Noise Model Research Articles

Tracking control of T-S fuzzy systems under probabilistic constraints and fading channels

This work investigates the probabilistic-constrained tracking control problem for T-S fuzzy systems under fading channels described by the memoryless multiplicative noise model. The main control objective is to confine the tracking error into its pre-given bounds no lower than a certain probability. To this end, a tracking controller is firstly synthesised by introducing the fading parameter as an amplification factor towards ‘retrieving’ the original information to some extent. An auxiliary function and the multi-dimensional Chebyshev inequality make it possible to derive sufficient conditions such that the tracking error falls into its specified domain with a frequency larger than a pre-given value. By employing an inequality involving unmatched membership functions of the controller and fuzzy system, the favourite property of matched membership functions can be employed. A numerical example illustrates the effectiveness of the proposed method.

CryoSamba: self-supervised deep volumetric denoising for cryo-electron tomography data.

Cryogenic electron tomography (cryo-ET) has rapidly advanced as a high-resolution imaging tool for visualizing subcellular structures in 3D with molecular detail. Direct image inspection remains challenging due to inherent low signal-to-noise ratios (SNR). We introduce CryoSamba, a self-supervised deep learning-based model designed for denoising cryo-ET images. CryoSamba enhances single consecutive 2D planes in tomograms by averaging motion-compensated nearby planes through deep learning interpolation, effectively mimicking increased exposure. This approach amplifies coherent signals and reduces high-frequency noise, substantially improving tomogram contrast and SNR. CryoSamba operates on 3D volumes without needing pre-recorded images, synthetic data, labels or annotations, noise models, or paired volumes. CryoSamba suppresses high-frequency information less aggressively than do existing cryo-ET denoising methods, while retaining real information, as shown both by visual inspection and by Fourier shell correlation analysis of icosahedrally symmetric virus particles. Thus, CryoSamba enhances the analytical pipeline for direct 3D tomogram visual interpretation.

Emergence of noise-induced barren plateaus in arbitrary layered noise models

In variational quantum algorithms the parameters of a parameterized quantum circuit are optimized in order to minimize a cost function that encodes the solution of the problem. The barren plateau phenomenon manifests as an exponentially vanishing dependence of the cost function with respect to the variational parameters, and thus hampers the optimization process. We discuss how, and in which sense, the phenomenon of noise-induced barren plateaus emerges in parameterized quantum circuits with a layered noise model. Previous results have shown the existence of noise-induced barren plateaus in the presence of local Pauli noise (Wang et al 2021 Nat. Commun. 12 6961). We extend these results analytically to arbitrary completely-positive trace preserving maps in two cases: (1) when a parameter-shift rule holds, (2) when the parameterized quantum circuit at each layer forms a unitary 2-design. The second example shows how highly expressive unitaries give rise not only to standard barren plateaus (McClean et al 2018 Nat. Commun. 9 4812), but also to noise-induced ones. In the second part of the paper, we study numerically the emergence of noise-induced barren plateaus in QAOA circuits focusing on the case of MaxCut problems on d-regular graphs and amplitude damping noise.

Using synthetic disk-integrated reflectance spectra to constrain direct imaging sensitivity requirements for a Mars-like exoplanet

The 2020 Decadal Survey on Astronomy and Astrophysics 11https://doi.org/10.17226/26141. recommended the prioritization of a space-based telescope capable of directly characterizing Earth-like exoplanets in reflected light. The planned suite of instruments onboard such a mission are expected to provide disk-integrated spectra with moderate spectral resolution and signal-to-noise (SNR). Although the detection and characterization of Earth-like exoplanets remains the primary focus of such a mission, land planets with limited available water, such as Mars, may be much more common. Mars-like exoplanets, therefore, are an equally significant set of targets when investigating the diverse climatologies and potential habitability of other worlds, especially if our own Solar System is any indication of planetary diversity. In this study, we constrain the direct imaging sensitivity requirements for observing and characterizing Mars-like exoplanets with the goal of informing future telescope design and mission planning. Employing an instrument noise model simulating a coronagraph-equipped, space-based telescope, spatially- and spectrally-resolved synthetic observations of Mars are produced. We evaluate the direct imaging sensitivity requirements across a range of wavelengths, from the ultraviolet (UV) to near-infrared (near-IR), to enable the spectral characterization of key atmospheric and surface features from disk-integrated reflectance spectra. Detectability at a given SNR is assessed through optical wavelength integration times for a range of phase angles, host star spectral types, and levels of atmospheric dustiness. Our results indicate that a Decadal-recommended space telescope featuring an aperture of 6-m is likely only proficient in detecting Mars-like exoplanets around K-type stars located within a 10 parsec (pc) radius from Earth. Furthermore, we demonstrate that when integrating over visible and near-IR wavelengths, required exposure times to detect such a planet are reasonable, especially near full phase angles. In the context of upcoming and proposed observatories, such as the Habitable Exoplanet Observatory (HabEx) and Large UV/Optical/IR Surveyor (LUVOIR), our findings provide valuable insights into the direct imaging capabilities and optimal observational strategies needed for detecting and studying Mars-like exoplanets.

