Real-time control of a Tokamak plasma using neural networks

This paper presents results from the first use of neural networks for the real-time feedback control of high temperature plasmas in a Tokamak fusion experiment. The Tokamak is currently the principal experimental device for research into the magnetic confinement approach to controlled fusion. In the Tokamak, hydrogen plasmas, at temperatures of up to 100 Million K, are confined by strong magnetic fields. Accurate control of the position and shape of the plasma boundary requires real-time feedback control of the magnetic field structure on a time-scale of a few tens of microseconds. Software simulations have demonstrated that a neural network approach can give significantly better performance than the linear technique currently used on most Tokamak experiments. The practical application of the neural network approach requires high-speed hardware, for which a fully parallel implementation of the multi-layer perceptron, using a hybrid of digital and analogue technology, has been developed.

Estimating conditional volatility with neural networks

It is well known that one of the obstacles to effective forecasting of exchange rates is heteroscedasticity (non-stationary conditional variance). The autoregressive conditional heteroscedastic (ARCH) model and its variants have been used to estimate a time dependent variance for many financial time series. However, such models are essentially linear in form and we can ask whether a non-linear model for variance can improve results just as non-linear models (such as neural networks) for the mean have done. In this paper we consider two neural network models for variance estimation. Mixture Density Networks (Bishop 1994, Nix and Weigend 1994) combine a Multi-Layer Perceptron (MLP) and a mixture model to estimate the conditional data density. They are trained using a maximum likelihood approach. However, it is known that maximum likelihood estimates are biased and lead to a systematic under-estimate of variance. More recently, a Bayesian approach to parameter estimation has been developed (Bishop and Qazaz 1996) that shows promise in removing the maximum likelihood bias. However, up to now, this model has not been used for time series prediction. Here we compare these algorithms with two other models to provide benchmark results: a linear model (from the ARIMA family), and a conventional neural network trained with a sum-of-squares error function (which estimates the conditional mean of the time series with a constant variance noise model). This comparison is carried out on daily exchange rate data for five currencies.

First year qualifying report: neural networks for extracting wind vectors from satellite scatterometer data

The ERS-1 Satellite was launched in July 1991 by the European Space Agency into a polar orbit at about km800, carrying a C-band scatterometer. A scatterometer measures the amount of radar back scatter generated by small ripples on the ocean surface induced by instantaneous local winds. Operational methods that extract wind vectors from satellite scatterometer data are based on the local inversion of a forward model, mapping scatterometer observations to wind vectors, by the minimisation of a cost function in the scatterometer measurement space.par This report uses mixture density networks, a principled method for modelling conditional probability density functions, to model the joint probability distribution of the wind vectors given the satellite scatterometer measurements in a single cell (the `inverse' problem). The complexity of the mapping and the structure of the conditional probability density function are investigated by varying the number of units in the hidden layer of the multi-layer perceptron and the number of kernels in the Gaussian mixture model of the mixture density network respectively. The optimal model for networks trained per trace has twenty hidden units and four kernels. Further investigation shows that models trained with incidence angle as an input have results comparable to those models trained by trace. A hybrid mixture density network that incorporates geophysical knowledge of the problem confirms other results that the conditional probability distribution is dominantly bimodal.par The wind retrieval results improve on previous work at Aston, but do not match other neural network techniques that use spatial information in the inputs, which is to be expected given the ambiguity of the inverse problem. Current work uses the local inverse model for autonomous ambiguity removal in a principled Bayesian framework. Future directions in which these models may be improved are given.

Autochthonous heritage languages and social media:writing and bilingual practices in Low German on Facebook

This article analyses how speakers of an autochthonous heritage language (AHL) make use of digital media, through the example of Low German, a regional language used by a decreasing number of speakers mainly in northern Germany. The focus of the analysis is on Web 2.0 and its interactive potential for individual speakers. The study therefore examines linguistic practices on the social network site Facebook, with special emphasis on language choice, bilingual practices and writing in the autochthonous heritage language. The findings suggest that social network sites such as Facebook have the potential to provide new mediatized spaces for speakers of an AHL that can instigate sociolinguistic change.

The impact of architecture on the performance of artificial neural networks

A number of researchers have investigated the impact of network architecture on the performance of artificial neural networks. Particular attention has been paid to the impact on the performance of the multi-layer perceptron of architectural issues, and the use of various strategies to attain an optimal network structure. However, there are still perceived limitations with the multi-layer perceptron and networks that employ a different architecture to the multi-layer perceptron have gained in popularity in recent years, particularly, networks that implement a more localised solution, where the solution in one area of the problem space does not impact, or has a minimal impact, on other areas of the space. In this study, we discuss the major architectural issues affecting the performance of a multi-layer perceptron, before moving on to examine in detail the performance of a new localised network, namely the bumptree. The work presented here examines the impact on the performance of artificial neural networks of employing alternative networks to the long established multi-layer perceptron. In particular, networks that impose a solution where the impact of each parameter in the final network architecture has a localised impact on the problem space being modelled are examined. The alternatives examined are the radial basis function and bumptree neural networks, and the impact of architectural issues on the performance of these networks is examined. Particular attention is paid to the bumptree, with new techniques for both developing the bumptree structure and employing this structure to classify patterns being examined.

