On-line learning in radial basis functions networks

An analytic investigation of the average case learning and generalization properties of Radial Basis Function Networks (RBFs) is presented, utilising on-line gradient descent as the learning rule. The analytic method employed allows both the calculation of generalization error and the examination of the internal dynamics of the network. The generalization error and internal dynamics are then used to examine the role of the learning rate and the specialization of the hidden units, which gives insight into decreasing the time required for training. The realizable and over-realizable cases are studied in detail; the phase of learning in which the hidden units are unspecialized (symmetric phase) and the phase in which asymptotic convergence occurs are analyzed, and their typical properties found. Finally, simulations are performed which strongly confirm the analytic results.

A basis function approach to Bayesian inference in diffusion processes

In this paper, we present a framework for Bayesian inference in continuous-time diffusion processes. The new method is directly related to the recently proposed variational Gaussian Process approximation (VGPA) approach to Bayesian smoothing of partially observed diffusions. By adopting a basis function expansion (BF-VGPA), both the time-dependent control parameters of the approximate GP process and its moment equations are projected onto a lower-dimensional subspace. This allows us both to reduce the computational complexity and to eliminate the time discretisation used in the previous algorithm. The new algorithm is tested on an Ornstein-Uhlenbeck process. Our preliminary results show that BF-VGPA algorithm provides a reasonably accurate state estimation using a small number of basis functions.

A structural method for the design of fault tolerant distributed control systems

Distributed digital control systems provide alternatives to conventional, centralised digital control systems. Typically, a modern distributed control system will comprise a multi-processor or network of processors, a communications network, an associated set of sensors and actuators, and the systems and applications software. This thesis addresses the problem of how to design robust decentralised control systems, such as those used to control event-driven, real-time processes in time-critical environments. Emphasis is placed on studying the dynamical behaviour of a system and identifying ways of partitioning the system so that it may be controlled in a distributed manner. A structural partitioning technique is adopted which makes use of natural physical sub-processes in the system, which are then mapped into the software processes to control the system. However, communications are required between the processes because of the disjoint nature of the distributed (i.e. partitioned) state of the physical system. The structural partitioning technique, and recent developments in the theory of potential controllability and observability of a system, are the basis for the design of controllers. In particular, the method is used to derive a decentralised estimate of the state vector for a continuous-time system. The work is also extended to derive a distributed estimate for a discrete-time system. Emphasis is also given to the role of communications in the distributed control of processes and to the partitioning technique necessary to design distributed and decentralised systems with resilient structures. A method is presented for the systematic identification of necessary communications for distributed control. It is also shwon that the structural partitions can be used directly in the design of software fault tolerant concurrent controllers. In particular, the structural partition can be used to identify the boundary of the conversation which can be used to protect a specific part of the system. In addition, for certain classes of system, the partitions can be used to identify processes which may be dynamically reconfigured in the event of a fault. These methods should be of use in the design of robust distributed systems.

Sequential, Bayesian geostatistics:a principled method for large data sets

The principled statistical application of Gaussian random field models used in geostatistics has historically been limited to data sets of a small size. This limitation is imposed by the requirement to store and invert the covariance matrix of all the samples to obtain a predictive distribution at unsampled locations, or to use likelihood-based covariance estimation. Various ad hoc approaches to solve this problem have been adopted, such as selecting a neighborhood region and/or a small number of observations to use in the kriging process, but these have no sound theoretical basis and it is unclear what information is being lost. In this article, we present a Bayesian method for estimating the posterior mean and covariance structures of a Gaussian random field using a sequential estimation algorithm. By imposing sparsity in a well-defined framework, the algorithm retains a subset of “basis vectors” that best represent the “true” posterior Gaussian random field model in the relative entropy sense. This allows a principled treatment of Gaussian random field models on very large data sets. The method is particularly appropriate when the Gaussian random field model is regarded as a latent variable model, which may be nonlinearly related to the observations. We show the application of the sequential, sparse Bayesian estimation in Gaussian random field models and discuss its merits and drawbacks.

