972 resultados para Multi layer perceptron
Resumo:
The ERS-1 Satellite was launched in July 1991 by the European Space Agency into a polar orbit at about km800, carrying a C-band scatterometer. A scatterometer measures the amount of radar back scatter generated by small ripples on the ocean surface induced by instantaneous local winds. Operational methods that extract wind vectors from satellite scatterometer data are based on the local inversion of a forward model, mapping scatterometer observations to wind vectors, by the minimisation of a cost function in the scatterometer measurement space.par This report uses mixture density networks, a principled method for modelling conditional probability density functions, to model the joint probability distribution of the wind vectors given the satellite scatterometer measurements in a single cell (the `inverse' problem). The complexity of the mapping and the structure of the conditional probability density function are investigated by varying the number of units in the hidden layer of the multi-layer perceptron and the number of kernels in the Gaussian mixture model of the mixture density network respectively. The optimal model for networks trained per trace has twenty hidden units and four kernels. Further investigation shows that models trained with incidence angle as an input have results comparable to those models trained by trace. A hybrid mixture density network that incorporates geophysical knowledge of the problem confirms other results that the conditional probability distribution is dominantly bimodal.par The wind retrieval results improve on previous work at Aston, but do not match other neural network techniques that use spatial information in the inputs, which is to be expected given the ambiguity of the inverse problem. Current work uses the local inverse model for autonomous ambiguity removal in a principled Bayesian framework. Future directions in which these models may be improved are given.
Resumo:
Obtaining wind vectors over the ocean is important for weather forecasting and ocean modelling. Several satellite systems used operationally by meteorological agencies utilise scatterometers to infer wind vectors over the oceans. In this paper we present the results of using novel neural network based techniques to estimate wind vectors from such data. The problem is partitioned into estimating wind speed and wind direction. Wind speed is modelled using a multi-layer perceptron (MLP) and a sum of squares error function. Wind direction is a periodic variable and a multi-valued function for a given set of inputs; a conventional MLP fails at this task, and so we model the full periodic probability density of direction conditioned on the satellite derived inputs using a Mixture Density Network (MDN) with periodic kernel functions. A committee of the resulting MDNs is shown to improve the results.
Resumo:
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.
Resumo:
A number of researchers have investigated the impact of network architecture on the performance of artificial neural networks. Particular attention has been paid to the impact on the performance of the multi-layer perceptron of architectural issues, and the use of various strategies to attain an optimal network structure. However, there are still perceived limitations with the multi-layer perceptron and networks that employ a different architecture to the multi-layer perceptron have gained in popularity in recent years, particularly, networks that implement a more localised solution, where the solution in one area of the problem space does not impact, or has a minimal impact, on other areas of the space. In this study, we discuss the major architectural issues affecting the performance of a multi-layer perceptron, before moving on to examine in detail the performance of a new localised network, namely the bumptree. The work presented here examines the impact on the performance of artificial neural networks of employing alternative networks to the long established multi-layer perceptron. In particular, networks that impose a solution where the impact of each parameter in the final network architecture has a localised impact on the problem space being modelled are examined. The alternatives examined are the radial basis function and bumptree neural networks, and the impact of architectural issues on the performance of these networks is examined. Particular attention is paid to the bumptree, with new techniques for both developing the bumptree structure and employing this structure to classify patterns being examined.
Resumo:
Bankruptcy prediction has been a fruitful area of research. Univariate analysis and discriminant analysis were the first methodologies used. While they perform relatively well at correctly classifying bankrupt and nonbankrupt firms, their predictive ability has come into question over time. Univariate analysis lacks the big picture that financial distress entails. Multivariate discriminant analysis requires stringent assumptions that are violated when dealing with accounting ratios and market variables. This has led to the use of more complex models such as neural networks. While the accuracy of the predictions has improved with the use of more technical models, there is still an important point missing. Accounting ratios are the usual discriminating variables used in bankruptcy prediction. However, accounting ratios are backward-looking variables. At best, they are a current snapshot of the firm. Market variables are forward-looking variables. They are determined by discounting future outcomes. Microstructure variables, such as the bid-ask spread, also contain important information. Insiders are privy to more information that the retail investor, so if any financial distress is looming, the insiders should know before the general public. Therefore, any model in bankruptcy prediction should include market and microstructure variables. That is the focus of this dissertation. The traditional models and the newer, more technical models were tested and compared to the previous literature by employing accounting ratios, market variables, and microstructure variables. Our findings suggest that the more technical models are preferable, and that a mix of accounting and market variables are best at correctly classifying and predicting bankrupt firms. Multi-layer perceptron appears to be the most accurate model following the results. The set of best discriminating variables includes price, standard deviation of price, the bid-ask spread, net income to sale, working capital to total assets, and current liabilities to total assets.