Pseudo-ISP: Learning pseudo in-camera signal processing pipeline from a color image denoiser

Existing deep denoisers usually ignore the problem of noise discrepancy between training and test images caused by the different noise modeling of sensor and in-camera signal processing (ISP) pipeline, which inevitably degrades the denoising performance. In this paper, we present an unpaired learning scheme to adapt the color image denoisers for handling test images with noise discrepancy. To this end, we consider a practical training setting equipped with a pre-trained color denoiser, a set of test noisy sRGB images, and an unpaired set of clean sRGB images. Then, we propose to alternate between two modules, i.e., Pseudo-ISP training for learning noise modeling of sensor and in-camera signal processing (ISP) pipeline and denoiser adaption. Instead of modeling the complex noise in sRGB images, we assume the signal-dependent and spatially independent noise in rawRGB space, and specifically design the Pseudo-ISP to learn the pseudo ISP pipeline and pseudo rawRGB noise model jointly. Applying the learned Pseudo-ISP to the unpaired set of clean sRGB images, the corresponding realistic noisy sRGB observations can be easily obtained. Conversely, using the generated paired data for model fine-tuning, the color denoiser can be well adapted for test images. Through iterating between Pseudo-ISP training and denoiser adaption, denoising performance of deep denoisers can be further improved. Experiments show that our Pseudo-ISP not only can boost simple Gaussian blurring-based denoiser to achieve competitive performance against CBDNet, but also is effective in improving state-of-the-art deep denoisers, e.g., CBDNet and RIDNet.

PINT: Maximum-likelihood Estimation of Pulsar Timing Noise Parameters

PINT is a pure-Python framework for high-precision pulsar timing developed on top of widely used and well-tested Python libraries, supporting both interactive and programmatic data analysis workflows. We present a new frequentist framework within PINT to characterize the single-pulsar noise processes present in pulsar timing data sets. This framework enables parameter estimation for both uncorrelated and correlated noise processes, as well as model comparison between different timing and noise models in a computationally inexpensive way. We demonstrate the efficacy of the new framework by applying it to simulated data sets as well as a real data set of PSR B1855+09. We also describe the new features implemented in PINT since it was first described in the literature.

DermoGAN: multi-task cycle generative adversarial networks for unsupervised automatic cell identification on in-vivo reflectance confocal microscopy images of the human epidermis.

Accurate identification of epidermal cells on reflectance confocal microscopy (RCM) images is important in the study of epidermal architecture and topology of both healthy and diseased skin. However, analysis of these images is currently done manually and therefore time-consuming and subject to human error and inter-expert interpretation. It is also hindered by low image quality due to noise and heterogeneity. We aimed to design an automated pipeline for the analysis of the epidermal structure from RCM images. Two attempts have been made at automatically localizing epidermal cells, called keratinocytes, on RCM images: the first is based on a rotationally symmetric error function mask, and the second on cell morphological features. Here, we propose a dual-task network to automatically identify keratinocytes on RCM images. Each task consists of a cycle generative adversarial network. The first task aims to translate real RCM images into binary images, thus learning the noise and texture model of RCM images, whereas the second task maps Gabor-filtered RCM images into binary images, learning the epidermal structure visible on RCM images. The combination of the two tasks allows one task to constrict the solution space of the other, thus improving overall results. We refine our cell identification by applying the pre-trained StarDist algorithm to detect star-convex shapes, thus closing any incomplete membranes and separating neighboring cells. The results are evaluated both on simulated data and manually annotated real RCM data. Accuracy is measured using recall and precision metrics, which is summarized as the -score. We demonstrate that the proposed fully unsupervised method successfully identifies keratinocytes on RCM images of the epidermis, with an accuracy on par with experts' cell identification, is not constrained by limited available annotated data, and can be extended to images acquired using various imaging techniques without retraining.

