Estimating parameters in stochastic systems:a variational Bayesian approach

This work is concerned with approximate inference in dynamical systems, from a variational Bayesian perspective. When modelling real world dynamical systems, stochastic differential equations appear as a natural choice, mainly because of their ability to model the noise of the system by adding a variation of some stochastic process to the deterministic dynamics. Hence, inference in such processes has drawn much attention. Here a new extended framework is derived that is based on a local polynomial approximation of a recently proposed variational Bayesian algorithm. The paper begins by showing that the new extension of this variational algorithm can be used for state estimation (smoothing) and converges to the original algorithm. However, the main focus is on estimating the (hyper-) parameters of these systems (i.e. drift parameters and diffusion coefficients). The new approach is validated on a range of different systems which vary in dimensionality and non-linearity. These are the Ornstein–Uhlenbeck process, the exact likelihood of which can be computed analytically, the univariate and highly non-linear, stochastic double well and the multivariate chaotic stochastic Lorenz ’63 (3D model). As a special case the algorithm is also applied to the 40 dimensional stochastic Lorenz ’96 system. In our investigation we compare this new approach with a variety of other well known methods, such as the hybrid Monte Carlo, dual unscented Kalman filter, full weak-constraint 4D-Var algorithm and analyse empirically their asymptotic behaviour as a function of observation density or length of time window increases. In particular we show that we are able to estimate parameters in both the drift (deterministic) and the diffusion (stochastic) part of the model evolution equations using our new methods.

Short-term electricity demand and gas price forecasts using wavelet transforms and adaptive models

This paper presents some forecasting techniques for energy demand and price prediction, one day ahead. These techniques combine wavelet transform (WT) with fixed and adaptive machine learning/time series models (multi-layer perceptron (MLP), radial basis functions, linear regression, or GARCH). To create an adaptive model, we use an extended Kalman filter or particle filter to update the parameters continuously on the test set. The adaptive GARCH model is a new contribution, broadening the applicability of GARCH methods. We empirically compared two approaches of combining the WT with prediction models: multicomponent forecasts and direct forecasts. These techniques are applied to large sets of real data (both stationary and non-stationary) from the UK energy markets, so as to provide comparative results that are statistically stronger than those previously reported. The results showed that the forecasting accuracy is significantly improved by using the WT and adaptive models. The best models on the electricity demand/gas price forecast are the adaptive MLP/GARCH with the multicomponent forecast; their MSEs are 0.02314 and 0.15384 respectively.

Practical methods of tracking of nonstationary time series applied to real-world data

In this paper, we discuss some practical implications for implementing adaptable network algorithms applied to non-stationary time series problems. Two real world data sets, containing electricity load demands and foreign exchange market prices, are used to test several different methods, ranging from linear models with fixed parameters, to non-linear models which adapt both parameters and model order on-line. Training with the extended Kalman filter, we demonstrate that the dynamic model-order increment procedure of the resource allocating RBF network (RAN) is highly sensitive to the parameters of the novelty criterion. We investigate the use of system noise for increasing the plasticity of the Kalman filter training algorithm, and discuss the consequences for on-line model order selection. The results of our experiments show that there are advantages to be gained in tracking real world non-stationary data through the use of more complex adaptive models.

Why do firms invest in consumer advertising with limited sales response? A shareholder perspective

Marketing managers increasingly recognize the need to measure and communicate the impact of their actions on shareholder returns. This study focuses on the shareholder value effects of pharmaceutical direct-to-consumer advertising (DTCA) and direct-to-physician (DTP) marketing efforts. Although DTCA has moderate effects on brand sales and market share, companies invest vast amounts of money in it. Relying on Kalman filtering, the authors develop a methodology to assess the effects from DTCA and DTP on three components of shareholder value: stock return, systematic risk, and idiosyncratic risk. Investors value DTCA positively because it leads to higher stock returns and lower systematic risk. Furthermore, DTCA increases idiosyncratic risk, which does not affect investors who maintain well-diversified portfolios. In contrast, DTP marketing has modest positive effects on stock returns and idiosyncratic risk. The outcomes indicate that evaluations of marketing expenditures should include a consideration of the effects of marketing on multiple stakeholders, not just the sales effects on consumers.

