Search arXiv⌕ Search

arXiv subjects

Andrei Velichko

Publications and source records attributed to Andrei Velichko.

At least 19 recordsLinked to original sources
arXiv2026

Entropy-map SSIM analysis of Salt and Pepper Noise Removal via Recursive Median Filterring

This paper studies the removal of salt-and-pepper (SP) noise from grayscale images using a median filter (MF) within a recursive thresholding algorithm. Denoising performance is assessed using two complementary metrics: SSIM-Img and SSIM-Map.SSIM-Img is standard Image Quality Assessment (IQA), the conventional Structural Similarity Index (SSIM) computed between the restored and clean images. SSIM-Map is novel IQA, an SSIM-based evaluation computed between entropy maps of these images, where the maps are obtained using singular value-decomposition entropy in sliding windows. We show that SSIM-Map is more sensitive to residual impulse artifacts, blur, and local intensity transitions, and therefore complements the conventional SSIM-Img metric.

eess.IV↗
arXiv2026

Equation-Free Screening of Mittag-Leffler-Compatible Dynamics from Scalar Time Series via kNN Multi-Horizon Profiles

Fractional models provide a natural description of systems with memory, but a noninteger derivative should not be introduced solely because a time series is curved or slowly relaxing. We develop an equation-free preliminary screening framework that asks whether a scalar time series produces a multi-horizon k-nearest-neighbor (kNN) profile more compatible with Mittag-Leffler-type behavior than with selected conventional alternatives. In an ideal matched Caputo-relaxation benchmark, the complete generation-kNN-profile-model-comparison pipeline reproduces the expected Mittag-Leffler geometry and recovers the generating order to within approximately $10^{-3}$; this is interpreted as controlled calibration rather than as general fractional-order identification. Under 3% trajectory-specific observational noise, the held-out Mittag-Leffler preference is most consistent when the generating dynamics are well separated from the integer-order limit and becomes progressively less decisive as $α\rightarrow1$. The fitted order $α_{\mathrm{fit}}$, however, shows substantially larger realization-to-realization variability. Thus, relative model compatibility is more robust than single-realization order estimation in the present noisy benchmark. Noise-free nonfractional controls show a separate limitation of specificity: a stretched exponential can generate a strongly Mittag-Leffler-compatible profile, whereas inclusion of the generating rational/Hill family recovers that family and its parameters to numerical precision in the matched setting. A positive Mittag-Leffler-versus-exponential screen therefore does not uniquely establish fractional origin. A fractional chaotic system is treated only as an exploratory extension: the Mittag-Leffler growth family gives lower finite-window RMSE than exponential and logistic/saturating alternatives over the detected pre-transition interval.

math.DS↗
arXiv2026

State-specific respiratory signatures for affective and stress recognition: Interpretable respiratory markers, autocorrelation lags, and compact CNN models

Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition, yet many studies emphasize classification accuracy without identifying which respiratory properties separate different states. Using the chest respiratory channel of the WESAD dataset, we analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal one-dimensional convolutional neural networks (1D-CNNs) and physically grouped handcrafted respiratory signatures. The primary task is stress versus non-stress detection, while baseline, stress, amusement, and meditation are additionally analyzed in a one-vs-rest setting to reveal state-specific respiratory markers. The feature space is organized into respiratory timing, breath-to-breath variability, waveform statistics, spectral/time-frequency descriptors, and autocorrelation/nonlinear predictability descriptors, with the raw 60 s signal treated as a sixth representation for the CNN branch. We introduce autocorrelation transition lags (Zpm/Zmp) as interpretable markers of respiratory correlation scale and separately evaluate exploratory forecast-error-growth/Lyapunov-like descriptors. In the final CNN refit setting, the raw-signal model achieved the strongest stress-vs-rest performance (accuracy 96.72%, macro-F1 95.30%, MCC 90.61%). In contrast, compact feature models were stronger for baseline (MCC 65.34%), amusement (MCC 35.69%), and especially meditation (MCC 88.65%). Strict nested reanalysis of the auxiliary Top-20 stress search yielded mean MCC=82.29% versus 85.45% originally, indicating modest selection optimism. These results show that CNNs are most useful for the practical stress detector, whereas interpretable respiratory signatures provide stronger and more physiologically transparent state-specific markers for several non-stress conditions.

eess.SP↗
arXiv2026

Local SVD-Entropy Maps as a Complementary Structural Representation for Full-Reference and No-Reference Image Quality Assessment

