Curvature-driven smoothing: a learning algorithm for feed-forward networks

The performance of feed-forward neural networks in real applications can be often be improved significantly if use is made of a-priori information. For interpolation problems this prior knowledge frequently includes smoothness requirements on the network mapping, and can be imposed by the addition to the error function of suitable regularization terms. The new error function, however, now depends on the derivatives of the network mapping, and so the standard back-propagation algorithm cannot be applied. In this paper, we derive a computationally efficient learning algorithm, for a feed-forward network of arbitrary topology, which can be used to minimize the new error function. Networks having a single hidden layer, for which the learning algorithm simplifies, are treated as a special case.

Regularization and complexity control in feed-forward networks

In this paper we consider four alternative approaches to complexity control in feed-forward networks based respectively on architecture selection, regularization, early stopping, and training with noise. We show that there are close similarities between these approaches and we argue that, for most practical applications, the technique of regularization should be the method of choice.

Topographic mappings and feed-forward neural networks

This thesis is a study of the generation of topographic mappings - dimension reducing transformations of data that preserve some element of geometric structure - with feed-forward neural networks. As an alternative to established methods, a transformational variant of Sammon's method is proposed, where the projection is effected by a radial basis function neural network. This approach is related to the statistical field of multidimensional scaling, and from that the concept of a 'subjective metric' is defined, which permits the exploitation of additional prior knowledge concerning the data in the mapping process. This then enables the generation of more appropriate feature spaces for the purposes of enhanced visualisation or subsequent classification. A comparison with established methods for feature extraction is given for data taken from the 1992 Research Assessment Exercise for higher educational institutions in the United Kingdom. This is a difficult high-dimensional dataset, and illustrates well the benefit of the new topographic technique. A generalisation of the proposed model is considered for implementation of the classical multidimensional scaling (¸mds}) routine. This is related to Oja's principal subspace neural network, whose learning rule is shown to descend the error surface of the proposed ¸mds model. Some of the technical issues concerning the design and training of topographic neural networks are investigated. It is shown that neural network models can be less sensitive to entrapment in the sub-optimal global minima that badly affect the standard Sammon algorithm, and tend to exhibit good generalisation as a result of implicit weight decay in the training process. It is further argued that for ideal structure retention, the network transformation should be perfectly smooth for all inter-data directions in input space. Finally, there is a critique of optimisation techniques for topographic mappings, and a new training algorithm is proposed. A convergence proof is given, and the method is shown to produce lower-error mappings more rapidly than previous algorithms.

Economic and socio-economic evaluation of bioenergy schemes fueled with energy crops in Greece

The main aim of this thesis is to evaluate the economic and socio-economic viability of energy crops as raw material for bioenergy schemes at the local level. The case examined is Greece, a southern Mediterranean country. Based on the current state, on foreseen trends and on the information presented in the literature review (conducted at the beginning of the study), the main goal was defined as follows: To examine the evidence supporting a strong role for dedicated energy crops local bioenergy developments in Greece, a sector that is forecasted to be increasingly important in the short to medium term.' Two perennial energy crops, cardoon (Cynara cardunculus L.) and giant reed (Arundo donax L.) were evaluated. The thesis analysed their possible introduction in the agricultural system of Rhodope, northern Greece, as alternative land use, through comparative financial appraisal with the main conventional crops. Based on the output of this comparative analysis, the breakeven for the two selected energy crops was defined along with a sensitivity analysis for the risk of the potential implementation. Following, the author performed an economic and socio-economic evaluation of a district heating system fuelled with energy crops in the selected region. Finally, the author, acknowledging that bioenergy deployment should be studied in the context of innovations proceeded in examining the different perceptions of the key groups involved, farmers and potential end users. Results indicated that biomass exploitation for energy purposes is more likely to be accepted when it is seen clearly as one strand in a national energy, environmental and agricultural policy which embraces several sources of renewable energy, and which also encourages energy efficiency and conservation.

A techno-economic assessment of the use of fast pyrolysis bio-oil from UK energy crops in the production of electricity and combined heat and power

This thesis investigates the cost of electricity generation using bio-oil produced by the fast pyrolysis of UK energy crops. The study covers cost from the farm to the generator’s terminals. The use of short rotation coppice willow and miscanthus as feedstocks was investigated. All costs and performance data have been taken from published papers, reports or web sites. Generation technologies are compared at scales where they have proved economic burning other fuels, rather than at a given size. A pyrolysis yield model was developed for a bubbling fluidised bed fast pyrolysis reactor from published data to predict bio-oil yields and pyrolysis plant energy demands. Generation using diesel engines, gas turbines in open and combined cycle (CCGT) operation and steam cycle plants was considered. The use of bio-oil storage to allow the pyrolysis and generation plants to operate independently of each other was investigated. The option of using diesel generators and open cycle gas turbines for combined heat and power was examined. The possible cost reductions that could be expected through learning if the technology is widely implemented were considered. It was found that none of the systems analysed would be viable without subsidy, but with the current Renewable Obligation Scheme CCGT plants in the 200 to 350 MWe range, super-critical coal fired boilers co-fired with bio-oil, and groups of diesel engine based CHP schemes supplied by a central pyrolysis plant would be viable. It was found that the cost would reduce with implementation and the planting of more energy crops but some subsidy would still be needed to make the plants viable.