Early marketing matters:a time-varying parameter approach to persistence modeling

Are persistent marketing effects most likely to appear right after the introduction of a product? The authors give an affirmative answer to this question by developing a model that explicitly reports how persistent and transient marketing effects evolve over time. The proposed model provides managers with a valuable tool to evaluate their allocation of marketing expenditures over time. An application of the model to many pharmaceutical products, estimated through (exact initial) Kalman filtering, indicates that both persistent and transient effects occur predominantly immediately after a brand's introduction. Subsequently, the size of the effects declines. The authors theoretically and empirically compare their methodology with methodology based on unit root testing and demonstrate that the need for unit root tests creates difficulties in applying conventional persistence modeling. The authors recommend that marketing models should either accommodate persistent effects that change over time or be applied to mature brands or limited time windows only.

The effect of universal futures on opening and closing stock market price discovery

Purpose – On 29 January 2001, Euronext LIFFE introduced single security futures contracts on a range of global companies. The purpose of this paper is to examine the impact that the introduction of these futures contracts had on the behaviour of opening and closing UK equity returns. Design/methodology/approach – The paper models the price discovery process using the Amihud and Mendelson partial adjustment model which can be estimated using a Kalman filter. Findings – Empirical results show that during the pre-futures period both opening and closing returns under-react to new information. After the introduction of futures contracts opening returns over-react. A rise in the partial adjustment coefficient also takes place for closing returns but this is not large enough to cause over-reaction. Originality/value – This is the first study to examine the impact of a single security futures contract on the speed of spot market price discovery.

Serial correlation in the returns of UK capitalization based portfolios

This article examines whether UK portfolio returns are time varying so that expected returns follow an AR(1) process as proposed by Conrad and Kaul for the USA. It explores this hypothesis for four portfolios that have been formed on the basis of market capitalization. The portfolio returns are modelled using a kalman filter signal extraction model in which the unobservable expected return is the state variable and is allowed to evolve as a stationary first order autoregressive process. It finds that this model is a good representation of returns and can account for most of the autocorrelation present in observed portfolio returns. This study concludes that UK portfolio returns are time varying and the nature of the time variation appears to introduce a substantial amount of autocorrelation to portfolio returns. Like Conrad and Kaul if finds a link between the extent to which portfolio returns are time varying and the size of firms within a portfolio but not the monotonic one found for the USA. © 2004 Taylor and Francis Ltd.

Időben változó együtthatójú ökonometriai modellek

A cikk bevezetést nyújt az időben változó együtthatójú lineáris ökonometriai modellek megoldási módozataiba és elemzi ökonometriai képességeiket. Elsőként az állapot-tér modellkeretben működő Kalman-szűrőt és a hozzá szorosan kapcsolódó (ám kevéssé ismert) rugalmas legkisebb négyzetek módszerét ismertetjük, majd az alternatívaként használható Markov-típusú rezsimváltó modellt mutatjuk be. A két modellcsalád kvalitásait szimulációkkal illusztráljuk.

Location management and routing in urban vehicular ad hoc networks

In recent years, urban vehicular ad hoc networks (VANETs) are gaining importance for inter-vehicle communication, because they allow for the local communication between vehicles without any infrastructure, configuration effort, and without expensive cellular networks. But such architecture may increase the complexity of routing since there is no central control system in urban VANETs. Therefore, a challenging research task is to improve urban VANETs' routing efficiency. ^ Hence, in this dissertation we propose two location-based routing protocols and a location management protocol to facilitate location-based routing in urban VANETs. The Multi-hop Routing Protocol (MURU) is proposed to make use of predicted mobility and geometry map in urban VANETs to estimate a path's life time and set up robust end-to-end routing paths. The Light-weight Routing Protocol (LIRU) is proposed to take advantage of the node diversity under dynamic channel condition to exploit opportunistic forwarding to achieve efficient data delivery. A scalable location management protocol (MALM) is also proposed to support location-based routing protocols in urban VANETs. MALM uses high mobility in VANETs to help disseminate vehicles' historical location information, and a vehicle is able to implement Kalman-filter based predicted to predict another vehicle's current location based on its historical location information. ^

