Optimal Filter Research Articles

A Hybrid Extended Kalman Filter Based on Parametrized ANNs for the Improvement of the Forecasts of Numerical Weather and Wave Prediction Models

A hybrid optimization filter for weather and wave numerical models is proposed and tested in this study. Parametrized Artificial Neural Networks are utilized in conjunction with Extended Kalman Filters to provide a novel postprocess strategy for 10 m wind speed, 2 m air temperature, and significant wave height simulations. The innovation of the developed model is the implementation of Feedforward Neural Networks and Radial Basis Function Neural Networks as estimators of an exogenous parameter that adjusts the covariance matrices of the Extended Kalman Filter process. This hybrid system is evaluated through a time window process leading to promising results, thus enabling a decrease in systematic errors alongside the restriction of the error variability and the corresponding forecast uncertainty. The obtained results showed that the average reduction of the systematic error exceeded 75%, while the corresponding nonsystematic part of that error decreased by 35%.

Automated explainable wavelet-based sleep scoring system for a population suspected with insomnia, apnea and periodic leg movement

Sleep is an integral and vital component of human life, contributing significantly to overall health and well-being, but a considerable number of people worldwide experience sleep disorders. Sleep disorder diagnosis heavily depends on accurately classifying sleep stages. Traditionally, this classification has been performed manually by trained sleep technologists that visually inspect polysomnography records. However, in order to mitigate the labor-intensive nature of this process, automated approaches have been developed. These automated methods aim to streamline and facilitate sleep stage classification. This study aims to classify sleep stages in a dataset comprising subjects with insomnia, PLM, and sleep apnea. The dataset consists of PSG recordings from the multi-ethnic study of atherosclerosis (MESA) cohort of the national sleep research resource (NSRR), including 2056 subjects. Among these subjects, 130 have insomnia, 39 suffer from PLM, 156 have sleep apnea, and the remaining 1731 are classified as good sleepers. This study proposes an automated computerized technique to classify sleep stages, developing a machine-learning model with explainable artificial intelligence (XAI) capabilities using wavelet-based Hjorth parameters. An optimal biorthogonal wavelet filter bank (BOWFB) has been employed to extract subbands (SBs) from 30 seconds of electroencephalogram (EEG) epochs. Three EEG channels, namely: Fz_Cz, Cz_Oz, and C4_M1, are employed to yield an optimum outcome. The Hjorth parameters extracted from SBs were then fed to different machine learning algorithms. To gain an understanding of the model, in this study, we used SHAP (Shapley Additive explanations) method. For subjects suffering from the aforementioned diseases, the model utilized features derived from all channels and employed an ensembled bagged trees (EnBT) classifier. The highest accuracy of 86.8%, 87.3%, 85.0%, 84.5%, and 83.8% is obtained for the insomniac, PLM, apniac, good sleepers and complete datasets, respectively. Using these techniques and datasets, the study aims to enhance sleep stage classification accuracy and improve understanding of sleep disorders such as insomnia, PLM, and sleep apnea.

Machine learning-based CT radiomics enhances bladder cancer staging predictions: A comparative study of clinical, radiomics, and combined models.

