Automated Semantic Knowledge Acquisition From Sensor Data

Abstract

Abstract-The gathering of real world data is facilitated by many pervasive data sources such as sensor devices and smart phones. The abundance of the sensory data raise the need to make the data easily available and understandable for the potential users and applications. Using semantic enhancements is one approach to structure and organise the data and to make it processable and interoperable by machines. In particular, ontologies are used to represent information and their relations in machine interpretable forms. In this context, a significant amount of work has been done to create real world data description ontologies and data description models, however little effort has been done in creating and constructing meaningful topical ontologies from vast amount of sensory data by automated processes. Topical ontologies represent the knowledge from a certain domain providing a basic understanding of the concepts that serve as building blocks for further processing. There is a lack of solutions that construct the structure and relations of ontologies based on Real World Data. To address this challenge we introduce a knowledge acquisition method that processes Real World Data to automatically create and evolve topical ontologies based on rules that are automatically extracted from external sources. We use an extended k-means clustering method and apply a statistic model to extract and link relevant concepts from the raw sensor data and represent them in the form of a topical ontology. We use a rule-based system to label the concepts and make them understandable for the human user or semantic analysis and reasoning tools and software. The evaluation of our work shows that the construction of a topological ontology from raw sensor data is achievable with only small construction errors.

A middleware approach for reliable resource selection on Internet‐of‐Things

“…But it faces limitations related to trust, privacy, and security . Knowledge acquisition is done through collaboration of three techniques, i.e., clustering, statistical, and rule‐based that helps in the construction of patterns, relationship, and properties between resources . The approach provides data gathering through sensors with small construction errors.…”

“…5 Knowledge acquisition is done through collaboration of three techniques, i.e., clustering, statistical, and rule-based that helps in the construction of patterns, relationship, and properties between resources. 6,7 The approach provides data gathering through sensors with small construction errors. Another approach, i.e., intelligent resource inquisition framework on Internet-of-Things (IRIF-IoT), is suggested to address the challenge of resource discovery through usage of semantic description and ontology.…”

Towards a Semantic Web of Things: A Hybrid Semantic Annotation, Extraction, and Reasoning Framework for Cyber-Physical System

“…In Figure 2, the processing of raw streaming data into high-level states and events are represented with dotted lines, and the line does not represent the exact predicts/relations between the entities but only describes reference methods of how data streams could be transformed into states or events. The SAO ontology is reused to annotate streaming sensory data for further high-level state mining and reasoning with other prior knowledge as [25] proposed. Event-Rule-Actuator-Action: Since events were generated from sensory observations, the rule will be defined by service providers/developers which describes which event to subscribe to and what action should be triggered by actuators in some condition. The rule is defined for further semantic reasoning by combining forward knowledge with events ( ssn:Sensors :hasState :State and :generates ssn:Stimulus ) and backward knowledge with actions ( san:Actuator :triggers :Action ).…”

Stream-Based Reasoning for IoT Applications — Proposal of Architecture and Analysis of Challenges

“…An interesting end to end approach has been proposed by Ganz et al in [14]. The first step, named SensorSAX (as for Sensor Symbolic Aggregate Aproximation), is the discretization of data into qualitative attributes, encoded in some alphabet words.…”