We investigate a local spectral-complexity representation for perceptual image quality assessment (IQA) based on Shannon entropy of singular values computed directly from two-dimensional image patches. For each $3\times3$-pixel grayscale patch, SVD is applied directly and the normalized singular-value entropy defines one HSVD-map value. The construction requires neither flattening nor delay embedding, uses no boundary padding, and is invariant to $90^{\circ}$ rotations and mirror reflections at the local-descriptor level. A nested salt-and-pepper experiment on Lena separates absolute similarity to a clean reference from sensitivity to an additional degradation step. HSVD-SSIM responds more strongly to local corruption and retains a larger neighboring-state response at severe noise levels. Validation on all 10,125 distorted KADID-10k images shows that HSVD-SSIM is weaker than conventional SSIM as a standalone full-reference metric (SRCC $0.450$ vs. $0.619$), but complementary when combined with it: grouped cross-validation increases SRCC from $0.618$ to $0.659$, with a bootstrap 95\% confidence interval of $[0.036,0.046]$ for the gain. In a no-reference experiment, adding HSVD-derived single-image descriptors improves the best nonlinear model from SRCC $0.528$ to $0.575$ (95\% CI $[0.033,0.061]$) and also improves prediction of quality changes between neighboring distortion states. These results support direct local SVD entropy as an interpretable structural channel that complements conventional image-domain similarity and remains informative without a pristine reference.

eess.IV↗
arXiv2026

Data-Driven Characterisation of Wave-Forced Turbulence Using Time-Resolved Forecast-Error Growth

Periodic surface-wave forcing can reorganise turbulent flows through coherent spectral response, synchronization, intermittency, and changes in short-term predictability, so its dynamical effect need not vary monotonically with forcing frequency. We reanalyse laboratory acoustic Doppler velocimetry records obtained at constant discharge under four conditions (0, 0.5, 0.67, and 1~Hz) using one common KNN--GMAE forecast-error-growth protocol. A distance-weighted $k$-nearest-neighbour predictor generates out-of-sample forecasts over multiple horizons, and the slope of the early quasi-linear region of $\ln(\mathrm{GMAE})$ versus physical forecast time is reported as a finite-horizon forecast-error-growth rate, $\lFEG$. For the full 120-s records, $\lFEG$ is 5.68, 0.85, 3.39, and 4.11~s$^{-1}$ for 0, 0.5, 0.67, and 1~Hz, respectively. The ordering 0~Hz $>$ 1~Hz $>$ 0.67~Hz $>$ 0.5~Hz is preserved in all seven nearby parameter configurations, indicating that the comparative result is not an artefact of a single KNN setting. A 40-s sliding-window analysis with a 10-s step reveals substantial temporal structure. The no-wave condition remains predominantly high and the 0.5-Hz condition predominantly low, whereas the 1-Hz record has weaker local support for a single exponential-growth regime: only 3 of 9 windows satisfy the adopted early-fit criterion $\RFEG\geq0.90$, compared with 8/9, 7/9, and 7/9 for 0, 0.5, and 0.67~Hz.

nlin.CD↗
arXiv2026

Noise-Induced Predictability Redistribution Across Forecast Horizons of Extreme Events in Chaotic Dynamics

Extreme events (EEs) in chaotic dynamics are rare broad excursions whose forecastability can be altered by dynamical noise. We investigate how noise changes EE occurrence and prediction skill across forecast horizons in a third-order autonomous chaotic flow. A single clean-data threshold is frozen for all realizations, broad events are defined by one maximum per excursion, and a future window W=15 is predicted from a 15-time-unit history using HistGradientBoosting with chronological data separation. As the forecast gap G between the observed history and the future event window increases, the clean Matthews correlation coefficient (MCC) decreases from 0.641 at G=0 to 0.165 at G=15. Noise dependence is evaluated with ten paired realizations at eight amplitudes. The mean short-horizon score increases from 0.456 in clean data to 0.546 at sigma=0.007; the paired gain is 0.0895 (95% CI 0.0494-0.1295; Holm-adjusted p=0.0234). Noise strongly increases EE occurrence while event amplitude and width remain comparatively stable. Equalizing positive training counts across noise levels substantially attenuates the short-horizon gain, whereas strong noise reduces intermediate-horizon skill. We term this horizon-dependent, nonuniform change in forecast skill noise-induced predictability redistribution (NIPR).

nlin.CD↗
arXiv2026

When More Data Become Less Informative: Finite-Precision Periodicization and Collapse of Forecast-Error Lyapunov Estimates

