Model Adaptation Techniques Research Articles

Multi-Objective Optimization of a Permanent Magnet Actuator for High Voltage Vacuum Circuit Breaker Based on Adaptive Surrogate Modeling Technique

A novel mono-stable permanent magnet actuator (PMA) for high voltage vacuum circuit breaker (VCB) and its optimal design method are proposed in this paper. The proposed PMA is featured with a structure of separated magnetic circuits, which makes the holding part and closing driving part work independently without interference. The application of an auxiliary breaking coil decreases the response time in the initial phase of opening operation, and an external disc spring is adopted to accelerate the opening movement, which makes the PMA meet the fast-breaking requirement of high voltage VCB. As calculating the characteristics of the PMA accurately through numerical simulation is a time-consuming process, a multi-objective optimization (MOO) algorithm based on surrogate modeling technique and adaptive samples adding strategy are proposed to reduce the workload of numerical simulations during optimization. Firstly, initial surrogate models are constructed and evaluated, and then iteratively updated to improve their global approximating abilities. Secondly, according to the approximate MOO results obtained by the global surrogate models, additional samples are added to constantly update the surrogate models to gradually improve the models’ local accuracies in optimal solution regions and finally guide the algorithm to the true Pareto front. The efficiency and accuracy of the proposed algorithm are verified by test functions. By applying the optimization strategy to the design of the proposed PMA, a set of satisfying Pareto optimal solutions, which improve the overall performance of the PMA obviously, can be derived at a reasonable computation cost.

Distributed optimization for a class of uncertain MIMO nonlinear multi-agent systems with arbitrary relative degree

The paper is concerned with the distributed optimization problem (DOP) for a class of uncertain multi-input-multi-output (MIMO) nonlinear multi-agent systems with arbitrary relative degree. The target is to design distributed control laws such that the outputs of the agent systems converge to a consensus value and on which the sum of the local cost functions is minimized. By introducing pseudo gradient technique, internal model technique and adaptive control technique, a novel state based distributed control law is firstly constructed. An incremental type Lyapunov function based approach is presented to show that the proposed DOP is solved by the state based control law without requiring the eigenvalue information of Laplacian matrix. By further introducing distributed high-gain observer technique, an output based distributed control law is constructed and by which the DOP is solved under some mild assumption. The proposed control laws are validated on a group of Euler-Lagrange systems, a group of robot manipulators with flexible joints and a group of Chua circuit systems. The simulation results illustrate the effectiveness of the proposed methods.

Rendezvous problem of multiple linear uncertain systems under state-dependent dynamic networks

This paper studies the rendezvous problem for a class of linear systems with uncertain parameters and external disturbances under the state-dependent dynamic network, which is also called rendezvous network here. By combining potential function technique, distributed internal model design and adaptive control technique, a distributed adaptive state feedback control law is proposed to solve the rendezvous problem by completing the tasks of maintaining the connectivity of the rendezvous network, achieving asymptotic tracking, rejecting unknown external disturbances as well as handling uncertain parameters in the system dynamics, the leader system and the exosystem simultaneously.

Individualised modelling of affective data for intelligent tutoring systems: lessons learned

One on one tutoring from human expert tutors to human students is the most effective form of instruction found to date. There are many actions that human tutors perform which make them remarkably effective, including the attention that they pay to the cognitive and affective states of the human students that they tutor, and the use of this knowledge to modify the way that they instruct the material. According to theoretical models, learner state data is used to inform instructional data and decisions, which then influences the learning of the student. Naturally, the data about student state must be available in order to be used to adjust the instruction. Success amongst operational systems, however, has not been observed with generalised modelling techniques. Individualised and adaptive modelling techniques from other domains in the literature present an alternative to the approach which is not observing significant operational success. This work investigates individualised adaptive models, validates the approach, and shows that it can produce models of acceptable quality, but that doing so does not obviate the experimenter from creating quality generalised models prior to individualising.

