Semantic Methods for Data Mining in Smart Spaces

Semantic Methods for Data Mining in Smart Spaces

DOI: 10.4018/978-1-5225-8973-0.ch005
OnDemand PDF Download:
No Current Special Offers


This chapter shows the role of semantic methods in delivering AmI. The smart spaces paradigm applies ontological modeling for representing available IoT resources as shared information. This way, resources are virtualized by local information hubs, which are deployed on existing devices. The virtualization benefits from semantics since relations between resources are also represented, forming a semantic network. In turn, various ranking models can be implemented for information search and knowledge reasoning (e.g., based on such well-known algorithms as PageRank). The structural properties of the semantic network leads to advanced AmI support for constructing proactive services: discovery of certain structures (e.g., cycles) can be interpreted as formation of specific knowledge that initiates service construction and delivery.
Chapter Preview


Service construction in a smart space can be formulated in terms of flows of information changes (Korzun, 2014). It follows the vision of event-driven and information-driven programming. The events to react are ontologically represented in the smart space. This event-based interaction can be enhanced to information-driven interaction. The reaction is not on a simple event (some values are updated) but on forming a certain informational or knowledge fact, e.g., interaction models of emergent semantics (Aiello et al., 2008) and semantic connections (Vlist, Niezen, Rapp, Hu, Feijs, 2013).

Semantic integration of available resources is needed for creating smart services in smart space (Ovaska, Cinotti, & Toninelli, 2012). It supports creating new knowledge, working with users on a personal or mini-group level, contributing to the realization of their expectations.

A mediation layer is introduced for semantic integration where knowledge is derived based on a distributed set of multiple data sources, e.g., including such services as DBpedia (Bizer et al., 2009) and other services for semantic information publishing, enrichment, search, and visualization. We apply the semantic network model for resource integration. The smart space needs the following components.

Key Terms in this Chapter

Internet of Things (IoT): The internetworking of physical entities represented by devices that enable these entities to collect and exchange data for a achieving a common goal.

Data Mining: The process of discovering patterns in large data sets involving methods at the intersection of machine learning, statistics, and database systems.

Semantic Network: A knowledge base that represents semantic relations between concepts. Formally, the underlying representation model is a directed graph consisting of nodes, which represent concepts, and links, which represent semantic relations between concepts, mapping or connecting semantic fields.

Smart Space: A set of communicating nodes and information storages, which has embedded logic to acquire and apply knowledge about its environment and adapt to its inhabitants in order to improve their experience in the environment.

Information Service: A search extend of the shared information collected in the smart space.

Recommender System (or Recommendation System): An information filtering system that seeks to predict the "rating" (or "preference", "score", "rank") a user would give to an item (e.g., to an information fact).

Complete Chapter List

Search this Book: