Polarization of forecast densities : a new approach to time series classification

Time series classification has been extensively explored in many fields of study. Most methods are based on the historical or current information extracted from data. However, if interest is in a specific future time period, methods that directly relate to forecasts of time series are much more appropriate. An approach to time series classification is proposed based on a polarization measure of forecast densities of time series. By fitting autoregressive models, forecast replicates of each time series are obtained via the bias-corrected bootstrap, and a stationarity correction is considered when necessary. Kernel estimators are then employed to approximate forecast densities, and discrepancies of forecast densities of pairs of time series are estimated by a polarization measure, which evaluates the extent to which two densities overlap. Following the distributional properties of the polarization measure, a discriminant rule and a clustering method are proposed to conduct the supervised and unsupervised classification, respectively. The proposed methodology is applied to both simulated and real data sets, and the results show desirable properties.

Experiences with control of evaporators using extensive vapour bleeding

FOR SUGAR factories with cogeneration plants major changes to the process stations have been undertaken to reduce the consumption of exhaust steam from the turbines and maximise the generated power. In many cases the process steam consumption has been reduced from greater than 52% on cane to ~40% on cane. The main changes have been to install additional evaporation area at the front of the set, operate the pan stages on vapour from No 1 or No 2 effects and undertake juice heating using vapour bleed from evaporators as far down the set as the penultimate stage. Operationally, one of the main challenges has been to develop a control system for the evaporators that addresses the objectives of juice processing rate (throughput) and steam economy, while producing syrup consistently at the required brix and providing an adequate and consistent vapour pressure for the pan stage operations. The cyclic demand for vapour by batch pans causes process disturbances through the evaporator set and these must be regulated in an effective manner to satisfy the above list of objectives for the evaporator station. The impact of the cyclic pan stage vapour demand has been modelled to define the impact on juice rate, steam economy, syrup brix and head space pressures in the evaporators. Experiences with the control schemes used at Pioneer and Rocky Point Mills are discussed. For each factory the paper provides information on (a) the control system used, the philosophy behind the control system and experiences in reaching the current system for control (b) the performance of the control system to handle the disturbances imposed by the pan stage and operate within other constraints of the factory (c) deficiencies in the current system and plans for further improvements. Other processing changes to boost the performance of the evaporators are also discussed.

The geographical co-distribution and socio-ecological drivers of childhood pneumonia and diarrhoea in Queensland, Australia

This study aimed to explore the spatiotemporal patterns, geographic co-distribution, and socio-ecological drivers of childhood pneumonia and diarrhea in Queensland. A Bayesian conditional autoregressive model was used to quantify the impacts of socio-ecological factors on both childhood pneumonia and diarrhea at a postal area level. A distinct seasonality of childhood pneumonia and diarrhea was found. Childhood pneumonia and diarrhea mainly distributed in northwest of Queensland. Mount Isa was the high-risk cluster where childhood pneumonia and diarrhea co-distributed. Emergency department visits (EDVs) for pneumonia increased by 3% per 10-mm increase in monthly average rainfall, in wet seasons. In comparison, a 10-mm increase in monthly average rainfall may increase 4% of EDVs for diarrhea. Monthly average temperature was negatively associated with EDVs for childhood diarrhea, in wet seasons. Low socioeconomic index for areas (SEIFA) was associated with high EDVs for childhood pneumonia. Future pneumonia and diarrhea prevention and control measures in Queensland should focus more on Mount Isa.

Does the price of oil interact with clean energy prices in the stock market?

In this paper, we analyze the relationships among oil prices, clean energy stock prices, and technology stock prices, endogenously controlling for structural changes in the market. To this end, we apply Markov-switching vector autoregressive models to the economic system consisting of oil prices, clean energy and technology stock prices, and interest rates. The results indicate that there was a structural change in late 2007, a period in which there was a significant increase in the price of oil. In contrast to the previous studies, we find a positive relationship between oil prices and clean energy prices after structural breaks. There also appears to be a similarity in terms of the market response to both clean energy stock prices and technology stock prices. © 2013 Elsevier B.V.

An investigation of the impact of various geographical scales for the specification of spatial dependence

Ecological studies are based on characteristics of groups of individuals, which are common in various disciplines including epidemiology. It is of great interest for epidemiologists to study the geographical variation of a disease by accounting for the positive spatial dependence between neighbouring areas. However, the choice of scale of the spatial correlation requires much attention. In view of a lack of studies in this area, this study aims to investigate the impact of differing definitions of geographical scales using a multilevel model. We propose a new approach -- the grid-based partitions and compare it with the popular census region approach. Unexplained geographical variation is accounted for via area-specific unstructured random effects and spatially structured random effects specified as an intrinsic conditional autoregressive process. Using grid-based modelling of random effects in contrast to the census region approach, we illustrate conditions where improvements are observed in the estimation of the linear predictor, random effects, parameters, and the identification of the distribution of residual risk and the aggregate risk in a study region. The study has found that grid-based modelling is a valuable approach for spatially sparse data while the SLA-based and grid-based approaches perform equally well for spatially dense data.

