A survey on ontologies for human behavior recognition

Abstract

Describing user activity plays an essential role in ambient intelligence. In this work, we review different methods for human activity recognition, classified as data-driven and knowledge-based techniques. We focus on context ontologies whose ultimate goal is the tracking of human behavior. After studying upper and domain ontologies, both useful for human activity representation and inference, we establish an evaluation criterion to assess the suitability of the different candidate ontologies for this purpose. As a result, any missing features, which are relevant for modeling daily human behaviors, are identified as future challenges.

UPCaD: A Methodology of Integration Between Ontology-Based Context-Awareness Modeling and Relational Domain Data

“…Rodriguez et al [24] performed a comparison between ontologies that represent contexts and human activities. The comparison was made using a set of criteria, described as: (i) Learning curve; (ii) Definition of techniques and methods; (iii) Representation of social interaction; (iv) Sensor infrastructure and (v) Scalability.…”

“…To be able to create binding rules considering an ontology network it is necessary to integrate the ontology network resulting from Context Workflow (24). This integration is accomplished through the SQL-eCO plugin defining the location of the ontology networks resulting from Context Workflow and the integration between the DI ontology and the OWL-DL representation of the domain database schema.…”

Three-layered hierarchical scheme with a Kinect sensor microphone array for audio-based human behavior recognition

“…If the likelihood score of vocal GMM is larger than that of nonvocal GMM, the test acoustic data is recognized as vocal and forwarded to the second level for further recognition. Subsequently, the test data is recognized as one of the nine defined vocal acoustic events by using (2). With an additional GMM recognition layer, the required number of comparisons of the derived likelihood scores [see (2)] is considerably reduced, consequently improving the event recognition performance.…”

“…Human behavior recognition has attracted substantial attention in recent years [1][2][3][4][5][6][7][8]. It has practical application in fields such as home security, office surveillance, and elderly healthcare.…”

Efficient Cache Management Model for Cooperative Reasoning in Wide Area Surveillance

“…In distributed surveillance environment, various surveillance data is generated continuously and analysis with inference should be done in real time. Several intelligent systems based on ontology have been developed for reasoning and querying the semantic knowledge [2][3]. However they do not utilize semantic similarity for knowledge integration.…”