Learning soft computing control strategies in a modular neural network architecture

Modelling and control of nonlinear dynamical systems is a challenging problem since the dynamics of such systems change over their parameter space. Conventional methodologies for designing nonlinear control laws, such as gain scheduling, are effective because the designer partitions the overall complex control into a number of simpler sub-tasks. This paper describes a new genetic algorithm based method for the design of a modular neural network (MNN) control architecture that learns such partitions of an overall complex control task. Here a chromosome represents both the structure and parameters of an individual neural network in the MNN controller and a hierarchical fuzzy approach is used to select the chromosomes required to accomplish a given control task. This new strategy is applied to the end-point tracking of a single-link flexible manipulator modelled from experimental data. Results show that the MNN controller is simple to design and produces superior performance compared to a single neural network (SNN) controller which is theoretically capable of achieving the desired trajectory. (C) 2003 Elsevier Ltd. All rights reserved.

Locally regularised two-stage learning algorithm for RBF network centre selection

Nonlinear models constructed from radial basis function (RBF) networks can easily be over-fitted due to the noise on the data. While information criteria, such as the final prediction error (FPE), can provide a trade-off between training error and network complexity, the tunable parameters that penalise a large size of network model are hard to determine and are usually network dependent. This article introduces a new locally regularised, two-stage stepwise construction algorithm for RBF networks. The main objective is to produce a parsomous network that generalises well over unseen data. This is achieved by utilising Bayesian learning within a two-stage stepwise construction procedure to penalise centres that are mainly interpreted by the noise.

A New Gradient Descent Approach for Local Learning of Fuzzy Neural Models

The majority of reported learning methods for Takagi-Sugeno-Kang fuzzy neural models to date mainly focus on the improvement of their accuracy. However, one of the key design requirements in building an interpretable fuzzy model is that each obtained rule consequent must match well with the system local behaviour when all the rules are aggregated to produce the overall system output. This is one of the distinctive characteristics from black-box models such as neural networks. Therefore, how to find a desirable set of fuzzy partitions and, hence, to identify the corresponding consequent models which can be directly explained in terms of system behaviour presents a critical step in fuzzy neural modelling. In this paper, a new learning approach considering both nonlinear parameters in the rule premises and linear parameters in the rule consequents is proposed. Unlike the conventional two-stage optimization procedure widely practised in the field where the two sets of parameters are optimized separately, the consequent parameters are transformed into a dependent set on the premise parameters, thereby enabling the introduction of a new integrated gradient descent learning approach. A new Jacobian matrix is thus proposed and efficiently computed to achieve a more accurate approximation of the cost function by using the second-order Levenberg-Marquardt optimization method. Several other interpretability issues about the fuzzy neural model are also discussed and integrated into this new learning approach. Numerical examples are presented to illustrate the resultant structure of the fuzzy neural models and the effectiveness of the proposed new algorithm, and compared with the results from some well-known methods.

Computational learning of the conditional phase-type (C-Ph) distribution: Learning C-Ph distributions

This paper presents a new algorithm for learning the structure of a special type of Bayesian network. The conditional phase-type (C-Ph) distribution is a Bayesian network that models the probabilistic causal relationships between a skewed continuous variable, modelled by the Coxian phase-type distribution, a special type of Markov model, and a set of interacting discrete variables. The algorithm takes a dataset as input and produces the structure, parameters and graphical representations of the fit of the C-Ph distribution as output.The algorithm, which uses a greedy-search technique and has been implemented in MATLAB, is evaluated using a simulated data set consisting of 20,000 cases. The results show that the original C-Ph distribution is recaptured and the fit of the network to the data is discussed.

“Boundary-setting as a core activity in complex public systems”

Title: Boundary-setting as a core activity in complex public systems
Authors: Joanne Murphy & Mary Lee Rhodes

The definition of the boundary of a system is at the core of any systems approach (Midgley 2000; 2003). By defining boundaries we enable – and delimit – the range of outcomes sought and the actions and resources that can be brought to bear. In complex adaptive systems (CAS) analysis, the conceptualisaion and definition of boundaries is particularly challenging as they are constantly undergoing redefinition through agent action, interaction and entry/exit. (Rhodes et al 2011). The concept of ‘boundaries’ appears regularly in a wide range of literature around public management, administration, geopolitics, regeneration and organisational development. Discussions around boundaries focus on many things from concrete physical manifestations and barriers, to virtual interfaces between one organisational unit and another, or even entirely theoretical demarcations between different schools of thought (Kaboolian, 1998, Levi-Faur, 2004, Agranoff & McGuire, 2004).

