1,255,316 Hits in 8.8 sec

On Local LTI Model Coherence for LPV Interpolation

Qinghua Zhang, Lennart Ljung, Rik M. Pintelon
2019 IEEE Transactions on Automatic Control  
In the local approach to linear parameter varying (LPV) system identification, it is widely acknowledged that locally estimated linear state-space models should be made coherent before being interpolated  ...  The purpose of this paper is to analyze the relevance of two existing definitions and to point out the consequence of this analysis on the practice of LPV system identification.  ...  As the true multi-snapshot Σ * is unknown, the practical interpolation has to be based on the estimated model setΣ.  ... 
doi:10.1109/tac.2019.2948898 fatcat:rahgs2glfbgtncondmo2ko5tjq

From structurally independent local LTI models to LPV model

Qinghua Zhang, Lennart Ljung
2017 Automatica  
The local approach to linear parameter varying (LPV) system identification consists in interpolating individually estimated local linear time invariant (LTI) models corresponding to fixed values of the  ...  It is shown in this paper that, without any global structural assumption of the considered LPV system, individually estimated local state-space LTI models do not contain sufficient information for determining  ...  Coherent LTI models based on canonical forms In order to make local LTI models coherent, a natural idea is to find similarity transformations of the local LTI models leading to some LTI canonical state-space  ... 
doi:10.1016/j.automatica.2017.06.006 fatcat:bsfb5owkebdordc7onrdr2wg3e

Definition and validation of model transformations

Jochen M. Küster
2006 Journal of Software and Systems Modeling  
Like any piece of software, model transformations must be validated to ensure their usefulness for the intended application.  ...  This paper introduces the idea of systematic validation and then focusses on validation of syntactic correctness for rule-based model transformations.  ...  Acknowledgements: The author thanks Jana Koehler, Rainer Hauser and Shane Sendall for their advice and Reiko Heckel for discussions related to the topic of this paper.  ... 
doi:10.1007/s10270-006-0018-8 fatcat:ttunffturfestfodfv32pmw4ee

A Model-Checking Approach for Fault Analysis Based on Configurable Model Extraction

Hideto OGAWA, Makoto ICHII, Tomoyuki MYOJIN, Masaki CHIKAHISA, Yuichiro NAKAGAWA
2015 IEICE transactions on information and systems  
It was applied to an industrial software system to evaluate the efficiency of the configurable model extraction by POM for fault analysis.  ...  A practical model-checking (MC) approach for fault analysis, that is one of the most cost-effective tasks in software development, is proposed.  ...  Constructing a behavioral model of the target system has been an issue in regard to using MC in practice.  ... 
doi:10.1587/transinf.2014fop0012 fatcat:lbcx5oyfbvhgvgh5i7yvamnlgq

Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk) [article]

Steve Young
2013 arXiv   pre-print
The paper therefore concludes with a brief review of some of the more fundamental modelling work now in progress.  ...  This paper reviews the evolution of the statistical modelling techniques which underlie current-day systems, specifically hidden Markov models (HMMs) and N-grams.  ...  (YIMw)P(W) (13) w where Mrec encodes the full acoustic and language model used in recognition.9typically 10 to 32 Gaussians per state, and typically 5000 to 10000 states in a system This objective function  ... 
arXiv:1301.2318v1 fatcat:svxwkn5275eyfexigfh5k6itcq

Using Semantic Anchoring to Verify Behavior Preservation in Graph Transformations

Anantha Narayanan, Gabor Karsai
2007 Electronic Communications of the EASST  
For instance, it could be necessary to transform iLogix Statechart models into Matlab Stateflow models. The preservation of behavior of the models is crucial in such transformations.  ...  Graph transformation is often used to transform domain models from one domain specific language (DSML) to another.  ...  Acknowledgements: This material is based upon work supported by the National Science Foundation under Grant No. 0509098.  ... 
doi:10.14279/tuj.eceasst.4.22 dblp:journals/eceasst/NarayananK06 fatcat:mux7odkylrg4hiqv6tdw3g3o6y

On the Complexity of Parameter Calibration in Simulation Models

Marko Hofmann, David C. Gross
2005 The Journal of Defence Modeling and Simulation: Applications, Methodology, Technology  
Model calibration is the task of adjusting an already existing model to a reference system. In general, this is done by adjusting model parameters to a set of given samples from the reference system.  ...  X = , , ; M i X = Domain for each variable. ( ) M M P ϕ : Model transformation function  ...  In contrast to the model transformation function M ϕ the system transformation function S ϕ is, in general, not known. Definition 3.  ... 
doi:10.1177/154851290500200405 fatcat:ycpb7rfdc5fudlqsnsdcx4s2ge

The Application of Hidden Markov Models in Speech Recognition

Mark Gales, Steve Young
2007 Foundations and Trends® in Signal Processing  
The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then describe the various refinements which are needed to achieve state-of-the-art performance.  ...  Thus, the practical application of HMMs in modern systems involves considerable sophistication.  ...  Acknowledgments The authors would like to thank all research students and staff, past and present, who have contributed to the development of the HTK toolkit and HTK-derived speech recognition systems  ... 
doi:10.1561/2000000004 fatcat:mlbg7zun3nhntes4ev33zfeobi

