Search Results (17,705)

Wind power forecasting plays a crucial role in power dispatch and safety management of wind farms. However, the insufficient integration of multimodal heterogeneous data and the limitations of conventional graph construction strategies significantly restrict forecasting performance. Existing approaches either rely on simple feature aggregation, which cannot fully capture cross-modal dependencies, or adopt predefined or single-criterion graph construction methods that fail to characterize complex turbine relationships involving spatial, temporal, and nonlinear correlations. To address these challenges, this paper proposes a Multimodal Adaptive Fusion Graph Neural Network (MAF-GNN) for short-term wind power forecasting. First, a Modality-Aware Representation Learning (MARL) module is developed to extract informative multimodal representations by modeling modality-specific characteristics and cross-modal dependencies through attention-based fusion. Second, an Adaptive Graph Learning with Multi-Similarity (AGL-MS) module is introduced to parametrically integrate four complementary similarity priors—geographic distance, Dynamic Time Warping (DTW), Maximal Information Coefficient (MIC), and cosine similarity—for adaptive turbine correlation graph construction. Furthermore, a Credibility-Modulated Graph Convolutional Network (CM-GCN) is developed to reduce the influence of unreliable node information during message propagation. Extensive experiments conducted on the SDWPF dataset demonstrate that MAF-GNN reduces MAE by 14.0–21.3% compared with sequential baselines and achieves 5.3–10.2% improvement over spatiotemporal graph-based models. Ablation studies further verify the complementary effectiveness of each proposed module in improving forecasting performance. Full article

In the context of pavement management, conventional data collection methods for the evaluation of pavement functional condition are limited by relatively slow acquisition speeds, that prevent fast-lane motorway surveying at 120–130 km/h, and by survey frequency, which on vast networks typically occurs twice a year. Given these limitations, continuous pavement condition monitoring from moving vehicles offers an attractive solution to move towards real-time digital road assessment. In particular, such a result is achieved by making use of “intelligent” or “smart” tires, which by means of appropriate arrays of sensors can capture contact patch information, thereby providing quantitative information related to pavement roughness and macrotexture. In this study, smart tire data functional condition indicators, Dynamic Index (DI) and Pr index, were collected over several segments of a motorway network, with a total length of 405 km. Correlations were investigated between such parameters and the results of measurements coming from a traditional pavement monitoring technique, expressed in terms of international roughness index (IRI) and mean profile depth (MPD). Furthermore, the ability of smart tire indicators to identify time-dependent trends and to rank different motorway segments was assessed. Obtained results, which were generated by adopting different data processing and homogenization techniques, showed that DI displays a moderate correlation with IRI, while Pr exhibits a strong correlation with MPD. Pavement-age analysis highlighted the existence of meaningful trends for both dense-graded and open-graded asphalt-wearing courses. Motorway rankings based on average DI and Pr values were found to be in agreement with those obtained from average IRI and MPD values, thereby confirming the potential of smart tire technology as a complementary network-level monitoring tool for pavement asset management systems. Full article

Background/Objectives: Post-COVID follow-up may provide an opportunity to reassess persistent and modifiable cardiometabolic risk. We characterized six-month cardiometabolic and vascular trajectories after COVID-19 hospitalization and explored associations with routinely documented dietary counseling and omega-3 recommendations. Methods: This single-center retrospective longitudinal cohort included 238 adults hospitalized with COVID-19 between March 2020 and December 2024. Patients were classified according to recorded post-discharge management as usual care (n = 64), dietary management (n = 60), omega-3 supplementation (n = 59), or combined management (n = 55). Outcomes were assessed at the index visit and at visits labeled approximately three and six months later. Longitudinal changes were estimated using generalized estimating equations; six-month associations were evaluated using baseline-adjusted ANCOVA with robust standard errors and Benjamini–Hochberg correction. Results: Mean age was 54.0 ± 10.6 years, 54.6% were women, 82.4% had hypertension, 40.8% had diabetes, and mean body mass index was 33.8 ± 4.6 kg/m². At six months, endpoint-specific data were available for 182 participants for blood pressure, total cholesterol, triglycerides, and HDL-C; 180 for waist circumference; 179 for SCORE; 177 for LDL-C and bilateral carotid IMT analyses; 173 for HOMA-IR; and 164 for IL-6. Across the cohort, systolic and diastolic blood pressure decreased by 7.91 and 4.75 mmHg; several lipid, anthropometric, and insulin-resistance markers also improved. No omnibus group-by-time interaction was significant. After false-discovery-rate correction, only higher six-month HDL-C in the dietary and combined-management groups versus usual care remained statistically significant; all other between-group findings were nonsignificant after correction. Conclusions: Several cardiometabolic risk markers improved during follow-up, but no recorded management category showed consistent trajectory-level superiority. Because intervention content and adherence, time-updated medication use, acute COVID-19 severity, and lifestyle changes were not captured, the comparative findings are exploratory and noncausal. The isolated HDL-C associations should not be interpreted as evidence of cardiovascular benefit. No cardiac biomarkers, echocardiographic measures, incident heart failure, or cardiovascular events were assessed. Full article