Adaptive background modelling technique for moving object detection in video under dynamic environment

Adaptive background modelling technique for moving object detection in video under dynamic environment

Adaptive background modelling technique for moving object detection in video under dynamic environment

This work proposes a novel method for detection of motion based object having dynamic scenario in the background. The suggested scheme has a strong potential for real-time applications especially for rafting, river, sea-beach, swimming pools, ponds, etc. Apart from these, this work is very beneficial for surveillance of border, tunnel, traffic in the sea, forest, restricted zones, deep zones, etc. This work develops a statistical p based background subtraction method and implemented in three stages. In the first stage, a background model is developed using few initial frames. In the second stage, this work classifies the foreground using the difference frame and the appropriate threshold value. An automatic threshold value is generated at run-time and updated iteratively. It also reduces the problem of using a constant threshold. In the third stage, morphological filters and connected component based region filtering technique is applied to enhance the detection quality. The extensive experimental result shows more accurate results of proposed method. It also demonstrates better performance against considered state-of-the-art methods.

Data Categorization and Model Weighting Approach for Language Model Adaptation in Statistical Machine Translation

Language model encapsulates semantic, syntactic and pragmatic information about specific task. Intelligent systems especially natural language processing systems can show different results in terms of performance and precision when moving among genres and domains. Therefore researchers have explored different language model adaptation strategies in order to overcome effectiveness issue. There are two main categories in language model adaptation techniques. The first category includes the techniques that based on the data selection where task-oriented corpus can be extracted and used to train and generate models for specific translations. While the second category focuses on developing a weighting criterion to assign the test data to specific model corpus. The purpose of this research is to introduce language model adaptation approach that combines both categories (data selection and weighting criterion) of language model adaptation. This approach applies data selection for specific-task translations by dividing the corpus into smaller and topic-related corpora using clustering process. We investigate the effect of different approaches for clustering the bilingual data on the language model adaptation process in terms of translation quality using the Europarl corpus WMT07 that includes bilingual data for English-Spanish, English-German and English-French. A mixture of language models should assign any given data to the right language model to be used in the translation process using a specific weighting criterion. The proposed language model adaptation has achieved better translation quality compare to the baseline model in Statistical Machine Translation (SMT).

Application of ANN modeling techniques in the prediction of the diameter of PCL/gelatin nanofibers in environmental and medical studies.

Prediction of the diameter of a nanofiber is very difficult, owing to complexity of the interactions of the parameters which have an impact on the diameter and the fact that there is no comprehensive method to predict the diameter of a nanofiber. Therefore, the aim of this study was to compare the multi-layer perceptron (MLP), radial basis function (RBF), and support vector machine (SVM) models to develop mathematical models for the diameter prediction of poly(ε-caprolactone) (PCL)/gelatin (Gt) nanofibers. Four parameters, namely, the weight ratio, applied voltage, injection rate, and distance, were considered as input data. Then, a prediction of the diameter for the nanofiber model (PDNFM) was developed using data mining techniques such as MLP, RBFNN, and SVM. The PDNFMMLP is introduced as the most accurate model to predict the diameter of PCL/Gt nanofibers on the basis of costs and time-saving. According to the results of the sensitivity analysis, the value of the PCL/Gt weight ratio is the most significant input which influences PDNFMMLP in PCL/Gt electrospinning. Therefore, the PDNFM model, using a decision support system (DSS) tool can easily predict the diameter of PCL/Gt nanofibers prior to electrospinning.

Optimization of Fiber Orientation Model Parameters in the Presence of Flow-Fiber Coupling

In this paper, we propose a novel systematic procedure to minimize the discrepancy between the numerically predicted and the experimentally measured fiber orientation results on an injection-molded part. Fiber orientation model parameters are optimized simultaneously using Latin hypercube sampling and kriging-based adaptive surrogate modeling techniques. Via an adequate discrepancy measure, the optimized solution possesses correct skin–shell–core structure and global orientation evolution throughout the considered center-gated disk. Some non-trivial interaction between these parameters and flow-fiber coupling effects as well as their quantitative importance are illustrated. The parametric fine-tuning of orientation models mostly leads to a better agreement in the skin and shell regions, while the coupling effect via a fiber-dependent viscosity improves prediction in the core.