Dynamical system identification, model selection, and model uncertainty quantification by Bayesian inference.

This study presents a Bayesian maximum a posteriori (MAP) framework for dynamical system identification from time-series data. This is shown to be equivalent to a generalized Tikhonov regularization, providing a rational justification for the choice of the residual and regularization terms, respectively, from the negative logarithms of the likelihood and prior distributions. In addition to the estimation of model coefficients, the Bayesian interpretation gives access to the full apparatus for Bayesian inference, including the ranking of models, the quantification of model uncertainties, and the estimation of unknown (nuisance) hyperparameters. Two Bayesian algorithms, joint MAP and variational Bayesian approximation, are compared to the least absolute shrinkage and selection operator (LASSO), ridge regression, and the sparse identification of nonlinear dynamics (SINDy) algorithms for sparse regression by application to several dynamical systems with added Gaussian or Laplace noise. For multivariate Gaussian likelihood and prior distributions, the Bayesian formulation gives Gaussian posterior and evidence distributions, in which the numerator terms can be expressed in terms of the Mahalanobis distance or "Gaussian norm" ||y-y^||M-12=(y-y^)⊤M-1(y-y^), where y is a vector variable, y^ is its estimator, and M is the covariance matrix. The posterior Gaussian norm is shown to provide a robust metric for quantitative model selection for the different systems and noise models examined.

Analisis Hasil Safire pada Imaging CT Scan Kepala

Background: Iterative Reconstruction (IR) method was first applied to CT in 1960 and successfully used for the first time in clinical research by reconstructing 128 x 128 images according to image metrics and using high-resolution images of 512 x 512 for special research activities such as image evaluation. artifacts and noise. In 2008, the development of IR can improve image quality and reduce the amount of radiation in clinical CT diagnosis. Iterative reconstruction promises to improve image quality while reducing radiation dose. This has been demonstrated in CT of the thorax, coronary arteries, abdomen, spine and neck, paranasal sinuses, and head. Sinogram-Afirmed Iterative Reconstruction (SAFIRE) is one of the iterative algorithm reconstruction methods that uses noise modeling techniques, Sinogram-Afirmed Iterative Reconstruction (SAFIRE), promises to improve Cranial CT (CCT). In this new technique, raw data-based iteration for artifact reduction is combined with image-based iteration using smooth regularization that estimates the variance of image noise in various directions at each image pixel and adjusts it with a spatial variance regularization function simultaneously. Methods: This study is a literature review, where literature exploration is carried out on various databases with keywords such as, Reference sources used in compiling this article include google scollar, as well as articles in English and Indonesian scientific journals. Results: Itarative Reconstruction (IR) Head CT Scan, SAFIRE includes reducing or adding noise to the image results, artifacts, acquisition time, increasing SNR and CNR and reducing dose in the examination. Conclusion: Analysis of Safire results in Head CT-Scan Imaging has an Itarative Reconstruction (SAFIRE) procedure, the role of safire in head CT scans is to optimize noise in the Reconstructed image and can reduce artifacts in the image and increase SNR, CNR in the Reconstructed results so that it can provide better information.

Context-dependence of deterministic and nondeterministic contributions to closed-loop steering control.

In natural circumstances, sensory systems operate in a closed loop with motor output, whereby actions shape subsequent sensory experiences. A prime example of this is the sensorimotor processing required to align one's direction of travel, or heading, with one's goal, a behavior we refer to as steering. In steering, motor outputs work to eliminate errors between the direction of heading and the goal, modifying subsequent errors in the process. The closed-loop nature of the behavior makes it challenging to determine how deterministic and nondeterministic processes contribute to behavior. We overcome this by applying a nonparametric, linear kernel-based analysis to behavioral data of monkeys steering through a virtual environment in two experimental contexts. In a given context, the results were consistent with previous work that described the transformation as a second-order linear system. Classically, the parameters of such second-order models are associated with physical properties of the limb such as viscosity and stiffness that are commonly assumed to be approximately constant. By contrast, we found that the fit kernels differed strongly across tasks in these and other parameters, suggesting context-dependent changes in neural and biomechanical processes. We additionally fit residuals to a simple noise model and found that the form of the noise was highly conserved across both contexts and animals. Strikingly, the fitted noise also closely matched that found previously in a human steering task. Altogether, this work presents a kernel-based analysis that characterizes the context-dependence of deterministic and non-deterministic components of a closed-loop sensorimotor task.