Analysis of transport costs for energy crops for use in biomass pyrolysis plant networks

Fast pyrolysis of biomass produces a liquid bio-oil that can be used for electricity generation. Bio-oil can be stored and transported so it is possible to decouple the pyrolysis process from the generation process. This allows each process to be separately optimised. It is necessary to have an understanding of the transport costs involved in order to carry out techno-economic assessments of combinations of remote pyrolysis plants and generation plants. Published fixed and variable costs for freight haulage have been used to calculate the transport cost for trucks running between field stores and a pyrolysis plant. It was found that the key parameter for estimating these costs was the number of round trips a day a truck could make rather than the distance covered. This zone costing approach was used to estimate the transport costs for a range of pyrolysis plants size for willow woodchips and baled miscanthus. The possibility of saving transport costs by producing bio-oil near to the field stores and transporting the bio-oil to a central plant was investigated and it was found that this would only be cost effective for large generation plants.

Novel real-time homodyne coherent receiver using a feed-forward based carrier extraction scheme for phase modulated signals

We report a novel real-time homodyne coherent receiver based on a DPSK optical-electrical-optical (OEO) regenerator used to extract a carrier from carrier-less phase modulated signals based on feed-forward based modulation stripping. The performance of this non-DSP based coherent receiver was evaluated for 10.66Gbit/s BPSK signals. Self-homodyne coherent detection and homodyne detection with an injection-locked local oscillator laser was demonstrated. The performance was evaluated by measuring the electrical signal-to-noise (SNR) and recording the eye diagrams. Using injection-locking for the LO improves the performance and enables homodyne detection with optical injection-locking to operate with carrier-less BPSK signals without the need for polarization multiplexed pilot-tones.

Novel synchronous DPSK optical regenerator based on a feed-forward based carrier extraction scheme

We experimentally demonstrate a novel synchronous 10.66Gbit/s DPSK OEO regenerator which uses a feed-forward carrier extraction scheme with an injection-locked laser to synchronize the regenerated signal wavelength to the incoming signal wavelength. After injection-locking, a low-cost DFB laser used at the regenerator exhibited the same linewidth characteristics as the narrow line-width transmitter laser. The phase regeneration properties of the regenerator were evaluated by emulating random Gaussian phase noise applied to the DPSK signal before the regenerator using a phase modulator driven by an arbitrary waveform generator. The overall performance was evaluated in terms of electrical eye-diagrams, BER measurements, and constellation diagrams.

Full-field feed-forward equalizer with adaptive system optimization

We numerically investigate the combination of full-field detection and feed-forward equalizer (FFE) for adaptive chromatic dispersion compensation up to 2160 km in a 10 Gbit/s on-off keyed optical transmission system. The technique, with respect to earlier reports, incorporates several important implementation modules, including the algorithm for adaptive equalization of the gain imbalance between the two receiver chains, compensation of phase misalignment of the asymmetric Mach-Zehnder interferometer, and simplified implementation of field calculation. We also show that in addition to enabling fast adaptation and simplification of field calculation, full-field FFE exhibits enhanced tolerance to the sampling phase misalignment and reduced sampling rate when compared to the full-field implementation using a dispersive transmission line.

An analysis of food demand in Peru:implications for food-feed competition

In their policy proposals on how best to stimulate economic growth, economists have been increasingly emphasizing free markets. It is, however, possible that free-market-led economic growth can lead to increased income inequity which can further increase poverty. One of the more interesting but thus far insufficiently explored mechanisms for the latter is food–feed competition. Using Peruvian Living Standard Survey (PLSS) data for 1985–86 and 1990, the paper examines the demand patterns of households and concludes that the empirical evidence is in agreement with the hypotheses underlying the theory of food–feed competition.

Pyrolysis of contaminated energy crops and the characterisation of the gained biochar

The simultaneous use of willow as a vegetation filter and an energy crop can respond both to the increasing energy demand and to the problem of the soil and water contamination. Its characteristics guarantee that the resources are used economically. As a vegetation filter, willow uptakes organic and inorganic contaminants. As a fast growing energy crop it meets the requirements of rural areas without the exploitation of existing forestry. The aim of the research was to gather knowledge on the thermal behaviour of willow, uptaking contaminants and then used as an energy crop. For this reason pyrolysis experiments were performed in two different scales. In analytical scale metal-contaminated wood was investigated and bench scale pyrolysis experiments were performed with nitrogen-enriched willow, originated from a wastewater treatment plant. Results of the pyrolysis showed that 51-81 % of the wastewater derived nitrogen of willow was captured in the char product. Char had low surface area (1.4 to 5.4 m2/g), low bulk density (0.15–0.18 g/cm3), high pH values (7.8–9.4) and high water-holding capacity (1.8 to 4.3 cm3/g) while the bioavailability of char nutrients was low. Links were also established between the pyrolysis temperature and the product properties for maximising the biochar provided benefits for soil applications. Results also showed that the metal binding capacity of wood varied from one metal ion to another, char yield increased and levoglucosan yield decreased in their presence. While char yield was mainly affected by the concentration of the metal ions, levoglucosan yield was more dependent on the type of the ionic species. Combustion experiments were also carried out with metal-enriched char. The burnout temperatures, estimated ignition indices and the conversion indicate that the metal ions type and not the amount were the determining factors during the combustion. Results presented in the Thesis provide better understanding on the thermal behaviour of nitrogen-enriched and metal contaminated biomass which is crucial to design effective pyrolysis units and combustors. These findings are relevant for pyrolysis experiments, where the goal is to yield char for energetic or soil applications.

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.