Lihua Zhao

Ontology Integration for Linked Data

The Linked Open Data cloud contains tremendous amounts of interlinked instances with abundant knowledge for retrieval. However, because the ontologies are large and heterogeneous, it is time-consuming to learn all the ontologies manually and it is difficult to learn the properties important for describing instances of a specific class. To construct an ontology that helps users to easily access various data sets, we propose a semi-automatic system, called the Framework for InTegrating Ontologies, that can reduce the heterogeneity of the ontologies and retrieve frequently used core properties for each class. The framework consists of three main components: graph-based ontology integration, machine-learning-based approach for finding the core ontology classes and properties, and integrated ontology constructor. By analyzing the instances of linked data sets, this framework constructs a high-quality integrated ontology, which is easily understandable and effective in knowledge acquisition from various data sets using simple SPARQL queries.

Graph-based ontology analysis in the linked open data

The Linked Open Data (LOD) includes over 31 billion Resource Description Framework (RDF) triples interlinked by around 504 million SameAs links (as of September 2011). The data sets of the LOD use different ontologies to describe instances, that cause the ontology heterogeneity problem. Dealing with the heterogeneous ontologies is a challenging problem and it is time-consuming to manually learn big ontologies in the LOD. The heterogeneity of ontologies in the LOD can be reduced by automatically integrating related ontology classes and properties, which can be retrieved from interlinked instances. The interlinked instances can be represented as an undirected graph, from which we can discover the characteristics of instances and retrieve related ontology classes and properties that are important for linking instances. In this paper, we retrieve graph patterns from several linked data sets and perform ontology alignment methods on each graph pattern to identify related ontology classes and properties from the data sets. We successfully integrate various ontologies, analyze the characteristics of interlinked instances, and detect mistaken properties in the real data sets. Furthermore, our approach solves the ontology heterogeneity problem and helps Semantic Web application developers easily query on various data sets with the integrated ontology.

Mid-Ontology learning from linked data

The Linking Open Data(LOD) cloud is a collection of linked Resource Description Framework (RDF) data with over 26 billion RDF triples. Consuming linked data is a challenging task because each data set in the LOD cloud has specific ontology schema, and familiarity with ontology schema is required in order to query various linked data sets. However, manually checking each data set is time-consuming, especially when many data sets from various domains are used. This difficulty can be overcome without user interaction by using an automatic method that integrates different ontology schema. In this paper, we propose a Mid-Ontology learning approach that can automatically construct a simple ontology, linking related ontology predicates (class or property) in different data sets. Our Mid-Ontology learning approach consists of three main phases: data collection, predicate grouping, and Mid-Ontology construction. Experimental results show that our Mid-Ontology learning approach successfully integrates diverse ontology schema, and effectively retrieves related information.

Ontology-based decision making on uncontrolled intersections and narrow roads

Many Advanced Driver Assistance Systems (ADAS) have been developed to improve car safety. However, it is still a challenging problem to make autonomous vehicles to drive safely on urban streets such as uncontrolled intersections (without traffic lights) and narrow roads. In this paper, we introduce a decision making system that can assist autonomous vehicles at uncontrolled intersections and narrow roads. We constructed a machine understandable ontology-based Knowledge Base, which contains maps and traffic regulations. The system makes decisions in comply with traffic regulations such as Right-Of-Way rules when it receives a collision warning signal. The decisions are sent to a path planning system to change the route or stop to avoid collisions.

Instance-Based Ontological Knowledge Acquisition

The Linked Open Data (LOD) cloud contains tremendous amounts of interlinked instances, from where we can retrieve abundant knowledge. However, because of the heterogeneous and big ontologies, it is time consuming to learn all the ontologies manually and it is difficult to observe which properties are important for describing instances of a specific class. In order to construct an ontology that can help users easily access to various data sets, we propose a semi-automatic ontology integration framework that can reduce the heterogeneity of ontologies and retrieve frequently used core properties for each class. The framework consists of three main components: graph-based ontology integration, machine-learning-based ontology schema extraction, and an ontology merger. By analyzing the instances of the linked data sets, this framework acquires ontological knowledge and constructs a high-quality integrated ontology, which is easily understandable and effective in knowledge acquisition from various data sets using simple SPARQL queries.

Fast decision making using ontology-based knowledge base

Making fast driving decisions at intersections is a challenging problem for improving safety of autonomous vehicles. Furthermore, representing sensor data in a machine understandable format is essential to enable vehicles to understand traffic situations. Ontologies are used to represent knowledge of sensor data for autonomous vehicles to aware traffic situations. In this paper, we introduce a fast decision making system, which utilizes only related part of the ontology-based knowledge base to make decisions at intersections. The decision making system performs real-time reasoning using traffic regulations and a part of the map information from the knowledge base.

An Ontology-Based Intelligent Speed Adaptation System for Autonomous Cars

Intelligent Speed Adaptation (ISA) is one of the key technologies for Advanced Driver Assistance Systems (ADAS), which aims to reduce car accidents by supporting drivers to comply with the speed limit. Context awareness is indispensable for autonomous cars to perceive driving environment, where the information should be represented in a machine-understandable format. Ontologies can represent knowledge in a format that machines can understand and perform human-like reasoning. In this paper, we present an ontology-based ISA system that can detect overspeed situations by accessing to the ontology-based Knowledge Base (KB). We conducted experiments on a car simulator as well as on real-world data collected with an intelligent car. Sensor data are converted into RDF stream data and we construct SPARQL queries and a C-SPARQL query to access to the Knowledge Base. Experimental results show that the ISA system can promptly detect overspeed situations by accessing to the ontology-based Knowledge Base.

Missing RDF Triples Detection and Correction in Knowledge Graphs

Knowledge graphs (KGs) have become a powerful asset in information science and technology. To foster enhancing search, information retrieval and question answering domains KGs offer effective structured information. KGs represent real-world entities and their relationships in Resource Description Framework (RDF) triples format. Despite the large amount of knowledge, there are still missing and incorrect knowledge in the KGs. We study the graph patterns of interlinked entities to discover missing and incorrect RDF triples in two KGs - DBpedia and YAGO. We apply graph-based approach to map similar object properties and apply similarity based approach to map similar datatype properties. Our propose methods can utilize those similar ontology properties and efficiently discover missing and incorrect RDF triples in DBpedia and YAGO.