Ontology-Driven Event Detection and Indexing in Smart Spaces
ABSTRACT By riding the tide of sensor technologies, smart space services collects information about its surroundings and internal objects. However, sensor readings are usually at primitive stage and difficult to be viewed and further retrieved since they have little meaning for naive users, who usually prefer to identify activities or state changes using high-level semantics or concepts. To bridge this gap, we propose an ontology-driven event processing framework as part of the middleware for smart spaces. Smart space event ontology (SSEO) is developed to enable semantic indexing, detect machine-processable events and exchange event data between different processes. A model named Smart Space Event Processors (SSEP) maintains and coordinates various event processes (e.g., event patterns, ontology reasoning rules, and machine-learning algorithms) for semantic events in a smart space. An implementation of SSEP-OntoCEP is introduced. The model elaborates on event composition and semantic labeling by combining event composition technology and semantic reasoning into one coherent system. It has been applied in a smart-space infrastructure named SENSIP.
- SourceAvailable from: Feng Gao[Show abstract] [Hide abstract]
ABSTRACT: Recent development in sensor networks and mobile computing is gaining increasing interest from enterprises. Sensor data services can provide fine-grained information of the physical world and feed the event processing systems where high level business logic is evaluated and coarse-grained business events are derived. However current event processing systems are not user-oriented and take considerable effort to configure and implement mainly because of the granularity mismatch. In this paper, we present a intuitive way to model the complex event patterns based on semantic descriptions of sensor service capabilities. Then, we transform the event patterns into stream queries to facilitate an automatic implementation for the event processing system.01/2012; 1(1). DOI:10.1186/2192-1121-1-7
- [Show abstract] [Hide abstract]
ABSTRACT: Efficient resource and energy management is a key research and business area in todays IT markets. Cyber-physical ecosystems, like smart homes (SHs) and smart Environments (SEs) get interconnected, the efficient allocation of resources will become essential. Machine Learning and Semantic Web techniques for improving resource allocation and management are the focus of our research. They allow machines to process information on all levels, inferring expressive knowledge from raw data, in particular resource predictions from usage patterns. Our aim is to devise a novel approach for a machine learning (ML) and resource Management (RM) framework in SEs. It combines ML and Semantic Web techniques and integrates user interaction The main objective is to enable the creation of platforms that decrease the overall resource consumption by learning and predicting various usage patterns, and furthermore making decisions based on user-feedback. For this purpose, we evaluate recent research and applications, elicit framework requirements, and present a framework architecture. The approach and components are assessed and a prototype implementation is described.01/2012; DOI:10.1109/DEST.2012.6227910