Mike Jackson - Academia.edu (original) (raw)

Papers by Mike Jackson

This paper outlines the principle features of a Ph.D. programme of work. Section one describes th... more This paper outlines the principle features of a Ph.D. programme of work. Section one describes the aims of the research. Section two looks at the nature of digital maps and their importance in the broader context of geographic information. Section three looks at the two major aspects of the research. Section four discusses the role of category theory in the research. Finally the conclusion is presented in section five.

In this paper we propose a new classification method for automatic sleep scoring using an artific... more In this paper we propose a new classification method for automatic sleep scoring using an artificial neural network based decision tree. It attempts to treat sleep scoring progress as a series of two-class problems and solves them with a decision tree made up of a group of neural network classifiers, each of which uses a special feature set and is aimed at only one specific sleep stage in order to maximize the classification effect. A single electroencephalogram (EEG) signal is used for our analysis rather than depending on multiple biological signals, which makes greatly simplifies the data acquisition process. Experimental results demonstrate that the average epoch by epoch agreement between the visual and the proposed method in separating 30s wakefulness+S1, REM, S2 and SWS epochs was 88.83%. This study shows that the proposed method performed well in all the four stages, and can effectively limit error propagation at the same time. It could, therefore, be an efficient method for...

Information integration in organisations has been hindered by differences in the software applica... more Information integration in organisations has been hindered by differences in the software applications used and by the structure and semantic differences of the different data sources (de Bruijn, 2003). This is a common problem in the area of Enterprise Application Integration (EAI) where numerous ah-hoc programs have typically been created to perform the integration process. More recently ontologies have been introduced into this area as a possible solution to these problems, but most of the current approaches to ontology integration only address platform, syntactic and structural differences and do not address the semantic differences between the data sources (de Bruijn, 2003). For ontology semantic integration the underlying meaning of each element is needed. An approach based on introducing the contextualisation of the terms used in an ontology is proposed. This approach is called Contextual Semantic Integration for Ontologies.

Filomat

In general, Intelligent Tutoring Systems (ITS) fail to take account of the emotional and cognitiv... more In general, Intelligent Tutoring Systems (ITS) fail to take account of the emotional and cognitive states of the students who use them. This paper explores the relationship between emotion and cognition when students learn via the medium of video lectures. A cognitive emotional model was constructed to determine the student?s cognitive and emotional state while watching an instructional video. This model was a Bayesian belief network (BBN) model. With the method of ten times 10-fold cross-validation, evaluation results showed that the Bayesian network classifies the emotion state with 60% accuracy and classifies both the emotion and cognitive state with 48.82% accuracy. This model provides an emotional and cognitive states recognition solution for video lecture learners in a non-intrusive way with low cost.

International Journal of Information and Electronics Engineering

Affective computing is an interdisciplinary research field that has made plentiful and substantia... more Affective computing is an interdisciplinary research field that has made plentiful and substantial achievements in this decade. In previous Artificial Intelligence research, computers are expected to be endowed with intelligence analogous to human intelligence. In affective computing, computers are expected to be endowed with Emotional Intelligence, which means that the computer can recognize and interpret the emotional states of humans and adapt its behavior to give an appropriate response to those emotions. This paper describes the design of an experiment that is used to collect the emotional data for a cognition & emotion support e-learning project. The goal of this experiment is to explore the interrelationship between the teacher and the student from both emotional and cognitive aspects in a teaching situation, and then construct the interaction models of the emotional and cognitive levels. These models will be integrated in an affective learning system which supports the learner both from cognitive and emotional aspects. The paper addresses issues in experimental design including ethnography, ethical and practical problems related to this form of experimental work.

This article describes an alternative methodology, Object Role Modelling (ORM), and argues that i... more This article describes an alternative methodology, Object Role Modelling (ORM), and argues that it may be more accessible for novice database designers. The basis of the technique is as follows. The first stage involves the identification of entities in the application domain. Entities are defined as a thing in the real world which has an independent existence[Elmasri and Navathe 94]. Once the entities have been identified, the next stage is to identify relationships between them. For instance, if Warehouse and Part are recognised as entities in the application domain then there will probably be a relationship 'is stored in' between them. Relationships are classified in terms of their cardinality (one to one, many to many etc.) and the participation of the entities in the relationship (optional or mandatory). Once the entities and relationships have been identified then attributes may be assigned to them. Attributes are properties that describe entities and are equivalent to...

