Search results

This paper investigates the usefulness of switching Gaussian state space models as a tool for implementing dynamic model selection (DMS) or averaging (DMA) in time-varying parameter regression models. DMS methods allow for model switching, where a different model can be chosen at each point in time. Thus, they allow for the explanatory variables in the time-varying parameter regression model to change over time. DMA will carry out model averaging in a time-varying manner. We compare our exact method for implementing DMA/DMS to a popular existing procedure which relies on the use of forgetting factor approximations. In an application, we use DMS to select different predictors in an inflation forecasting application. We find strong evidence of model switching. We also compare different ways of implementing DMA/DMS and find forgetting factor approaches and approaches based on the switching Gaussian state space model to lead to similar results.

The purpose of this paper is to address the online localization of mobile (service) robots in real world dynamic environments. Most of the techniques developed so far have been designed for static environments. What is presented here is a novel technique for mobile robot localization in quasi‐dynamic environments.

The proposed approach employs a probability grid map and Baye's filtering techniques. The former is used for representing the possible changes in the surrounding environment which a robot might have to face.

Simulation and experimental results show that this approach has a high degree of robustness by taking into account both sensor and world uncertainty. The methodology has been tested under different environment scenarios where diverse complex objects having different sizes and shapes were used to represent movable and non‐movable entities.

The results can be applied to diverse robotic systems that need to move in changing indoor environments such as hospitals and places where people might require assistance from autonomous robotic devices. The methodology is fast, efficient and can be used in fast‐moving robots, allowing them to perform complex operations such as path planning and navigation in real time.

What is proposed here is a novel mobile robot localization approach that enables unmanned vehicles to effectively move in real time and know their current location in dynamic environments. Such an approach consists of two steps: a generation of the probability grid map; and a recursive position estimation methodology employing a variant of the Baye's filter.

Focuses on steady state modelling of basic unipolar non‐isolated PWM AC line matrix‐reactance choppers (MRC). Their single‐phase topologies are similar to well‐known basic DC/DC converter ones. The MRC are built up through the adaptation of DC/DC converter topologies, which are based on the substitution of self‐commutated unidirectional switches by bi‐directional ones.

Presents an approach to modelling of the MRC with averaging operator different to the one used in averaged modelling of the DC/DC converters. There is running averaging of each switching period in the proposed approach. Following this, there is a demonstration of the solutions convergence of the state space and averaged state space equations for infinitive switching frequency.

The running averaging of each switching period should be used if averaged state space method is applied to the analysis of presented choppers. A circuit averaged model build‐up procedure of the presented choppers is the same as for the DC/DC ones.

Presents a quantitative assessment of accuracy for the averaged models of the presented MRC for finite switching frequency.

The authors propose novel tests for the detection of Markov switching deviations from forecast rationality. Existing forecast rationality tests either focus on constant deviations from forecast rationality over the full sample or are constructed to detect smooth deviations based on non-parametric techniques. In contrast, the proposed tests are parametric and have an advantage in detecting abrupt departures from unbiasedness and efficiency, which the authors demonstrate with Monte Carlo simulations. Using the proposed tests, the authors investigate whether Blue Chip Financial Forecasts (BCFF) for the Federal Funds Rate (FFR) are unbiased. The tests find evidence of a state-dependent bias: forecasters tend to systematically overpredict interest rates during periods of monetary easing, while the forecasts are unbiased otherwise. The authors show that a similar state-dependent bias is also present in market-based forecasts of interest rates, but not in the forecasts of real GDP growth and GDP deflator-based inflation. The results emphasize the special role played by monetary policy in shaping interest rate expectations above and beyond macroeconomic fundamentals.

I review the burgeoning literature on applications of Markov regime switching models in empirical finance. In particular, distinct attention is devoted to the ability of Markov Switching models to fit the data, filter unknown regimes and states on the basis of the data, to allow a powerful tool to test hypotheses formulated in light of financial theories, and to their forecasting performance with reference to both point and density predictions. The review covers papers concerning a multiplicity of sub-fields in financial economics, ranging from empirical analyses of stock returns, the term structure of default-free interest rates, the dynamics of exchange rates, as well as the joint process of stock and bond returns.

This paper aims to propose a new unified and non-ideal switch model for analysis of switching circuits.

The model has a single unified structure that includes all possible states (on, off) of the switches. The analysis with the proposed switch model requires only one topology and uses the single system equation regardless of states of switches. Moreover, to improve accuracy, the model contains the on-state resistance and capacitive effect of switches. The system equations and the states of switches are updated by control variables, used in the model.

There are no restrictions on circuit topology and switch connections. Switches can be internally and externally controlled. The non-ideal nature of the model allows the switch to be modeled more realistically and eliminates the drawbacks of the ideal switch concept. After modeling with the proposed switch model, a linear circuit is obtained. Two examples related to switching circuits are included into the study. The results confirm the accuracy of the model.