Research and Design of Laser Scribing Robot Based on Surface Matching

Zhi Gang Xu, Chun Shu Xu, Le Ha, Rui Hu Zhou
2012 Applied Mechanics and Materials  
The date model can be generated by computer. The matching method is based on curvature and arc length of feature points.  ...  It can make the scribing path closest to the ideal track and has extensive utility value.  ...  According to constraint conditions, the data model matches with the ideal model by rotation and translation. The initial state is shown in Fig.7a .  ... 
doi:10.4028/ fatcat:qjabieqoevfwtmzirj72qpk774

Some Improvements on Deep Convolutional Neural Network Based Image Classification [article]

Andrew G. Howard
2013 arXiv   pre-print
The techiques include adding more image transformations to training data, adding more transformations to generate additional predictions at test time and using complementary models applied to higher resolution  ...  We investigate multiple techniques to improve upon the current state of the art deep convolutional neural network based image classification pipeline.  ...  When scaling down, anti aliasing seems to help a little bit but in practice we used bicubic scaling for up scaling and down scaling. .2 P re d i c t i o n s w i t h M u l t i p l e Vi e w s In order  ... 
arXiv:1312.5402v1 fatcat:rkq27xddevbazikkosgjwjeevm

Graph Modelling and Transformation: Theory meets Practice

Claudia Ermel, Karsten Ehrig
2010 Electronic Communications of the EASST  
In this paper, we focus on the role of graphs and graph transformation for four practical application areas from software system development.  ...  We present the typical problems in these areas and investigate how the respective systems are modelled by graphs and graph transformation.  ...  But to be useful in the context of larger systems, these principles should be integrated in tools that are used in practical applications.  ... 
doi:10.14279/tuj.eceasst.30.423 dblp:journals/eceasst/ErmelE10 fatcat:p6rbt7tiojf7hcq6qraul4dywe

Embedding of Nonlinear Systems in a Linear Parameter-Varying Representation

Hossam S. Abbas, Roland Tóth, Mihály Petreczky, Nader Meskin, Javad Mohammadpour
2014 IFAC Proceedings Volumes  
Based on the relative degree concept of NL systems, the states of a given NL representation are transformed to new coordinates that provide its normal form.  ...  In addition, if the states of the NL model can be measured or estimated, then the procedure can be modified to provide LPV models scheduled by these states. Examples are included for illustration.  ...  Existing approaches for the LPV modeling of NL dynamical systems can be classified into three main categories: linearization-based (including multiple-model design), state-transformation & function substitution-based  ... 
doi:10.3182/20140824-6-za-1003.02506 fatcat:zgfaqn4nbfgbvdvk6xghlj24lu

Polytopic model based interaction control for soft tissue manipulation

Arpad Takacs, Jozsef Kuti, Tamas Haidegger, Peter Galambos, Imre J. Rudas
2016 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)  
The performance of these systems in terms of safety and stability largely depends on the controller design, as it is desired to account for various disturbing conditions, such as uncertainties of the model  ...  Index Terms-Soft tissue modeling, telesurgery control, Polytopic model based control, TP Model Transformation, qLPV modeling, LMI-based controller design  ...  Definition 4: (TP Model Transformation): TP Model Transformation is a numerical method that transforms the LPV/qLPV models to polytopic TP model, so that the LMI methods developed for polytopic model based  ... 
doi:10.1109/smc.2016.7844843 dblp:conf/smc/TakacsKHGR16 fatcat:mcg3vus45ncrjlv5hjpmolzpue

Migrating supervisory control architectures using model transformations

B. Graaf, S. Weber, A. van Deursen
2006 Conference on Software Maintenance and Reengineering (CSMR'06)  
This migration, from a paradigm based on finite-state machines to a paradigm based on task-resource systems, is described in terms of model transformations.  ...  We propose a generic migration approach that involves normalising a legacy architecture that, in turn, is transformed.  ...  We would like to thank the Ideals team and ASML, in particular Remco van Engelen, Ed de Gast, Koen van der Heijden, Barend van den Nieuwelaar, Joost Worms and Asia van de Mortel-Fronczak for their input  ... 
doi:10.1109/csmr.2006.35 dblp:conf/csmr/GraafWD06 fatcat:ofpkmk3yo5b27nq37e6ofvyjne

HMMs and Related Speech Recognition Technologies [chapter]

Steve Young
2008 Springer Handbook of Speech Processing  
Almost all present day continuous speech recognition (CSR) systems are based on Hidden Markov Models (HMMs).  ...  The aim of this chapter is to review the core architecture of a HMM-based CSR system and then outline the major areas of refinement incorporated into modernday systems.  ...  ML-based Linear Transforms An alternative approach to adaptation is to build a set of linear transforms to map an existing model set into a new adapted model set such that the likelihood of the adaptation  ... 
doi:10.1007/978-3-540-49127-9_27 fatcat:nfsf7symrreeno6qylvckoqc3i
« Previous Showing results 1 — 15 out of 1,255,316 results