Automatic Parameter Estimation Research Articles

Scene transformation for detector adaptation

This paper focuses on detecting vehicles in different target scenes with the same pre-trained detector which is very challenging due to view variations. To address this problem, we propose a novel approach for detection adaptation based on scene transformation, which contributes in both view transformation and automatic parameter estimation. Instead of modifying the pre-trained detectors, we transform scenes into frontal/rear view handling with pitch and yaw view variations. Without human interactions but only some general prior knowledge, the transformation parameters are automatically initialized, and then online optimized with spatial–temporal voting, which guarantees that the transformation matches the pre-trained detector. Since there is no need of labeling new samples and manual camera calibration, our approach can considerably reduce manual interactions. Experiments on challenging real-world videos demonstrate that our approach achieves significant improvements over the pre-trained detector, and it is even comparable to the performance of the detector trained on fully labeled sequences.

Segmentation of brain magnetic resonance angiography images based on MAP–MRF with multi-pattern neighborhood system and approximation of regularization coefficient

Existing maximum a posteriori probability and Markov random field (MRF) models have limitations associated with: (1) the ordinary neighborhood system being unable to differentiate subtle changes due to several-to-one correspondence within the neighborhood; and (2) difficulty finding an appropriate parameter to balance between the spatial context and the data likelihood. Aiming at overcoming the limitations and applications to segmentation of cerebral vessels from magnetic resonance angiography images, we have proposed (1) a multi-pattern neighborhood system and corresponding energy equation to enable the MRF model for segmenting fine cerebral vessels with complicated context; and (2) an iterative approximation algorithm based on the maximum pseudo-likelihood and the space coding mode for the automatic parameter estimation of high level model of MRF. In the implementation, two computational strategies have been employed to speed up: the candidate space of cerebral vessels based on a threshold of the response to multi-scale filtering, and parallel computation of major equations. Three phantoms simulating segmentation challenges of vessels have been devised to quantitatively validate the algorithm. In addition, 10 three-dimensional clinical data sets have been used to validate the algorithm qualitatively. It has been shown that the proposed method could yield smaller error, improve the spatial resolution of MRF model, and better balance the smoothing and data likelihood than the traditional trial-and-error estimation. Comparative studies have shown that the proposed method is better than the 3 segmentation algorithms (Hassouna et al., 2006; Hao et al., 2008; Gao et al., 2011) in terms of segmentation accuracy, robustness to noise and varying curvatures as well as radii.

A correlative study on data from pork carcass and processed meat (Bauernspeck) for automatic estimation of chemical parameters by means of near-infrared spectroscopy

The use of near-infrared spectroscopy (NIRS) is proposed in this study for the characterization of the quality parameters of a smoked and dry-cured meat product known as Bauernspeck (originally from Northern Italy), as well as of some technological traits of the pork carcass used for its manufacturing. In particular, NIRS is shown to successfully estimate several key quality parameters (including water activity, moisture, dry matter, ash and protein content), suggesting its suitability for real time application in replacement of expensive and time consuming chemical analysis. Furthermore, a correlative approach based on canonical correlation analysis was used to investigate the spectral regions that are mostly correlated to the characteristics of interest. The identification of these regions, which can be linked to the absorbance of the main functional chemical groups, is intended to provide a better understanding of the chemical structure of the substrate under investigation.

Clinical refinement of the automatic lung parameter estimator (ALPE)

The automatic lung parameter estimator (ALPE) method was developed in 2002 for bedside estimation of pulmonary gas exchange using step changes in inspired oxygen fraction (FIO₂). Since then a number of studies have been conducted indicating the potential for clinical application and necessitating systems evolution to match clinical application. This paper describes and evaluates the evolution of the ALPE method from a research implementation (ALPE1) to two commercial implementations (ALPE2 and ALPE3). A need for dedicated implementations of the ALPE method was identified: one for spontaneously breathing (non-mechanically ventilated) patients (ALPE2) and one for mechanically ventilated patients (ALPE3). For these two implementations, design issues relating to usability and automation are described including the mixing of gasses to achieve FIO₂ levels, and the automatic selection of FIO₂. For ALPE2, these improvements are evaluated against patients studied using the system. The major result is the evolution of the ALPE method into two dedicated implementations, namely ALPE2 and ALPE3. For ALPE2, the usability and automation of FIO₂ selection has been evaluated in spontaneously breathing patients showing that variability of gas delivery is 0.3 % (standard deviation) in 1,332 breaths from 20 patients. Also for ALPE2, the automated FIO2 selection method was successfully applied in 287 patient cases, taking 7.2 ± 2.4 min and was shown to be safe with only one patient having SpO₂ < 86 % when the clinician disabled the alarms. The ALPE method has evolved into two practical, usable systems targeted at clinical application, namely ALPE2 for spontaneously breathing patients and ALPE3 for mechanically ventilated patients. These systems may promote the exploration of the use of more detailed descriptions of pulmonary gas exchange in clinical practice.