Neural networks for perpetual grouping

A number of researchers have investigated the application of neural networks to visual recognition, with much of the emphasis placed on exploiting the network's ability to generalise. However, despite the benefits of such an approach it is not at all obvious how networks can be developed which are capable of recognising objects subject to changes in rotation, translation and viewpoint. In this study, we suggest that a possible solution to this problem can be found by studying aspects of visual psychology and in particular, perceptual organisation. For example, it appears that grouping together lines based upon perceptually significant features can facilitate viewpoint independent recognition. The work presented here identifies simple grouping measures based on parallelism and connectivity and shows how it is possible to train multi-layer perceptrons (MLPs) to detect and determine the perceptual significance of any group presented. In this way, it is shown how MLPs which are trained via backpropagation to perform individual grouping tasks, can be brought together into a novel, large scale network capable of determining the perceptual significance of the whole input pattern. Finally the applicability of such significance values for recognition is investigated and results indicate that both the NILP and the Kohonen Feature Map can be trained to recognise simple shapes described in terms of perceptual significances. This study has also provided an opportunity to investigate aspects of the backpropagation algorithm, particularly the ability to generalise. In this study we report the results of various generalisation tests. In applying the backpropagation algorithm to certain problems, we found that there was a deficiency in performance with the standard learning algorithm. An improvement in performance could however, be obtained when suitable modifications were made to the algorithm. The modifications and consequent results are reported here.

A constructive learning algorithm based on back-propagation

There are been a resurgence of interest in the neural networks field in recent years, provoked in part by the discovery of the properties of multi-layer networks. This interest has in turn raised questions about the possibility of making neural network behaviour more adaptive by automating some of the processes involved. Prior to these particular questions, the process of determining the parameters and network architecture required to solve a given problem had been a time consuming activity. A number of researchers have attempted to address these issues by automating these processes, concentrating in particular on the dynamic selection of an appropriate network architecture.The work presented here specifically explores the area of automatic architecture selection; it focuses upon the design and implementation of a dynamic algorithm based on the Back-Propagation learning algorithm. The algorithm constructs a single hidden layer as the learning process proceeds using individual pattern error as the basis of unit insertion. This algorithm is applied to several problems of differing type and complexity and is found to produce near minimal architectures that are shown to have a high level of generalisation ability.

Analysis of constructivist, network-based discourses:concepts, prospects, and illustrations

The authors propose a new approach to discourse analysis which is based on meta data from social networking behavior of learners who are submerged in a socially constructivist e-learning environment. It is shown that traditional data modeling techniques can be combined with social network analysis - an approach that promises to yield new insights into the largely uncharted domain of network-based discourse analysis. The chapter is treated as a non-technical introduction and is illustrated with real examples, visual representations, and empirical findings. Within the setting of a constructivist statistics course, the chapter provides an illustration of what network-based discourse analysis is about (mainly from a methodological point of view), how it is implemented in practice, and why it is relevant for researchers and educators.

Do social capital building strategies influence the financing behavior of Chinese private small and medium-sized enterprises?

Using data from 65,485 Chinese private small and medium-sized enterprises over the period 2000-2006, we examine the extent to which firms can improve access to debt by adopting strategies aimed at building social capital, namely entertaining and gift giving to others in their social network, and obtaining political affiliation. We find that although entertainment and gift-giving expenditure leads to higher levels of total and short-term debt, it does not enable firms to obtain greater long-term debt. In contrast, we demonstrate that obtaining political affiliation allows firms greater access to long-term debt.