An automatic tuning strategy for local fuzzy logic ramp metering algorithm using Particle Swarm Optimization (PSO)

Freeway systems are becoming more congested each day. One contribution to freeway traffic congestion comprises platoons of on-ramp traffic merging into freeway mainlines. As a relatively low-cost countermeasure to the problem, ramp meters are being deployed in both directions of an 11-mile section of I-95 in Miami-Dade County, Florida. The local Fuzzy Logic (FL) ramp metering algorithm implemented in Seattle, Washington, has been selected for deployment. The FL ramp metering algorithm is powered by the Fuzzy Logic Controller (FLC). The FLC depends on a series of parameters that can significantly alter the behavior of the controller, thus affecting the performance of ramp meters. However, the most suitable values for these parameters are often difficult to determine, as they vary with current traffic conditions. Thus, for optimum performance, the parameter values must be fine-tuned. This research presents a new method of fine tuning the FLC parameters using Particle Swarm Optimization (PSO). PSO attempts to optimize several important parameters of the FLC. The objective function of the optimization model incorporates the METANET macroscopic traffic flow model to minimize delay time, subject to the constraints of reasonable ranges of ramp metering rates and FLC parameters. To further improve the performance, a short-term traffic forecasting module using a discrete Kalman filter was incorporated to predict the downstream freeway mainline occupancy. This helps to detect the presence of downstream bottlenecks. The CORSIM microscopic simulation model was selected as the platform to evaluate the performance of the proposed PSO tuning strategy. The ramp-metering algorithm incorporating the tuning strategy was implemented using CORSIM's run-time extension (RTE) and was tested on the aforementioned I-95 corridor. The performance of the FLC with PSO tuning was compared with the performance of the existing FLC without PSO tuning. The results show that the FLC with PSO tuning outperforms the existing FL metering, fixed-time metering, and existing conditions without metering in terms of total travel time savings, average speed, and system-wide throughput.

Fluorescence-enhanced optical imaging on three-dimensional phantoms using a hand-held probe based frequency-domain intensified charge coupled device (ICCD) optical imager

Fluorescence-enhanced optical imaging is an emerging non-invasive and non-ionizing modality towards breast cancer diagnosis. Various optical imaging systems are currently available, although most of them are limited by bulky instrumentation, or their inability to flexibly image different tissue volumes and shapes. Hand-held based optical imaging systems are a recent development for its improved portability, but are currently limited only to surface mapping. Herein, a novel optical imager, consisting primarily of a hand-held probe and a gain-modulated intensified charge coupled device (ICCD) detector, is developed towards both surface and tomographic breast imaging. The unique features of this hand-held probe based optical imager are its ability to; (i) image large tissue areas (5×10 sq. cm) in a single scan, (ii) reduce overall imaging time using a unique measurement geometry, and (iii) perform tomographic imaging for tumor three-dimensional (3-D) localization. Frequency-domain based experimental phantom studies have been performed on slab geometries (650 ml) under different target depths (1-2.5 cm), target volumes (0.45, 0.23 and 0.10 cc), fluorescence absorption contrast ratios (1:0, 1000:1 to 5:1), and number of targets (up to 3), using Indocyanine Green (ICG) as fluorescence contrast agents. An approximate extended Kalman filter based inverse algorithm has been adapted towards 3-D tomographic reconstructions. Single fluorescence target(s) was reconstructed when located: (i) up to 2.5 cm deep (at 1:0 contrast ratio) and 1.5 cm deep (up to 10:1 contrast ratio) for 0.45 cc-target; and (ii) 1.5 cm deep for target as small as 0.10 cc at 1:0 contrast ratio. In the case of multiple targets, two targets as close as 0.7 cm were tomographically resolved when located 1.5 cm deep. It was observed that performing multi-projection (here dual) based tomographic imaging using a priori target information from surface images, improved the target depth recovery over using single projection based imaging. From a total of 98 experimental phantom studies, the sensitivity and specificity of the imager was estimated as 81-86% and 43-50%, respectively. With 3-D tomographic imaging successfully demonstrated for the first time using a hand-held based optical imager, the clinical translation of this technology is promising upon further experimental validation from in-vitro and in-vivo studies.

