Bias-free identification of a linear model-predictive steering controller from measured driver steering behavior

Recent developments in modeling driver steering control with preview are reviewed. While some validation with experimental data has been presented, the rigorous application of formal system identification methods has not yet been attempted. This paper describes a steering controller based on linear model-predictive control. An indirect identification method that minimizes steering angle prediction error is developed. Special attention is given to filtering the prediction error so as to avoid identification bias that arises from the closed-loop operation of the driver-vehicle system. The identification procedure is applied to data collected from 14 test drivers performing double lane change maneuvers in an instrumented vehicle. It is found that the identification procedure successfully finds parameter values for the model that give small prediction errors. The procedure is also able to distinguish between the different steering strategies adopted by the test drivers. © 2006 IEEE.

Impacts of concurrency, iteration, design review, and problem complexity on design project lead time and error generation

A case study of an aircraft engine manufacturer is used to analyze the effects of management levers on the lead time and design errors generated in an iteration-intensive concurrent engineering process. The levers considered are amount of design-space exploration iteration, degree of process concurrency, and timing of design reviews. Simulation is used to show how the ideal combination of these levers can vary with changes in design problem complexity, which can increase, for instance, when novel technology is incorporated in a design. Results confirm that it is important to consider multiple iteration-influencing factors and their interdependencies to understand concurrent processes, because the factors can interact with confounding effects. The article also demonstrates a new approach to derive a system dynamics model from a process task network. The new approach could be applied to analyze other concurrent engineering scenarios. © The Author(s) 2012.

Improving LVCSR system combination using neural network language model cross adaptation

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. The standard approach involves only cross adapting acoustic models. To fully exploit the complimentary features among sub-systems, language model (LM) cross adaptation techniques can be used. Previous research on multi-level n-gram LM cross adaptation is extended to further include the cross adaptation of neural network LMs in this paper. Using this improved LM cross adaptation framework, significant error rate gains of 4.0%-7.1% relative were obtained over acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. Copyright © 2011 ISCA.

Use of contexts in language model interpolation and adaptation

Language models (LMs) are often constructed by building multiple individual component models that are combined using context independent interpolation weights. By tuning these weights, using either perplexity or discriminative approaches, it is possible to adapt LMs to a particular task. This paper investigates the use of context dependent weighting in both interpolation and test-time adaptation of language models. Depending on the previous word contexts, a discrete history weighting function is used to adjust the contribution from each component model. As this dramatically increases the number of parameters to estimate, robust weight estimation schemes are required. Several approaches are described in this paper. The first approach is based on MAP estimation where interpolation weights of lower order contexts are used as smoothing priors. The second approach uses training data to ensure robust estimation of LM interpolation weights. This can also serve as a smoothing prior for MAP adaptation. A normalized perplexity metric is proposed to handle the bias of the standard perplexity criterion to corpus size. A range of schemes to combine weight information obtained from training data and test data hypotheses are also proposed to improve robustness during context dependent LM adaptation. In addition, a minimum Bayes' risk (MBR) based discriminative training scheme is also proposed. An efficient weighted finite state transducer (WFST) decoding algorithm for context dependent interpolation is also presented. The proposed technique was evaluated using a state-of-the-art Mandarin Chinese broadcast speech transcription task. Character error rate (CER) reductions up to 7.3 relative were obtained as well as consistent perplexity improvements. © 2012 Elsevier Ltd. All rights reserved.

N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.

A Hierarchical Model for Ordinal Matrix Factorization

This paper proposes a hierarchical probabilistic model for ordinal matrix factorization. Unlike previous approaches, we model the ordinal nature of the data and take a principled approach to incorporating priors for the hidden variables. Two algorithms are presented for inference, one based on Gibbs sampling and one based on variational Bayes. Importantly, these algorithms may be implemented in the factorization of very large matrices with missing entries. The model is evaluated on a collaborative filtering task, where users have rated a collection of movies and the system is asked to predict their ratings for other movies. The Netflix data set is used for evaluation, which consists of around 100 million ratings. Using root mean-squared error (RMSE) as an evaluation metric, results show that the suggested model outperforms alternative factorization techniques. Results also show how Gibbs sampling outperforms variational Bayes on this task, despite the large number of ratings and model parameters. Matlab implementations of the proposed algorithms are available from cogsys.imm.dtu.dk/ordinalmatrixfactorization.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple sub-systems that may even be developed at different sites. Cross system adaptation, in which model adaptation is performed using the outputs from another sub-system, can be used as an alternative to hypothesis level combination schemes such as ROVER. Normally cross adaptation is only performed on the acoustic models. However, there are many other levels in LVCSR systems' modelling hierarchy where complimentary features may be exploited, for example, the sub-word and the word level, to further improve cross adaptation based system combination. It is thus interesting to also cross adapt language models (LMs) to capture these additional useful features. In this paper cross adaptation is applied to three forms of language models, a multi-level LM that models both syllable and word sequences, a word level neural network LM, and the linear combination of the two. Significant error rate reductions of 4.0-7.1% relative were obtained over ROVER and acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. © 2012 Elsevier Ltd. All rights reserved.