Noise barriers as a mitigation measure for highway traffic noise: Empirical evidence from three study cases

Noise barriers are path interventions between noise sources and human receivers used mainly along road corridors to improve the acoustic environment for affected residents. Despite their widespread use, the impact of these interventions on community perception is still insufficiently investigated. This paper presents findings from a longitudinal study evaluating the efficacy of noise barriers in three residential areas alongside highways, compared to a reference case in a relatively quiet area. Noise exposure was objectively quantified via acoustic measurements and noise modelling, while socio-acoustic surveys measured the residents' subjective response in terms of noise annoyance as well as other aspects of quality of life. While noise exposure (Lday) decreased on average by 4.4–11.7 dBA at near-barrier points, direct reductions in pre to post-intervention noise annoyance were observed only in one case. Additionally, only in this particular case were the appraisals of the acoustic environment restored to a condition similar to low-level noise emissions (reference case). Contextual factors potentially downgrading the interventions' effectiveness are discussed, such as the history of complaints and coping, mistrust towards road authorities, high expectations, and the impacts of the COVID-19 pandemic. While noise exposure reductions did not directly lead to noise annoyance decreases, an ordinal regression pooling all cases revealed that larger reductions in noise exposure were associated with a higher likelihood of residents reporting decreased traffic noise annoyance in the post-survey. No evidence was found regarding noise barriers’ impact on the subjective assessment of other aspects of quality of life, such as health complaints, concentration disturbance, and sleep quality.

Visual processing and decision-making in autism and dyslexia: Insights from cross-syndrome approaches.

Atypical visual processing has been reported in developmental conditions like autism and dyslexia, and some accounts propose a causal role for visual processing in the development of these conditions. However, few studies make direct comparisons between conditions, or use sufficiently sensitive methods, meaning that it is hard to say whether atypical visual processing tells us anything specific about these conditions, or whether it reflects a more general marker of atypical development. Here I review findings from two computational modelling approaches (equivalent noise and diffusion modelling) and related electroencephalography (EEG) indices which we have applied to data from autistic, dyslexic and typically developing children to reveal how the component processes involved in visual processing and decision-making are altered in autism and dyslexia. The results identify both areas of convergence and divergence in autistic and dyslexic children's visual processing and decision-making, with implications for influential theoretical accounts such as weak central coherence, increased internal noise, and dorsal-stream vulnerability. In both sets of studies, we also see considerable variability across children in all three groups. To better understand this variability, and further understand the convergence and divergence identified between conditions, future studies would benefit from studying how the component processes reviewed here relate to transdiagnostic dimensions, which will also give insights into individual differences in visual processing and decision-making more generally.

Adaptive Bregman–Kaczmarz: an approach to solve linear inverse problems with independent noise exactly

We consider the block Bregman–Kaczmarz method for finite dimensional linear inverse problems. The block Bregman–Kaczmarz method uses blocks of the linear system and performs iterative steps with these blocks only. We assume a noise model that we call independent noise, i.e. each time the method performs a step for some block, one obtains a noisy sample of the respective part of the right-hand side which is contaminated with new noise that is independent of all previous steps of the method. One can view these noise models as making a fresh noisy measurement of the respective block each time it is used. In this framework, we are able to show that a well-chosen adaptive stepsize of the block Bregman–Kaczmarz method is able to converge to the exact solution of the linear inverse problem. The plain form of this adaptive stepsize relies on unknown quantities (like the Bregman distance to the solution), but we show a way how these quantities can be estimated purely from given data. We illustrate the finding in numerical experiments and confirm that these heuristic estimates lead to effective stepsizes.

Leaf functional trait evolution and its putative climatic drivers in African Coffea species.

Leaf traits are known to be strong predictors of plant performance and can be expected to (co)vary along environmental gradients. We investigated the variation, integration, environmental relationships, and evolutionary history of leaf functional traits in the genus Coffea L., typically a rainforest understory shrub, across Africa. A better understanding of the adaptive processes involved in leaf trait evolution can inform the use and conservation of coffee genetic resources in a changing climate. We used phylogenetic comparative methods to investigate the evolution of six leaf traits measured from herbarium specimens of 58 African Coffea species. We added environmental data and data on maximum plant height for each species to test trait-environment correlations in various (sub)clades, and we compared continuous trait evolution models to identify variables driving trait diversification. A substantial leaf trait variation was detected across the genus Coffea in Africa, which was mostly interspecific. Of these traits, stomatal size and stomatal density exhibited a clear trade-off. We observed low densities of large stomata in early branching lineages and higher densities of smaller stomata in more recent taxa, which we hypothesise to be related to declining CO2 levels since the mid-Miocene. Brownian Motion evolution was rejected in favour of White Noise or Ornstein-Uhlenbeck models for all traits, implying these traits are adaptively significant rather than driven by pure drift. The evolution of leaf area was likely driven by precipitation, with smaller leaves in dryer climates across the genus. Generally, Coffea leaf traits appear to be evolutionarily labile and governed by stabilising selection, though evolutionary patterns and correlations differ depending on the traits and clades considered. Our study highlights the importance of a phylogenetic perspective when studying trait relationships across related taxa, as well as the consideration of various taxonomic ranges.