Electricity load forecasting is essential for balancing energy supply and demand, reducing energy waste, and maintaining power grid stability. Accurate forecasts enable power utilities to optimize energy dispatch and mitigate the risk of supply shortages or outages. However, conventional forecasting methods often struggle to capture highly nonlinear local fluctuations in electricity consumption and long-term temporal dependencies. To address these challenges, this study proposes MSCNN-ResLSTM, a hybrid model for multi-step electricity load forecasting. The proposed model integrates Multi-Scale Convolutional Neural Networks (MSCNNs) to extract local time-series features at multiple temporal scales, residual blocks (ResBlocks) to enhance feature representation through residual connections, and Long Short-Term Memory (LSTM) networks to model long-range temporal dependencies. To comprehensively evaluate its effectiveness, a cross-paradigm experimental framework is established in which MSCNN-ResLSTM is compared with seven representative benchmark models from three methodological categories: traditional machine learning (Extreme Gradient Boosting-XGBoost), classical recurrent and convolutional neural networks (LSTM, Temporal Convolutional Network-TCN, CNN-LSTM, MSCNN-LSTM, and Direct LSTM (Seq2Seq)), and self-attention-based architectures (Transformer). Experimental results show that MSCNN-ResLSTM achieves higher forecasting accuracy and greater stability across the full 24-step prediction horizon, consistently outperforming all competing baselines while effectively suppressing recursive error propagation. Full article

European wild ungulates are captured for different purposes, requiring the assessment of animal welfare and health. Specific guidelines to assess stress and pathophysiological compromise in captured wild ungulates are lacking. This review aims to set the bases for establishing standardised protocols allowing the evaluation of capture and handling stress in wild European ungulates. Physical and chemical capture and handling elicit stress, a physiological response activating sympathetic–adrenal medulla and hypothalamic–pituitary–adrenal cortex axes, releasing catecholamines and corticosteroids, respectively. While being an adaptive response, if prolonged over time, the effects become harmful and life-threatening, increasing body temperature and heart rate, and provoking muscular and renal ischemia. This clinical outcome is known as capture myopathy, which encompasses four sequential syndromes: Hyper acute or capture shock, Acute or ataxic-myoglobinuric, Sub-acute or ruptured muscle, and Chronic debility or delayed per-acute. Monitoring temperature, heart rate, serum muscular enzyme (CK, AST, ALT, and LDH) activities and lactate, creatinine, urea, and potassium concentrations characterises pathophysiological compromise. Wild ungulate capture and handling protocols should include not only methodology but also monitoring, data recording, sample collection, and analyses. This information should serve to improve protocols and eventually develop specific guidelines for stress and welfare assessment when capturing and handling wild ungulates. Full article

Accurate stock price forecasting remains a challenging problem due to the noisy, nonlinear, and non-stationary characteristics of financial time series. Although recent advances in deep learning have improved predictive capabilities, most prior studies evaluate forecasting models primarily using statistical error metrics, with limited consideration of their practical value in trading and investment decision-making. This creates a gap between predictive performance and real-world economic utility. This study proposes a decision-oriented evaluation framework for multi-step stock price forecasting that jointly assesses predictive accuracy and trading profitability within a unified experimental setting. Using data from 91 ASX 100 stocks after data cleaning, with a testing period spanning 2019–2020, several deep learning architectures, including Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU), Seq2Seq, and attention-based sequence models, are systematically compared under identical training and trading conditions. The results show that the Seq2Seq model achieved the best overall performance, obtaining the lowest average MAPE of 0.0293 and the highest ROI of 23.2%, while the attention-based model achieved a similar MAPE of 0.0294 but a lower ROI of 12.4%. Although differences in forecasting accuracy were relatively small, the Seq2Seq model achieved the highest observed trading profitability and generated a higher observed return than a passive market benchmark under the proposed evaluation framework. These findings suggest that evaluation based solely on prediction accuracy may not fully capture the practical value of forecasting models. Full article

The dynamic response and material failure of concrete under hypervelocity impact are critical for assessing the performance of protective structures. This study investigates the depth of penetration and damage mechanisms of concrete targets subjected to ovoid long-rod tungsten alloy projectiles at hypervelocity regimes ranging from 1000 m/s to 1600 m/s. Three numerical algorithms within LS-DYNA, the traditional Finite Element Method (FEM), fixed-coupling FEM-SPH, and adaptive FEM-SPH, were systematically evaluated and validated against experimental data and established empirical formulas. The results reveal a significant transition in algorithmic performance at hypervelocities compared to high-velocity regimes. The fixed-coupling FEM-SPH model demonstrates superior predictive accuracy in the 1000–1600 m/s range, with an average error of 5.6% and a maximum error of 10.4%, effectively capturing the near-rigid penetration characteristics and stable projectile morphology observed in experiments. In contrast, the adaptive FEM-SPH algorithm, which is typically robust at lower velocities, exhibited the lowest precision with an average error of 32.6% (maximum 36.6%), likely due to the instability of SPH conversion criteria under extreme strain rates. While traditional FEM remains the most computationally efficient, requiring only 14.6% of the processing time of the fixed-coupling model, it suffers from substantial deviations (average error of 29%) as the projectile transitions into semi-broken penetration modes with significant mass abrasion, which increased from 10% to 27% in the simulations. The comparative analysis reveals that numerical stress oscillations in traditional FEM and the limitations of current adaptive conversion criteria make fixed-coupling SPH formulations the most reliable scheme for hypervelocity long-rod penetration assessments. This study provides critical guidelines for selecting appropriate numerical schemes for extreme loading scenarios, balancing the requirements for physical fidelity, accuracy, and computational efficiency in protective structural design. Full article