An adaptive modelling technique for parameters extraction of photovoltaic devices under varying sunlight and temperature conditions

The batteries used with standalone PV systems are very sensitive to the current-voltage charging. Thus, for choosing the right battery, a PV system designer needs to make an accurate estimate of the current and voltage outputs of the PV module under consideration. However, this task is challenging due to randomness in the field operating conditions. To achieve this goal, the PV module in this work has been represented by a well-known equivalent one-diode electrical circuit with five unknown PV parameters. Using multiple current-voltage curves at different operating conditions, the proposed methodology extracts the five unknown PV parameters against each current-voltage curve. Each PV parameter is then plotted independently, first against the varying sunlight and then against the varying temperature. Then introducing a novel concept of shift-factors, the proposed methodology couples the two independent plots of each PV parameter and helps predict the value of that PV parameter at any operating condition. Unlike other works from the literature, the variations of these five PV parameters by the proposed methodology have been shown to be in accordance with the PV device theory and the physical behavior of the PV devices. The proposed model has been validated against both the PV panel’s datasheet information and the experimental in-field data. With realistic values captured for each PV parameter by the proposed methodology, the validations show a significant increase in the prediction accuracy of the current-voltage output of the PV panel. It has also been shown how this methodology can be used to better understand the behavior of the PV system and aid in its preventive/corrective maintenance.

A fast and robust sub-optimal control approach using reduced order model adaptation techniques

Classical adjoint-based optimization approach for the optimal control of partial differential equations is known to require a large amount of CPU time and memory storage. In this article, in order to reduce these requirements, a posteriori and a priori model order reduction techniques such as POD (Proper Orthogonal Decomposition) and PGD (Proper Generalized Decomposition) are used. As a matter of fact, these techniques allows a fast access to the temporal dynamics of a solution approximated in a suitable subspace of low dimension, spanned by a set of basis functions that form a reduced basis. The costly high fidelity model is then projected onto this basis and results in a system of ordinary differential equations which can be solved in quasi-real time. A disadvantage of considering a fixed POD basis in a suboptimal control loop, is basically the dependence of such bases on a posteriori information coming from high fidelity simulations. Therefore, a non robustness of the POD basis can be expected for certain perturbations in the original parameter for which it was built. As a result, update the reduced bases with respect to each variation in the control parameter using the POD method is still costly. To get over this difficulty, we equip the usual reduced optimal control algorithm with an intermediate basis adaptation step. The first proposed approach consists in adapting the reduced basis for a new control parameter by interpolating over a set of POD bases previously computed for a range of control parameters. To achieve that, an interpolation technique based on properties of the tangent subspace of the Grassmann manifold (ITSGM) is considered. The second approach is the PGD method, which by nature, enrich a space time decomposition trying to enhance the approximation by learning from its own errors. Relaying on this property, this method is employed in the control loop as a basis corrector, in such a way the given spatial basis is adapted for the new control parameter by performing just few enrichments. These two approaches are applied in the sub-control of the two dimensional non-linear reaction-diffusion equations and Burgers equations.

Understanding Prediabetes in a Medicare Advantage Population Using Data Adaptive Techniques.

The objective was to identify individuals with undiagnosed prediabetes from administrative data using adaptive techniques. The data source was a national Medicare Advantage Prescription Drug (MAPD) plan administrative data set. A retrospective, cross-sectional study developed and evaluated data adaptive logistic regression, decision tree, neural network, and ensemble predictive models for metabolic syndrome and prediabetes using 3 mutually exclusive cohorts (N = 279,903). The misclassification rate (MCR), average squared error (ASE), c-statistics, sensitivity (SN), and false positive (FP) rates were compared to select the final predictive models. MAPD individuals with continuous enrollment from 2013 to 2014 were included. Metabolic syndrome and prediabetes were defined using clinical guidelines, diagnosis, and laboratory data. A total of 512 variables identified through subject matter expertise in addition to utilizing all data available were evaluated for the modeling. The ensemble model demonstrated better discrimination (c-statistics, MCR, and ASE of 0.83, 0.24, and 0.16, respectively), high SN, and low FP rate in predicting metabolic syndrome than the individual data adaptive modeling techniques. Logistic regression demonstrated better discrimination (c-statistics, MCR, and ASE of 0.67, 0.13, and 0.11 respectively), high SN, and low FP rate in predicting prediabetes than the other adaptive modeling techniques or ensemble methods. The scored data predicted prediabetes in 44% of the MAPD population, which is comparable to 2005-2006 National Health and Nutrition Examination Survey prediabetes rates of 41%. The logistic regression model demonstrated good performance in predicting undiagnosed prediabetes in MAPD individuals.

