Pronunciation modeling for ASR – knowledge-based and data-derived methods

This paper focuses on modeling pronunciation variation in two different ways: data-derived and knowledge-based. The knowledge-based approach consists of using phonological rules to generate variants. The data-derived approach consists of performing phone recognition, followed by smoothing using decision trees (D-trees) to alleviate some of the errors in the phone recognition. Using phonological rules led to a small improvement in WER; a data-derived approach in which the phone recognition was smoothed using D-trees prior to lexicon generation led to larger improvements compared to the baseline. The lexicon was employed in two different recognition systems: a hybrid HMM/ANN system and a HMM-based system, to ascertain whether pronunciation variation was truly being modeled. This proved to be the case as no significant differences were found between the results obtained with the two systems. A comparison between the knowledge-based and data-derived methods showed that 17% of variants generated by the phonological rules were also found using phone recognition, and this increases to 46% when the phone recognition output is smoothed by using D-trees.     

Uncertainty and imprecision modeling for the mobile robot localization problem

This article deals with uncertainty and imprecision treatment during the mobile robot localization process. The imprecision determination is based on the use of the interval formalism. Indeed, the mobile robot is equipped with an exteroceptive sensor and odometers. The imprecise data given by these two sensors are fused by constraint propagation on intervals. At the end of the algorithm, we get 3D localization subpaving which is supposed to contain the robot’s position in a guaranteed way. Concerning the uncertainty, it is managed through a propagation architecture based on the use of the Transferable Belief Model of Smets. This architecture enables to propagate uncertainty from low level data (sensor data) in order to quantify the global uncertainty of the robot localization estimation.

Large language models as an “operating” system for software and systems modeling

Software and Systems Modeling -     

A subject-specific software solution for the modeling and the visualization of muscles deformations

Today, to create and to simulate a virtual anatomical version of a subject is useful in the decision process of surgical treatments. The muscular activity is one of the factors which can contribute to abnormal movements such as in spasticity or static contracture. In this paper, we propose a numerical solution, based on the Finite Element (FE) method, able to estimate muscles deformations during contraction. Organized around a finite element solver and a volumetric environment, this solution is made of all the modeling and simulation processes from the discretization of the studied domain to the visualization of the results. The choices of materials and properties of the FE model are also presented such as the hyperelasticity, the contention model based on inter-meshes neighboring nodes pairing, and the estimation of nodal forces based on the subject-specific muscular forces and action lines.

A mathematical modeling framework for software reliability testing†

Software reliability testing refers to various software testing activities that are driven to achieve a quantitative reliability goal given a priori or lead to a quantitative reliability assessment for the software under test. In this paper we develop a modeling framework for the software reliability testing process, comprising a simplifying model and a generalized model. In both models the software testing action selection process and the defect removal mechanism are explicitly described. Both the discrete-time domain and the continuous-time domain are involved. The generalized model is more accurate or realistic than the simplifying model since the former avoids the assumption that defects are equally detectable and the assumption that defects are removed upon being detected. However simulation examples show that the simplifying model really captures some of essential features of the software testing process after a short initial testing stage. The modeling framework is practically realistic, mathematically rigorous, and quantitatively precise. It demonstrates that the relationship between software testing and delivered software reliability, which was poor understood, can well be formulated and quantified. Rigorous examinations show that several common assumptions adopted in software reliability modeling, including the independence assumption, the exponentiality assumption, and the NHPP assumption, are theoretically false in general. This paper sets a good starting point to further formalize and quantify the software testing process and its relation to delivered software reliability.     

A critical review on idealization and modeling for interaction among soil–foundation–structure system

The interaction among structures, their foundations and the soil medium below the foundations alter the actual behaviour of the structure considerably than what is obtained from the consideration of the structure alone. Thus, a reasonably accurate model for the soil–foundation–structure interaction system with computational validity, efficiency and accuracy is needed in improved design of important structures. The present study makes an attempt to gather the possible alternative models available in the literature for this purpose. Emphasis has been given on the physical modeling of the soil media, since it appears that the modeling of the structure is rather straightforward. The strengths and limitations of the models described in a single paper may be of help to the civil engineers to choose a suitable one for their study and design.     