Largest Lyapunov exponents (LLEs) quantify exponential sensitivity, but data-driven estimates are often obtained from finite-precision trajectories. We show that increasing the length of a single reduced-precision chaotic record can eventually degrade a forecast-error LLE estimate. Using the logistic map at r=4, an ESP32 single-precision trajectory is reproduced bit-for-bit by NumPy float32. Across 10,000 random float32 initial conditions, every trajectory reaches an exact recurrence before iteration 7612. For one long float32 record, the estimated LLE changes from 0.6853 at N=15,000 to 0.1827 at N=20,000 and approximately zero at N=30,000 as exact train-test histories saturate. At N=100,000, the long float32 record gives 0.0016, whereas independently restarted length-100 trajectories give 0.6917; matched float64 controls remain near ln(2)=0.6931. The collapse is reproduced for 28 representative initial conditions, and its onset is strongly correlated with the recurrence scale set by transient length and digital period (Pearson r=0.982). Thus, finite-state recurrence can turn additional samples into duplicate futures rather than new dynamical information, while independent restarts substantially delay this saturation.

nlin.CD↗
arXiv2026

Cross-Sectional Separability versus Longitudinal Response in Short-Record Parkinsonian Gait Analysis Using FEG-Pro: Nordic Walking and Adapted Physical Activity

\textbf{Objective:} Machine-learning separation of rehabilitation cohorts does not inherently establish a differential intervention response. This study used Forecast-Error Growth Profiling (FEG-Pro) to distinguish cross-sectional cohort separability from subject-level longitudinal change following Nordic Walking (NW) and Adapted Physical Activity (APA) in Parkinson's disease. \textbf{Methods:} Publicly available short gait records from 24 participants (NW=14, APA=10) were analyzed. Lower-limb signals at baseline and 12 weeks were transformed into FEG-Pro and Forecast-Error Distribution Entropy descriptors. We compared individual change scores ($Δ=T1-T0$) between groups using baseline-adjusted sensitivity analyses and false-discovery-rate (FDR) correction. Additionally, a fully nested machine-learning pipeline evaluated whether multidimensional change vectors could identify the intervention. \textbf{Results:} The self-selected cohorts already differed clinically at baseline. Among 1,098 extracted features, none exhibited robust between-group differences in longitudinal change after FDR correction or baseline adjustment. Furthermore, nested classification based on multidimensional change vectors failed to perform above chance (mean MCC = $-0.178 \pm 0.228$). In contrast, exploratory cross-sectional models separated the cohorts with peak MCC values of 0.604 at baseline and 0.554 post-intervention. \textbf{Conclusion:} This cohort did not provide robust evidence of modality-specific longitudinal responses to NW or APA. These findings demonstrate that cross-sectional separability of self-selected cohorts must not be interpreted as an intervention effect; true rehabilitation biomarkers require subject-level longitudinal validation, baseline adjustment, and leakage-safe evaluation.

eess.SP↗
arXiv2026

Equation-Free Period-Aware Forecast-Error Contraction for Estimating Negative Largest Lyapunov Exponents from Short Trajectory Ensembles

Estimating positive largest Lyapunov exponents from data is comparatively natural because neighboring trajectories separate, whereas stable dynamics require resolving contraction before measurement noise or finite precision erases the signal. We introduce a period-aware forecast-error contraction procedure for estimating a dominant negative Lyapunov exponent from ensembles of short scalar trajectories without using governing equations or an analytical Jacobian. A k-nearest-neighbor predictor is trained on trajectory histories, the geometric-mean absolute forecast error is evaluated at phase-consistent horizons, and the exponent is obtained from the slope of the logarithmic error profile. Unlike data-driven approaches that reconstruct local evolution matrices or differentiate a learned surrogate, the proposed method extracts the contraction rate directly from out-of-sample forecast errors. Two adaptations are essential: the forecast step is synchronized with the detected orbit period, and candidate slopes are accepted only when they form a stable consensus across several transient lengths. On the logistic map, the method recovers 92 of 112 negative-exponent parameter values with a mean absolute error of 0.0253 and $R^2=0.886$. On a two-dimensional map without fixed points, independent scalar pipelines based on the three observables $x_n$, $y_n$, and $z_n$ give mean absolute errors of 0.00879--0.01145 and $R^2=0.983$--$0.986$. Because the estimation stage uses only observed trajectories, the framework provides a basis for repeated-relaxation experiments in which short sensor responses are available but the governing equations and analytical Jacobian are unknown. Experimental validation remains a subject of future work.

