Distributed space-time block coding with incremental relay: performance improvement under imperfect synchronisation

This paper addresses the impact of imperfect synchronisation on D-STBC when combined with incremental relay. To suppress such an impact, a novel detection scheme is proposed, which retains the two key features of the STBC principle: simplicity (i.e. linear computational complexity), and optimality (i.e. maximum likelihood). These two features make the new detector very suitable for low power wireless networks (e.g. sensor networks).

A fast identification algorithm for Box-Cox transformation based radial basis function neural network

In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.

Modified radial basis function neural network using output transformation

A modified radial basis function (RBF) neural network and its identification algorithm based on observational data with heterogeneous noise are introduced. The transformed system output of Box-Cox is represented by the RBF neural network. To identify the model from observational data, the singular value decomposition of the full regression matrix consisting of basis functions formed by system input data is initially carried out and a new fast identification method is then developed using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator (MLE) for a model base spanned by the largest eigenvectors. Finally, the Box-Cox transformation-based RBF neural network, with good generalisation and sparsity, is identified based on the derived optimal Box-Cox transformation and an orthogonal forward regression algorithm using a pseudo-PRESS statistic to select a sparse RBF model with good generalisation. The proposed algorithm and its efficacy are demonstrated with numerical examples.

CAMCR: Computer-Assisted Mixture model analysis for Capture–Recapture count data

Population size estimation with discrete or nonparametric mixture models is considered, and reliable ways of construction of the nonparametric mixture model estimator are reviewed and set into perspective. Construction of the maximum likelihood estimator of the mixing distribution is done for any number of components up to the global nonparametric maximum likelihood bound using the EM algorithm. In addition, the estimators of Chao and Zelterman are considered with some generalisations of Zelterman’s estimator. All computations are done with CAMCR, a special software developed for population size estimation with mixture models. Several examples and data sets are discussed and the estimators illustrated. Problems using the mixture model-based estimators are highlighted.

The demand for a healthy diet: estimating the almost ideal demand system with infrequency of purchase

A Bayesian method of estimating multivariate sample selection models is introduced and applied to the estimation of a demand system for food in the UK to account for censoring arising from infrequency of purchase. We show how it is possible to impose identifying restrictions on the sample selection equations and that, unlike a maximum likelihood framework, the imposition of adding up at both latent and observed levels is straightforward. Our results emphasise the role played by low incomes and socio-economic circumstances in leading to poor diets and also indicate that the presence of children in a household has a negative impact on dietary quality.

Image restoration for a rectangular poor-pixels detector

This paper presents a unique two-stage image restoration framework especially for further application of a novel rectangular poor-pixels detector, which, with properties of miniature size, light weight and low power consumption, has great value in the micro vision system. To meet the demand of fast processing, only a few measured images shifted up to subpixel level are needed to join the fusion operation, fewer than those required in traditional approaches. By maximum likelihood estimation with a least squares method, a preliminary restored image is linearly interpolated. After noise removal via Canny operator based level set evolution, the final high-quality restored image is achieved. Experimental results demonstrate effectiveness of the proposed framework. It is a sensible step towards subsequent image understanding and object identification.

Autoregressive conditional kurtosis

This article proposes a new model for autoregressive conditional heteroscedasticity and kurtosis. Via a time-varying degrees of freedom parameter, the conditional variance and conditional kurtosis are permitted to evolve separately. The model uses only the standard Student’s t-density and consequently can be estimated simply using maximum likelihood. The method is applied to a set of four daily financial asset return series comprising U.S. and U.K. stocks and bonds, and significant evidence in favor of the presence of autoregressive conditional kurtosis is observed. Various extensions to the basic model are proposed, and we show that the response of kurtosis to good and bad news is not significantly asymmetric.