TAGUS — A user and learner modeling workbench

In this paper we will describe, outline and exemplify the functionalities and architecture of a User and Learner Modeling System called TAGUS (within the project Theory and Applications for General User/Learner-modeling Systems).TAGUS was developed with two main goals: (1) to develop a framework to represent models of users and learners where the meta-cognitive activities of learners were taken into account; and (2) to try to capture in a system some general mechanisms and techniques for user and learner modeling in the form of services.The basic idea of TAGUS is to achieve a kind of workbench where some techniques and approaches for user and learner modeling are implemented and applied. TAGUS provides a set of services, to be used by people testing methods or by applications using user models. These services, provided to external agents, embed some mechanisms for maintaining models of the users and learners. Thus, TAGUS plays a role of a user and learner modeling server.To achieve this goal, we first identified some basic mechanisms in user and learner modeling, and based on them we established a general modeling cycle. This cycle involves two main stages: the acquisition and the maintenance of the model. The different strategies and techniques are specified in separate modules or knowledge sources in TAGUS, which uses them to execute parts of that cycle. The architecture of TAGUS is composed of: a User or Learner Model (ULM); a set of maintenance functions; an acquisition engine; a reason maintenance system; a meta-reasoner and two interfaces.At the same time, TAGUS provides a language for defining the models of the users and learners, which can be used with different techniques, in order to test the models and simulate them in the system. This language is used not only to represent the models, but also as a way of establishing the communication between TAGUS and its environment.TAGUS was built incrementally around a set of core functions for the manipulation of the User or Learner Model (ULM). Other layers of this set were built where the last layer corresponds to the services TAGUS supplies.     

New efficient method for dynamic modeling and simulation of flexible multibody systems moving in plane

Efficient, precise dynamic analysis for general flexible multibody systems has become a research focus in the field of flexible multibody dynamics. In this paper, the finite element method and component mode synthesis are introduced to describe the deformations of the flexible components, and the dynamic equations of flexible bodies moving in plane are deduced. By combining the discrete time transfer matrix method of multibody system with these dynamic equations of flexible component, the transfer equations and transfer matrices of flexible bodies moving in plane are developed. Finally, a high-efficient dynamic modeling method and its algorithm are presented for high-speed computation of general flexible multibody dynamics. Compared with the ordinary dynamics methods, the proposed method combines the strengths of the transfer matrix method and finite element method. It does not need the global dynamic equations of system and has the low order of system matrix and high computational efficiency. This method can be applied to solve the dynamics problems of flexible multibody systems containing irregularly shaped flexible components. It has advantages for dynamic design of complex flexible multibody systems. Formulations as well as a numerical example of a multi-rigid-flexible-body system containing irregularly shaped flexible components are given to validate the method.     

The knowledge modeling system of ready-mixed concrete enterprise and artificial intelligence with ANN-GA for manufacturing production

Based on the characteristics of ready-mixed concrete enterprises, this paper puts forward that knowledge management (KM) is an effective way to contribute to enterprise production and operation. The knowledge content and relevant models of concrete enterprises are proposed, including advanced enterprise management, decision support for production operation, production and operation cost, and marketing-customer relationship. Afterwards knowledge contents are divided into static, strategic and reasoning knowledge. Besides knowledge unified expression is put forward accordingly. In addition, the KM system for process ready-mixed concrete enterprises management is established to facilitate effective production processing. As part of exploratory study, artificial neural network coupled with genetic algorithm (ANN-GA) as knowledge mining technology is applied in KM system to predict the 28-day compressive strength in concrete enterprises. The results shows that compared to back-propagation artificial neural network, the convergence rate of ANN-GA algorithm has been significantly improved and almost all the relative errors of predicted compressive strength of concrete C30 are within 3 %. It not only confirms the validity of the models, but also proves that ANN-GA algorithm is an effective knowledge mining method applied in concrete industry.     

