Neural networks for identification of nonlinear systems under random piecewise polynomial disturbances

The problem of identification of a nonlinear dynamic system is considered. A two-layer neural network is used for the solution of the problem. Systems disturbed with unmeasurable noise are considered, although it is known that the disturbance is a random piecewise polynomial process. Absorption polynomials and nonquadratic loss functions are used to reduce the effect of this disturbance on the estimates of the optimal memory of the neural-network model.

International evidence on the predictability of returns to securitized real estate assets: econometric models versus neural networks

The performance of various statistical models and commonly used financial indicators for forecasting securitised real estate returns are examined for five European countries: the UK, Belgium, the Netherlands, France and Italy. Within a VAR framework, it is demonstrated that the gilt-equity yield ratio is in most cases a better predictor of securitized returns than the term structure or the dividend yield. In particular, investors should consider in their real estate return models the predictability of the gilt-equity yield ratio in Belgium, the Netherlands and France, and the term structure of interest rates in France. Predictions obtained from the VAR and univariate time-series models are compared with the predictions of an artificial neural network model. It is found that, whilst no single model is universally superior across all series, accuracy measures and horizons considered, the neural network model is generally able to offer the most accurate predictions for 1-month horizons. For quarterly and half-yearly forecasts, the random walk with a drift is the most successful for the UK, Belgian and Dutch returns and the neural network for French and Italian returns. Although this study underscores market context and forecast horizon as parameters relevant to the choice of the forecast model, it strongly indicates that analysts should exploit the potential of neural networks and assess more fully their forecast performance against more traditional models.

Traditional Chinese medicine research in the post-genomic era: good practice, priorities, challenges and opportunities

Background and aims: GP-TCM is the 1st EU-funded Coordination Action consortium dedicated to traditional Chinese medicine (TCM) research. This paper aims to summarise the objectives, structure and activities of the consortium and introduces the position of the consortium regarding good practice, priorities, challenges and opportunities in TCM research. Serving as the introductory paper for the GPTCM Journal of Ethnopharmacology special issue, this paper describes the roadmap of this special issue and reports how the main outputs of the ten GP-TCM work packages are integrated, and have led to consortium-wide conclusions. Materials and methods: Literature studies, opinion polls and discussions among consortium members and stakeholders. Results: By January 2012, through 3 years of team building, the GP-TCM consortium had grown into a large collaborative network involving ∼200 scientists from 24 countries and 107 institutions. Consortium members had worked closely to address good practice issues related to various aspects of Chinese herbal medicine (CHM) and acupuncture research, the focus of this Journal of Ethnopharmacology special issue, leading to state-of-the-art reports, guidelines and consensus on the application of omics technologies in TCM research. In addition, through an online survey open to GP-TCM members and non-members, we polled opinions on grand priorities, challenges and opportunities in TCM research. Based on the poll, although consortium members and non-members had diverse opinions on the major challenges in the field, both groups agreed that high-quality efficacy/effectiveness and mechanistic studies are grand priorities and that the TCM legacy in general and its management of chronic diseases in particular represent grand opportunities. Consortium members cast their votes of confidence in omics and systems biology approaches to TCM research and believed that quality and pharmacovigilance of TCM products are not only grand priorities, but also grand challenges. Non-members, however, gave priority to integrative medicine, concerned on the impact of regulation of TCM practitioners and emphasised intersectoral collaborations in funding TCM research, especially clinical trials. Conclusions: The GP-TCM consortium made great efforts to address some fundamental issues in TCM research, including developing guidelines, as well as identifying priorities, challenges and opportunities. These consortium guidelines and consensus will need dissemination, validation and further development through continued interregional, interdisciplinary and intersectoral collaborations. To promote this, a new consortium, known as the GP-TCM Research Association, is being established to succeed the 3-year fixed term FP7 GP-TCM consortium and will be officially launched at the Final GP-TCM Congress in Leiden, the Netherlands, in April 2012.