Predicting the accurate preoperative staging of bladder cancer (BLCA), which markedly affects treatment decisions and patient outcomes, using traditional clinical parameters is challenging. Nevertheless, emerging studies in radiomics, especially machine learning-based computed tomography (CT) image-based radiomics, hold promise in improving stage prediction accuracy in various tumors. However, the comparative performance and clinical utility of models for BLCA are under investigation. We aimed to investigate the application value of machine learning-based CT radiomics in preoperative staging prediction by comparing the performance of clinical, radiomics, and clinical-radiomics combined models. A retrospective cohort of 105 patients with initial BLCA was randomized into training (70%) and testing (30%) cohorts. Radiomics features were extracted from CT images using the optimal feature filter, followed by the application of the least absolute shrinkage and selection operator algorithm for optimum feature selection. Furthermore, machine learning algorithms were used to establish a radiomics model within the training cohort. Independent risk factors for muscle-invasive BLCA (MIBC) obtained by multivariate logistic regression (LR) analysis were separately used to construct a clinical model. For a clinical-radiomics fusion model, radiomics features were combined with clinical parameters. Performance was evaluated based on receiver operating characteristic curves, calibration curves, decision curve analysis (DCA), and standard performance metrics. Patients exhibited a significantly higher age (p=0.029), larger tumor size (p=0.01), and an increased neutrophil-to-lymphocyte ratio (NLR; p=0.045) in the MIBC group than in the NMIBC group. LR analysis revealed age (p=0.026), tumor size (p=0.007), and NLR (p=0.019) as significant predictors for constructing the clinical model. In the testing cohort, the radiomics model, which used an Support Vector Machine classifier, achieved the highest area under the curve (AUC) value of 0.857. The clinical-radiomics model outperformed the remaining two models, with AUC values of 0.958 and 0.893 in the training and testing cohorts, respectively. DeLong's test indicated significant differences between the three models. Calibration curves showed good agreement, and DCA confirmed the superior clinical utility of the clinical-radiomics model. Machine learning-based CT radiomics combined with clinical parameters was a promising approach in staging BLCA accurately, which outperformed the individual models. Integrating radiomics features with clinical information holds the potential to improve personalized treatment planning and patient outcomes in BLCA.

A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials.

With the development of data mining technology, the analysis of event-related potential (ERP) data has evolved from statistical analysis of time-domain features to data-driven techniques based on supervised and unsupervised learning. However, there are still many challenges in understanding the relationship between ERP components and the representation of familiar and unfamiliar faces. To address this, this paper proposes a model based on Dynamic Multi-Scale Convolution for group recognition of familiar and unfamiliar faces. This approach uses generated weight masks for cross-subject familiar/unfamiliar face recognition using a multi-scale model. The model employs a variable-length filter generator to dynamically determine the optimal filter length for time-series samples, thereby capturing features at different time scales. Comparative experiments are conducted to evaluate the model's performance against SOTA models. The results demonstrate that our model achieves impressive outcomes, with a balanced accuracy rate of 93.20% and an F1 score of 88.54%, outperforming the methods used for comparison. The ERP data extracted from different time regions in the model can also provide data-driven technical support for research based on the representation of different ERP components.

Optimal Baseflow Separation Through Chemical Mass Balance: Comparing the Usages of Two Tracers, Two Concentration Estimation Methods, and Four Baseflow Filters

AbstractOptimizing empirical baseflow filters using environmental tracers (e.g., specific electrical conductance (SEC), turbidity) is an effective and efficient way to quantify the contribution of baseflow to total flow. To execute this baseflow separation, three key components are needed: The tracer, the method to estimate tracer concentration in different flow components, and the empirical baseflow filter. However, a comprehensive evaluation of the various combinations of these components, especially with a large sample of catchments, is currently lacking in the literature. Therefore, our study assembles 16 hybrid baseflow filters from two tracers, two concentration estimation methods, and four empirical baseflow filters, and evaluated their performance in baseflow separation and producing two long‐term baseflow signatures for 1,100 catchments in the Contiguous United States. Our results suggest that SEC is a superior tracer to turbidity for baseflow separation. Additionally, using monthly maximum and minimum values to represent tracer concentration in flow components produces better separation than using a power function relationship between flow rate and concentration. The four empirical baseflow filters offer a similar level of performance, regardless of the other options used. Yet, some of these filters produce inconsistent results in calculating the baseflow signatures for the catchments. Our analysis shed light on the optimization of hybrid baseflow filters for the accurate quantification of baseflow contribution.