Resumo:
Scientific and technological advancements in the area of fibrous and textile materials have greatly enhanced their application potential in several high-end technical and industrial sectors including construction, transportation, medical, sports, aerospace engineering, electronics and so on. Excellent performance accompanied by light-weight, mechanical flexibility, tailor-ability, design flexibility, easy fabrication and relatively lower cost are the driving forces towards wide applications of these materials. Cost-effective fabrication of various advanced and functional materials for structural parts, medical devices, sensors, energy harvesting devices, capacitors, batteries, and many others has been possible using fibrous and textile materials. Structural membranes are one of the innovative applications of textile structures and these novel building skins are becoming very popular due to flexible design aesthetics, durability, lightweight and cost benefits. Current demand on high performance and multi-functional materials in structural applications has motivated to go beyond the basic textile structures used for structural membranes and to use innovative textile materials. Structural membranes with self-cleaning, thermoregulation and energy harvesting capability (using solar cells) are examples of such recently developed multi-functional membranes. Besides these, there exist enormous opportunities to develop wide varieties of multi-functional membranes using functional textile materials. Additionally, it is also possible to further enhance the performance and functionalities of structural membranes using advanced fibrous architectures such as 2D, 3D, hybrid, multi-layer and so on. In this context, the present paper gives an overview of various advanced and functional fibrous and textile materials which have enormous application potential in structural membranes.
Resumo:
I use a multi-layer feedforward perceptron, with backpropagation learning implemented via stochastic gradient descent, to extrapolate the volatility smile of Euribor derivatives over low-strikes by training the network on parametric prices.
Resumo:
The objective of this work was to evaluate sampling density on the prediction accuracy of soil orders, with high spatial resolution, in a viticultural zone of Serra Gaúcha, Southern Brazil. A digital elevation model (DEM), a cartographic base, a conventional soil map, and the Idrisi software were used. Seven predictor variables were calculated and read along with soil classes in randomly distributed points, with sampling densities of 0.5, 1, 1.5, 2, and 4 points per hectare. Data were used to train a decision tree (Gini) and three artificial neural networks: adaptive resonance theory, fuzzy ARTMap; self‑organizing map, SOM; and multi‑layer perceptron, MLP. Estimated maps were compared with the conventional soil map to calculate omission and commission errors, overall accuracy, and quantity and allocation disagreement. The decision tree was less sensitive to sampling density and had the highest accuracy and consistence. The SOM was the less sensitive and most consistent network. The MLP had a critical minimum and showed high inconsistency, whereas fuzzy ARTMap was more sensitive and less accurate. Results indicate that sampling densities used in conventional soil surveys can serve as a reference to predict soil orders in Serra Gaúcha.
Resumo:
The present success in the manufacture of multi-layer interconnects in ultra-large-scale integration is largely due to the acceptable planarization capabilities of the chemical-mechanical polishing (CMP) process. In the past decade, copper has emerged as the preferred interconnect material. The greatest challenge in Cu CMP at present is the control of wafer surface non-uniformity at various scales. As the size of a wafer has increased to 300 mm, the wafer-level non-uniformity has assumed critical importance. Moreover, the pattern geometry in each die has become quite complex due to a wide range of feature sizes and multi-level structures. Therefore, it is important to develop a non-uniformity model that integrates wafer-, die- and feature-level variations into a unified, multi-scale dielectric erosion and Cu dishing model. In this paper, a systematic way of characterizing and modeling dishing in the single-step Cu CMP process is presented. The possible causes of dishing at each scale are identified in terms of several geometric and process parameters. The feature-scale pressure calculation based on the step-height at each polishing stage is introduced. The dishing model is based on pad elastic deformation and the evolving pattern geometry, and is integrated with the wafer- and die-level variations. Experimental and analytical means of determining the model parameters are outlined and the model is validated by polishing experiments on patterned wafers. Finally, practical approaches for minimizing Cu dishing are suggested.
Resumo:
The present success in the manufacture of multi-layer interconnects in ultra-large-scale integration is largely due to the acceptable planarization capabilities of the chemical-mechanical polishing (CMP) process. In the past decade, copper has emerged as the preferred interconnect material. The greatest challenge in Cu CMP at present is the control of wafer surface non-uniformity at various scales. As the size of a wafer has increased to 300 mm, the wafer-level non-uniformity has assumed critical importance. Moreover, the pattern geometry in each die has become quite complex due to a wide range of feature sizes and multi-level structures. Therefore, it is important to develop a non-uniformity model that integrates wafer-, die- and feature-level variations into a unified, multi-scale dielectric erosion and Cu dishing model. In this paper, a systematic way of characterizing and modeling dishing in the single-step Cu CMP process is presented. The possible causes of dishing at each scale are identified in terms of several geometric and process parameters. The feature-scale pressure calculation based on the step-height at each polishing stage is introduced. The dishing model is based on pad elastic deformation and the evolving pattern geometry, and is integrated with the wafer- and die-level variations. Experimental and analytical means of determining the model parameters are outlined and the model is validated by polishing experiments on patterned wafers. Finally, practical approaches for minimizing Cu dishing are suggested.