Parameter estimation of a pressure swing adsorption model for air separation using multi-objective optimisation and support vector regression model

In order to successfully estimate parameters of a numerical model, multiple criteria should be considered. Multi-objective Differential Evolution (MODE) and Multi-objective Genetic Algorithm (MOGA) have proved effective in numerous such applications, where most of the techniques relying on the condition of Pareto efficiency to compare different solutions. We describe the performance of two population based search algorithms (Nondominated Sorting Differential Evolution (NSDE) and Nondominated Sorting Genetic Algorithm (NGAII)) when applied to parameter estimation of a pressure swing adsorption (PSA) model. Full PSA mode is a complicated dynamic processing involving all transfer phenomena (mass, heat and momentum transfer) and has proven to be successful in a wide of applications. The limitation of using full PSA models is their expensive computational requirement. The parameter estimation analysis usually needs to run the numerical model and evaluate the performance thousands of times. However, in real world applications, there is simply not enough time and resources to perform such a huge number of model runs. In this study, a computational framework, known as v-support vector regression (v-SVR) PSA model, is presented for solving computationally expensive simulation problems. Formulation of an automatic parameter estimation strategy for the PSA model is outline. The simulations show that the NSDE is able to find better spread of solutions and better convergence near the true Pareto-optimal front compared to NSGAII-one elitist MOGA that pays special attention to creating a diverse Pareto-optimal front.

VACTIV: A graphical dialog based program for an automatic processing of line and band spectra

The program VACTIV–Visual ACTIV–has been developed for an automatic analysis of spectrum-like distributions, in particular gamma-ray spectra or alpha-spectra and is a standard graphical dialog based Windows XX application, driven by a menu, mouse and keyboard.On the one hand, it was a conversion of an existing Fortran program ACTIV [1] to the DELPHI language; on the other hand, it is a transformation of the sequential syntax of Fortran programming to a new object-oriented style, based on the organization of event interactions.New features implemented in the algorithms of both the versions consisted in the following •as peak model both an analytical function and a graphical curve could be used;•the peak search algorithm was able to recognize not only Gauss peaks but also peaks with an irregular form; both narrow peaks (2–4 channels) and broad ones (50–100 channels);•the regularization technique in the fitting guaranteed a stable solution in the most complicated cases of strongly overlapping or weak peaks. The graphical dialog interface of VACTIV is much more convenient than the batch mode of ACTIV.[1] V.B. Zlokazov, Computer Physics Communications, 28 (1982) 27–37. NEW VERSION PROGRAM SUMMARYProgram Title: VACTIVCatalogue identifier: ABAC_v2_0Licensing provisions: noProgramming language: DELPHI 5-7 Pascal.Computer: IBM PC series.Operating system: Windows XX.RAM: 1 MBKeywords: Nuclear physics, spectrum decomposition, least squares analysis, graphical dialog, object-oriented programming.Classification: 17.6.Catalogue identifier of previous version: ABAC_v1_0Journal reference of previous version: Comput. Phys. Commun. 28 (1982) 27Does the new version supersede the previous version?: Yes.Nature of problem: Program VACTIV is intended for precise analysis of arbitrary spectrum-like distributions, e.g. gamma-ray and X-ray spectra and allows the user to carry out the full cycle of automatic processing of such spectra, i.e. calibration, automatic peak search and estimation of parameters of interest. VACTIV can run on any standard modern laptop.Reasons for the new version: At the time of its creation (1999) VACTIV was seemingly the first attempt to apply the newest programming languages and styles to systems of spectrum analysis. Its goal was to both get a convenient and efficient technique for data processing, and to elaborate the formalism of spectrum analysis in terms of classes, their properties, their methods and events of an object-oriented programming language.Summary of revisions: Compared with ACTIV, VACTIV preserves all the mathematical algorithms, but provides the user with all the benefits of an interface, based on a graphical dialog.It allows him to make a quick intervention in the work of the program; in particular, to carry out the on-line control of the fitting process: depending on the intermediate results and using the visual form of data representation, to change the conditions for the fitting and so achieve the optimum performance, selecting the optimum strategy.To find the best conditions for the fitting one can compress the spectrum, delete the blunders from it, smooth it using a high-frequency spline filter and build the background using a low-frequency spline filter; use not only automatic methods for the blunder deletion, the peak search, the peak model forming and the calibration, but also use manual mouse clicking on the spectrum graph.Restrictions: To enhance the reliability and portability of the program the majority of the most important arrays have a static allocation; all the arrays are allocated with a surplus, and the total pool of the program is restricted only by the size of the computer virtual memory. A spectrum has the static size of 32 K real words. The maximum size of the least-square matrix is 314 (the maximum number of fitted parameters per one analyzed spectrum interval, not for the whole spectrum), from which it follows that the maximum number of peaks in one spectrum interval is 154. The maximum total number of peaks in the spectrum is not restricted.Running time: The calculation time is negligibly small compared with the time for the dialog; using ini-files the program can be partly used in a semi-dialog mode.