Complementary Phone Error training

This paper introduces a novel method for the training of a complementary acoustic model with respect to set of given acoustic models. The method is based upon an extension of the Minimum Phone Error (MPE) criterion and aims at producing a model that makes complementary phone errors to those already trained. The technique is therefore called Complementary Phone Error (CPE) training. The method is evaluated using an Arabic large vocabulary continuous speech recognition task. Reductions in word error rate (WER) after combination with a CPE-trained system were obtained with up to 0.7% absolute for a system trained on 172 hours of acoustic data and up to 0.2% absolute for the final system trained on nearly 2000 hours of Arabic data.

Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application

A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the function of human being, rather than traditional statistical Pattern Recognition using "optimal separating" as its main principle. So the new model of Pattern Recognition is called the Biomimetic Pattern Recognition (BPR)(1). Its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. Therefore, it is also called the Topological Pattern Recognition (TPR). The fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. We experimented with the Biomimetic Pattern Recognition (BPR) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. Onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. For the total 8800 tests, the correct recognition rate is 99.87%. The rejection rate is 0.13% and on the condition of zero error rates, the correct rate of BPR was much better than that of RBF-SVM.

Reduction-Based Model Updating of a Scaled Offshore Platform Structure

This paper attempts to develop a reduction-based model updating technique for jacket offshore platform structure. A reduced model is used instead of the direct finite-element model of the real structure in order to circumvent such difficulties as huge degrees of freedom and incomplete experimental data that are usually civil engineers' trouble during the model updating. The whole process consists of three steps: reduction of FE model, the first model updating to minimize the reduction error, and the second model updating to minimize the modeling error of the reduced model and the real structure. According to the performance of jacket platforms, a local-rigidity assumption is employed to obtain the reduced model. The technique is applied in a downscale model of a four-legged offshore platform where its effectiveness is well proven. Furthermore, a comparison between the real structure and its numerical models in the following model validation shows that the updated models have good approximation to the real structure. Besides, some difficulties in the field of model updating are also discussed.

Application of the Sanchez-Lacombe lattice fluid theory to the system pvme/ps and model calculations

Cloud point curves reported in the literature for five representatives of the system poly(vinyl methyl ether)/polystyrene were evaluated theoretically by means of the Sanchez-Lacombe lattice fluid theory. The measured phase separation behavior can be described within experimental error using only one adjustable parameter (quantifying the interaction between the unlike mers). The Flory-Huggins interaction parameters calculated from this theoretical description depend in good approximation linearly on composition (volume fractions) and on the inverse temperature. An evaluation of these data yields a maximum heat effect which is almost one order of magnitude less (ca. -0.25 J/cm(3)) than obtained via Hess's cycle (dissolution of the components and of the blend) from calorimetric measurements. Model calculations on the basis of the present theory demonstrate that the critical points shift to a different extent upon a certain relative change in the molar mass of the blend components. The sensitivity of the calculated phase diagrams against changes in the scaling parameter decreases in the following order: interaction energies between unlike mers, differences in the scaling temperatures, pressures and densities.

A hybrid coupled ocean-atmosphere model and ENSO prediction study

A hybrid coupled ocean-atmosphere model is designed, which consists of a global AGCM and a simple anomaly ocean model in the tropical Pacific. Retroactive experimental predictions initiated in each season from 1979 to 1994 are performed. Analyses indicate that: (1) The overall predictive capability of this model for SSTA over the central-eastern tropical Pacific can reach one year, and the error is not larger than 0.8 degrees C. (2) The prediction skill depends greatly on the season when forecasts start. However, the phenomenon of SPB (spring prediction barrier) is not found in the model. (3) The ensemble forecast method can effectively improve prediction results. A new initialization scheme is discussed.

A new empirical model for retrieving sea surface salinity in L band

Sea surface salinity is a key physical parameter in ocean science. It is important in the ocean remote sensing to retrieve sea surface salinity by the microwave probe technology. Based on the in situ measurement data and remote sensing data of the Yellow Sea, we have built a new empirical model in this paper, which can be used to retrieve sea surface salinity of the Yellow Sea by means of the brightness temperature of the sea water at L-band. In this model, the influence of the roughness of the sea surface is considered, and the retrieved result is in good agreement with the in situ measurement data, where the mean absolute error of the retrieved sea surface salinity is about 0.288 psu. This result shows that our model has greater retrieval precision compared with similar models.

Robust 2-D Model-Based Object Recognition

Techniques, suitable for parallel implementation, for robust 2D model-based object recognition in the presence of sensor error are studied. Models and scene data are represented as local geometric features and robust hypothesis of feature matchings and transformations is considered. Bounds on the error in the image feature geometry are assumed constraining possible matchings and transformations. Transformation sampling is introduced as a simple, robust, polynomial-time, and highly parallel method of searching the space of transformations to hypothesize feature matchings. Key to the approach is that error in image feature measurement is explicitly accounted for. A Connection Machine implementation and experiments on real images are presented.

Error Detection and Recovery for Robot Motion Planning with Uncertainty

Robots must plan and execute tasks in the presence of uncertainty. Uncertainty arises from sensing errors, control errors, and uncertainty in the geometry of the environment. The last, which is called model error, has received little previous attention. We present a framework for computing motion strategies that are guaranteed to succeed in the presence of all three kinds of uncertainty. The motion strategies comprise sensor-based gross motions, compliant motions, and simple pushing motions.