nlin.CD↗
arXiv2026

Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series

Detecting transient chaos from scalar observations without governing equations represents a fundamental challenge in nonlinear dynamics. We propose a geometry-guided machine learning framework that unifies predictive trajectory divergence with macroscopic attractor morphology to track abrupt regime shifts. The methodology extracts a local instability scale via out-of-sample k-nearest neighbor forecast errors to establish the ML-FTLE estimator, subsequently mapping this temporal divergence onto a structural closeness matrix derived from a minimal dictionary of Poincare occupancy grids. By employing partial least squares regression, we extract a latent geometric component calibrated directly to the empirical finite-time Lyapunov spectrum, yielding the Poincare-based geometric-guided FTLE. Validation against analytical QR-FTLE baselines confirms that fusing topological state spaces with predictive divergence systematically improves continuous transition tracking. The Structural Similarity Index optimally resolves gradual damping, while Hausdorff Distance exhibits extreme resilience during abrupt phase-space collapses. Furthermore, macroscopic spatial discretization acts as a robust topological regularizer against additive Gaussian noise, preserving deterministic signatures even at moderate signal thresholds. This equation-free framework provides a highly accurate, noise-resilient diagnostic for monitoring structural transitions in complex non-stationary systems.

nlin.CD↗
arXiv2026

Local Lyapunov analysis via micro-ensembles: finite-time Lyapunov exponent estimation and KNN-based predictive comparison in complex-valued BAM neural networks

Complex-valued bidirectional associative memory (BAM) neural networks with fractional-order dynamics and delays can exhibit transient instabilities that degrade synchronization and short-horizon predictability. This paper develops a unified analytical and data-driven framework to assess stability, synchronization, and predictability in such networks. First, using Caputo fractional calculus and Lyapunov-Mittag-Leffler techniques, we derive sufficient conditions for global Mittag-Leffler synchronization of a drive-response BAM pair under a linear error-feedback controller and obtain an explicit time-to-tolerance bound. Second, to quantify local transient instability from finite trajectory data, we propose a micro-ensemble finite-time Lyapunov exponent (FTLE) estimator based on the geometric-mean growth of small perturbations over short windows, avoiding variational equations. We further introduce k-nearest-neighbor prediction-error Lyapunov proxies, including full-state and modulus-based variants, to connect local instability to forecasting performance. Numerical experiments on fractional-order complex-valued BAM benchmarks confirm effective synchronization under the proposed control and demonstrate a clear correspondence between FTLE levels and prediction errors. The resulting framework provides practical and reproducible diagnostics for complex-valued neural systems in data-limited settings.

nlin.CD↗
arXiv2026

FEG-Pro: Forecast-Error Growth Profiling for Finite-Horizon Instability Analysis of Nonlinear Time Series

Estimating the largest Lyapunov exponent from a scalar time series is difficult when the governing equations, tangent dynamics, and full state vector are unavailable. We propose FEG-Pro, a forecast-error growth profiling framework for nonlinear scalar time series. The method constructs autocorrelation-guided sparse histories, performs distance-weighted k-nearest-neighbor multi-horizon forecasting, and analyzes the logarithmic growth of geometrically averaged forecast errors. Its primary output is the finite-horizon forecast-error growth slope, lambda_FEG. When the error-growth curve supports a quasi-linear regime, this slope can be compared with reference largest Lyapunov exponents as an estimate of the dominant instability rate. The same pipeline also extracts the formal fit-selection regime, curvature, residual roughness after quadratic detrending, monotonicity, and forecast-error distribution entropy (FEDE) from signed multi-horizon errors. These secondary descriptors are intended not only as diagnostic controls for the slope, but also as candidate machine-learning features for nonlinear signal analysis, because they encode profile geometry and distributional uncertainty not captured by lambda_FEG alone. We evaluate the method on chaotic maps, Mackey-Glass delay dynamics, and scalar Lorenz-63 observables with known or reference exponents. Full-record experiments show good agreement in quasi-linear cases and meaningful curve-shape information in curved or weak profiles. A dyadic length-halving experiment on representative logistic, Mackey-Glass, and Lorenz records shows that residual roughness and mean FEDE often change monotonically and remain interpretable as record length decreases, even when the slope becomes biased or highly variable. The results support treating forecast-error growth as a structured profile and feature-generation framework rather than a single-number estimator.