Testing the ionospheric model delay and uncertainty estimates with an uncombined navigation filter

In the last decade, new algorithmic positioning techniques have been developed for Global Navigation Satellite Systems (GNSS). These have brought a new focus on high accuracy applications which do not combine multiple frequencies to remove ionospheric errors (i.e. PPP-RTK, Fast-PPP). Not only do these algorithms focus on improvements in the position domain but also in acquiring the positioning solution as fast as possible. In this work, capabilities of different global ionospheric models are assessed, analyzing both the Ionospheric delay accuracy and the associated model uncertainty. Accurate model uncertainties are crucial for reducing the convergence time in uncombined filters, and to guarantee unbiased convergence in the first place. The assessment is done using an uncombined navigation filter with different ionospheric models: GPS ICA, IGS vTEC (vertical Total Electron Content) maps (IGSG, CODG and UQRG), two realizations of the ESA-UGI (Voxel and Multi-Layer), the Madrigal TEC, and the Spire Global vTEC maps. To quantify the model uncertainties without the use of a reference ionospheric model, global maps of an uncertainty inflation factor are computed to show the inflation required to produce optimal filter convergence. These maps demonstrate that some models are too optimistic in the reporting of their own uncertainty estimates, requiring an uncertainty factor up to 10 times the quoted value.

GAINN: The Galaxy Assembly and Interaction Neural Networks for High-redshift JWST Observations

We present the Galaxy Assembly and Interaction Neural Networks (Gainn), a series of artificial neural networks for predicting the redshift, stellar mass, halo mass, and mass-weighted age of simulated galaxies based on James Webb Space Telescope (JWST) photometry. Our goal is to determine the best neural network for predicting these variables at 11 < z < 15. The parameters of the optimal neural network can then be used to estimate these variables for real, observed galaxies. The inputs of the neural networks are JWST filter magnitudes of a subset of five broadband filters (F150W, F200W, F277W, F356W, and F444W) and two medium-band filters (F162M and F182M). We compare the performance of the neural networks using different combinations of these filters, as well as different activation functions and numbers of layers. The best neural network predicted redshift with a normalized rms error of 0.010−0.001+0.003 , stellar mass with rms = 0.089−0.022+0.044 , halo mass with a mean-squared error of 0.022−0.008+0.014 , and mass-weighted age with rms = 12.466−2.408+5.065 . We also test the performance of Gainn on real data from MACS0647JD, an object observed by JWST. Predictions from Gainn for the first projection of the object (JD1) have normalized bias 〈Δz〉 < 0.00228, which is significantly smaller than found with template-fitting methods. We find that the optimal filter combination is F277W, F356W, F162M, and F200W when considering both theoretical accuracy and observational resources from JWST.

Quality Enhancement of MIROS Wave Radar Data at Ieodo Ocean Research Station Using ANN

Remote sensing wave observation data are crucial when analyzing ocean waves, the main external force of coastal disasters. Nevertheless, it has limitations in accuracy when used in low-wind environments. Therefore, this study collected the raw data from MIROS Wave and Current Radar (MWR) and wave radar at the Ieodo Ocean Research Station (IORS) and applied the optimal filter by combining filters provided by MIROS software. The data were validated by a comparison with South Jeju ocean buoy data. The results showed it maintained accuracy for significant wave height, but errors were observed in significant wave periods and extreme waves. Hence, this study used an artificial neural network (ANN) to improve these errors. The ANN was generalized by separating the data into training and test datasets through stratified sampling, and the optimal model structure was derived by adjusting the hyperparameters. The application of ANN effectively improved the accuracy in significant wave periods and high wave conditions. Consequently, this study reproduced past wave data by enhancing the reliability of the MWR, contributing to understanding wave generation and propagation in storm conditions, and improving the accuracy of wave prediction. On the other hand, errors persisted under high wave conditions because of wave shadow effects, necessitating more data collection and future research.