A methodology to estimate time varying user responses to travel time and travel time reliability in a road pricing environment

Road pricing has emerged as an effective means of managing road traffic demand while simultaneously raising additional revenues to transportation agencies. Research on the factors that govern travel decisions has shown that user preferences may be a function of the demographic characteristics of the individuals and the perceived trip attributes. However, it is not clear what are the actual trip attributes considered in the travel decision- making process, how these attributes are perceived by travelers, and how the set of trip attributes change as a function of the time of the day or from day to day. In this study, operational Intelligent Transportation Systems (ITS) archives are mined and the aggregated preferences for a priced system are extracted at a fine time aggregation level for an extended number of days. The resulting information is related to corresponding time-varying trip attributes such as travel time, travel time reliability, charged toll, and other parameters. The time-varying user preferences and trip attributes are linked together by means of a binary choice model (Logit) with a linear utility function on trip attributes. The trip attributes weights in the utility function are then dynamically estimated for each time of day by means of an adaptive, limited-memory discrete Kalman filter (ALMF). The relationship between traveler choices and travel time is assessed using different rules to capture the logic that best represents the traveler perception and the effect of the real-time information on the observed preferences. The impact of travel time reliability on traveler choices is investigated considering its multiple definitions. It can be concluded based on the results that using the ALMF algorithm allows a robust estimation of time-varying weights in the utility function at fine time aggregation levels. The high correlations among the trip attributes severely constrain the simultaneous estimation of their weights in the utility function. Despite the data limitations, it is found that, the ALMF algorithm can provide stable estimates of the choice parameters for some periods of the day. Finally, it is found that the daily variation of the user sensitivities for different periods of the day resembles a well-defined normal distribution.

A study of stock market linkages between the US and frontier countries

My dissertation investigates the financial linkages and transmission of economic shocks between the US and the smallest emerging markets (frontier markets). The first chapter sets up an empirical model that examines the impact of US market returns and conditional volatility on the returns and conditional volatilities of twenty-one frontier markets. The model is estimated via maximum likelihood; utilizes the GARCH model of errors, and is applied to daily country data from the MSCI Barra. We find limited, but statistically significant exposure of Frontier markets to shocks from the US. Our results suggest that it is not the lagged US market returns that have impact; rather it is the expected US market returns that influence frontier market returns The second chapter sets up an empirical time-varying parameter (TVP) model to explore the time-variation in the impact of mean US returns on mean Frontier market returns. The model utilizes the Kalman filter algorithm as well as the GARCH model of errors and is applied to daily country data from the MSCI Barra. The TVP model detects statistically significant time-variation in the impact of US returns and low, but statistically and quantitatively important impact of US market conditional volatility. The third chapter studies the risk-return relationship in twenty Frontier country stock markets by setting up an international version of the intertemporal capital asset pricing model. The systematic risk in this model comes from covariance of Frontier market stock index returns with world returns. Both the systematic risk and risk premium are time-varying in our model. We also incorporate own country variances as additional determinants of Frontier country returns. Our results suggest statistically significant impact of both world and own country risk in explaining Frontier country returns. Time-variation in the world risk premium is also found to be statistically significant for most Frontier market returns. However, own country risk is found to be quantitatively more important.