Modelling and inverting complex-valued Wiener systems

We develop a complex-valued (CV) B-spline neural network approach for efficient identification and inversion of CV Wiener systems. The CV nonlinear static function in the Wiener system is represented using the tensor product of two univariate B-spline neural networks. With the aid of a least squares parameter initialisation, the Gauss-Newton algorithm effectively estimates the model parameters that include the CV linear dynamic model coefficients and B-spline neural network weights. The identification algorithm naturally incorporates the efficient De Boor algorithm with both the B-spline curve and first order derivative recursions. An accurate inverse of the CV Wiener system is then obtained, in which the inverse of the CV nonlinear static function of the Wiener system is calculated efficiently using the Gaussian-Newton algorithm based on the estimated B-spline neural network model, with the aid of the De Boor recursions. The effectiveness of our approach for identification and inversion of CV Wiener systems is demonstrated using the application of digital predistorter design for high power amplifiers with memory

Single-carrier frequency domain equalisation for hammerstein communication systems using complex-valued neural networks

Single-carrier (SC) block transmission with frequency-domain equalisation (FDE) offers a viable transmission technology for combating the adverse effects of long dispersive channels encountered in high-rate broadband wireless communication systems. However, for high bandwidthefficiency and high power-efficiency systems, the channel can generally be modelled by the Hammerstein system that includes the nonlinear distortion effects of the high power amplifier (HPA) at transmitter. For such nonlinear Hammerstein channels, the standard SC-FDE scheme no longer works. This paper advocates a complex-valued (CV) B-spline neural network based nonlinear SC-FDE scheme for Hammerstein channels. Specifically, We model the nonlinear HPA, which represents the CV static nonlinearity of the Hammerstein channel, by a CV B-spline neural network, and we develop two efficient alternating least squares schemes for estimating the parameters of the Hammerstein channel, including both the channel impulse response coefficients and the parameters of the CV B-spline model. We also use another CV B-spline neural network to model the inversion of the nonlinear HPA, and the parameters of this inverting B-spline model can easily be estimated using the standard least squares algorithm based on the pseudo training data obtained as a natural byproduct of the Hammerstein channel identification. Equalisation of the SC Hammerstein channel can then be accomplished by the usual one-tap linear equalisation in frequency domain as well as the inverse B-spline neural network model obtained in time domain. Extensive simulation results are included to demonstrate the effectiveness of our nonlinear SC-FDE scheme for Hammerstein channels.

Processes controlling atmospheric dispersion through city centres

We develop a process-based model for the dispersion of a passive scalar in the turbulent flow around the buildings of a city centre. The street network model is based on dividing the airspace of the streets and intersections into boxes, within which the turbulence renders the air well mixed. Mean flow advection through the network of street and intersection boxes then mediates further lateral dispersion. At the same time turbulent mixing in the vertical detrains scalar from the streets and intersections into the turbulent boundary layer above the buildings. When the geometry is regular, the street network model has an analytical solution that describes the variation in concentration in a near-field downwind of a single source, where the majority of scalar lies below roof level. The power of the analytical solution is that it demonstrates how the concentration is determined by only three parameters. The plume direction parameter describes the branching of scalar at the street intersections and hence determines the direction of the plume centreline, which may be very different from the above-roof wind direction. The transmission parameter determines the distance travelled before the majority of scalar is detrained into the atmospheric boundary layer above roof level and conventional atmospheric turbulence takes over as the dominant mixing process. Finally, a normalised source strength multiplies this pattern of concentration. This analytical solution converges to a Gaussian plume after a large number of intersections have been traversed, providing theoretical justification for previous studies that have developed empirical fits to Gaussian plume models. The analytical solution is shown to compare well with very high-resolution simulations and with wind tunnel experiments, although re-entrainment of scalar previously detrained into the boundary layer above roofs, which is not accounted for in the analytical solution, is shown to become an important process further downwind from the source.

The role of animal nutrition in designing optimal foods of animal origin as reviewed by the COST Action Feed for Health (FA0802)

This review provides an overview of the main scientific outputs of a network (Action) supported by the European Cooperation in Science and Technology (COST) in the field of animal science, namely the COST Action Feed for Health (FA0802). The main aims of the COST Action Feed for Health (FA0802) were: to develop an integrated and collaborative network of research groups that focuses on the roles of feed and animal nutrition in improving animal wellbeing and also the quality, safety and wholesomeness of human foods of animal origin; to examine the consumer concerns and perceptions as regards livestock production systems. The COST Action Feed for Health has addressed these scientific topics during the last four years. From a practical point of view three main scientific fields of achievement can be identified: feed and animal nutrition; food of animal origin quality and functionality and consumers’ perceptions. Finally, the present paper has the scope to provide new ideas and solutions to a range of issues associated with the modern livestock production system.