Exploring multi-pollution variability in the urban environment: geospatial AI-driven modeling of air and noise

ABSTRACT This study addresses the critical need for comprehensive multi-pollution modeling in urban environments by employing Geospatial Artificial Intelligence (GeoAI) techniques. Specifically, it aims to elucidate the variability of air and noise pollution levels in Tehran, Iran, and develop precise multi-pollution susceptibility maps. A spatial database was compiled, encompassing annual average data (2019–2022) of the Air Quality Index (AQI) and Equivalent Continuous Sound Level (Leq), along with 19 influential factors related to both pollutants. The study utilized the CatBoost machine learning algorithm, enhanced with Grey Wolf Optimizer (GWO) and Harris Hawks Optimization (HHO) algorithms, to model and predict pollution patterns. Key quantitative achievements include a remarkable 15% reduction in Root Mean Square Error (RMSE) for air pollution and a 12% reduction in noise pollution when using the CatBoost-HHO configuration compared to the standalone CatBoost algorithm. Validation of the multi-pollution maps utilizing the Area Under the Curve (AUC) analysis showed high accuracy, with the CatBoost-HHO achieving AUC values of 0.943 for air pollution and 0.936 for noise pollution, outperforming CatBoost-GWO and standalone CatBoost models. These results underscore the efficacy of our approach in accurately identifying and mapping multi-pollution hotspots, contributing valuable insights for urban environmental management and public health preservation.

HRMF-DRP: A next-generation solution for overcoming provisioning challenges in cloud environments

The cloud computing infrastructure is a distributed environment and the existing research works have some provisioning problems such as suboptimal resource utilization and high execution time. The Heterogeneity Resource Management Framework for Dynamic Resource Provisioning (HRMF-DRP) is proposed for focusing on task scheduling and workload management. This framework incorporates advanced algorithms for dataset preprocessing, task clustering, workload prediction, and dynamic resource provisioning. For data preprocessing, the real-world workload traces were captured from the Planet Lab dataset that are taken as input for the preprocessing stage. The data preprocessing is responsible for ensuring data quality and reliability by using different models like missing data handling, outlier detection and removal as well as standardization and normalization. In this paper, the tasks are grouped into clusters by utilizing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model and this model categorizes the data points into border points, core points and noise points based on their density. The temporal dependencies are captured for the workload prediction by using Long Short-Term Memory (LSTM) neural network model. A Gaussian Mixture Model (GMM) model is responsible for estimating the number of Virtual machines (VMs) present in the workload prediction process. The Self-Adaptive Genetic Algorithm (SAGA) is implemented for task mapping that adjusts the parameters to change workload patterns for contributing adaptability and robustness. The different experimental evaluations are conducted based on the task completion time, workload balance index, resource utilization efficiency and workload prediction accuracy. The proposed model achieved the workload prediction accuracy of 98.5%, cost of $89.6, execution time of 125ms, Task Completion Time (TCT) of 40ms, Workload Balance Index (WBI) of 0.96 and Resource Utilization Efficiency (RUE) of 0.93. The quantitative results collectively position HRMF-DRP as a practical and efficient solution, promising advancements in dynamic resource provisioning for cloud computing, particularly within the Infrastructure as a Service (IaaS) cloud model.