Parametric Method of Frequency-Dependent I/Q Imbalance Compensation for Wideband Quadrature Modulator

This paper proposes a parametric method of frequency-dependent I/Q imbalance compensation for wideband quadrature modulators using the spectrum measurement of a radio frequency (RF) signal that is easily performed by a general-purpose spectrum analyzer. The proposed method empirically estimates the frequency-dependent circuit parameters using only the magnitude of the frequency spectrum of the RF signal that is fed back from the spectrum analyzer. The frequency dependency of the I/Q imbalance effect generated by the difference between the overall frequency responses of the I and Q branches is modeled by frequency-dependent circuit parameters. By dividing the entire signal band into several sub-bands, the transmit signals are predistorted per sub-band in the frequency domain. To estimate the frequency-dependent circuit parameters, in this study, the modified method of steepest descent developed for single-band compensation is extended to the frequency-domain sub-band compensation scheme. We demonstrate the compensation effect by implementing an automatic sub-band circuit parameter estimation system.

NeRvolver: a computational intelligence-based system for automated construction, tuning, and analysis of neuronal models

Building neuronal models, even on the single-cell level, requires tremendous amounts of effort invested in the design of a realistic and functioning structure (e.g., the number and characteristics of compartments) and proper tuning of the model’s parameter values (e.g., membrane and axial conductances). Due to the ever-increasing computational power of modern computers facilitating the use of more and more complex neuronal models, hand-tuning of models’ parameters is becoming less and less feasible. Therefore, automated methods for neuronal model construction have been lately gaining much attention. Although a significant number of techniques for automatic model parameter estimation have been recently proposed (e.g., [1,3,4]), they are predominantly limited to “fine-tuning” of already designed models in a predetermined search space of parameter values. Furthermore, although unquestionably successful, present approaches are almost exclusively domain-specific, designed to deal with particular neuron types, or explicit classes of electrical activity (e.g., spiking neurons). Finally, most of the existing systems attempt to produce a single, best-matching model, and rely on a direct comparison between the voltage trace of the model and its biological equivalent. Here, we propose a computational intelligence-based system for automated construction and tuning of neuronal models that builds upon the existing research in the area of automatic neuron model parameter optimization, but at the same time significantly expands the current approaches. The system, called NeRvolver, is designed to not only optimize the parameters of existing neuronal models, but also to allow for creation of entire sets of models matching some predefined criteria (e.g., in terms of the neuron’s characteristics such as spike height, inter-spiking interval, burst duration, period, etc.) “from scratch” (by utilizing, for example, only a limited set of generic currents as the starting point in the process of model construction). Furthermore, in addition to generating neuronal models, through the hybridization of multi-objective evolutionary algorithms (MOEA) and fuzzy logic (FL), the system generates classification rules describing biological phenomena discovered during the process of model creation or tuning (e.g., “IF sodium axon conductance is low, THEN spike frequency is low”). The purpose of generating such rules is twofold: 1) they can be used in subsequent runs of the modeling algorithm to improve its convergence time, and 2) they may potentially provide insights into the functioning of the biological neurons being modeled. For example, by using the aforementioned rule, the system may automatically increase the sodium axon conductance across the individuals in the evolutionary algorithm’s current population, if a higher spike frequency is desired. This is akin to the idea of local improvement of the genetic material using memes in memetic algorithms [2]. In addition, based on the above-quoted rule, the conclusion may be drawn that sufficient sodium axon conductance is necessary for adequate spike frequency. Such inferences, here automatically generated by the modeling system, can obviously be extremely useful for the understanding of the underlying biological phenomena.