Stochastic output feedback model predictive control

This paper addresses the issue of output feedback model predictive control for linear systems with input constraints and stochastic disturbances. We show that the optimal policy uses the Kalman filter for state estimation, but the resultant state estimates are not utilized in a certainty equivalence control law

Design of a nonlinear excitation controller using inverse filtering for transient stability enhancement

This paper proposes a nonlinear excitation controller to improve transient stability, oscillation damping and voltage regulation of the power system. The energy function of the predicted system states is used to obtain the desired flux for the next time step, which in turn is used to obtain a supplementary control input using an inverse filtering method. The inverse filtering technique enables the system to provide an additional input for the excitation system, which forces the system to track the desired flux. Synchronous generator flux saturation model is used in this paper. A single machine infinite bus (SMIB) test system is used to demonstrate the efficacy of the proposed control method using time-domain simulations. The robustness of the controller is assessed under different operating conditions.

Inspection of pole-like structures using a vision-controlled VTOL UAV and shared autonomy

We present an approach for the inspection of vertical pole-like infrastructure using a vertical take-off and landing (VTOL) unmanned aerial vehicle and shared autonomy. Inspecting vertical structures, such as light and power distribution poles, is a time consuming, dangerous and expensive task with high operator workload. To address these issues, we propose a VTOL platform that can operate at close-quarters, whilst maintaining a safe stand-off distance and rejecting environmental disturbances. We adopt an Image based Visual Servoing (IBVS) technique using only two line features to stabilise the vehicle with respect to a pole. Visual, inertial and sonar data are used, making the approach suitable for indoor or GPS-denied environments. Results from simulation and outdoor flight experiments demonstrate the system is able to successfully inspect and circumnavigate a pole.

Uncertainty quantification applied to the performance analysis of a conical diffuser

This paper offers an uncertainty quantification (UQ) study applied to the performance analysis of the ERCOFTAC conical diffuser. A deterministic CFD solver is coupled with a non-statistical generalised Polynomial Chaos(gPC)representation based on a pseudo-spectral projection method. Such approach has the advantage to not require any modification of the CFD code for the propagation of random disturbances in the aerodynamic field. The stochactic results highlihgt the importance of the inlet velocity uncertainties on the pressure recovery both alone and when coupled with a second uncertain variable. From a theoretical point of view, we investigate the possibility to build our gPC representation on arbitray grid, thus increasing the flexibility of the stochastic framework.

Assessment of the concentrations of polybrominated diphenyl ether flame retardants in the Australian population : levels in blood

Polybrominated diphenyl ethers (PBDEs), a common class of brominated flame retardants, are a ubiquitous part of our built environment, and for many years have contributed to improved public safety by reducing the flammability of everyday goods. Recently, PBDEs have come under increased international attention because of their potential to impact upon the environment and human health. Some PBDE compounds have been nominated for possible inclusion on the Stockholm Convention on Persistent Organic Pollutants, to which Australia is a Party. Work under the Stockholm Convention has demonstrated the capacity of some PBDEs to persist and accumulate in the environment and to be carried long distances. Much is unknown about the impact of PBDEs on living organisms, however recent studies show that some PBDEs can inhibit growth in colonies of plankton and algae and depress the reproduction of zooplankton. Laboratory mice and rats have also shown liver disturbances and damage to developing nervous systems as a result of exposure to PBDEs. In 2004, the Australian Government Department of the Environment and Water Resources began three studies to examine levels of PBDEs in aquatic sediments, indoor environments and human blood, as knowledge about PBDEs in Australia was very limited. The aim of these studies was to improve this knowledge base so that governments were in a better position to consider appropriate management actions. Due to the high costs for laboratory analysis of PBDEs, the number of samples collected for each study was limited and so caution is required when interpreting the findings. Nevertheless, these studies will provide governments with an indication of how prevalent PBDEs are in the Australian population and the environment and will also contribute to international knowledge about these chemicals. The Department of the Environment and Water Resources will be working closely with othergovernment agencies, industry and the community to investigate any further action that may be required to address PBDEs in Australia.

Weather variability and influenza A (H7N9) transmission in Shanghai, China: A Bayesian spatial analysis

Abstract Background A novel avian influenza A (H7N9) virus was first found in humans in Shanghai, and infected over 433 patients in China. To date, very little is known about the spatiotemporal variability or environmental drivers of the risk of H7N9 infection. This study explored the spatial and temporal variation of H7N9 infection and assessed the effects of temperature and rainfall on H7N9 incidence. Methods A Bayesian spatial conditional autoregressive (CAR) model was used to assess the spatiotemporal distribution of the risk of H7N9 infection in Shanghai, by district and fortnight for the period 19th February–14th April 2013. Data on daily laboratory-confirmed H7N9 cases, and weather variability including temperature (°C) and rainfall (mm) were obtained from the Chinese Information System for Diseases Control and Prevention and Chinese Meteorological Data Sharing Service System, respectively, and aggregated by fortnight. Results High spatial variations in the H7N9 risk were mainly observed in the east and centre of Shanghai municipality. H7N9 incidence rate was significantly associated with fortnightly mean temperature (Relative Risk (RR): 1.54; 95% credible interval (CI): 1.22–1.94) and fortnightly mean rainfall (RR: 2.86; 95% CI: 1.47–5.56). Conclusion There was a substantial variation in the spatiotemporal distribution of H7N9 infection across different districts in Shanghai. Optimal temperature and rainfall may be one of the driving forces for H7N9.