nlin.CD↗
arXiv2026

Imaging Exploration of Molecular Subtypes in Tongue Squamous Cell Carcinoma

Tongue squamous cell carcinoma (TSCC) is an aggressive malignancy with marked biological heterogeneity and variable clinical outcomes. Although molecular profiling has improved understanding of TSCC heterogeneity, its clinical use remains constrained by invasive tissue sampling and limited representation of whole-tumor spatial complexity. Meanwhile, most radiomics studies in TSCC have focused on downstream clinical endpoints, and whether imaging can non-invasively reflect intrinsic molecular subtypes remains unclear. In this study, an integrated transcriptomic-radiomics framework was used to investigate the relationship between preoperative imaging phenotypes and molecular subtypes in TSCC. Transcriptomic data from 60 TSCC cases in The Cancer Genome Atlas were analyzed using unsupervised consensus clustering, followed by differential expression and functional enrichment analyses. Matched preoperative imaging data from The Cancer Imaging Archive were manually annotated for primary tumor regions, and radiomic features were extracted using PyRadiomics; group differences were assessed with the U-test. Two stable molecular subtypes, C1 and C2, were identified. Their biological differences were mainly associated with squamous epithelial differentiation, inflammatory signaling, and lipid metabolism, with C2 showing greater enrichment of immune-related pathways. In addition, 10 radiomic features differed significantly between the two subtypes, mainly wavelet-derived texture features from gray-level size zone, dependence, co-occurrence, and run length matrices (P=0.00202-0.0162). These findings support the potential of radiomics as a non-invasive approach for characterizing molecular heterogeneity in TSCC and provide an initial radiogenomic framework for biologically informed preoperative assessment.

q-bio.GN↗
arXiv2026

Interpretable AI-Assisted Early Reliability Prediction for a Two-Parameter Parallel Root-Finding Scheme

We propose an interpretable AI-assisted reliability diagnostic framework for parameterized root-finding schemes based on kNN-LLE proxy stability profiling and multi-horizon early prediction. The approach augments a numerical solver with a lightweight predictive layer that estimates solver reliability from short prefixes of iteration dynamics, enabling early identification of stable and unstable parameter regimes. For each configuration in the parameter space, raw and smoothed proxy profiles of a largest Lyapunov exponent (LLE) estimator are constructed, from which contractivity-based reliability scores summarizing finite-time convergence are derived. Machine learning models predict the reliability score from early segments of the proxy profile, allowing the framework to determine when solver dynamics become diagnostically informative. Experiments on a two-parameter parallel root-finding scheme show reliable prediction after only a few iterations: the best models achieve R^2=0.48 at horizon T=1, improve to R^2=0.67 by T=3, and exceed R^2=0.89 before the characteristic minimum-location scale of the stability profile. Prediction accuracy increases to R^2=0.96 at larger horizons, with mean absolute errors around 0.03, while inference costs remain negligible (microseconds per sample). The framework provides interpretable stability indicators and supports early decisions during solver execution, such as continuing, restarting, or adjusting parameters.

math.NA↗
arXiv2026

Optimizing Parallel Schemes with Lyapunov Exponents and kNN-LLE Estimation

Inverse parallel schemes remain indispensable tools for computing the roots of nonlinear systems, yet their dynamical behavior can be unexpectedly rich, ranging from strong contraction to oscillatory or chaotic transients depending on the choice of algorithmic parameters and initial states. A unified analytical-data-driven methodology for identifying, measuring, and reducing such instabilities in a family of uni-parametric inverse parallel solvers is presented in this study. On the theoretical side, we derive stability and bifurcation characterizations of the underlying iterative maps, identifying parameter regions associated with periodic or chaotic behavior. On the computational side, we introduce a micro-series pipeline based on kNN-driven estimation of the local largest Lyapunov exponent (LLE), applied to scalar time series derived from solver trajectories. The resulting sliding-window Lyapunov profiles provide fine-grained, real-time diagnostics of contractive or unstable phases and reveal transient behaviors not captured by coarse linearized analysis. Leveraging this correspondence, we introduce a Lyapunov-informed parameter selection strategy that identifies solver settings associated with stable behavior, particularly when the estimated LLE indicates persistent instability. Comprehensive experiments on ensembles of perturbed initial guesses demonstrate close agreement between the theoretical stability diagrams and empirical Lyapunov profiles, and show that the proposed adaptive mechanism significantly improves robustness. The study establishes micro-series Lyapunov analysis as a practical, interpretable tool for constructing self-stabilizing root-finding schemes and opens avenues for extending such diagnostics to higher-dimensional or noise-contaminated problems.