Automatic procedure for induction motor parameter estimation at standstill

The study presents a self-commissioning procedure for the automatic parameter estimation of three-phase induction motor drives. The procedure consists of a step-by-step approach with different test signals to obtain the parameter values while maintaining the motor at standstill. The actual implementation is capable of mapping both inverter and motor parameters non-linearities, providing accurate data for the tuning of common current regulators and for advanced sensorless drives as well. Theoretical and experimental results are provided, proving the effectiveness of the procedure.

Effect of Temporal and Spatial Rainfall Resolution on HSPF Predictive Performance and Parameter Estimation

Watershed-scale rainfall-runoff models are used for environmental management and regulatory modeling applications, but their effectiveness is limited by predictive uncertainties associated with model input data. This study evaluated the effect of temporal and spatial rainfall resolution on the predictive performance of Hydrological Simulation Program—Fortran (HSPF) using manual and automatic calibration procedures. Furthermore, the effect of automatic parameter estimation on the physical significance of calibrated parameter values was evaluated. Temporal resolutions examined included 15 min, 30 min, 1 h, and 2 h, and spatial resolution effects evaluated included the effect of a spatially averaged network of four rain gauges and Next-Generation Radar (NEXRAD) for selected rain events. Model efficiencies ranged from 0.31 to 0.86 when individual rain gauges (RG71, RG73, RG74, and RG77) were used one at a time. Model efficiency improved and ranged from 0.86 to 0.94 when a spatially averaged network of four ra...

Parameterising hydrological models – Comparing optimisation and robust parameter estimation

In most conditions, calibration is a prerequisite for successfully applying conceptual and physically based rainfall–runoff models. The goal of this paper is to comparatively analyse the potential of both event-based automatic calibration (PEST) as described in Skahill and Doherty (2006) and robust parameter estimation (ROPE) as proposed by Bardossy and Singh (2008). The results of our modelling study in the Rietholzbach catchment (Switzerland) show that ROPE performs better in validation of small to medium sized events. This indicates that ROPE might be better suited to parameterise models when the modellers intention is focussed on a maximising the generalisation capacity of the model, e.g. for evaluating transient process characteristics. We base our study on the hydrological model WaSiM-ETH, using a combined ROPE and automatic parameter estimation approach to investigate optimal parameter sets. The PEST algorithm used in this study outperforms the ROPE application by a factor of roughly 100 in terms of time required for computation.

Automation of an algorithm based on fuzzy clustering for analyzing tumoral heterogeneity in human skin carcinoma tissue sections

This study aims to develop a new FT–IR spectral imaging of tumoral tissue permitting a better characterization of tumor heterogeneity and tumor/surrounding tissue interface. Infrared (IR) data were acquired on 13 biopsies of paraffin-embedded human skin carcinomas. Our approach relies on an innovative fuzzy C-means (FCM)-based clustering algorithm, allowing the automatic and simultaneous estimation of the optimal FCM parameters (number of clusters K and fuzziness index m). FCM seems more suitable than classical ‘hard' clusterings, as it permits the assignment of each IR spectrum to every cluster with a specific membership value. This characteristic allows differentiating the nuances in the assignment of pixels, particularly those corresponding to tumoral tissue and those located at the tumor/peritumoral tissue interface. FCM images permit to highlight a marked heterogeneity within the tumor and characterize the interconnection between tissular structures. For the infiltrative tumors, a progressive gradient in the membership values of the pixels of the invasive front was also revealed.