However, managing ‘beyond’ such boundaries is a routinely recurring aspiration that transcends sectors and local concerns. Unsurprisingly then, there is an increasing understanding of the need to acknowledge and manage such boundaries (whether they be physical, social or organisational) within public management as a discipline (Currie et al 2007, Fitzsimmons and White, 1997, Murtagh, 2002). This paper explores the impact of boundaries on public management strategic decision-making in the sectors of urban regeneration and healthcare. In particular, it focuses on demarcations to physical space, communal identity and within professional relationships in these sectors.

The first section describes the research that gave rise to the paper and the cases examined. Next we briefly define what we mean by boundaries. We explore issues that have emerged from our analysis of urban regeneration and health care singularly, before looking at how the concept of boundaries is a recurrent concern across the sectors. The main contribution of the paper is an exploration of how a CAS lens can bring a new insight into the concept of boundaries and decision-making in the two sets of case studies. This discussion will concentrate on initial conditions, bifurcation and adaptation as key CAS factors in relation to boundaries. We conclude with a brief discussion on the benefits of a CAS lens to an analysis of boundaries in public management decision-making.
References:

Agranoff, R. and McGuire, M. (2003) Collaborative Public Management: Strategies for Local Government. Washington, DC: Georgetown Univ. Press.

Currie, G., Lockett, A. (2007) “A critique of transformational leadership: moral, professional & contingent dimensions of leadership within public services organizations”. Human Relations 60: 341-370.

Fitzsimmons and White, (1997) "Crossing boundaries: communication between professional groups", Journal of Management in Medicine, Vol. 11 Iss: 2, pp.96 – 101

Kaboolian, L. (1998) “The New Public Management: Challenging the Boundaries of the Management vs. Administration Debate” Public Administration Review Vol. 58, No. 3 pp.189-193

Levi-Faur D. and Vigoda-Gadot Eran (eds) (2004) International Public Policy and Management: Policy Learning Beyond Regional, Cultural and Political Boundaries, Marcel Dekker,
Midgley, G. (ed) (2003) Systems Thinking. London: Sage Publications

Midgley, G. (2000) Systemic Intervention: Philosophy, Methodology and Practice. New York, NY: Kluwer.

Murtagh, B. (2002). The Politics of Territory: Policy and Segregation in Northern Ireland. Basingstoke, Palgrave.

Rhodes, ML, Joanne Murphy, Jenny Muir, John Murray (2011) Public Management & Complexity Theory: Richer Decision Making in Irish Public Services, UK: Routledge

Locating binding poses in protein-ligand systems using reconnaissance metadynamics

A molecular dynamics-based protocol is proposed for finding and scoring protein-ligand binding poses. This protocol uses the recently developed reconnaissance metadynamics method, which employs a self-learning algorithm to construct a bias that pushes the system away from the kinetic traps where it would otherwise remain. The exploration of phase space with this algorithm is shown to be roughly six to eight times faster than unbiased molecular dynamics and is only limited by the time taken to diffuse about the surface of the protein. We apply this method to the well-studied trypsin-benzamidine system and show that we are able to refind all the poses obtained from a reference EADock blind docking calculation. These poses can be scored based on the length of time the system remains trapped in the pose. Alternatively, one can perform dimensionality reduction on the output trajectory and obtain a map of phase space that can be used in more expensive free-energy calculations.

A self-learning algorithm for biased molecular dynamics

A new self-learning algorithm for accelerated dynamics, reconnaissance metadynamics, is proposed that is able to work with a very large number of collective coordinates. Acceleration of the dynamics is achieved by constructing a bias potential in terms of a patchwork of one-dimensional, locally valid collective coordinates. These collective coordinates are obtained from trajectory analyses so that they adapt to any new features encountered during the simulation. We show how this methodology can be used to enhance sampling in real chemical systems citing examples both from the physics of clusters and from the biological sciences.

