and the creation of virtual museums. The book describes the limitations of existing ontology techniques in semantic multimedia data processing, as well as some open problems in the representations and applications of multimedia ontology. As an antidote, it introduces new ontology representation and reasoning schemes that overcome these limitations. The long, compiled efforts reflected in Multimedia Ontology: Representation and Applications are a signpost for new achievements and developments in efficiency and accessibility in the field.