math.NA↗
arXiv2026

Direct Finite-Time Contraction (Step-Log) Profiling--Driven Optimization of Parallel Schemes for Nonlinear Problems on Multicore Architectures

Efficient computation of all distinct solutions of nonlinear problems is essential in many scientific and engineering applications. Although high-order parallel iterative schemes offer fast convergence, their practical performance is often limited by sensitivity to internal parameters and the lack of reproducible tuning procedures. Classical parameter selection tools based on analytical conditions and dynamical-system diagnostics can be problem-dependent and computationally demanding, which motivates lightweight data-driven alternatives. In this study, we propose a parameterized single-step bi-parametric parallel Weierstrass-type scheme with third-order convergence together with a training-free tuning framework based on Direct finite-time contraction (step-log) profiling. The approach extracts Lyapunov-like finite-time contraction information directly from solver trajectories via step norms and step-log ratios, aggregates the resulting profiles over micro-launch ensembles, and ranks parameter candidates using two compact scores: the stability minimum S_min and the stability moment S_mom. Numerical results demonstrate consistent improvements in convergence rate, stability, and robustness across diverse nonlinear test problems, establishing the proposed profiling-based strategy as an efficient and reproducible alternative to classical parameter tuning methods.

math.NA↗
arXiv2025

Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps

This paper studies the removal of salt-and-pepper noise from images using median filter (MF) and simple three-layer autoencoder (AE) within recursive threshold algorithm. The performance of denoising is assessed with two metrics: the standard Structural Similarity Index SSIMImg of restored and clean images and a newly applied metric SSIMMap - the SSIM of entropy maps of these images computed via 2D Sample Entropy in sliding windows. We shown that SSIMMap is more sensitive to blur and local intensity transitions and complements SSIMImg. Experiments on low- and high-resolution grayscales images demonstrate that recursive threshold MF robustly restores images even under strong noise (50-60 %), whereas simple AE is only capable of restoring images with low levels of noise (<30 %). We propose two scalable schemes: (i) 2MF, which uses two MFs with different window sizes and a final thresholding step, effective for highlighting sharp local details at low resolution; and (ii) MFs-AE, which aggregates features from multiple MFs via an AE and is beneficial for restoring the overall scene structure at higher resolution. Owing to its simplicity and computational efficiency, MF remains preferable for deployment on resource-constrained platforms (edge/IoT), whereas AE underperforms without prior denoising. The results also validate the practical value of SSIMMap for objective blur assessment and denoising parameter tuning.

eess.IV↗
arXiv2025

Objective Features Extracted from Motor Activity Time Series for Food Addiction Analysis Using Machine Learning -- A Pilot Study

Wearable sensors and IoT/IoMT platforms enable continuous, real-time monitoring, but objective digital markers for eating disorders are limited. In this study, we examined whether actimetry and machine learning (ML) could provide objective criteria for food addiction (FA) and symptom counts (SC). In 78 participants (mean age 22.1 +/- 9.5 y; 73.1% women), one week of non-dominant wrist actimetry and psychometric data (YFAS, DEBQ, ZSDS) were collected. The time series were segmented into daytime activity and nighttime rest, and statistical and entropy descriptors (FuzzyEn, DistEn, SVDEn, PermEn, PhaseEn; 256 features) were calculated. The mean Matthews correlation coefficient (MCC) was used as the primary metric in a K-nearest neighbors (KNN) pipeline with five-fold stratified cross-validation (one hundred repetitions; 500 evaluations); SHAP was used to assist in interpretation. For binary FA, activity-segment features performed best (MCC = 0.78 +/- 0.02; Accuracy ~ 95.3% +/- 0.5; Sensitivity ~ 0.77 +/- 0.03; Specificity ~ 0.98 +/- 0.004), exceeding OaS (Objective and Subjective Features) (MCC = 0.69 +/- 0.03) and rest-only (MCC = 0.50 +/- 0.03). For SC (four classes), OaS slightly surpassed actimetry (MCC = 0.40 +/- 0.01 vs 0.38 +/- 0.01; Accuracy ~ 58.1% vs 56.9%). Emotional and restrained eating were correlated with actimetric features. These findings support wrist-worn actimetry as a digital biomarker of FA that complements questionnaires and may facilitate privacy-preserving clinical translation.

cs.LG↗