IMC and Adaptive Associated with PID Controllers for Nonlinear Level Process

Level control in a specially shaped tanks is crucial in many industries like food manufacturing industries, petroleum industries and hydrometallurgical industries. The level of the tank can be controlled by controlling the head of the tank or by means of balancing the inflow rate and out flow rate. Different shapes of the tanks are utilised in the process industries according to the application. For high viscous fluids and complete drain is required the conical bottom tanks are prefered. But the nonlinearity due to the tapered bottom area of the tank makes the level control in the conical tank the toughest task. The conventional controllers will not gives a clear solution for this case. This work deals with development of a suitable controller for such process. The conventional three mode controller is designed and it is modified with the Internal Model Controller(IMC) and Adaptive PID controller techniques. The designed controllers are simulated using MATLAB/SIMULINK environment. From the simulation results it has been proved that the adaptive controlling techniques give good control performance than other controllers.

Unobtrusive detection of body movements during sleep using Wi-Fi received signal strength with model adaptation technique

Although sleep is essential to healthy living, many people have issues related to insufficient or poor quality sleep. In this study, we propose a method for unobtrusively detecting body movements during sleep by measuring changes in Wi-Fi signal strength between two Wi-Fi-enabled devices because prior research has found a correlation between sleep state and body movements such as rolling over. In our method, users place two Wi-Fi-enabled devices, on the left and right sides of their bed when sleeping. Our method then detects body movement by measuring changes in Wi-Fi signal strength between the two devices. By doing so, our method can detect motion without any sensors connected to the user, using devices that are equipped with commercially available Wi-Fi modules. The main feature of our method is its ability to train a user’s body movement detection model on other users’ training data. We employ a model adaptation technique called the maximum likelihood linear regression (MLLR) to adapt a user-independent movement detection model to the user of interest. In this study, we evaluated our method using 60 sessions of data collected from six participants, and achieved approximately 82% accuracy on average with user-independent movement detection models.

Speech recognition for under-resourced languages: Data sharing in hidden Markov model systems


 
 
 For purposes of automated speech recognition in under-resourced environments, techniques used to share acoustic data between closely related or similar languages become important. Donor languages with abundant resources can potentially be used to increase the recognition accuracy of speech systems developed in the resource poor target language. The assumption is that adding more data will increase the robustness of the statistical estimations captured by the acoustic models. In this study we investigated data sharing between Afrikaans and Flemish – an under-resourced and well-resourced language, respectively. Our approach was focused on the exploration of model adaptation and refinement techniques associated with hidden Markov model based speech recognition systems to improve the benefit of sharing data. Specifically, we focused on the use of currently available techniques, some possible combinations and the exact utilisation of the techniques during the acoustic model development process. Our findings show that simply using normal approaches to adaptation and refinement does not result in any benefits when adding Flemish data to the Afrikaans training pool. The only observed improvement was achieved when developing acoustic models on all available data but estimating model refinements and adaptations on the target data only.
 
 
 
 
 Significance: 
 
 
 
 Acoustic modelling for under-resourced languages
 Automatic speech recognition for Afrikaans
 Data sharing between Flemish and Afrikaans to improve acoustic modelling for Afrikaans
 
 
 

Process Identification with Autoregressive Linear Regression Method using Experimental Data: Review

Objective: To obtain mathematical model and parameters of poorly understood and imprecisely known plant/process. Methods: One solution to this problem is to obtain these using identification techniques. Process identification is a technique where a mathematical model of the process under study is build from process input-output data. Several autoregressive models are used to estimate the present value of the model using its past values of the process. Initially, the data set is generated for the given system and the auto regressive model is fitted to it, for the estimation of the model parameters. Residual error for a system is calculated using auto regression model parameters. Findings: A mathematical model for plant under study can be formulated with different system identification using Linear Regression methods like Auto Regressive eXogenous variable (ARX), Auto Regressive Moving Average with an eXogenous variable (ARMAX), Output Error (OE) and Box-Jenkins (BJ). For high model order ARX model is preferred and takes low computations but only suitable for white noise. The ARMAX model considers disturbance affecting process and provides higher performance index i.e. fitness which reveals percentage variation in output estimated by respective model. The Output-Error (OE) model estimates process model but cannot model disturbance features. The residual analysis of Box- Jenkins model shows that the prediction error is not auto-correlated, correlated and is uncorrelated with the input applied to process, thus showing Box- Jenkins model ability to capture noise dynamics of process. Applications/Improvements: The process model can be identified for the unknown, poorly known or partially known system and formulated model can be used in model Predictive controller design and Adaptive control techniques.