Patterns of nucleotide substitution in angiosperm cpDNA trnL (UAA)-trnF (GAA) regions

Patterns of substitution in chloroplast encoded trnL_F regions were compared between species of Actaea (Ranunculales), Digitalis (Scrophulariales), Drosera (Caryophyllales), Panicoideae (Poales), the small chromosome species clade of Pelargonium (Geraniales), each representing a different order of flowering plants, and Huperzia (Lycopodiales). In total, the study included 265 taxa, each with > 900-bp sequences, totaling 0.24 Mb. Both pairwise and phylogeny-based comparisons were used to assess nucleotide substitution patterns. In all six groups, we found that transition/transversion ratios, as estimated by maximum likelihood on most-parsimonious trees, ranged between 0.8 and 1.0 for ingroups. These values occurred both at low sequence divergences, where substitutional saturation, i.e., multiple substitutions having occurred at the same (homologous) nucleotide position, was not expected, and at higher levels of divergence. This suggests that the angiosperm trnL-F regions evolve in a pattern different from that generally observed for nuclear and animal mtDNA (transitional/transversion ratio > or = 2). Transition/transversion ratios in the intron and the spacer region differed in all alignments compared, yet base compositions between the regions were highly similar in all six groups. A>-C transversions were significantly less frequent than the other four substitution types. This correlates with results from studies on fidelity mechanisms in DNA replication that predict A<->T and G<->C transversions to be least likely to occur. It therefore strengthens confidence in the link between mutation bias at the polymerase level and the actual fixation of substitutions as recorded on evolutionary trees, and concomitantly, in the neutrality of nucleotide substitutions as phylogenetic markers.

Molecular systematics of the Cactaceae

Bayesian, maximum-likelihood, and maximum-parsimony phylogenies, constructed using nucleotide sequences from the plastid gene region trnK-matK, are employed to investigate relationships within the Cactaceae. These phylogenies sample 666 plants representing 532 of the 1438 species recognized in the family. All four subfamilies, all nine tribes, and 69% of currently recognized genera of Cactaceae are sampled. We found strong support for three of the four currently recognized subfamilies, although relationships between subfamilies were not well defined. Major clades recovered within the largest subfamilies, Opuntioideae and Cactoideae, are reviewed; only three of the nine currently accepted tribes delimited within these subfamilies, the Cacteae, Rhipsalideae, and Opuntieae, are monophyletic, although the Opuntieae were recovered in only the Bayesian and maximum-likelihood analyses, not in the maximum-parsimony analysis, and more data are needed to reveal the status of the Cylindropuntieae, which may yet be monophyletic. Of the 42 genera with more than one exemplar in our study, only 17 were monophyletic; 14 of these genera were from subfamily Cactoideae and three from subfamily Opuntioideae. We present a synopsis of the status of the currently recognized genera

Multiband OFDM modulation and demodulation for ultra wideband communications

This chapter considers the Multiband Orthogonal Frequency Division Multiplexing (MB- OFDM) modulation and demodulation with the intention to optimize the Ultra-Wideband (UWB) system performance. OFDM is a type of multicarrier modulation and becomes the most important aspect for the MB-OFDM system performance. It is also a low cost digital signal component efficiently using Fast Fourier Transform (FFT) algorithm to implement the multicarrier orthogonality. Within the MB-OFDM approach, the OFDM modulation is employed in each 528 MHz wide band to transmit the data across the different bands while also using the frequency hopping technique across different bands. Each parallel bit stream can be mapped onto one of the OFDM subcarriers. Quadrature Phase Shift Keying (QPSK) and Dual Carrier Modulation (DCM) are currently used as the modulation schemes for MB-OFDM in the ECMA-368 defined UWB radio platform. A dual QPSK soft-demapper is suitable for ECMA-368 that exploits the inherent Time-Domain Spreading (TDS) and guard symbol subcarrier diversity to improve the receiver performance, yet merges decoding operations together to minimize hardware and power requirements. There are several methods to demap the DCM, which are soft bit demapping, Maximum Likelihood (ML) soft bit demapping, and Log Likelihood Ratio (LLR) demapping. The Channel State Information (CSI) aided scheme coupled with the band hopping information is used as a further technique to improve the DCM demapping performance. ECMA-368 offers up to 480 Mb/s instantaneous bit rate to the Medium Access Control (MAC) layer, but depending on radio channel conditions dropped packets unfortunately result in a lower throughput. An alternative high data rate modulation scheme termed Dual Circular 32-QAM that fits within the configuration of the current standard increasing system throughput thus maintaining the high rate throughput even with a moderate level of dropped packets.

Generalized beta generated distributions

This article introduces generalized beta-generated (GBG) distributions. Sub-models include all classical beta-generated, Kumaraswamy-generated and exponentiated distributions. They are maximum entropy distributions under three intuitive conditions, which show that the classical beta generator skewness parameters only control tail entropy and an additional shape parameter is needed to add entropy to the centre of the parent distribution. This parameter controls skewness without necessarily differentiating tail weights. The GBG class also has tractable properties: we present various expansions for moments, generating function and quantiles. The model parameters are estimated by maximum likelihood and the usefulness of the new class is illustrated by means of some real data sets.

