The recent financial crisis has seen huge swings in corporate bond spreads. It is analyzed what quality VAR-based forecasts would have had prior and during the crisis period. Given that forecasts of the mean of interest rates or financial market prices are subject to large uncertainty independent of the class of models used, major emphasis is put on the quality of measures of forecast uncertainty. The VAR considered is based on a model first suggested in the literature in 2005. In a rolling window analysis, both the model’s forecasts and joint prediction bands are calculated making use of recently proposed methods. Besides a traditional analysis of the forecast quality, the performance of the proposed prediction bands is assessed. It is shown that the actual coverage of joint prediction bands is superior to the coverage of naïve prediction bands constructed pointwise.
This paper points out that the ARMA models followed by GARCH squares are volatile and gives explicit and general forms of their dependent and volatile innovations. The volatility function of the ARMA innovations is shown to be the square of the corresponding GARCH volatility function. The prediction of GARCH squares is facilitated by the ARMA structure and predictive intervals are considered. Further, the developments suggest families of volatile ARMA processes.
The modified configuration of the 155 mm rocket assisted projectile equipped with lateral thrusters was proposed. Six degree of freedom mathematical model was used to investigate the quality of the considered projectile. Impact point prediction guidance scheme intended for low control authority projectile was developed to minimize the dispersion radius. Simple point mass model was applied to calculate the impact point coordinates during the flight. Main motor time delay impact on range characteristics was investigated. Miss distance errors and Circular Error Probable for various lateral thruster total impulse were obtained. Monte-Carlo simulations proved that the impact point dispersion could be reduced significantly when the circular array of 15 solid propellant lateral thrusters was used. Single motor operation time was set to be 0.025~s. Finally, the warhead radii of destruction were analyzed.
For building applications, woven fabrics have been widely used as finishing elements of room interior but not in particular aimed for sound absorbers. Considering the micro perforation of the woven fabrics, they should have potential to be used as micro-perforated panel (MPP) absorbers; some measurement results indicated such absorption ability. Hence, it is of importance to have a sound absorption model of the woven fabrics to enable us predicting their sound absorption characteristic that is beneficial in engineering design phase. Treating the woven fabric as a rigid frame, a fluid equivalent model is employed based on the formulation of Johnson-Champoux-Allard (JCA). The model obtained is then validated by measurement results where three kinds of commercially available woven fabrics are evaluated by considering their perforation properties. It is found that the model can reasonably predict their sound absorption coefficients. However, the presence of perturbations in pores give rise to inaccuracy of resistive component of the predicted surface impedance. The use of measured static flow resistive and corrected viscous length in the calculations are useful to cope with such a situation. Otherwise, the use of an optimized simple model as a function of flow resistivity is also applicable for this case.
The paper presents local dynamic approach to integration of an ensemble of predictors. The classical fusing of many predictor results takes into account all units and takes the weighted average of the results of all units forming the ensemble. This paper proposes different approach. The prediction of time series for the next day is done here by only one member of an ensemble, which was the best in the learning stage for the input vector, closest to the input data actually applied. Thanks to such arrangement we avoid the situation in which the worst unit reduces the accuracy of the whole ensemble. This way we obtain an increased level of statistical forecasting accuracy, since each task is performed by the best suited predictor. Moreover, such arrangement of integration allows for using units of very different quality without decreasing the quality of final prediction. The numerical experiments performed for forecasting the next input, the average PM10 pollution and forecasting the 24-element vector of hourly load of the power system have confirmed the superiority of the presented approach. All quality measures of forecast have been significantly improved.
A strip yield model implementation by the present authors is applied to predict fatigue crack growth observed in structural steel specimens under various constant and variable amplitude loading conditions. Attention is paid to the model calibration using the constraint factors in view of the dependence of both the crack closure mechanism and the material stress-strain response on the load history. Prediction capabilities of the model are considered in the context of the incompatibility between the crack growth resistance for constant and variable amplitude loading.