Reviewing child deaths - Learning from the American experience

Current systems for investigating child deaths in England, Wales and Northern Ireland have come under intense scrutiny in recent years and questions have been raised about the accuracy of child death investigations and resulting statistics. Research has highlighted the ways in which multidisciplinary input can contribute to investigative and review processes, a perspective which is further supported by recent UK policy developments. The experience of creating multidisciplinary child death review teams (CDRTs) in America highlights the potential benefits the introduction of a similar system might have. These benefits include improved multi-agency working and communication, more effective identification of suspicious cases, a decrease in inadequate death certification and a broader and more in-depth understanding of the causes of child deaths through the systematic collection and analysis of data. While a lack of funding, regional coordination and evaluation limit the impact of American CDRTs, the positive aspects of this process make it worthwhile, and timely, to consider how such a model might fit within our own context. Current policy developments such as the Home Office review of coroner services, the Children Bill and related Department for Education and Skills (DfES) work on developing screening groups demonstrate that strides have been made in respect of introducing a multidisciplinary process. Similarly, the development of local protocols for the investigation and/or review of child deaths in England, Wales and Northern Ireland highlights an increased focus on multidisciplinary processes. However, key issues from the American experience, such as the remit of CDRTs/screening panels, the need for national coordination and the importance of rigorous evaluation, can inform the development of a similar process in the UK. Copyright ©2005 John Wiley & Sons, Ltd.

A systematic review protocol on the use of online learning and blended learning for teaching clinical skills to undergraduate health professional students

Aim: This paper is a review protocol that will be used to identify, critically appraise and synthesize the best current evidence relating to the use of online learning and blended learning approaches in teaching clinical skills in undergraduate nursing.

Background: Although previous systematic reviews on online learning versus face to face learning have been undertaken (Cavanaugh et al. 2010, Cook et al. 2010), a systematic review on the impact of online learning and blended learning for teaching clinical skills has yet to be considered in undergraduate nursing. By reviewing nursing students’ online learning experiences, systems can potentially be designed to ensure all students’ are supported appropriately to meet their learning needs.

Methods/Design: The key objectives of the review are to evaluate how online-learning teaching strategies assist nursing students learn; to evaluate the students satisfaction with this form of teaching; to explore the variety of online-learning strategies used; to determine what online-learning strategies are more effective and to determine if supplementary face to face instruction enhances learning. A search of the following databases will be made MEDLINE, CINAHL, BREI, ERIC and AUEI. This review will follow the Joanna Briggs Institute guidance for systematic reviews of quantitative and qualitative research.

Conclusion: This review intends to report on a combination of student experience and learning outcomes therefore increasing its utility for educators and curriculum developers involved in healthcare education.

Towards optimal software engineering: learning from agile practice

In essence, optimal software engineering means creating the right product, through the right process, to the overall satisfaction of everyone involved. Adopting the agile approach to software development appears to have helped many companies make substantial progress towards that goal. The purpose of this paper is to clarify that contribution from comparative survey information gathered in 2010 and 2012. The surveys were undertaken in software development companies across Northern Ireland. The paper describes the design of the surveys and discusses optimality in relation to the results obtained. Both surveys aimed to achieve comprehensive coverage of a single region rather than rely on a voluntary sample. The main outcome from the work is a collection of insights into the nature and advantages of agile development, suggesting how further progress towards optimality might be achieved.

The Development of an Immersive Virtual Reality Environment for Manufacturing and Improving Organizational Learning

This paper examines the applicability of an immersive virtual reality (VR) system to the process of organizational learning in a manufacturing context. The work focuses on the extent to which realism has to be represented in a simulated product build scenario in order to give the user an effective learning experience for an assembly task. Current technologies allow the visualization and manipulation of objects in VR systems but physical behaviors such as contact between objects and the effects of gravity are not commonly represented in off the shelf simulation solutions and the computational power required to facilitate these functions remains a challenge. This work demonstrates how physical behaviors can be coded and represented through the development of more effective mechanisms for the computer aided design (CAD) and VR interface.