Resumo:
The influence of the interlayer coupling on formation of the quantized Hall conductor phase at the filling factor v = 2 was studied in the multi-layer GaAs/AlGaAs heterostructures. The disorder broadened Gaussian photoluminescence line due to the localized electrons was found in the quantized Hall phase of the isolated multi-quantum well structure. On the other hand, the quantized Hall phase of the weakly coupled multi-layers emitted an unexpected asymmetrical line similar to that one observed in the metallic electron systems. We demonstrated that the observed asymmetry is caused by a partial population of the extended electron states formed in the quantized Hall conductor phase due to the interlayer percolation. A sharp decrease of the single-particle scattering time associated with these extended states was observed at the filling factor v = 2. (c) 2007 Elsevier B.V. All rights reserved.
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Graphene, in single layer or multi-layer forms, holds great promise for future electronics and high-temperature applications. Resistance to oxidation, an important property for high-temperature applications, has not yet been extensively investigated. Controlled thinning of multi-layer graphene (MLG), e.g., by plasma or laser processing is another challenge, since the existing methods produce non-uniform thinning or introduce undesirable defects in the basal plane. We report here that heating to extremely high temperatures (exceeding 2000 K) and controllable layer-by-layer burning (thinning) can be achieved by low-power laser processing of suspended high-quality MLG in air in "cold-wall" reactor configuration. In contrast, localized laser heating of supported samples results in non-uniform graphene burning at much higher rates. Fully atomistic molecular dynamics simulations were also performed to reveal details of oxidation mechanisms leading to uniform layer-by-layer graphene gasification. The extraordinary resistance of MLG to oxidation paves the way to novel high-temperature applications as continuum light source or scaffolding material.
Resumo:
I grafi sono molto utilizzati per la rappresentazione di dati, sopratutto in quelle aree dove l’informazione sull’interconnettività e la topologia dei dati è importante tanto quanto i dati stessi, se non addirittura di più. Ogni area di applicazione ha delle proprie necessità, sia in termini del modello che rappresenta i dati, sia in termini del linguaggio capace di fornire la necessaria espressività per poter fare interrogazione e trasformazione dei dati. È sempre più frequente che si richieda di analizzare dati provenienti da diversi sistemi, oppure che si richieda di analizzare caratteristiche dello stesso sistema osservandolo a granularità differenti, in tempi differenti oppure considerando relazioni differenti. Il nostro scopo è stato quindi quello di creare un modello, che riesca a rappresentare in maniera semplice ed efficace i dati, in tutte queste situazioni. Entrando più nei dettagli, il modello permette non solo di analizzare la singola rete, ma di analizzare più reti, relazionandole tra loro. Il nostro scopo si è anche esteso nel definire un’algebra, che, tramite ai suoi operatori, permette di compiere delle interrogazioni su questo modello. La definizione del modello e degli operatori sono stati maggiormente guidati dal caso di studio dei social network, non tralasciando comunque di rimanere generali per fare altri tipi di analisi. In seguito abbiamo approfondito lo studio degli operatori, individuando delle proprietà utili per fare delle ottimizzazioni, ragionando sui dettagli implementativi, e fornendo degli algoritmi di alto livello. Per rendere più concreta la definizione del modello e degli operatori, in modo da non lasciare spazio ad ambiguità, è stata fatta anche un’implementazione, e in questo elaborato ne forniremo la descrizione.
Resumo:
Adsorption of pure nitrogen, argon, acetone, chloroform and acetone-chloroform mixture on graphitized thermal carbon black is considered at sub-critical conditions by means of molecular layer structure theory (MLST). In the present version of the MLST an adsorbed fluid is considered as a sequence of 2D molecular layers, whose Helmholtz free energies are obtained directly from the analysis of experimental adsorption isotherm of pure components. The interaction of the nearest layers is accounted for in the framework of mean field approximation. This approach allows quantitative correlating of experimental nitrogen and argon adsorption isotherm both in the monolayer region and in the range of multi-layer coverage up to 10 molecular layers. In the case of acetone and chloroform the approach also leads to excellent quantitative correlation of adsorption isotherms, while molecular approaches such as the non-local density functional theory (NLDFT) fail to describe those isotherms. We extend our new method to calculate the Helmholtz free energy of an adsorbed mixture using a simple mixing rule, and this allows us to predict mixture adsorption isotherms from pure component adsorption isotherms. The approach, which accounts for the difference in composition in different molecular layers, is tested against the experimental data of acetone-chloroform mixture (non-ideal mixture) adsorption on graphitized thermal carbon black at 50 degrees C. (C) 2005 Elsevier Ltd. All rights reserved.