Proceedings of the 2008 ACM symposium on Applied computing - SAC '08, 2008

Understanding the meaning of each term in an ontology is essential for successfully integrating a... more Understanding the meaning of each term in an ontology is essential for successfully integrating and aligning ontologies. Much ontology integration research to date is focused on syntactic, structural and semantic matching where the actual meaning of the concepts is disregarded.

Lecture Notes in Computer Science, 2001

GNC Kirby, A. Dearle, and DIK Sjøberg (Eds.): POS-9, LNCS 2135, pp. 177-186, 2001. © Springer-Ver... more GNC Kirby, A. Dearle, and DIK Sjøberg (Eds.): POS-9, LNCS 2135, pp. 177-186, 2001. © Springer-Verlag Berlin Heidelberg 2001 ... A Comparison of Two Persistent Storage Tools for Implementing a Search Engine ... Andrea Garratt, Mike Jackson, Peter Burden, and Jon ...

2013 6th International Conference on Biomedical Engineering and Informatics, 2013

ABSTRACT Imaging cerebral glucose metabolism with positron emission tomography (PET) has been wid... more ABSTRACT Imaging cerebral glucose metabolism with positron emission tomography (PET) has been widely used in studying Alzheimer's disease (AD) and mild cognitive impairment (MCI). In this study, we used fluoro-deoxyglucose (FDG) PET images to investigate reduced glucose metabolism in 90 AD subjects, 90 MCI subjects and 90 healthy elderly normal controls (NC). Compared to NC, the AD showed a significant hypometabolism in left and right middle temporal, left cingulate gyrus, medial frontal gyrus and left parahippocampal gyrus. Compared to NC, the MCI showed a significant hypometabolism in the right inferior temporal gyrus and right fusiform gyrus. Compared to MCIs, the AD also showed a significant hypometabolism in left and right middle temporal, left cingulate gyrus, left angular gyrus and right parahippocampal gyrus. This study demonstrates the different cerebral metabolic patterns of AD, MCI and controls. It also shows that glucose metabolism is a sensitive measure of change in cognition and functional ability in AD and MCI, and that might be valuable in predicting future cognitive decline.

The 2013 International Joint Conference on Neural Networks (IJCNN), 2013

Studies in Computational Intelligence, 2010

... in this chapter provides an effec-tive solution to the building of intelligent decision-centr... more ... in this chapter provides an effec-tive solution to the building of intelligent decision-centric ... 2.3 Stakeholder Attitudes to Context-Aware Mobile Learning Personalized mobile learning involves many considerations that impinge on indi-viduals including attitudinal and ethical ...

2010 International Conference on Complex, Intelligent and Software Intensive Systems, 2010

Symposium on Assessment of Quality Software Development Tools, 1994

Measurement is a much advocated, yet infrequently applied technique of software engineering. A ma... more Measurement is a much advocated, yet infrequently applied technique of software engineering. A major contributory factor to this state of affairs is that the majority of software metrics are developed, collected and applied in a haphazard fashion. The result is metrics that frequently are poorly formulated, inappropriate to the specific needs and environment of the using organisation and hard to

2006 First International Symposium on Pervasive Computing and Applications, 2006

Applying Intelligent Technologies, 2010

There have been significant developments in higher education resulting in interest in personalise... more There have been significant developments in higher education resulting in interest in personalised educational provision. Concomitant with these changes is the evolving capability and ubiquity of mobile technologies. To facilitate personalisation and leverage the power of mobile technologies in mobile pedagogic systems identification of individuals is a prerequisite; this can be achieved using an individual’s profile (termed context). This chapter considers the background to context with related research. Context modelling, the processing of contextual information, context matching and the context matching algorithm, ontology, and the Semantic Web technologies are introduced. Context reasoning and inference in rule-based systems is considered and the context reasoning ontology is presented with scenario-based evaluation. The chapter concludes with a discussion, consideration of future research, and open research questions.