A characteristic modeling method of error-free compression for nonlinear systems

The existence of error when compressing nonlinear functions into the coefficients of the characteristic model is known to be a key issue in existing characteristic modeling approaches, which is solved in this work by an error-free compression method. We first define a key concept of relevant states with corresponding compressing methods into their coefficients, where the coefficients are continuous and bounded and the compression is error-free. Then, we give the conditions for decoupling characteristic modeling for MIMO systems, and sequentially, we establish characteristic models for nonlinear systems with minimum phase and relative order two as well as the flexible spacecrafts, realizing the equivalence in the characteristic model theory. Finally, we explicitly explain the reasons for normalization in the characteristic model theory.     

A hierarchical fuzzy system for modeling driver’s behavior

The study of human behavior during driving is of primary importance for improving the driver??s security. In this study, we propose a hierarchical driver_vehicle_environment fuzzy system to analyze driver??s behavior under stress conditions on a road. We include climate, road and car conditions in fuzzy modeling. For obtaining fuzzy rules, experts?? opinions are benefited by means of questionnaires on effects of parameters such as climate, road and car conditions on driving capabilities. The number of fuzzy rules is optimized by Particle Swarm Optimization (PSO) algorithm. Also the frequency of pressing on brake and gas pedals and the number of car??s direction changes are used to determine the driver??s behavior under different conditions. Three different positions are considered for driving and decision making; one position in driving lane and two positions in opposite lane. A fuzzy model called Model 1 is presented for modeling the change of steering angle and speed control by considering time distances with existing cars in these three positions, the information about the speed and direction of car, and the steering angle of car. The behaviors of different drivers under two stress conditions are investigated. Also we obtained two other models based on fuzzy rules called Model 2 and Model 3 by using Sugeno fuzzy inference. Model 2 has two linguistic terms and Model 3 has four linguistic terms for estimating the time distances with other cars. The results of three models are compared. The comparative studies have shown that simulation results are in good agreement with the real world situations.     

Stochastic modeling and analysis of road–tramway intersections

In the last decades, the socio-demographic evolution of the population has substantially changed mobility demand, posing new challenges in minimizing urban congestion and reducing environmental impact. In this scenario, understanding how different modes of transport can efficiently share (partially or totally) a common infrastructure is crucial for urban development. To this aim, we present a stochastic model-based analysis of critical intersections shared by tram traffic and private traffic, combining a microscopic model of the former with a macroscopic model of the latter. Advanced simulation tools are typically used for such kind of analyses, by playing various traffic scenarios. However, simulation is not an exhaustive approach, and some critical, possibly rare, event may be ignored. For this reason, our aim is instead to adopt suitable analytical solution techniques and tools that can support instead a complete, exhaustive analysis, so being able to take into account rare events as well. Transient analysis of the overall traffic model using the method of stochastic state classes is adopted to support the evaluation of relevant performance measures, namely the probability of traffic congestion over time and the average number of private vehicles in the queue over time. A sensitivity analysis is performed with respect to multiple parameters, notably including the arrival rate of private vehicles, the frequency of tram rides, and the time needed to recover from traffic congestion.

     

Application experience of component modeling in Transas Group’S training system development for cargo-ballast and technological operations

The paper examines the experience of mathematical model development for the Tech- Sim/LCHS 5000 Series training systems from Transas Group (Russia). It overviews the subject area and the problems solved during the training simulator development. The applicationspecific requirements to model fidelity and software implementation are analyzed. The objectoriented approach applied, its implementation using Rand Model Designer, and the features of standard component library are described. The actions required to enable the operation of the models developed in real-time simulation are discussed.     

Three-stage performance modeling using DEA–BPNN for better practice benchmarking

This paper proposes an innovative three-stage model using data envelopment analysis (DEA) and backpropagation neural network (BPNN) for supporting ‘better practice’ benchmarking as contrasted with the traditional ‘best practice’ benchmarking. Research has shown that DEA models have the capability of setting optimal goals, but the drawback of the standard DEA approach is its inability to propose actionable targets necessary for incremental improvement. Overcoming the shortfalls of DEA and its superiority-driven practices, the neural network approach accommodates stepwise improvement through adaptive learning and prediction capability. Consequently, the proposed three-stage model is capable of generating feasible improvement options for managers as an intelligent decision support tool. At its core, the innovative approach provides a sound methodological foundation for shaping a ‘better practice’ paradigm and contributes to the literature through methodological advancement. The effectiveness of the model is empirically tested through the use of data from the healthcare industry, and the results confirm a practical utility of the model.     

