A novel information theory method for filter feature selection

In this paper, we propose a novel filter for feature selection. Such filter relies on the estimation of the mutual information between features and classes. We bypass the estimation of the probability density function with the aid of the entropic-graphs approximation of Rényi entropy, and the subsequent approximation of the Shannon one. The complexity of such bypassing process does not depend on the number of dimensions but on the number of patterns/samples, and thus the curse of dimensionality is circumvented. We show that it is then possible to outperform a greedy algorithm based on the maximal relevance and minimal redundancy criterion. We successfully test our method both in the contexts of image classification and microarray data classification.

Informational Barriers to Energy Efficiency - Theory and European Policies. Bruges European Economic Research (BEER) Papers 15/2009

This BEER addresses informational barriers to energy efficiency. It is a widely acknowledged result that an energy efficiency gap exists implying that the level of energy efficiency is at an inefficiently low level. Several barriers to energy efficiency create this gap and the presence of asymmetric information is likely to be one such barrier. In this article a theoretical framework is presented addressing the issues of moral hazard and adverse selection related to energy efficiency. Based on the theoretical framework, European policies on energy efficiency are evaluated. The article is divided into two main parts. The first part presents the theory on information asymmetries and its consequences on energy efficiency focusing on the problems of moral hazard and adverse selection. Having established a theoretical framework to understand the agency barriers to energy efficiency, the second part evaluates the policies of the European Union on energy efficiency. The BEER finds that problems of moral hazard and adverse selection indeed can help explain the seemingly low levels of energy. In both presented models the cost to the principal from implementing high energy efficiency outcome is increased with the informational asymmetries. The theory reveals two implications to policies on energy efficiency. First, the development of measures to enable contractual parties to base remuneration on energy performance must be enhanced, and second, the information on technologies and the education of consumers and installers on energy efficiency must be increased. This could be complemented with certification of installers and energy efficiency advisors to enable consumers to select good agents. Finally, it is found that the preferred EU policy instrument on energy efficiency, so far, seems to be the use of minimum requirements. Less used in EU legislation is the use of measuring and verification as well as the use of certifications. Therefore, it is concluded that the EU should consider an increased use of these instruments, and in particular focus on a further development of standards on measurability and verification as well as an increased focus on education of consumers as well as installers and advisors on energy efficiency.

Mixed Public-Private Enterprises in Europe: Economic Theory and an Empirical Analysis of Italian Water Utilities. Bruges European Economic Research (BEER) Papers 4/July 2006

Mixed enterprises, which are entities jointly owned by the public and private sector, are spreading all over Europe in local utilities. Well aware that in the vast majority of cases the preference of local authorities towards such governance structure is determined by practical reasons rather than by the ambition to implement new regulatory designs (an alternative to the typical “external” regulation), our purpose is to confer some scientific value to this phenomenon which has not been sufficiently investigated in the economic literature. This paper aims at proposing an economic analysis of mixed enterprises, especially of the specific configuration in which the public partner acts as controller and the private one (or “industrial” partner) as service provider. We suggest that the public service concession to mixed enterprises could embody, under certain conditions, a noteworthy substitute to the traditional public provision and the concession to totally private enterprises, as it can push regulated operators to outperform and limit the risk of private opportunism. The starting point of the entire analysis is that ownership allows the (public) owner to gather more information about the actual management of the firm, according to property rights theory. Following this stream of research, we conclude that under certain conditions mixed enterprises could significantly reduce asymmetric information between regulators and regulated firms by implementing a sort of “internal” regulation. With more information, in effect, the public authority (as owner/controller of the regulated firm, but also as member of the regulatory agency) can stimulate the private operator to be more efficient and can monitor it more effectively with respect to the fulfilment of contractual obligations (i.e., public service obligations, quality standards, etc.). Moreover, concerning the latter function, the board of directors of the mixed enterprise can be the suitable place where public and private representatives (respectively, welfare and profit maximisers) can meet to solve all disputes arising from incomplete contracts, without recourse to third parties. Finally, taking into account that a disproportionate public intervention in the “private” administration (or an ineffective protection of the general interest) would imply too many drawbacks, we draw some policy implications that make an equitable debate on the board of the firm feasible. Some empirical evidence is taken from the Italian water sector.

Theory and calculation of the nonlinear energy transfer between sea waves in deep water /

"May 1982."

Ex ante evaluations of alternate data structures for end user queries: Theory and experimental test

The data structure of an information system can significantly impact the ability of end users to efficiently and effectively retrieve the information they need. This research develops a methodology for evaluating, ex ante, the relative desirability of alternative data structures for end user queries. This research theorizes that the data structure that yields the lowest weighted average complexity for a representative sample of information requests is the most desirable data structure for end user queries. The theory was tested in an experiment that compared queries from two different relational database schemas. As theorized, end users querying the data structure associated with the less complex queries performed better Complexity was measured using three different Halstead metrics. Each of the three metrics provided excellent predictions of end user performance. This research supplies strong evidence that organizations can use complexity metrics to evaluate, ex ante, the desirability of alternate data structures. Organizations can use these evaluations to enhance the efficient and effective retrieval of information by creating data structures that minimize end user query complexity.