Practical Trainable Temporal Postprocessor for Multistate Quantum Measurement

We develop and demonstrate a trainable temporal postprocessor (TPP) harnessing a simple but versatile machine learning algorithm to provide optimal processing of quantum measurement data subject to arbitrary noise processes for the readout of an arbitrary number of quantum states. We demonstrate the TPP on the essential task of qubit state readout, which has historically relied on temporal processing via matched filters in spite of their applicability for only specific noise conditions. Our results show that the TPP can reliably outperform standard filtering approaches under complex readout conditions, such as high-power readout. Using simulations of quantum measurement noise sources, we show that this advantage relies on the TPP’s ability to learn optimal linear filters that account for general quantum noise correlations in data, such as those due to quantum jumps, or correlated noise added by a phase-preserving quantum amplifier. Furthermore, we derive an exact analytic form for the optimal TPP weights: this positions the TPP as a linearly scaling generalization of matched filtering, valid for an arbitrary number of states under the most general readout noise conditions, all while preserving a training complexity that is essentially negligible in comparison with that of training neural networks for processing temporal quantum measurement data. The TPP can be autonomously and reliably trained on measurement data and requires only linear operations, making it ideal for field-programmable gate array implementations in circuit QED for real-time processing of measurement data from general quantum systems. Published by the American Physical Society 2024

Optimal design of multilayer optical thin film structure for smart energy saving applications using needle optimization approach

In this work, a novel design of a one dimensional photonic crystal (1D PC) is investigated. The 1DPC structure is composed of alternating layers of tantalum pentoxide (Ta2O5) and silicon dioxide (Sio2). The proposed 1D PC structure is designed to act as short wave pass (SWP) edge filter that selectively passes light of short wavelengths, while the infrared light is blocked. In this study, Essential Macleod software is used to create the optimal design with the computational support of the needle synthesis technique. By varying the incidence angle of the mean polarized light mode, we can determine the features of the optimal SWP edge filter design, which leads to an important application for this filter. It can shed light on the filter’s suitability as a smart energy saving window coating for hot climate regions. The study includes different hot regions in Saudi Arabia such as Mecca, Riyadh, Dammam, Arar and Alaqiq. They were used as case studies in this research. According to the study of the optimal design of SWP edge filter applied in Mecca, Riyadh, Dammam, Arar and Alaqiq provinces, the light transmittance in the visible region is more than 99% during the summer solstice and more than 96% during the winter solstice. The photonic band gab (PBG) is almost constant during the summer solstice without shifting or decreasing in size whereas in the winter solstice, the PBG shifts toward the short wavelengths and decreases in size by increasing the angle of incidence. This allows an amount of solar energy to enter in winter. Riyadh, Dammam, and Arar provinces experienced a significant increase in solar energy during the winter solstice, more than Mecca and Alaqiq provinces.

A simulation-driven difference mode decomposition method for fault diagnosis in axial piston pumps

The strong periodic shocks produced by axial piston pumps during normal operation greatly weaken the performance of fault diagnosis methods. Extracting the fault resonance band seems to be an effective solution to weaken the impact of strong periodic shocks. However, these methods still fail to eliminate in-band noise, leading to the failure of the method. To address this issue, a simulation-driven difference mode decomposition (SDMD) method is proposed. Firstly, the raw signal is processed using the transmission path elimination technology to weaken the influence of excessive amplitude of the noise spectral line caused by the transmission path. Secondly, the finite element method is employed to construct a simulation model to assist in constructing the optimal filter. The signal is filtered by the optimal filter to initially eliminate out-of-band noise. Finally, the filtered signal is input into the convex optimization function for further purification to eliminate the in-band noise. Simulation and experimental verification show that the SDMD can more accurately extract the fault features under the influence of strong periodic shocks.

Optimal loop filter design of a DC immunity single-phase PLL based single delay operator

Optimal loop filter design of a DC immunity single-phase PLL based single delay operator

ResPrune: An energy-efficient restorative filter pruning method using stochastic optimization for accelerating CNN