Nonlinear equalization of Hammerstein OFDM systems

A practical orthogonal frequency-division multiplexing (OFDM) system can generally be modelled by the Hammerstein system that includes the nonlinear distortion effects of the high power amplifier (HPA) at transmitter. In this contribution, we advocate a novel nonlinear equalization scheme for OFDM Hammerstein systems. We model the nonlinear HPA, which represents the static nonlinearity of the OFDM Hammerstein channel, by a B-spline neural network, and we develop a highly effective alternating least squares algorithm for estimating the parameters of the OFDM Hammerstein channel, including channel impulse response coefficients and the parameters of the B-spline model. Moreover, we also use another B-spline neural network to model the inversion of the HPA’s nonlinearity, and the parameters of this inverting B-spline model can easily be estimated using the standard least squares algorithm based on the pseudo training data obtained as a byproduct of the Hammerstein channel identification. Equalization of the OFDM Hammerstein channel can then be accomplished by the usual one-tap linear equalization as well as the inverse B-spline neural network model obtained. The effectiveness of our nonlinear equalization scheme for OFDM Hammerstein channels is demonstrated by simulation results.

Collabowrighting the hyper(play)text: a postdramatic digital poetics

The aim of this research is to exhibit how literary playtexts can evoke multisensory trends prevalent in 21st century theatre. In order to do so, it explores a range of practical forms and theoretical contexts for creating participatory, site-specific and immersive theatre. With reference to literary theory, specifically to semiotics, reader-response theory, postmodernism and deconstruction, it attempts to revise dramatic theory established by Aristotle’s Poetics. Considering Gertrude Stein’s essay, Plays (1935), and relevant trends in theatre and performance, shaped by space, technology and the everchanging role of the audience member, a postdramatic poetics emerges from which to analyze the plays of Mac Wellman and Suzan-Lori Parks. Distinguishing the two textual lives of a play as the performance playtext and the literary playtext, it examines the conventions of the printed literary playtext, with reference to models of practice that radicalize the play form, including works by Mabou Mines, The Living Theatre and Fiona Templeton. The arguments of this practice-led Ph.D. developed out of direct engagement with the practice project, which explores the multisensory potential of written language when combined with hypermedia. The written thesis traces the development process of a new play, Rumi High, which is presented digitally as a ‘hyper(play)text,’ accessible through the Internet at www.RumiHigh.org. Here, ‘playwrighting’ practice is expanded spatially, collaboratively and textually. Plays are built, designed and crafted with many layers of meaning that explore both linguistic and graphic modes of poetic expression. The hyper(play)text of Rumi High establishes playwrighting practice as curatorial, where performance and literary playtexts are in a reciprocal relationship. This thesis argues that digital writing and reading spaces enable new approaches to expressing the many languages of performance, while expanding the collaborative network that produces the work. It questions how participatory forms of immersive and site-specific theatre can be presented as interactive literary playtexts, which enable the reader to have a multisensory experience. Through a reflection on process and an evaluation of the practice project, this thesis problematizes notions of authorship and text.

MODELING THE EVOLUTION OF COMPLEX NETWORKS THROUGH THE PATH-STAR TRANSFORMATION AND OPTIMAL MULTIVARIATE METHODS

The topology of real-world complex networks, such as in transportation and communication, is always changing with time. Such changes can arise not only as a natural consequence of their growth, but also due to major modi. cations in their intrinsic organization. For instance, the network of transportation routes between cities and towns ( hence locations) of a given country undergo a major change with the progressive implementation of commercial air transportation. While the locations could be originally interconnected through highways ( paths, giving rise to geographical networks), transportation between those sites progressively shifted or was complemented by air transportation, with scale free characteristics. In the present work we introduce the path-star transformation ( in its uniform and preferential versions) as a means to model such network transformations where paths give rise to stars of connectivity. It is also shown, through optimal multivariate statistical methods (i.e. canonical projections and maximum likelihood classification) that while the US highways network adheres closely to a geographical network model, its path-star transformation yields a network whose topological properties closely resembles those of the respective airport transportation network.