Rayleigh Mixture Model for Plaque Characterization in Intravascular Ultrasound

Vulnerable plaques are the major cause of carotid and coronary vascular problems, such as heart attack or stroke. A correct modeling of plaque echomorphology and composition can help the identification of such lesions. The Rayleigh distribution is widely used to describe (nearly) homogeneous areas in ultrasound images. Since plaques may contain tissues with heterogeneous regions, more complex distributions depending on multiple parameters are usually needed, such as Rice, K or Nakagami distributions. In such cases, the problem formulation becomes more complex, and the optimization procedure to estimate the plaque echomorphology is more difficult. Here, we propose to model the tissue echomorphology by means of a mixture of Rayleigh distributions, known as the Rayleigh mixture model (RMM). The problem formulation is still simple, but its ability to describe complex textural patterns is very powerful. In this paper, we present a method for the automatic estimation of the RMM mixture parameters by means of the expectation maximization algorithm, which aims at characterizing tissue echomorphology in ultrasound (US). The performance of the proposed model is evaluated with a database of in vitro intravascular US cases. We show that the mixture coefficients and Rayleigh parameters explicitly derived from the mixture model are able to accurately describe different plaque types and to significantly improve the characterization performance of an already existing methodology.

1A2-Q15 Mobile Mapping Systemにおける広域三次元計測のためのレーザスキャナを利用したカメラ外部パラメータの推定(ITSとロボット・メカトロ技術)

This paper describes an extrinsic camera parameter estimation method for a 3D measurement using a mobile mapping system (MMS). MMS can acquire the 3D information of the road environment efficiently using the laser scanner. However, a measurement range is limited because of the performance of the laser scanner, the use of camera for the 3D measurement is expected. In the 3D measurement using the camera, the accurate extrinsic camera parameter estimation is required. We propose an automatic camera parameter estimation method that uses the measurement data of laser scanner acquired by the MMS. In the result of experiment, it is confirmed that the proposed method can estimate the extrinsic camera parameter to an accuracy of 0.07 degree.

Optimization of Hydraulic Parameters of Iranshahr Alluvial Aquifer

Problem statement: The Iranshahr aquifer consists of an unconfined layer. We simulated groundwater flow of the Iranshahr aquifer in a conceptual model. This model is a suitable tool for management of groundwater system and would also be effective when applied in other countries. Approach: In this study, we constructed the conceptual model of Iranshahr aquifer, which is important and applicable in environmental studies. We used the automatic parameter estimation method and hydraulic head observation through calibration in order to identify the best parameter values. During the calibration, the optimized values of the parameters obtained. 24 parameters estimated by means of regression and the rest remaining unestimated parameters optimized using the trial-and-error method. Results: The results of the model show a good fit between observation and simulated values. Automated calibration procedure estimated the hydraulic parameters of the aquifer. Conclusion: The optimized values and the zonation of the hydraulic parameters of the aquifer showed the best areas for developing and extracting groundwater from the aquifer taking the optimized hydraulics values into account.

A system for the automatic estimation of morphometric parameters of corneal endothelium in alizarine red-stained images

Background/aimsA computer program for the automatic estimation of endothelium morphometric parameters (cell density, pleomorphism, polymegethism) in alizarine red-stained images is presented and evaluated.MethodsImages of corneal endothelium from 30 porcine eyes...

A new camera calibration method from vanishing points in a vision system

The problem of finding intrinsic parameters of a camera is extremely important for practical applications. In this paper, we present an approach for automatic estimation of intrinsic parameters from images by using the vanishing points in orthogonal directions. Firstly, image lines are extracted and clustered into groups corresponding to three dominant vanishing points. Secondly, the intrinsic parameters of the camera are determined by using the vanishing points in each image. The rotation matrix of the projection matrix is computed from the vanishing points and image edges while the translation matrix is obtained with additional translation motion between the viewpoints. Our approach does not need any prior information about the cameras being used. Experiments with real images show that our new technique is robust and accurate.

