Nonlinear time series prediction based on a power-law noise model

In this paper we investigate the influence of a power-law noise model, also called noise, on the performance of a feed-forward neural network used to predict time series. We introduce an optimization procedure that optimizes the parameters the neural networks by maximizing the likelihood function based on the power-law model. We show that our optimization procedure minimizes the mean squared leading to an optimal prediction. Further, we present numerical results applying method to time series from the logistic map and the annual number of sunspots demonstrate that a power-law noise model gives better results than a Gaussian model.

A new model based approach for the prediction and optimisation of thermal homogeneity in single screw extrusion

In polymer extrusion, delivery of a melt which is homogenous in composition and temperature is important for good product quality. However, the process is inherently prone to temperature fluctuations which are difficult to monitor and control via single point based conventional thermo- couples. In this work, the die melt temperature profile was monitored by a thermocouple mesh and the data obtained was used to generate a model to predict the die melt temperature profile. A novel nonlinear model was then proposed which was demonstrated to be in good agreement with training and unseen data. Furthermore, the proposed model was used to select optimum process settings to achieve the desired average melt temperature across the die while improving the temperature homogeneity. The simulation results indicate a reduction in melt temperature variations of up to 60%.

Development of a risk model for adverse drug events in the elderly

The aim of this study was to develop a predictive model for adverse drug events (ADEs) in elderly patients. Socio-demographic and medical data were collected from chart reviews, computerised information and a patient interview, for a population of 929 elderly patients (aged greater than or equal to 65 years) whose admission to the Waveney/B raid Valley Hospital in Northern Ireland was not scheduled. A further 204 patients formed a validation group. An ADE score was assigned to each patient using a modified Naranjo algorithm scoring system. The ADE scores ranged from 0 to 8. For the purposes of developing a risk model, scores of 4 or more were considered to constitute a high risk of an ADE.

Model selection for prognostic time-to-event gene signature discovery with applications in early breast cancer data

Model selection between competing models is a key consideration in the discovery of prognostic multigene signatures. The use of appropriate statistical performance measures as well as verification of biological significance of the signatures is imperative to maximise the chance of external validation of the generated signatures. Current approaches in time-to-event studies often use only a single measure of performance in model selection, such as logrank test p-values, or dichotomise the follow-up times at some phase of the study to facilitate signature discovery. In this study we improve the prognostic signature discovery process through the application of the multivariate partial Cox model combined with the concordance index, hazard ratio of predictions, independence from available clinical covariates and biological enrichment as measures of signature performance. The proposed framework was applied to discover prognostic multigene signatures from early breast cancer data. The partial Cox model combined with the multiple performance measures were used in both guiding the selection of the optimal panel of prognostic genes and prediction of risk within cross validation without dichotomising the follow-up times at any stage. The signatures were successfully externally cross validated in independent breast cancer datasets, yielding a hazard ratio of 2.55 [1.44, 4.51] for the top ranking signature.

Combining global climate and regional landscape models to improve prediction of invasion risk

Aim
It is widely acknowledged that species distributions result from a variety of biotic and abiotic factors operating at different spatial scales. Here, we aimed to (1) determine the extent to which global climate niche models (CNMs) can be improved by the addition of fine-scale regional data; (2) examine climatic and environmental factors influencing the range of 15 invasive aquatic plant species; and (3) provide a case study for the use of such models in invasion management on an island.

Location
Global, with a case study of species invasions in Ireland.

Methods
Climate niche models of global extent (including climate only) and regional environmental niche models (with additional factors such as human influence, land use and soil characteristics) were generated using maxent for 15 invasive aquatic plants. The performance of these models within the invaded range of the study species in Ireland was assessed, and potential hotspots of invasion suitability were determined. Models were projected forward up to 2080 based on two climate scenarios.

Results
While climate variables are important in defining the global range of species, factors related to land use and nutrient level were of greater importance in regional projections. Global climatic models were significantly improved at the island scale by the addition of fine-scale environmental variables (area under the curve values increased by 0.18 and true skill statistic values by 0.36), and projected ranges decreased from an average of 86% to 36% of the island.

Main conclusions
Refining CNMs with regional data on land use, human influence and landscape may have a substantial impact on predictive capacity, providing greater value for prioritization of conservation management at subregional or local scales.

An Evaluation of 1D Loss Model Collections for the Off-Design Performance Prediction of an Automotive Turbocharger Compressor

Abstract. Single-zone modelling is used to assess different collections of impeller 1D loss models. Three collections of loss models have been identified in literature, and the background to each of these collections is discussed. Each collection is evaluated using three modern automotive turbocharger style centrifugal compressors; comparisons of performance for each of the collections are made. An empirical data set taken from standard hot gas stand tests for each turbocharger is used as a baseline for comparison. Compressor range is predicted in this study; impeller diffusion ratio is shown to be a useful method of predicting compressor surge in 1D, and choke is predicted using basic compressible flow theory. The compressor designer can use this as a guide to identify the most compatible collection of losses for turbocharger compressor design applications. The analysis indicates the most appropriate collection for the design of automotive turbocharger centrifugal compressors.

Simplified model for prediction of compressive strength of alkali-activated natural pozzolans

The assessment of pozzolanic activity is essential for estimating the reaction of a material as pozzolan. Natural pozzolans can be activated and condensed with sodium silicate in an alkaline environment to synthesize high performance cementitious construction materials with low environmental impact. In this paper, the pozzolanic activities of five natural pozzolans are studied. The correlation between type and chemical composition of natural pozzolan, which affects the formation of the geopolymer gel phase, both for the calcined and untreated natural pozzolans, have been reviewed. The improvement in pozzolanic properties was studied following heat treatment including calcinations and/or elevated curing temperature by using alkali solubility, and compressive strength tests. A model was developed to allow prediction of the alkali-activated pozzolan strength versus their chemical compositions, alkali solubility, and crystallinity.

Comparison of excess radiological risk of building materials and industrial by-products according to I-index (EU-BSS) and revised room model (IAEA SSG-32)

To get a better insight into the radiological features of industrial by-products that can be reused in building materials a review of the reported scientific data can be very useful. The current study is based on the continuously growing database of the By-BM (H2020-MSCA-IF-2015) project (By-products for Building Materials). Currently, the By-BM database contains individual data of about 431 by-products and 1095 building and raw materials. It was found that in case of the building materials the natural radionuclide content varied widely (Ra-226: <DL-27851 Bq/kg; Th-232: <DL-906 Bq/kg, K-40: <DL-17922 Bq/kg), more so than for the by-products (Ra-226: 7-3152 Bq/kg; Th-232: <DL-1350 Bq/kg, K-40: <DL-3001 Bq/kg). The average Ra-226, Th-232 and K-40 contents of the reported by-products were respectively 2.52, 2.35 and 0.39 times higher than the building materials. The gamma exposure of bulk building products was calculated according to IAEA Specific Safety Guide No. SSG-32 and the European Commission Radiation Protection 112 based I-index (EU BSS). It was found that in most cases the I-index without density consideration provides a significant overestimation in excess effective dose.