Dempster–Shafer structure based fuzzy logic system for stochastic modeling

The Dempster–Shafer (D–S) theory of evidence is introduced to improve fuzzy inference under the complex stochastic environment. The Dempster–Shafer based fuzzy set (DFS) is first proposed, together with its union and intersection operations, to capture the principal stochastic uncertainties. Then, the fuzzy inference will be modified based on the extensional Dempster rule of combination. This new approach is able to capture the stochastic disturbance acting on fuzzy membership function, and provide a more effective inference under strong stochastic uncertainty. Finally, the numerical simulation and the experimental prediction of the wind speed are conducted to show the potential of the proposed method in stochastic modeling.     

Syllable modeling in continuous speech recognition for Tamil language

In automatic speech recognition, the phone has probably been a dominating sub-word unit for more than one decade. Context Dependent phone or triphone modeling accounts for contextual variations between adjacent phones and state tying addresses modeling of triphones that are not seen during training. Recently, syllable is gaining momentum as a new sub-word unit. Syllable being a larger unit than a phone addresses the severe contextual variations between phones within it. Therefore, it is more stable than a phone and models pronunciation variability in a systematic way. Tamil language has challenging features like agglutination and morpho-phonology. In this paper, attempts have been made to provide solutions to these issues by using the syllable as a sub-word unit in an acoustic model. Initially, a small vocabulary context independent word models and a medium vocabulary context dependent phone models are developed. Subsequently, an algorithm based on prosodic syllable is proposed and two experiments have been conducted. First, syllable based context independent models have been trained and tested. Despite large number of syllables, this system has performed reasonably well compared to context independent word models in terms of word error rate and out of vocabulary words. Subsequently, in the second experiment, syllable information is integrated in conventional triphone modeling wherein cross-syllable triphones are replaced with monophones and the number of context dependent phone models is reduced by 22.76% in untied units. In spite of reduction in the number of models, the accuracy of the proposed system is comparable to that of the baseline triphone system.     

Tolerance analysis — Form defects modeling and simulation by modal decomposition and optimization

Tolerance analysis aims on checking whether specified tolerances enable functional and assembly requirements. The tolerance analysis approaches discussed in literature are generally assumed without the consideration of parts’ form defects. This paper presents a new model to consider the form defects in an assembly simulation. A Metric Modal Decomposition (MMD) method is henceforth, developed to model the form defects of various parts in a mechanism. The assemblies including form defects are further assessed using mathematical optimization. The optimization involves two models of surfaces: real model and difference surface-base method, and introduces the concept of signed distance. The optimization algorithms are then compared in terms of time consumption and accuracy. To illustrate the methods and their respective applications, a simplified over-constrained industrial mechanism in three dimensions is also used as a case study.     

Key characterization factors of accurate power modeling for Fin FET circuits

Due to its excellent device features, manufacture process compatibility and diversity of the circuit structures, The Fin FET is considered appropriate candidate for the conventional bulk-MOSFET in sub-22 nm technology nodes. However, the power estimation CAD tools for Fin FET are missing at the moment, which mainly results from the absence of Fin FET power analysis and Fin FET power model. Three key factors for Fin FET power model are: the dimension of the look-up-tables, that to find out the most significant factors that influence Fin FET power and to make them as indexes for the look-up-tables; the distance between sampling points; and the interpolation method. In this paper, various factors that may contribute to the Fin FET power consumption are evaluated. Of all the factors, the continuous ones are compared with sensitivity method. As to other discrete factors, methods of building them in power model are given according to the features of the each factor and the way it influences the power. Based on the simulation result, standard cell power library model for Fin FET is proposed. The research work lays foundation for accurate power analysis and modeling for high-level power analysis of Fin FET circuits. Besides, these key factors are also crucial for low-power Fin FET circuit design.