Learning real-world heterogeneous noise models with a benchmark dataset

Noise modeling is an important research field in computer vision; the design of an accurate model for imaging sensor noise depends on not only a comprehensive benchmark dataset of the real world, but also a precise design of the noise modeling algorithm. However, due to the inaccurate estimation method of noise-free images and limited shooting scenes, the current realistic datasets could not describe the diverse noise properties sufficiently. Moreover, popular parametric noise models are not sophisticated enough to characterize the real-world noise exactly. In this work, we first construct a more comprehensive dataset of the real world by capturing more indoor and outdoor scenes under different lighting conditions using diverse smartphones, then we propose a non-parametric noise estimation method capable of modeling the spatial heterogeneity of real-world noise patterns. Specifically, in order to characterize the spatial heterogeneity of real-world noise, we assume a non-i.i.d Gaussian distribution and propose a deep convolutional neural network (DCNN)-based approach for learning pixel-wise noise variance maps. To learn the pixel-wise variance map, we have constructed a variance estimation network mapping from the conditional signals (clean image, ISO, and camera model) to surrogate labels obtained from the nonlocal search of similar patches from the clean-noisy image pair. Finally, we conducted denoising and classification experiments using different kinds of simulated noisy images, compared to the Poisson-Gaussian and Noise Flow noise models, the proposed method achieves denoising performance improvements (PSNR) of 1.13 dB and 2.51 dB respectively on the proposed real-world test dataset, denoising and classification results on the real noisy data captured by mobile phones have verified that our approach is more accurate than current noise modeling methods.

Normal-skew mixture-based robust probability hypothesis density filter under unknown statistical properties of noise

In multi-target tracking (MTT), the statistical properties of noise in real-world scenarios are often unknown. When noise modeling does not align with the actual noise, it can lead to inaccurate estimations of the number and locations of targets. To address this issue, we model the noise as a normal-skewed mixture (NSM) distribution (NSMD), comprising a linear combination of a normal distribution (ND) and a Gaussian scale distribution (GSD). By varying the parameters of the NSMD, it can fit arbitrary normal and/or heavy-tailed, and/or skewed nonsmooth noise. To enable the NSMD to adaptively fit noise with unknown statistical properties, we introduce a hierarchical model and a variational Bayesian (VB) approach to adjust the shape of the NSMD. The marginal likelihood function is then derived for filtering updates. Based on the NSMD and the marginal likelihood function, we propose a robust NSM-based probabilistic hypothesis density (NSM-PHD) filter to achieve improved MTT accuracy when noise statistical characteristics are unknown. Simulation results demonstrate that the NSM-PHD effectively enhances MTT accuracy under conditions of unknown noise statistical properties.

Hyperspectral Image Denoising by Pixel-Wise Noise Modeling and TV-Oriented Deep Image Prior

Model-based hyperspectral image (HSI) denoising methods have attracted continuous attention in the past decades, due to their effectiveness and interpretability. In this work, we aim at advancing model-based HSI denoising, through sophisticated investigation for both the fidelity and regularization terms, or correspondingly noise and prior, by virtue of several recently developed techniques. Specifically, we formulate a novel unified probabilistic model for the HSI denoising task, within which the noise is assumed as pixel-wise non-independent and identically distributed (non-i.i.d) Gaussian predicted by a pre-trained neural network, and the prior for the HSI image is designed by incorporating the deep image prior (DIP) with total variation (TV) and spatio-spectral TV. To solve the resulted maximum a posteriori (MAP) estimation problem, we design a Monte Carlo Expectation–Maximization (MCEM) algorithm, in which the stochastic gradient Langevin dynamics (SGLD) method is used for computing the E-step, and the alternative direction method of multipliers (ADMM) is adopted for solving the optimization in the M-step. Experiments on both synthetic and real noisy HSI datasets have been conducted to verify the effectiveness of the proposed method.

Supervised Factor Analysis Transfer: Calibration transfer with noise modeling and response variable integration

Multivariate calibration models often encounter challenges in extrapolating beyond the calibration instruments due to variations in hardware configurations, signal processing algorithms, or environmental conditions. Calibration transfer techniques have been developed to mitigate this issue. In this study, we introduce a novel methodology known as Supervised Factor Analysis Transfer (SFAT) aimed at achieving robust and interpretable calibration transfer. SFAT operates from a probabilistic framework and integrates response variables into its transfer process to effectively align data from the target instrument to that of the source instrument. Within the SFAT model, the data from the source instrument, the target instrument, and the response variables are collectively projected onto a shared set of latent variables. These latent variables serve as the conduit for information transfer between the three distinct domains, thereby facilitating effective spectra transfer. Moreover, SFAT explicitly models the noise variances associated with each variable, thereby minimizing the transfer of non-informative noise. Furthermore, we provide empirical evidence showcasing the efficacy of SFAT across three real-world datasets, demonstrating its superior performance in calibration transfer scenarios.