Who adopts Green Revolution (GR) technology in Ghana?

Sub-Saharan Africa in general and Ghana in particular, missed out on the Green revolution. Efforts are being made to re-introduce the revolution, and this calls for more socio-economic research into the factors influencing the adoption of new technologies, hence, this study. The study sought to find out how socio-economic factors contribute to adoption of Green revolution technology in Ghana. The method of analysis involved a maximum likelihood estimation of a probit model. The proportion of Green revolution inputs was found to be greater for the following: households whose heads had formal education, households with higher levels of non-farm income, credit and labor supply as well as those living in urban centers. It is recommended that levels of complementary inputs such as credit, extension services and infrastructure are increased. Also, households must be encouraged to form farmer-groups as an important source of farm labor. Furthermore, the fundamental problems of illiteracy must be addressed through increasing the levels of formal and non-formal education; and the gap between the rural and urban centers must be bridged through infrastructural and rural development. However, care must be taken to ensure that small-scale farmers are not marginalized, in terms of access to these complementary inputs that go with effective adoption of new technology. With these policies well implemented, Ghana can catch up with her Asian counterparts in this re-introduction of the revolution.

Adoption of green revolution services and poverty reduction in Ghana

In Sub-Saharan Africa (SSA) the technological advances of the Green Revolution (GR) have not been very successful. However, the efforts being made to re-introduce the revolution call for more socio-economic research into the adoption and the effects of the new technologies. The paper discusses an investigation on the effects of GR technology adoption on poverty among households in Ghana. Maximum likelihood estimation of a poverty model within the framework of Heckman's two stage method of correcting for sample selection was employed. Technology adoption was found to have positive effects in reducing poverty. Other factors that reduce poverty include education, credit, durable assets, living in the forest belt and in the south of the country. Technology adoption itself was also facilitated by education, credit, non-farm income and household labour supply as well as living in urban centres. Inarguably, technology adoption can be taken seriously by increasing the levels of complementary inputs such as credit, extension services and infrastructure. Above all, the fundamental problems of illiteracy, inequality and lack of effective markets must be addressed through increasing the levels of formal and non-formal education, equitable distribution of the 'national cake' and a more pragmatic management of the ongoing Structural Adjustment Programme.

Robust evaluation of fixed-event forecast rationality

In this paper we introduce a new testing procedure for evaluating the rationality of fixed-event forecasts based on a pseudo-maximum likelihood estimator. The procedure is designed to be robust to departures in the normality assumption. A model is introduced to show that such departures are likely when forecasters experience a credibility loss when they make large changes to their forecasts. The test is illustrated using monthly fixed-event forecasts produced by four UK institutions. Use of the robust test leads to the conclusion that certain forecasts are rational while use of the Gaussian-based test implies that certain forecasts are irrational. The difference in the results is due to the nature of the underlying data. Copyright © 2001 John Wiley & Sons, Ltd.

Extending the Lincoln–Petersen estimator for multiple identifications in one source

The Lincoln–Petersen estimator is one of the most popular estimators used in capture–recapture studies. It was developed for a sampling situation in which two sources independently identify members of a target population. For each of the two sources, it is determined if a unit of the target population is identified or not. This leads to a 2 × 2 table with frequencies f11, f10, f01, f00 indicating the number of units identified by both sources, by the first but not the second source, by the second but not the first source and not identified by any of the two sources, respectively. However, f00 is unobserved so that the 2 × 2 table is incomplete and the Lincoln–Petersen estimator provides an estimate for f00. In this paper, we consider a generalization of this situation for which one source provides not only a binary identification outcome but also a count outcome of how many times a unit has been identified. Using a truncated Poisson count model, truncating multiple identifications larger than two, we propose a maximum likelihood estimator of the Poisson parameter and, ultimately, of the population size. This estimator shows benefits, in comparison with Lincoln–Petersen’s, in terms of bias and efficiency. It is possible to test the homogeneity assumption that is not testable in the Lincoln–Petersen framework. The approach is applied to surveillance data on syphilis from Izmir, Turkey.