Approximating differentiable relationships between delay embedded dynamical systems with radical basis functions

This thesis is about the study of relationships between experimental dynamical systems. The basic approach is to fit radial basis function maps between time delay embeddings of manifolds. We have shown that under certain conditions these maps are generically diffeomorphisms, and can be analysed to determine whether or not the manifolds in question are diffeomorphically related to each other. If not, a study of the distribution of errors may provide information about the lack of equivalence between the two. The method has applications wherever two or more sensors are used to measure a single system, or where a single sensor can respond on more than one time scale: their respective time series can be tested to determine whether or not they are coupled, and to what degree. One application which we have explored is the determination of a minimum embedding dimension for dynamical system reconstruction. In this special case the diffeomorphism in question is closely related to the predictor for the time series itself. Linear transformations of delay embedded manifolds can also be shown to have nonlinear inverses under the right conditions, and we have used radial basis functions to approximate these inverse maps in a variety of contexts. This method is particularly useful when the linear transformation corresponds to the delay embedding of a finite impulse response filtered time series. One application of fitting an inverse to this linear map is the detection of periodic orbits in chaotic attractors, using suitably tuned filters. This method has also been used to separate signals with known bandwidths from deterministic noise, by tuning a filter to stop the signal and then recovering the chaos with the nonlinear inverse. The method may have applications to the cancellation of noise generated by mechanical or electrical systems. In the course of this research a sophisticated piece of software has been developed. The program allows the construction of a hierarchy of delay embeddings from scalar and multi-valued time series. The embedded objects can be analysed graphically, and radial basis function maps can be fitted between them asynchronously, in parallel, on a multi-processor machine. In addition to a graphical user interface, the program can be driven by a batch mode command language, incorporating the concept of parallel and sequential instruction groups and enabling complex sequences of experiments to be performed in parallel in a resource-efficient manner.

A peak-clustering method for MEG group analysis to minimise artefacts due to smoothness

Magnetoencephalography (MEG), a non-invasive technique for characterizing brain electrical activity, is gaining popularity as a tool for assessing group-level differences between experimental conditions. One method for assessing task-condition effects involves beamforming, where a weighted sum of field measurements is used to tune activity on a voxel-by-voxel basis. However, this method has been shown to produce inhomogeneous smoothness differences as a function of signal-to-noise across a volumetric image, which can then produce false positives at the group level. Here we describe a novel method for group-level analysis with MEG beamformer images that utilizes the peak locations within each participant's volumetric image to assess group-level effects. We compared our peak-clustering algorithm with SnPM using simulated data. We found that our method was immune to artefactual group effects that can arise as a result of inhomogeneous smoothness differences across a volumetric image. We also used our peak-clustering algorithm on experimental data and found that regions were identified that corresponded with task-related regions identified in the literature. These findings suggest that our technique is a robust method for group-level analysis with MEG beamformer images.

Pulse width modulation (PWM) method for power components estimation in power meters

The scope of this paper is to present the Pulse Width Modulation (PWM) based method for Active Power (AP) and Reactive Power (RP) measurements as can be applied in Power Meters. Necessarily, the main aim of the material presented is a twofold, first to present a realization methodology of the proposed algorithm, and second to verify the algorithm’s robustness and validity. The method takes advantage of the fact that frequencies present in a power line are of a specific fundamental frequency range (a range centred on the 50 Hz or 60 Hz) and that in case of the presence of harmonics the frequencies of those dominating in the power line spectrum can be specified on the basis of the fundamental. In contrast to a number of existing methods a time delay or shifting of the input signal is not required by the method presented and the time delay by n/2 of the Current signal with respect to the Voltage signal required by many of the existing measurement techniques, does not apply in the case of the PWM method as well.

Drying kinetic analysis of municipal solid waste using modified page model and pattern search method

This work studied the drying kinetics of the organic fractions of municipal solid waste (MSW) samples with different initial moisture contents and presented a new method for determination of drying kinetic parameters. A series of drying experiments at different temperatures were performed by using a thermogravimetric technique. Based on the modified Page drying model and the general pattern search method, a new drying kinetic method was developed using multiple isothermal drying curves simultaneously. The new method fitted the experimental data more accurately than the traditional method. Drying kinetic behaviors under extrapolated conditions were also predicted and validated. The new method indicated that the drying activation energies for the samples with initial moisture contents of 31.1 and 17.2 % on wet basis were 25.97 and 24.73 kJ mol−1. These results are useful for drying process simulation and industrial dryer design. This new method can be also applied to determine the drying parameters of other materials with high reliability.