This paper contributes a different switch model for analysis of switching converters to the literature. The main advantage of the model is that it has a unified and non-ideal property. With the proposed switch model, the transient events, like voltage spikes and high-frequency noises, caused by inductor and capacitor elements at switching instants can be observed properly.

The authors introduce a new approach to estimate high-dimensional factor-augmented vector autoregressive models (FAVAR) where the loadings are subject to idiosyncratic regime-switching dynamics. Our Bayesian estimation method alleviates computational challenges and makes the estimation of high-dimensional FAVAR with heterogeneous regime-switching straightforward to implement. The authors perform extensive simulation experiments to study the finite sample performance of our estimation method, demonstrating its relevance in high-dimensional settings. Next, the authors illustrate the performance of the proposed framework for studying the impact of credit market disruptions on a large set of macroeconomic variables. The results of this study underline the importance of accounting for non-linearities in factor loadings when evaluating the propagation of aggregate shocks.

This paper aims to propose a new linear parameter varying (LPV) controller for the robot tracking control problem. Using the identification of the robot dynamics in different work space points about modeling trajectory based on the least square of error algorithm, an LPV model for the robotic arm is extracted.

Parameter set mapping based on parameter component analysis results in a reduced polytopic LPV model that reduces the complexity of the implementation. An approximation of the required torque is computed based on the reduced LPV models. The state-feedback gain of each zone is computed by solving some linear matrix inequalities (LMIs) to sufficiently decrease the time derivative of a Lyapunov function. A novel smoothing method is used for the proposed controller to switch properly in the borders of the zones.

The polytopic set of the resulting gains creates the smooth switching polytopic LPV (SS-LPV) controller which is applied to the trajectory tracking problem of the six-degree-of-freedom PUMA 560 robotic arm. A sufficient condition ensures that the proposed controller stabilizes the polytopic LPV system against the torque estimation error.

Smoothing of the switching LPV controller is performed by defining some tolerances and creating some quasi-zones in the borders of the main zones leading to the compressed main zones. The proposed torque estimation is not a model-based technique; so the model variation and other disturbances cannot destroy the performance of the suggested controller. The proposed control scheme does not have any considerable computational load, because the control gains are obtained offline by solving some LMIs, and the torque computation is done online by a simple polytopic-based equation.

In this paper, a new SS-LPV controller is addressed for the trajectory tracking problem of robotic arms. Robot workspace is zoned into some main zones in such a way that the number of models in each zone is almost equal. Data obtained from the modeling trajectory is used to design the state-feedback control gain.

This study aims to present a modified interleaved boost converter (MIBC) topology for improving the reliability and efficiency of power electronic systems.

The MIBC topology was implemented with two parallel converters, operated with a −180 degree phase shift. Using this methodology, ripples are reduced. The state-space model was analysed with a two-switch MIBC for different modes of operation. The simulation was carried out and validated using a hardware prototype.

The performance of the proposed MIBC shows better output voltage, current and power than the interleaved boost converter (IBC) for the solar PV array. The output power of the proposed converter is 1.353 times higher than that of existing converters, such as boost converter (BC) and IBC. The output power of the four-phase IBC is 30 kW, whereas that of the proposed two-phase MIBC is 40.59 kW. The efficiency of MIBC was better than that of IBC (87.01%). By incorporating interleaved techniques, the total inductor current is reduced by 29.60% compared with the existing converter.

The proposed MIBC can be used in a grid-connected system with an inverter circuit for DC-to-AC conversion, electric vehicle speed control, power factor correction circuit, high-efficiency converters and battery chargers.

The work presented in this paper is a modified version of IBC. This modified MIBC was modelled using the state-space approach. Furthermore, the state-space model of a two-phase MIBC was implemented using a Simulink model, and the same was validated using a hardware setup.

This paper aims to examine regime switching behaviour of the nominal exchange rate in Uganda to shed light on the necessity (as well as efficacy) of the participation of the central bank market.

The homogenous two‐state Markov chain methodology was employed to investigate the possibility of regime changes in the nominal exchange rate. The maximum likelihood parameter estimates were obtained using the Broyden‐Fletcher‐Goldfarb‐Shanno iteration algorithm.

The results validate the expectation of the two distinct state spaces characterized as sharp and disruptive but short‐lived depreciations as well as small appreciations occurring through a long period. The central bank intervention actions are shown to be largely successful in mitigating the disruptive effects of the sharp depreciations.

The paper lends empirical support to the intervention actions of the Bank of Uganda. In face of the numerous disruptions to the short‐term exchange rate process, failure to intervene may cause rational panic and given the nature of investor behavior, this may quickly spread and even cause further disruptions. It is important for the central bank to send signals that these disruptions are temporary.

The homogenous Markov chain specification employed in this study makes it possible to avoid the pitfalls that may arise by attempting to specify a structural model for the exchange rate. In addition, inference about the different possible state spaces is made on the basis of all available information.