An investigation into inductive parameter learning in complex hierarchical knowledge structures representing clinical expertise

This dissertation investigates the very important and current problem of modelling human expertise. This is an apparent issue in any computer system emulating human decision making. It is prominent in Clinical Decision Support Systems (CDSS) due to the complexity of the induction process and the vast number of parameters in most cases. Other issues such as human error and missing or incomplete data present further challenges. In this thesis, the Galatean Risk Screening Tool (GRiST) is used as an example of modelling clinical expertise and parameter elicitation. The tool is a mental health clinical record management system with a top layer of decision support capabilities. It is currently being deployed by several NHS mental health trusts across the UK. The aim of the research is to investigate the problem of parameter elicitation by inducing them from real clinical data rather than from the human experts who provided the decision model. The induced parameters provide an insight into both the data relationships and how experts make decisions themselves. The outcomes help further understand human decision making and, in particular, help GRiST provide more accurate emulations of risk judgements. Although the algorithms and methods presented in this dissertation are applied to GRiST, they can be adopted for other human knowledge engineering domains.

Evaluating and developing project-based learning:an empirical approach to evaluating CDIO

As a global profession, engineering is integral to the maintenance and further development of society. Indeed, contemporary social problems requiring engineering solutions are not only a consequence of natural and ‘manmade’ disasters (such as the Japanese earthquake or the oil leakage in the Gulf of Mexico) but also encapsulate 21st Century dilemmas around sustainability, poverty and pollution [2,6,7]. Given the complexity of such problems and the constant need for innovation, the demand for engineering education to provide a ready supply of suitably qualified engineering graduates, able to make innovative decisions has never been higher [3,5]. Bearing this in mind, and taking account problems of attrition in engineering education [1,6,4] innovation in the way in which the curriculum is developed and delivered is crucial. CDIO [Conceive, Design, Implement, Operate] provides a potentially ground-breaking solution to such dilemmas. Aimed at equipping students with practical engineering skills supported by the necessary theoretical background, CDIO could potentially change the way engineering is perceived and experienced within higher education. Aston University introduced CDIO into its Mechanical Engineering and Design programmes in October 2011. From its induction, engineering education researchers have ‘shadowed’ the staff responsible for developing and teaching the programme. Utilising an Action Research Design, and adopting a mixed methodological research design, the researchers have worked closely with the teaching team to critically reflect on the processes involved in introducing CDIO into the curriculum. Concurrently, research has been conducted to capture students’ perspectives of CDIO. In evaluating the introduction of CDIO at Aston, the researchers have developed a distinctive research strategy with which to evaluate CDIO. It is the emergent findings from this research that form the basis of this paper. Although early-on in its development CDIO is making a significant difference to engineering education at the University. The paper draws attention to pedagogical, practical and professional issues – discussing each one in turn and in doing so critically analysing the value of CDIO from academic, student and industrial perspectives. The paper concludes by noting that whilst CDIO represents a forwardthinking approach to engineering education, the need for constant innovation in learning and teaching should not be forgotten. Indeed, engineering education needs to put itself at the forefront of pedagogic practice. Providing all-rounded engineers, ready to take on the challenges of the 21st Century!

A learning feed-forward current controller for linear reciprocating vapor compressors

Direct-drive linear reciprocating compressors offer numerous advantages over conventional counterparts which are usually driven by a rotary induction motor via a crank shaft. However, to ensure efficient and reliable operation under all conditions, it is essential that motor current of a linear compressor follows a sinusoidal current command with a frequency which matches the system resonant frequency. The design of a high-performance current controller for linear compressor drive presents a challenge since the system is highly nonlinear, and an effective solution must be low cost. In this paper, a learning feed-forward current controller for the linear compressors is proposed. It comprises a conventional feedback proportional-integral controller and a feed-forward B-spline neural network (BSNN). The feed-forward BSNN is trained online and in real time in order to minimize the current tracking error. Extensive simulation and experiment results with a prototype linear compressor show that the proposed current controller exhibits high steady state and transient performance. © 2009 IEEE.

Experience with Rule Induction & k-Nearest Neighbour Methods for Interface Agents that Learn

Peer reviewed

Automatic learning of pre-miRNAs from different species.

Discovery of microRNAs (miRNAs) relies on predictive models for characteristic features from miRNA precursors (pre-miRNAs). The short length of miRNA genes and the lack of pronounced sequence features complicate this task. To accommodate the peculiarities of plant and animal miRNAs systems, tools for both systems have evolved differently. However, these tools are biased towards the species for which they were primarily developed and, consequently, their predictive performance on data sets from other species of the same kingdom might be lower. While these biases are intrinsic to the species, their characterization can lead to computational approaches capable of diminishing their negative effect on the accuracy of pre-miRNAs predictive models. We investigate in this study how 45 predictive models induced for data sets from 45 species, distributed in eight subphyla/classes, perform when applied to a species different from the species used in its induction. Results: Our computational experiments show that the separability of pre-miRNAs and pseudo pre-miRNAs instances is species-dependent and no feature set performs well for all species, even within the same subphylum/class. Mitigating this species dependency, we show that an ensemble of classifiers reduced the classification errors for all 45 species. As the ensemble members were obtained using meaningful, and yet computationally viable feature sets, the ensembles also have a lower computational cost than individual classifiers that rely on energy stability parameters, which are of prohibitive computational cost in large scale applications. Conclusion: In this study, the combination of multiple pre-miRNAs feature sets and multiple learning biases enhanced the predictive accuracy of pre-miRNAs classifiers of 45 species. This is certainly a promising approach to be incorporated in miRNA discovery tools towards more accurate and less species-dependent tools.