Selecting optimal instantiations of data models - Theory and validation of an ex ante approach

The schema of an information system can significantly impact the ability of end users to efficiently and effectively retrieve the information they need. Obtaining quickly the appropriate data increases the likelihood that an organization will make good decisions and respond adeptly to challenges. This research presents and validates a methodology for evaluating, ex ante, the relative desirability of alternative instantiations of a model of data. In contrast to prior research, each instantiation is based on a different formal theory. This research theorizes that the instantiation that yields the lowest weighted average query complexity for a representative sample of information requests is the most desirable instantiation for end-user queries. The theory was validated by an experiment that compared end-user performance using an instantiation of a data structure based on the relational model of data with performance using the corresponding instantiation of the data structure based on the object-relational model of data. Complexity was measured using three different Halstead metrics: program length, difficulty, and effort. For a representative sample of queries, the average complexity using each instantiation was calculated. As theorized, end users querying the instantiation with the lower average complexity made fewer semantic errors, i.e., were more effective at composing queries. (c) 2005 Elsevier B.V. All rights reserved.

Advanced mean field methods:theory and practice

A major problem in modern probabilistic modeling is the huge computational complexity involved in typical calculations with multivariate probability distributions when the number of random variables is large. Because exact computations are infeasible in such cases and Monte Carlo sampling techniques may reach their limits, there is a need for methods that allow for efficient approximate computations. One of the simplest approximations is based on the mean field method, which has a long history in statistical physics. The method is widely used, particularly in the growing field of graphical models. Researchers from disciplines such as statistical physics, computer science, and mathematical statistics are studying ways to improve this and related methods and are exploring novel application areas. Leading approaches include the variational approach, which goes beyond factorizable distributions to achieve systematic improvements; the TAP (Thouless-Anderson-Palmer) approach, which incorporates correlations by including effective reaction terms in the mean field theory; and the more general methods of graphical models. Bringing together ideas and techniques from these diverse disciplines, this book covers the theoretical foundations of advanced mean field methods, explores the relation between the different approaches, examines the quality of the approximation obtained, and demonstrates their application to various areas of probabilistic modeling.

Transducer diffraction theory and development of an ultrasonic tomogram

The work described in this thesis is the development of an ultrasonic tomogram to provide outlines of cross-sections of the ulna in vivo. This instrument, used in conjunction with X-ray densitometry previously developed in this department, would provide actual bone mineral density to a high resolution. It was hoped that the accuracy of the plot obtained from the tomogram would exceed that of existing ultrasonic techniques by about five times. Repeat measurements with these instruments to follow bone mineral changes would involve very low X-ray doses. A theoretical study has been made of acoustic diffraction, using a geometrical transform applicable to the integration of three different Green's functions, for axisymmetric systems. This has involved the derivation of one of these in a form amenable to computation. It is considered that this function fits the boundary conditions occurring in medical ultrasonography more closely than those used previously. A three dimensional plot of the pressure field using this function has been made for a ring transducer, in addition to that for disc transducers using all three functions. It has been shown how the theory may be extended to investigate the nature and magnitude of the particle velocity, at any point in the field, for the three functions mentioned. From this study. a concept of diffraction fronts has been developed, which has made it possible to determine energy flow also in a diffracting system. Intensity has been displayed in a manner similar to that used for pressure. Plots have been made of diffraction fronts and energy flow direction lines.

Information-theory analysis of skewed coding for suppression of pattern-dependent errors in digital communications

We present information-theory analysis of the tradeoff between bit-error rate improvement and the data-rate loss using skewed channel coding to suppress pattern-dependent errors in digital communications. Without loss of generality, we apply developed general theory to the particular example of a high-speed fiber communication system with a strong patterning effect. © 2007 IEEE.

Basic Structure of the General Information Theory

The basic structure of the General Information Theory (GIT) is presented in the paper. The main divisions of the GIT are outlined. Some new results are pointed.

Stochastic Arithmetic Theory and Experiments

Stochastic arithmetic has been developed as a model for exact computing with imprecise data. Stochastic arithmetic provides confidence intervals for the numerical results and can be implemented in any existing numerical software by redefining types of the variables and overloading the operators on them. Here some properties of stochastic arithmetic are further investigated and applied to the computation of inner products and the solution to linear systems. Several numerical experiments are performed showing the efficiency of the proposed approach.

Informational institutions in the agrifood sector:meta-information and meta-governance of environmental sustainability

In the agrifood sector, the explosive increase in information about environmental sustainability, often in uncoordinated information systems, has created a new form of ignorance ('meta-ignorance') that diminishes the effectiveness of information on decision-makers. Flows of information are governed by informal and formal social arrangements that we can collectively call Informational Institutions. In this paper, we have reviewed the recent literature on such institutions. From the perspectives of information theory and new institutional economics, current informational institutions are increasing the information entropy of communications concerning environmental sustainability and stakeholders' transaction costs of using relevant information. In our view this reduces the effectiveness of informational governance. Future research on informational governance should explicitly address these aspects.

Information theory analysis of regenerative channels

In this paper we summarize our recently proposed work on the information theory analysis of regenerative channels. We discuss how the design and the transfer function properties of the regenerator affect the noise statistics and enable Shannon capacities higher than that of the corresponding linear channels (in the absence of regeneration).

Knowledge Protection in Firms : Theory and Evidence from HP Labs

Publisher PDF