Convolutional Neural Networks (CNNs) are frequently employed for image pattern recognition and other computer vision tasks. When over-parameterized deep learning models are used for inference, resource-constrained edge devices may struggle. As a result, model compression, particularly filter pruning, has become critical. A reduction in model size might result in less calculation, resulting in faster hardware execution and lower energy consumption. One of the drawbacks of current pruning strategies is that once the filters are pruned, their weights are permanently lost. To address this constraint, we propose a unique two-phase pruning technique in which the filters to be pruned are selected using two criteria: l2-norm and redundancy. Second, rather than omitting the selected filters for all future epochs, we restore them to their original value with some stochasticity. Retaining the most optimal filter weights in earlier epochs enables the survival of the fittest filters, resulting in higher model convergence. Experiments on three benchmark datasets, CIFAR-10, CIFAR-100, and ILSVRC-2012, reveal that our strategy outperforms other state-of-the-art pruning methods by a minimum reduction of 57% FLOPs with an accuracy loss as minimal as 0.08 %.

An optimized filter design approach for enhancing imaging quality in industrial linear accelerator.

The polychromatic X-rays generated by a linear accelerator (Linac) often result in noticeable hardening artifacts in images, posing a significant challenge to accurate defect identification. To address this issue, a simple yet effective approach is to introduce filters at the radiation source outlet. However, current methods are often empirical, lacking scientifically sound metrics. This study introduces an innovative filter design method that optimizes filter performance by balancing the impact of ray intensity and energy on image quality. Firstly, different spectra under various materials and thicknesses of filters were obtained using GEometry ANd Tracking (Geant4) simulation. Subsequently, these spectra and their corresponding incident photon counts were used as input sources to generate different reconstructed images. By comprehensively comparing the intensity differences and noise in images of defective and non-defective regions, along with considering hardening indicators, the optimal filter was determined. The optimized filter was applied to a Linac-based X-ray computed tomography (CT) detection system designed for identifying defects in graphite materials within high-temperature gas-cooled reactor (HTR), with defect dimensions of 2 mm. After adding the filter, the hardening effect reduced by 22%, and the Defect Contrast Index (DCI) reached 3.226. The filter designed based on the parameters of Average Difference (AD) and Defect Contrast Index (DCI) can effectively improve the quality of defect images.

Genetic Algorithm as the Solution of Non-Linear Inverse Heat Conduction Problems: A Novel Sequential Approach

Abstract Direct measurement of surface heat flux could be extremely challenging, if not impossible, in numerous applications. In such cases, the use of temperature measurement data from subsurface locations can facilitate the determination of surface heat flux and temperature through the solution of the inverse heat conduction problem (IHCP). Several different techniques have been developed over the years for solving IHCPs, with different levels of complexity and accuracy. The filter coefficient technique has proved to be a promising approach for solving IHCPs. Inspired by the filter coefficient approach, a novel method is presented in this paper for solving one-dimensional IHCPs in a domain with temperature-dependent material properties. A test case is developed in COMSOL Multiphysics where the front side of a slab is subject to known transient heat flux and the temperature distributions within the domain are calculated through numerical simulation. The IHCP solution in the form of filter coefficients is defined and a genetic algorithm (GA) is used for the calculation of filter matrix. The number of significant filter coefficients required to evaluate surface heat flux at each time-step is determined through trial and error and the optimal number is selected for evaluating the solution. The structure of the filter matrix is assessed and discussed. The resulting filter coefficients are then used to evaluate the surface heat flux for several different test cases and the performance of the proposed approach is assessed in detail. The results showed that the presented approach is robust and can result in finding optimal filter coefficients that can accurately estimate various types of surface heat flux profiles using temperature data from a limited number of time steps and in a near real-time fashion.

Fine-tuning digital FIR filters with gray wolf optimization for peak performance

The design of optimum filters constitutes a fundamental aspect within the realm of signal processing applications. The process entails the calculation of ideal coefficients for a filter in order to get a passband with a flat response and an unlimited level of attenuation in the stopband. The objective of this work is to solve the FIR filter design problem and to compare the optimal solutions obtained from evolutionary algorithms. The design of optimal FIR low pass (LP), high pass (HP), and band stop (BS) filters is achieved by the utilization of nature-inspired optimization approaches, namely gray wolf optimization ,cuckoo search, particle swarm optimization, and genetic algorithm. The filters are evaluated in terms of their stop band attenuation, pass band ripples, and departure from the anticipated response. In addition, this study compares the optimization strategies applied in the context of algorithm execution time which is achievement of global optimal outcomes for the design of digital finite impulse response (FIR) filters. The results indicate that when the Gray wolf algorithm is applied to the development of a finite impulse response (FIR) filter, it produces a higher level of performance than other approaches, as supported by enhanced design precision, decreased execution time, and achievement of an optimal solution.