Weather forecasting requires knowledge of the laws of atmospheric movement. Apart from classic fluid mechanics, we must consider the rotational motion of our planet, the differential heating of its surface through the absorption of solar radiation, as well as water evaporation and condensation processes.
In individual dogs, despite good quality of raw sperm, some parameters are significantly changed after thawing, which cannot be predicted. We therefore investigated whether motility parameters objectively obtained by CASA, membrane integrity (MI), cell morphology or a combination are suitable to improve the prediction of bad post-thaw quality. For this purpose 250 sperm analysis protocols from 141 healthy stud dogs, all patients introduced for sperm cryopreservation, were evaluated and a Classification and Regression Tree (CART) -analysis performed. The sperm was routinely collected, analysed, and frozen by using a modified Uppsala system. After thawing, data were routinely examined by using CASA, fluorescent microscopy for membrane integrity (MI) and Hancock’s fixation for evaluation of cell morphology. Samples were sorted by post-thaw progressive motility (P) in good (P > / = 50%, n=135) and bad freezers (P<50%, n=115). Among bad freezers, 73.9% showed in addition post-thaw total morphological abberations of >40% and/or MI <50%.
Bad freezers were significantly older than good freezers (p<0.05). Progressive motility (P), velocity curvilinear (VCL), mean coefficient (STR), and linear coefficient (LIN) were potential predictors for post-thaw sperm quality since specifity was best (85.8%) and sensitivity (75.4 %) and accuracy (80.4 %) good. For these objectively measured raw sperm parameters, cut-off values were calculated allowing prediction of bad post-thaw results with high accuracy: P = 83.1 % VCL = 161.3 µm/sec, STR = 0.83 %, and LIN = 0.48 %. Raw sperm samples with values below these cut off values will have below average post-thaw quality with a probability of 85.8%. We conclude that VCL, P, STR and LIN are potential predictors of the outcome of sperm cryopreservation, when combined.
The existing traffic noise prediction models in road intersections relate mainly to the typical solutions of intersection geometry and traffic organisation. There are no models for large and more complex intersections such as signalised roundabouts. This paper presents the results of studies on the development of a traffic noise prediction model for this type of intersection. The model was developed using a multiple regression method based on the results of field measurements of traffic parameters and noise levels in the vicinity of signalised roundabouts in Poland. The obtained model consists of two groups of variables affecting noise levels at the intersection. The first group determines in detail the influence of traffic and geometry of the closest entry. The second group shows the influence of more distant noise sources (traffic at the three remaining entries of the intersection) and the influence of the dimensions of the entire intersection. The developed model was verified through additional field measurements, as well as compared to the results of two methods of traffic noise prediction: the French ‘NMPB-Routes-2008’ and the German ‘RLS-90’. The obtained results confirmed a higher accuracy of calculations performed using the developed model in the range of: −1.2 dB ÷ +1.0 dB, while the ‘NMPB-Routes-2008’ and ‘RLS-90’ calculate precision were respectively: −2.8 dB ÷ +1.3 dB, and +0.8 dB ÷ +5.2 dB. Therefore, the developed model allows for a more accurate prediction of noise levels in the vicinity of signalised roundabouts in a flat terrain without buildings and noise barriers.
A novel VC (voice conversion) method based on hybrid SVR (support vector regression) and GMM (Gaussian mixture model) is presented in the paper, the mapping abilities of SVR and GMM are exploited to map the spectral features of the source speaker to those of target ones. A new strategy of F0 transformation is also presented, the F0s are modeled with spectral features in a joint GMM and predicted from the converted spectral features using the SVR method. Subjective and objective tests are carried out to evaluate the VC performance; experimental results show that the converted speech using the proposed method can obtain a better quality than that using the state-of-the-art GMM method. Meanwhile, a VC method based on non-parallel data is also proposed, the speaker-specific information is investigated using the SVR method and preliminary subjective experiments demonstrate that the proposed method is feasible when a parallel corpus is not available.