Discovering future disaster management capability needs using scenario planning

In recent years disaster risk reduction efforts have focused on disturbances ranging from climate variability, seismic hazards, geo-political instability and public and animal health crises. These factors combined with uncertainty derived from inter-dependencies within and across systems of critical infrastructure create significant problems of governance for the private and public sector alike. The potential for rapid spread of impacts, geographically and virtually, can render a comprehensive understanding of disaster response and recovery needs and risk mitigation issues beyond the grasp of competent authority. Because of such cascading effects communities and governments at local and state-levels are unlikely to face single incidents but rather series of systemic impacts: often appearing concurrently. A further point to note is that both natural and technological hazards can act directly on socio-technical systems as well as being propagated by them: as network events. Such events have been categorised as ‘outside of the box,’ ‘too fast,’ and ‘too strange’ (Lagadec, 2004). Emergent complexities in linked systems can make disaster effects difficult to anticipate and recovery efforts difficult to plan for. Beyond the uncertainties of real world disasters, that might be called familiar or even regular, can we safely assume that the generic capability we use now will suit future disaster contexts? This paper presents initial scoping of research funded by the Bushfire and Natural Hazards Cooperative Research Centre seeking to define future capability needs of disaster management organisations. It explores challenges to anticipating the needs of representative agencies and groups active in before, during and after phases of emergency and disaster situations using capability deficit assessments and scenario assessment.

Socio-environmental drivers and suicide in Australia: Bayesian spatial analysis

Background The impact of socio-environmental factors on suicide has been examined in many studies. Few of them, however, have explored these associations from a spatial perspective, especially in assessing the association between meteorological factors and suicide. This study examined the association of meteorological and socio-demographic factors with suicide across small areas over different time periods. Methods Suicide, population and socio-demographic data (e.g., population of Aboriginal and Torres Strait Islanders (ATSI), and unemployment rate (UNE) at the Local Government Area (LGA) level were obtained from the Australian Bureau of Statistics for the period of 1986 to 2005. Information on meteorological factors (rainfall, temperature and humidity) was supplied by Australian Bureau of Meteorology. A Bayesian Conditional Autoregressive (CAR) Model was applied to explore the association of socio-demographic and meteorological factors with suicide across LGAs. Results In Model I (socio-demographic factors), proportion of ATSI and UNE were positively associated with suicide from 1996 to 2000 (Relative Risk (RR)ATSI = 1.0107, 95% Credible Interval (CI): 1.0062-1.0151; RRUNE = 1.0187, 95% CI: 1.0060-1.0315), and from 2001 to 2005 (RRATSI = 1.0126, 95% CI: 1.0076-1.0176; RRUNE = 1.0198, 95% CI: 1.0041-1.0354). Socio-Economic Index for Area (SEIFA) and IND, however, had negative associations with suicide between 1986 and 1990 (RRSEIFA = 0.9983, 95% CI: 0.9971-0.9995; RRATSI = 0.9914, 95% CI: 0.9848-0.9980). Model II (meteorological factors): a 1°C higher yearly mean temperature across LGAs increased the suicide rate by an average by 2.27% (95% CI: 0.73%, 3.82%) in 1996–2000, and 3.24% (95% CI: 1.26%, 5.21%) in 2001–2005. The associations between socio-demographic factors and suicide in Model III (socio-demographic and meteorological factors) were similar to those in Model I; but, there is no substantive association between climate and suicide in Model III. Conclusions Proportion of Aboriginal and Torres Strait Islanders, unemployment and temperature appeared to be statistically associated with of suicide incidence across LGAs among all selected variables, especially in recent years. The results indicated that socio-demographic factors played more important roles than meteorological factors in the spatial pattern of suicide incidence.

Alive SMC^2: Bayesian model selection for low-count time series models with intractable likelihoods

In this paper we present a new method for performing Bayesian parameter inference and model choice for low count time series models with intractable likelihoods. The method involves incorporating an alive particle filter within a sequential Monte Carlo (SMC) algorithm to create a novel pseudo-marginal algorithm, which we refer to as alive SMC^2. The advantages of this approach over competing approaches is that it is naturally adaptive, it does not involve between-model proposals required in reversible jump Markov chain Monte Carlo and does not rely on potentially rough approximations. The algorithm is demonstrated on Markov process and integer autoregressive moving average models applied to real biological datasets of hospital-acquired pathogen incidence, animal health time series and the cumulative number of poison disease cases in mule deer.