An adaptive stock index trading decision support system

Predicting the direction and movement of stock index prices is difficult, often leading to excessive trading, transaction costs, and missed opportunities. Often traders need a systematic method to not only spot trading opportunities, but to also provide a consistent approach, thereby minimizing trading errors and costs. While mechanical trading systems exist, they are usually designed for a specific stock, stock index, or other financial asset, and are often highly dependent on preselected inputs and model parameters that are expected to continue providing trading information well after the initial training or back-tested model development period. The following research leads to a detailed trading model that provides a more effective and intelligent way for recognizing trading signals and assisting investors with trading decisions by utilizing a system that adapts both the inputs and the prediction model based on the desired output. To illustrate the adaptive approach, multiple inputs and modeling techniques are utilized, including neural networks, particle swarm optimization, and denoising. Simulations with stock indexes illustrate how traders can generate higher returns using the developed adaptive decision support system model. The benefits of adding adaptive and intelligent decision making to forecasts are also discussed.

Heterogeneous Sensor Data Fusion Approach for Real-time Monitoring in Ultraprecision Machining (UPM) Process Using Non-Parametric Bayesian Clustering and Evidence Theory

The aim of this paper is to detect the incipient anomalies in a ultraprecision machining (UPM) process by integrating multiple in situ sensor signals. To realize this aim we forward a Bayesian non-parametric Dirichlet Process (DP) decision-making approach for real-time monitoring of UPM process using the data gathered from multiple, heterogeneous sensors. The sensor signals are acquired under different experimental conditions from a UPM setup instrumented with a heterogeneous sensing array consisting of miniature tri-axis force, tri-axis vibration, and acoustic emission (AE) sensors mounted in close proximity to the cutting tool. We track the prominent nonlinear and non-Gaussian signal patterns evident in the experimentally acquired sensor data using an adaptive non-parametric DP modeling technique. A cohesive decision concerning the UPM process condition is made by developing a new supervised learning method, which integrates the DP-model state estimates with an evidence theoretic sensor data fusion method. Using this combined DP-evidence theoretic approach, UPM process drifts and anomalies, such as sudden changes in the depth of cut, feed rate, and spindle speed that deleteriously affect surface finish, and hence cause high yield losses, are detected and classified with over 90% accuracy (with ${ standard deviation). We compared these results with popular classification techniques, e.g., naive Bayes, self-organizing map, and support vector machine; these conventional techniques had classification accuracy in the range of 83%–88%. Consequently, this research makes the following practically relevant contributions: 1) real-time identification of the incipient UPM process anomalies from multiple sensors and 2) prescribing the optimal subset of sensors signals contingent to particular process anomalies.

Parallelizing Multimodal Background Modeling on a Low-Power Integrated GPU

Background modeling techniques for embedded computer vision applications must balance accuracy, speed, and power. Basic background modeling techniques run quickly, but their accuracy is not sufficient for computer vision problems involving dynamic background. In contrast, adaptive background modeling techniques are more robust, but run more slowly. Due to its high inherent fine-grain parallelism, robust adaptive background modeling has been implemented on GPUs with significant performance improvements over CPUs. However, these implementations are infeasible in embedded applications due to the high power ratings of the targeted general-purpose GPU platforms. This paper focuses on exploiting fine-grain data parallelism and optimizing memory access patterns to target a low-cost adaptive background modeling algorithm multimodal mean (MMM) to a low-power GPU with thermal design power (TDP) of only 12 watts. The algorithm has comparable accuracy with the Gaussian mixture model (GMM) algorithm, but less computational and memory cost. It achieves a frame rate of 392 fps with a full VGA resolution (640x480) frame on the low-power integrated GPU NVIDIA ION. This is a 20x speed-up of the MMM algorithm compared to the embedded CPU platform Intel Atom of comparable TDP. In addition, the MMM algorithm attains a 5-6x speed up over the GMM implementation on the ION GPU platform.

Nonlinear Controller Design For A Shell And Tube Heat Exchanger – An Experimentation Approach

In this paper the outlet water temperature control of the shell and tube heat exchanger was implemented in real time system with the Generic Model Control (GMC) and adaptive control technique in simulation. The steady state model of the heat exchanger is used for the GMC and the dynamic model of the shell and tube heat exchanger is used for the adaptive control technique. MATLAB-2010-Simulink was used as a tool to implement the control algorithm in hardware loop