Off-line and on-line affective recognition of a computer user through a biosignal processing approach

Physiological signals, which are controlled by the autonomic nervous system (ANS), could be used to detect the affective state of computer users and therefore find applications in medicine and engineering. The Pupil Diameter (PD) seems to provide a strong indication of the affective state, as found by previous research, but it has not been investigated fully yet. ^ In this study, new approaches based on monitoring and processing the PD signal for off-line and on-line affective assessment ("relaxation" vs. "stress") are proposed. Wavelet denoising and Kalman filtering methods are first used to remove abrupt changes in the raw Pupil Diameter (PD) signal. Then three features (PDmean, PDmax and PDWalsh) are extracted from the preprocessed PD signal for the affective state classification. In order to select more relevant and reliable physiological data for further analysis, two types of data selection methods are applied, which are based on the paired t-test and subject self-evaluation, respectively. In addition, five different kinds of the classifiers are implemented on the selected data, which achieve average accuracies up to 86.43% and 87.20%, respectively. Finally, the receiver operating characteristic (ROC) curve is utilized to investigate the discriminating potential of each individual feature by evaluation of the area under the ROC curve, which reaches values above 0.90. ^ For the on-line affective assessment, a hard threshold is implemented first in order to remove the eye blinks from the PD signal and then a moving average window is utilized to obtain the representative value PDr for every one-second time interval of PD. There are three main steps for the on-line affective assessment algorithm, which are preparation, feature-based decision voting and affective determination. The final results show that the accuracies are 72.30% and 73.55% for the data subsets, which were respectively chosen using two types of data selection methods (paired t-test and subject self-evaluation). ^ In order to further analyze the efficiency of affective recognition through the PD signal, the Galvanic Skin Response (GSR) was also monitored and processed. The highest affective assessment classification rate obtained from GSR processing is only 63.57% (based on the off-line processing algorithm). The overall results confirm that the PD signal should be considered as one of the most powerful physiological signals to involve in future automated real-time affective recognition systems, especially for detecting the "relaxation" vs. "stress" states.^

A criança com paralisia cerebral na educação infantil: um olhar sobre a prática docente

La inclusión de los niños con discapacidad en la educación infantil, además de ser un tema poco planteado en la comunidad científica, es un reto actual en lo que se refiere a la práctica docente. Basándose en este aspecto, nuestro objetivo en esta investigación realizada, que resultó en la elaboración de este trabajo, fue analizar cómo se procesa la práctica docente con vistas a la inclusión escolar de un niño con parálisis cerebral, en un Centro Municipal de Educación Infantil (CMEI), en la ciudad de Natal / RN. Más específicamente, buscamos: reflexionar sobre la práctica de la profesora responsable por la clase, en lo que se refiere al desarrollo del niño con parálisis cerebral; analizar las interacciones entre educador y niño con parálisis cerebral; observar la práctica docente en la perspectiva de favorecer la interacción entre el niño con parálisis cerebral y otros niños. Para ello, realizamos una pesquisa exploratoria, cualitativa, y así que optamos por el método del Estudio de Caso. Utilizamos como procedimientos metodológicos el análisis documental, la investigación bibliográfica, la entrevista semiestructurada, la observación y la filmación de escenas relacionadas a la práctica docente. Los sujetos de la investigación fueron la profesora y el niño con parálisis cerebral. Los datos construidos durante la investigación señalaron el hecho de que la práctica de la profesora no estaba encaminada a las necesidades específicas de la alumna con parálisis cerebral, todavía, se desarrollaba de una manera similar para todos los niños en la clase. La presencia de limitaciones significativas para la inclusión de la niña con parálisis cerebral en la educación infantil puede ser considerado como el resultado de la ausencia de una adecuada preparación docente, tanto en el nivel de la formación inicial, cuanto de una formación continua y también la escasez de directrices para el maestro, en proceso; directrices estas acerca de la educación de los niños con parálisis cerebral, lo que hacía imposible a la profesora contribuir de manera efectiva a su mayor desarrollo cognitivo y social.