Feature analysis of spammers in social networks with active honeypots:a case study of Chinese microblogging networks

In this poster we presented our preliminary work on the study of spammer detection and analysis with 50 active honeypot profiles implemented on Weibo.com and QQ.com microblogging networks. We picked out spammers from legitimate users by manually checking every captured user's microblogs content. We built a spammer dataset for each social network community using these spammer accounts and a legitimate user dataset as well. We analyzed several features of the two user classes and made a comparison on these features, which were found to be useful to distinguish spammers from legitimate users. The followings are several initial observations from our analysis on the features of spammers captured on Weibo.com and QQ.com. ¦The following/follower ratio of spammers is usually higher than legitimate users. They tend to follow a large amount of users in order to gain popularity but always have relatively few followers. ¦There exists a big gap between the average numbers of microblogs posted per day from these two classes. On Weibo.com, spammers post quite a lot microblogs every day, which is much more than legitimate users do; while on QQ.com spammers post far less microblogs than legitimate users. This is mainly due to the different strategies taken by spammers on these two platforms. ¦More spammers choose a cautious spam posting pattern. They mix spam microblogs with ordinary ones so that they can avoid the anti-spam mechanisms taken by the service providers. ¦Aggressive spammers are more likely to be detected so they tend to have a shorter life while cautious spammers can live much longer and have a deeper influence on the network. The latter kind of spammers may become the trend of social network spammer. © 2012 IEEE.

Understanding supply chain disruption risk with the aid of social networks and information flows analysis

Supply Chain Risk Management (SCRM) has become a popular area of research and study in recent years. This can be highlighted by the number of peer reviewed articles that have appeared in academic literature. This coupled with the realisation by companies that SCRM strategies are required to mitigate the risks that they face, makes for challenging research questions in the field of risk management. The challenge that companies face today is not only to identify the types of risks that they face, but also to assess the indicators of risk that face them. This will allow them to mitigate that risk before any disruption to the supply chain occurs. The use of social network theory can aid in the identification of disruption risk. This thesis proposes the combination of social networks, behavioural risk indicators and information management, to uniquely identify disruption risk. The propositions that were developed from the literature review and exploratory case study in the aerospace OEM, in this thesis are:- By improving information flows, through the use of social networks, we can identify supply chain disruption risk. - The management of information to identify supply chain disruption risk can be explored using push and pull concepts. The propositions were further explored through four focus group sessions, two within the OEM and two within an academic setting. The literature review conducted by the researcher did not find any studies that have evaluated supply chain disruption risk management in terms of social network analysis or information management studies. The evaluation of SCRM using these methods is thought to be a unique way of understanding the issues in SCRM that practitioners face today in the aerospace industry.

Who you are or whom you know? Consumption interdependences in social networks

This paper presents an analysis of whether a consumer's decision to switch from one mobile phone provider to another is driven by individual consumer characteristics or by actions of other consumers in her social network. Such consumption interdependences are estimated using a unique dataset, which contains transaction data based on anonymized call records from a large European mobile phone carrier to approximate a consumer's social network. Results show that network effects have an important impact on consumers' switching decisions: switching decisions are interdependent between consumers who interact with each other and this interdependence increases in the closeness between two consumers as measured by the calling data. In other words, if a subscriber switches carriers, she is also affecting the switching probabilities of other individuals in her social circle. The paper argues that such an approach is of high relevance to both switching of providers and to the adoption of new products. © 2013 Copyright Taylor and Francis Group, LLC.

Network effects, network structure and consumer interaction in mobile telecommunications in Europe and Asia

This paper estimates the importance of (tariff-mediated) network effects and the impact of a consumer's social network on her choice of mobile phone provider. The study uses network data obtained from surveys of students in several European and Asian countries. We use the Quadratic Assignment Procedure, a non-parametric permutation test, to adjust for the particular error structure of network data. We find that respondents strongly coordinate their choice of mobile phone providers, but only if their provider induces network effects. This suggests that this coordination depends on network effects rather than on information contagion or pressure to conform to the social environment.

Connecting social media to e-commerce:cold-start product recommendation using microblogging information

In recent years, the boundaries between e-commerce and social networking have become increasingly blurred. Many e-commerce websites support the mechanism of social login where users can sign on the websites using their social network identities such as their Facebook or Twitter accounts. Users can also post their newly purchased products on microblogs with links to the e-commerce product web pages. In this paper, we propose a novel solution for cross-site cold-start product recommendation, which aims to recommend products from e-commerce websites to users at social networking sites in 'cold-start' situations, a problem which has rarely been explored before. A major challenge is how to leverage knowledge extracted from social networking sites for cross-site cold-start product recommendation. We propose to use the linked users across social networking sites and e-commerce websites (users who have social networking accounts and have made purchases on e-commerce websites) as a bridge to map users' social networking features to another feature representation for product recommendation. In specific, we propose learning both users' and products' feature representations (called user embeddings and product embeddings, respectively) from data collected from e-commerce websites using recurrent neural networks and then apply a modified gradient boosting trees method to transform users' social networking features into user embeddings. We then develop a feature-based matrix factorization approach which can leverage the learnt user embeddings for cold-start product recommendation. Experimental results on a large dataset constructed from the largest Chinese microblogging service Sina Weibo and the largest Chinese B2C e-commerce website JingDong have shown the effectiveness of our proposed framework.