Heinz Dreher

Automatically grading essays with markit

Markit

Ontology based data warehouse modeling and managing ecology of human body for disease and drug prescription management

Health care sector is currently experiencing a major crisis with information overload. With the increasing prevalence of chronic diseases and the ageing population the amount of paper-work is more than ever before. In the US, a hospital admission of one patient generates an estimate of 60 pieces of paper. The federal governments of various countries have passed policies and initiatives that focus on introducing information systems into the health care sector. Technology will immensely reduce the cost of managing patients and even reduce the risks of mis-diagnosing and prescribing incorrect medications to patients. This paper primarily focuses on introducing the concept of ontology based warehouse modelling and managing ecology of human body for disease and drug prescription management. Disorders of the human body and factors such as the patientpsilas age, living and working conditions, familial and genetic influences can be simulated into Metadata in a warehousing environment. In this environment, various relationships are identified and described between these factors and the diseases. Secondly, we also introduce ontological representation of the various human body systems such as the digestive, musculoskeletal and nervous system in disease processes. Although this is an extensive and complex knowledge domain, the work in this paper is one of the first to attempt to introduce the use of ontology based data warehousing and data mining conceptually. We also aim at implementing and applying this research in practice.

Ontology based data warehouse modeling and mining of earthquake data: prediction analysis along Eurasian-Australian continental plates

Seismological observatories archive volumes of heterogeneous types of earthquake data. These organizations, by virtue of their geographic operations, handle complicated hierarchical data structures. In order to effectively and efficiently perform seismological observatories business activities, the flow of data and information must be consistent and information is shared among its units, situated at different geographic locations. In order to improve information sharing among observatories, heterogeneous nature of earthquake data from various sources are intelligently integrated. Data warehouse is a solution, in which, earthquake data entities are modeled using ontology-base multidimensional representation. These data are structured and stored in multi-dimensions in a warehousing environment to minimize the complexity of heterogeneous data. Authors are of the view that data integration process adds value to knowledge building and information sharing among different observatories. Authors suggest that warehoused data modeling facilitates earthquake prediction analysis more effectively.

Interactive on-line formative evaluation of student assignments

Automated Essay Grading (AEG) technology has been maturing over the final decades of the last century to the point where it is now poised to permit a transition in ‘assessment-thinking’. The administrative convenience of using objective testing to attempt to assess deep learning, learning at the conceptual level, has now been obviated by efficient and effective automated means to assess student learning. Further, the new generation AEG systems such as MarkIT deliver an unprecedented interactive formative assessment feedback capability, which is set to transform individualized learning and instruction as implemented in existing Learning Management Systems (LMS).

Improving Web Search by Categorization, Clustering, and Personalization

This research combines Web snippet categorization, clustering and personalization techniques to recommend relevant results to users. RIB --- Recommender Intelligent Browser which categorizes Web snippets using socially constructed Web directory such as the Open Directory Project (ODP) is to be developed. By comparing the similarities between the semantics of each ODP category represented by the category-documents and the Web snippets, the Web snippets are organized into a hierarchy. Meanwhile, the Web snippets are clustered to boost the quality of the categorization. Based on an automatically formed user profile which takes into consideration desktop computer information and concept drift, the proposed search strategy recommends relevant search results to users. This research also intends to verify text categorization, clustering, and feature selection algorithms in the context where only Web snippets are available.

Data warehouse structuring methodologies for efficient mining of Western Australian petroleum data sources

Representing the knowledge domain of a petroleum system is a complex problem. In the present study, logical modelling of shared attributes of resources industry entities (dimensions or objects) has been used for construction of a dynamic and time-variant metadata model. This work demonstrates effectiveness of multidimensional data modelling for petroleum industry, which will be further investigated for fine-grain data presentation and interpretation for quality knowledge discovery.

Data warehousing and mining technologies for adaptability in turbulent resources business environments

Resources businesses often undergo turbulent and volatile periods, due to rapid increase of resource demand and poorly organised resources data volumes. This volatile industry operates multifaceted business units that manage heterogeneous data sources. Data integration and interactive business processes, distributed across complex business environments, need attention. Historical resources data, geographically (spatial dimension) archived for decades (periodic dimension), are source of analysing past business data dimensions and predicting their future turbulences. Periodic data, modelled in an integrated and robust warehouse environment, are explored using data mining methodologies. The data models presented, will optimise future inputs in the turbulent resources business environments.

3D virtual worlds as collaborative communities enriching human endeavours: Innovative applications in e-Learning

3D Virtual Worlds are potent Digital Ecosystems because the 3D interface simulates real-world environments and the community of users creates a dynamic, real-to-life economy and in-world culture. Some Virtual Worlds such as Second Life empower users to generate in-world content through object building tools and programming languages; indeed the content in Second Life is entirely user-generated. This promotes a rich culture of innovation surrounding this emerging technology that continually develops the capabilities of the 3D Digital Ecosystem. The collaborative culture spans both the 3D in-world environment and 2D ecosystems: for example, Web 2.0 applications such as wikis and blogs facilitate support, discussion, and documentation for user-generated innovations. Innovation in 3D Digital Ecosystems such as Second Life are applied to all domains of human endeavour that exist in the real-world, including recreation, socialisation, commerce, and education. This paper shares the authors’ professional experience using Second Life in tertiary Information Systems/Science education. Case studies describe the specific applications. They are followed by discussion of the benefits of 3D Digital Ecosystems for education and suggestions for future research, development, and practice.

3D virtual worlds enriching innovation and collaboration in information systems research, development, and commercialisation

The increasing rate of technological development is changing how we interact socially, commercially, and politically, making this an exciting yet challenging time in which to live. As the pace of development is destabilising the status quo, it is increasingly important for individuals and organisations alike to adapt. Research, development, and commercialisation are important tools in facilitating innovation for organisations engaging in the modern knowledge/networked economy. As an emergent player in the networked economy, Digital Ecosystems have great potential for innovation. In particular 3D Virtual Worlds offer exciting opportunities for Information Systems research, development, and commercialisation. By their very structure, 3D Virtual Worlds such as Second Life provide a powerful context for innovation and collaboration: Second Life users are immersed in a 3D environment and empowered by a menu-based object-builder and a programming language; in-built text, voice, and body-language communication tools enrich communication, collaboration, and help provide a rich contextual presence. The community of users apply themselves to all realms of human endeavour, from recreational socialisation to systems development and entrepreneurial ventures. The current paper describes a university research commercialisation systems development project (of an Automated Essay Grading system called MarkIT), that utilises a 3D Digital Ecosystem for both promotion and implementation. Subsequently, this paper discusses the benefits, limitations, and suggestions for future innovation in research, development, and commercialisation of Information Systems incorporating 3D Virtual Worlds.

Determining and Satisfying Search Users Real Needs via Socially Constructed Search Concept Classification

The focus of the research is to disambiguate search query by categorizing search results returned by search engines and interacting with the user to achieve query and results refinement. A novel special search-browser has been developed which combines search engine results, the open directory project (ODP) based lightweight ontology as navigator and classifier, and search results categorizing. Categories are formed based on the ODP as a predefined ontology and Lucene is to be employed to calculate the similarity between retrieved items of the search engine and concepts in the ODP. With the interaction of users, the search-browser improves the quality of search results by excluding the irrelevant documents and ontologically categorizing results for user inspection.