Modeling worldwide highway networks

This Letter addresses the problem of modeling the highway systems of different countries by using complex networks formalism. More specifically, we compare two traditional geographical models with a modified geometrical network model where paths, rather than edges, are incorporated at each step between the origin and the destination vertices. Optimal configurations of parameters are obtained for each model and used for the comparison. The highway networks of Australia, Brazil, India, and Romania are considered and shown to be properly modeled by the modified geographical model. (C) 2009 Elsevier B.V. All rights reserved.

On the effects of geographical constraints on task execution in complex

In the present work, the effects of spatial constraints on the efficiency of task execution in systems underlain by geographical complex networks are investigated, where the probability of connection decreases with the distance between the nodes. The investigation considers several configurations of the parameters defining the network connectivity, and the Barabasi-Albert network model is also considered for comparisons. The results show that the effect of connectivity is significant only for shorter tasks, the locality of connection simplied by the spatial constraints reduces efficiency, and the addition of edges can improve the efficiency of the execution, although with increasing locality of the connections the improvement is small.

Comparison Of Demand Pattern Calibration In Water Distribution Networks With Geographic And Non-Geographic Parameterization

Demands are one of the most uncertain parameters in a water distribution network model. A good calibration of the model demands leads to better solutions when using the model for any purpose. A demand pattern calibration methodology that uses a priori information has been developed for calibrating the behaviour of demand groups. Generally, the behaviours of demands in cities are mixed all over the network, contrary to smaller villages where demands are clearly sectorised in residential neighbourhoods, commercial zones and industrial sectors. Demand pattern calibration has a final use for leakage detection and isolation. Detecting a leakage in a pattern that covers nodes spread all over the network makes the isolation unfeasible. Besides, demands in the same zone may be more similar due to the common pressure of the area rather than for the type of contract. For this reason, the demand pattern calibration methodology is applied to a real network with synthetic non-geographic demands for calibrating geographic demand patterns. The results are compared with a previous work where the calibrated patterns were also non-geographic.

Leakage Detection And Localization Method Based On A Hybrid Inverse/Direct Modelling Approach Suitable For Handling Multiple-Leak Scenarios

When an accurate hydraulic network model is available, direct modeling techniques are very straightforward and reliable for on-line leakage detection and localization applied to large class of water distribution networks. In general, this type of techniques based on analytical models can be seen as an application of the well-known fault detection and isolation theory for complex industrial systems. Nonetheless, the assumption of single leak scenarios is usually made considering a certain leak size pattern which may not hold in real applications. Upgrading a leak detection and localization method based on a direct modeling approach to handle multiple-leak scenarios can be, on one hand, quite straightforward but, on the other hand, highly computational demanding for large class of water distribution networks given the huge number of potential water loss hotspots. This paper presents a leakage detection and localization method suitable for multiple-leak scenarios and large class of water distribution networks. This method can be seen as an upgrade of the above mentioned method based on a direct modeling approach in which a global search method based on genetic algorithms has been integrated in order to estimate those network water loss hotspots and the size of the leaks. This is an inverse / direct modeling method which tries to take benefit from both approaches: on one hand, the exploration capability of genetic algorithms to estimate network water loss hotspots and the size of the leaks and on the other hand, the straightforwardness and reliability offered by the availability of an accurate hydraulic model to assess those close network areas around the estimated hotspots. The application of the resulting method in a DMA of the Barcelona water distribution network is provided and discussed. The obtained results show that leakage detection and localization under multiple-leak scenarios may be performed efficiently following an easy procedure.

Aplicação de redes neurais na classificação de rentabilidade futura de empresas

Este trabalho tem por motivação evidenciar a eficiência de redes neurais na classificação de rentabilidade futura de empresas, e desta forma, prover suporte para o desenvolvimento de sistemas de apoio a tomada de decisão de investimentos. Para serem comparados com o modelo de redes neurais, foram escolhidos o modelo clássico de regressão linear múltipla, como referência mínima, e o de regressão logística ordenada, como marca comparativa de desempenho (benchmark). Neste texto, extraímos dados financeiros e contábeis das 1000 melhores empresas listadas, anualmente, entre 1996 e 2006, na publicação Melhores e Maiores – Exame (Editora Abril). Os três modelos foram construídos tendo como base as informações das empresas entre 1996 e 2005. Dadas as informações de 2005 para estimar a classificação das empresas em 2006, os resultados dos três modelos foram comparados com as classificações observadas em 2006, e o modelo de redes neurais gerou o melhor resultado.