Prediction of three-dimensional flow field inside realistic fibrous filter obtained from x-ray computed tomography images using deep convolutional neural networks

Deep-learning models garnered considerable attention in the field of fluid mechanics for physics discovery and approximation-model generation. This study aims to develop an approximation model to predict the flow field inside realistic fibrous filters based on an image-to-image approach to replace three-dimensional (3D) computational fluid dynamics (CFD) simulations, which are computationally expensive and difficult to apply to realistic fibrous filters. A data-driven framework is proposed using deep convolutional neural networks (CNNs) to provide a per-pixel prediction of the flow field. The model inputs are two-dimensional x-ray computed tomography images, whereas the outputs are the 3D distributions of the velocity vectors and pressure. High-resolution 3D CFD simulations are performed to create a database to train and test the CNN model. The model is applied to surgical and N95 face masks. The relative error of the CNN model over the test dataset is approximately 10% in regions with high velocity and pressure, and the model can provide a detailed high-resolution prediction of the flow field with a speedup of about three orders of magnitudes. A strict generalization test is conducted for completely unseen 3D segments with complex microstructures. The model generalizability still needs more improvements; however, the model can provide a low-resolution 3D flow field for those segments that can be used as the initial condition for CFD simulation to reduce the CFD computational time. This framework can be utilized for other types of filters and provides a basis for the design and optimization of fibrous filters.

172 Experimental study on optimum CADR filter thickness of air purifiers

172 Experimental study on optimum CADR filter thickness of air purifiers

Investigation of bidirectional three-phase four-leg converter with LCL filter

A three-phase four-leg bidirectional power converter used as an input stage of an energy storage system using the inductance (L), capacitance (C), and inductance (L) or LCL filter on the grid side is considered. The article provides a variant of the three-phase four-leg bidirectional converter control system implementation based on 3D space vector pulse-width modulation and per-phase voltage control. A brief analysis of the applied control algorithms of the three-phase four-leg bidirectional converter in inverter and rectifier modes is given. A computer model has been built to investigate the operating modes of the converters of the designated class with both balanced and unbalanced load. Studies were carried out by computer modeling methods in order to optimize the parameters of the LCL filter on the grid side with bidirectional energy exchange. Optimal LCL filter parameters and modulation frequencies are determined for the developed converter, providing acceptable quality indicators when operating in bidirectional mode.

Filter Design for Estimation of Stellar Metallicity: Insights from Experiments with Gaia XP Spectra

We search for an optimal filter design for the estimation of stellar metallicity, based on synthetic photometry from Gaia XP spectra convolved with a series of filter-transmission curves defined by different central wavelengths and bandwidths. Unlike previous designs based solely on maximizing metallicity sensitivity, we find that the optimal solution provides a balance between the sensitivity and uncertainty of the spectra. With this optimal filter design, the best precision of metallicity estimates for relatively bright (G ∼ 11.5) stars is excellent, σ [Fe/H] = 0.034 dex for FGK dwarf stars, superior to that obtained utilizing custom sensitivity-optimized filters (e.g., SkyMapper v). By selecting hundreds of high-probability member stars of the open cluster M67, our analysis reveals that the intrinsic photometric-metallicity scatter of these cluster members is only 0.036 dex, consistent with this level of precision. Our results clearly demonstrate that the internal precision of photometric-metallicity estimates can be extremely high, even providing the opportunity to perform chemical tagging for very large numbers of field stars in the Milky Way. This experiment shows that it is crucial to take into account uncertainty alongside the sensitivity when designing filters for measuring the stellar metallicity and other parameters.