Lake sediments during the transient eutrophication period: Reactive-transport model and identifiability study

The modeling of diagenetic processes in the sediment of deep eutrophic lakes requires a dynamic approach covering seasonal changes to decadal trends. Due to the large base of scientific knowledge, the description of environmental systems is often based on complex simulation models that contain parameterizations of a large number of processes. The parameters of such models are usually not identifiable from a data set available for a specific system. In such situations, identifiability analysis techniques are useful in order to find identifiable subsets of parameters and to gain insight into the degree of non-identifiability. In this study a dynamic diagenetic model was developed to gain insight into the history of sedimentation and diagenetic processes in the sediments of Lake Zug, Switzerland, over the past 400 years. This reconstruction was constrained by measured data of 11 pore water concentration profiles, 6 particulate mass fractions in the sediment, sediment porosity and sediment core dating. According to the model, methanogenesis dominated the mineralization in the anoxic zone below the sediment–water interface with a fraction of 77% of organic matter degraded via this pathway. The contributions of Mn, Fe, and sulfate reduction to the organic matter degradation were less important (6%, 2%, and 15% respectively). The detailed analysis of an aerobic degradation at the sediment–water interface requires high-resolution measurements of dissolved substances. The model reproduced the main features of the seasonal variation of dissolved ammonia depth profiles quite well but failed to reproduce a sharp phosphate peak that was observed during summer, which indicates either spatial heterogeneity or short-term dynamics in the phosphorus release. Based on the time dependence of sedimentation fluxes, the model described changes in the accumulation of FeS in sediments from 1940 to 1994 as a result of increasing eutrophication, which opens the perspective for paleolimnological reconstructions based on quantitative diagenetic models. Based on identifiability analysis techniques this study shows that for a diagenetic model of the sediment of Lake Zug, an exceptionally large number of model parameters (25) can be identified from the available data. The result, based on numerical identifiability criteria, is verified by an automatic parameter estimation procedure. Furthermore, it is discussed if the identified parameter values are reasonable, or if the model parameters or model deficiencies that are fitted lead to a significant bias in their estimates.

Automatic illumination and color compensation using mean shift and sigma filter

We present a novel framework for automatic illumination and color compensation algorithm using mean shift and the sigma filter (ICCMS) to restore distorted images taken under the arbitrary lighting conditions. The proposed method is effective for appropriate illumination compensation, vivid color restoration, artifacts suppression, automatic parameter estimation, and low computational cost for HW implementation. We show the efficiency of the mean shift filter and sigma filter for illumination compensation with small sized kernel while considering the processing time and removing the artifacts such as HALO and noise amplification. The proposed color restoration function can restore the natural color and correct color noise artifact more perceptually compared with conventional methods. For the automatic processing, the image statistics analysis estimates suitable parameter and all constants are pre-defined. We also introduce the ROI-based parameter estimation dealing with small shadow area against spacious well-exposed background in an image for the touch-screen camera. The object evaluation is performed by CMC, CIEde2000, PSNR, SSIM, and 3D CIELAB gamut with state-of-the-art research and existing commercial solutions.

Automated estimation of stellar fundamental parameters from low resolution spectra: the PLS method

PLS (Partial Least Squares regression) is introduced into an automatic estimation of fundamental stellar spectral parameters. It extracts the most correlative spectral component to the parameters (Teff, log g and [Fe/H]), and sets up a linear regression function from spectra to the corresponding parameters. Considering the properties of stellar spectra and the PLS algorithm, we present a piecewise PLS regression method for estimation of stellar parameters, which is composed of one PLS model for Teff, and seven PLS models for log g and [Fe/H] estimation. Its performance is investigated by large experiments on flux calibrated spectra and continuum normalized spectra at different signal-to-noise ratios (SNRs) and resolutions. The results show that the piecewise PLS method is robust for spectra at the medium resolution of 0.23 nm. For low resolution 0.5 nm and 1 nm spectra, it achieves competitive results at higher SNR. Experiments using ELODIE spectra of 0.23 nm resolution illustrate that our piecewise PLS models trained with MILES spectra are efficient for O ∼ G stars: for flux calibrated spectra, the systematic offsets are 3.8%, 0.14 dex, and -0.09 dex for Teff, log g and [Fe/H], with error scatters of 5.2%, 0.44 dex and 0.38 dex, respectively; for continuum normalized spectra, the systematic offsets are 3.8%, 0.12dex, and -0.13dex for Teff, log g and [Fe/H], with error scatters of 5.2%, 0.49 dex and 0.41 dex, respectively. The PLS method is rapid, easy to use and does not rely as strongly on the tightness of a parameter grid of templates to reach high precision as Artificial Neural Networks or minimum distance methods do.