Modelling nonlinear vehicle dynamics with neural networks

The nonlinear modelling ability of neural networks has been widely recognised as an effective tool to identify and control dynamic systems, with applications including nonlinear vehicle dynamics which this paper focuses on using multi-layer perceptron networks. Existing neural network literature does not detail some of the factors which effect neural network nonlinear modelling ability. This paper investigates into and concludes on required network size, structure and initial weights, considering results for networks of converged weights. The paper also presents an online training method and an error measure representing the network's parallel modelling ability over a range of operating conditions. Copyright © 2010 Inderscience Enterprises Ltd.

Application of neural networks to the ranking of perinatal variables influencing birthweight.

In this paper we compare Multi-Layer Perceptrons (a neural network type) with Multivariate Linear Regression in predicting birthweight from nine perinatal variables which are thought to be related. Results show, that seven of the nine variables, i.e., gestational age, mother's body-mass index (BMI), sex of the baby, mother's height, smoking, parity and gravidity, are related to birthweight. We found no significant relationship between birthweight and each of the two variables, i.e., maternal age and social class.

The modified Kanerva model for automatic speech recognition

A parallel processing network derived from Kanerva's associative memory theory Kanerva 1984 is shown to be able to train rapidly on connected speech data and recognize further speech data with a label error rate of 0·68%. This modified Kanerva model can be trained substantially faster than other networks with comparable pattern discrimination properties. Kanerva presented his theory of a self-propagating search in 1984, and showed theoretically that large-scale versions of his model would have powerful pattern matching properties. This paper describes how the design for the modified Kanerva model is derived from Kanerva's original theory. Several designs are tested to discover which form may be implemented fastest while still maintaining versatile recognition performance. A method is developed to deal with the time varying nature of the speech signal by recognizing static patterns together with a fixed quantity of contextual information. In order to recognize speech features in different contexts it is necessary for a network to be able to model disjoint pattern classes. This type of modelling cannot be performed by a single layer of links. Network research was once held back by the inability of single-layer networks to solve this sort of problem, and the lack of a training algorithm for multi-layer networks. Rumelhart, Hinton & Williams 1985 provided one solution by demonstrating the "back propagation" training algorithm for multi-layer networks. A second alternative is used in the modified Kanerva model. A non-linear fixed transformation maps the pattern space into a space of higher dimensionality in which the speech features are linearly separable. A single-layer network may then be used to perform the recognition. The advantage of this solution over the other using multi-layer networks lies in the greater power and speed of the single-layer network training algorithm. © 1989.

Interactions between building integrated photovoltaics and microclimate in urban environments

BIPV (building integrated photovoltaics) has progressed in the past years and become an element to be considered in city planning. BIPV has significant influence on microclimate in urban environments and the performance of BIPV is also affected by urban climate. The thermal model and electrical performance model of ventilated BIPV are combined to predict PV temperature and PV power output in Tianjin, China. Then, by using dynamic building energy model, the building cooling load for installing BIPV is calculated. A multi-layer model AUSSSM of urban canopy layer is used to assess the effect of BIPV on the Urban Heat Island (UHI). The simulation results show that in comparison with the conventional roof, the total building cooling load with ventilation PV roof may be decreased by 10%. The UHI effect after using BIPV relies on the surface absorptivity of original building. In this case, the daily total PV electricity output in urban areas may be reduced by 13% compared with the suburban areas due to UHI and solar radiation attenuation because of urban air pollution. The calculation results reveal that it is necessary to pay attention to and further analyze interactions between BIPV and microdimate in urban environments to decrease urban pollution, improve BIPV performance and reduce cooling load. Copyright © 2006 by ASME.

An analysis of competing toughening mechanisms in layered and particulate solids

The relative potency of common toughening mechanisms is explored for layered solids and particulate solids, with an emphasis on crack multiplication and plasticity. First, the enhancement in toughness due to a parallel array of cracks in an elastic solid is explored, and the stability of co-operative cracking is quantified. Second, the degree of synergistic toughening is determined for combined crack penetration and crack kinking at the tip of a macroscopic, mode I crack; specifically, the asymptotic problem of self-similar crack advance (penetration mode) versus 90 ° symmetric kinking is considered for an isotropic, homogeneous solid with weak interfaces. Each interface is treated as a cohesive zone of finite strength and toughness. Third, the degree of toughening associated with crack multiplication is assessed for a particulate solid comprising isotropic elastic grains of hexagonal shape, bonded by cohesive zones of finite strength and toughness. The study concludes with the prediction of R-curves for a mode I crack in a multi-layer stack of elastic and elastic-plastic solids. A detailed comparison of the potency of the above mechanisms and their practical application are given. In broad terms, crack tip kinking can be highly potent, whereas multiple cracking is difficult to activate under quasi-static conditions. Plastic dissipation can give a significant toughening in multi-layers especially at the nanoscale. © 2013 Springer Science+Business Media Dordrecht.

Tandem system adaptation using multiple linear feature transforms

Adaptation to speaker and environment changes is an essential part of current automatic speech recognition (ASR) systems. In recent years the use of multi-layer percpetrons (MLPs) has become increasingly common in ASR systems. A standard approach to handling speaker differences when using MLPs is to apply a global speaker-specific constrained MLLR (CMLLR) transform to the features prior to training or using the MLP. This paper considers the situation when there are both speaker and channel, communication link, differences in the data. A more powerful transform, front-end CMLLR (FE-CMLLR), is applied to the inputs to the MLP to represent the channel differences. Though global, these FE-CMLLR transforms vary from time-instance to time-instance. Experiments on a channel distorted dialect Arabic conversational speech recognition task indicates the usefulness of adapting MLP features using both CMLLR and FE-CMLLR transforms. © 2013 IEEE.

Highly electron transparent Graphene for field emission triode gates

The enhanced emission performance of a graphene/Mo hybrid gate electrode integrated into a nanocarbon field emission micro-triode electron source is presented. Highly electron transparent gate electrodes are fabricated from chemical vapor deposited bilayer graphene transferred to Mo grids with experimental and simulated data, showing that liberated electrons efficiently traverse multi-layer graphene membranes with transparencies in excess of 50-68%. The graphene hybrid gates are shown to reduce the gate driving voltage by 1.1 kV, whilst increasing the electron transmission efficiency of the gate electrode significantly. Integrated intensity maps show that the electron beam angular dispersion is dramatically improved (87.9°) coupled with a 63% reduction in beam diameter. Impressive temporal stability is noted (<1.0%) with surprising negligible long-term damage to the graphene. A 34% increase in triode perveance and an amplification factor 7.6 times that of conventional refractory metal grid gate electrode-based triodes are noted, thus demonstrating the excellent stability and suitability of graphene gates in micro-triode electron sources. A nanocarbon field emission triode with a hybrid gate electrode is developed. The graphene/Mo gate shows a high electron transparency (50-68%) which results in a reduced turn-on potential, increased beam collimation, reduced beam diameter (63%), enhanced stability (<1% variation), a 34% increase in perveance, and an amplification 7.6 times that of equivalent conventional refractory metal gate triodes. © 2013 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.