As the global economy accelerates toward low-carbon transformation, climate financial risks are emerging as a key challenge to monetary policy design and financial stability oversight. This study examines the contagion effects and dynamic interdependencies among domestic climate-sensitive industries, financial climate risk indices, and international climate markets. Using daily data from April 2020 to April 2025, we apply a multiscale tail risk modeling framework that integrates wavelet decomposition, conditional volatility modeling, and vine-copula techniques to capture time-varying and asymmetric dependence structures across markets. The results show that the three markets display volatility clustering, fat tails, and nonlinear dependence. The international climate market shows weaker and more volatile connections with the two domestic markets, suggesting that external climate expectations operate mainly through indirect dependence across market states. The risk spillover results further show that climate financial risk contagion differs between upside and downside states and varies across short and medium horizons. These findings have important implications for integrating climate risk into macroprudential surveillance. Central banks and regulators should strengthen early warning mechanisms, climate stress testing, and scenario analysis by considering market-specific, nonlinear, and multiscale risk spillovers. The main contribution of this study is to integrate multiscale decomposition, conditional volatility modelling, and vine-copula dependence analysis into a unified empirical framework for identifying climate financial risk contagion across markets. The findings offer useful evidence for climate stress testing, early warning systems, and financial stability monitoring in emerging markets. Full article

Background/Objectives: Despite the increasing rates of disability associated with aging, obesity, and osteoarthritis requiring surgery, optimizing rehabilitation after hospital discharge remains a major challenge and a key determinant of care safety, quality, and sustainability. The aim of this exploratory study is to evaluate the predictive performance of machine learning (ML) models for predicting Inpatient Rehabilitation Length Of Stay (IRLOS), Function in the Activities of Daily Living (FADL) and discharge destination (DD) in patients who underwent total joint replacement for hip and knee osteoarthritis, using Real-World Data routinely collected in a tertiary orthopedic hospital. Methods: 2103 patients were included and temporally split into a development cohort (2019; n = 1711) and a temporal validation cohort (2018; n = 392). A total of 73 routinely collected perioperative variables were used to train multiple ML models, including both black-box and transparent methods. IRLOS and FADL were modeled as regression tasks, while DD was treated as a binary classification task. Model development followed a rigorous pipeline with feature selection, cross-validation, and hyperparameter tuning. Performance was assessed using appropriate metrics and evaluated across joint type (hip/knee) and via temporal validation. Model interpretability was examined using SHAP and model-specific analyses, further supported by clinical analysis. Results: In temporal validation, models achieved modest performance for IRLOS (R² = 0.17; MAE = 2.52 days) and FADL (R² = 0.25; MAE = 2.25 days), with no significant performance degradation over time. DD prediction showed good discrimination (AUC = 0.85; balanced accuracy = 0.80) despite outcome imbalance, with high sensitivity (0.92) and negative predictive value (≈1.00), but low positive predictive value (0.09). Performance was stable across hip and knee subgroups. The interpretability analysis further highlighted several key predictors related to perioperative complexity (e.g., surgical duration and transfusion), baseline functional status, and social factors (e.g., living situation and employment), confirming that rehabilitation outcomes are multidimensional and influenced by both medical and non-medical determinants. Conclusions: The analysis identified several relevant predictors related to perioperative complexity, baseline functional status, and social context. The models showed stable behavior across intervention type and across time through temporal validation, suggesting that they capture relevant patterns in rehabilitation pathways, although predictive performance was moderate. Full article

Egocentric multi-view image analysis refers to the processing of utilizing synchronized video streams captured from multiple wearable cameras worn on the head or body, providing complementary first-person perspectives of dynamic, real-world interactions. Unlike single-view egocentric vision, which may suffer from severe occlusions, motion blur, and limited field-of-view or traditional fixed-camera multi-view setups (assuming static geometry and controlled environments), egocentric multi-view systems leverage body-worn rigs to enable a more robust and flexible 3D understanding in open-world, mobile scenarios. In this work, we present a systematic survey of advancements in cross-view feature fusion, geometric consistency enforcement, open-world detection, human–object interaction (HOI) modeling, action segmentation, 3D reconstruction, and novel-view synthesis specifically tailored to wearable multi-camera platforms. Key datasets released between 2024 and 2026—including HOT3D (833 min of synchronized multi-view hand/object interactions from Project Aria and Quest 3), MultiEgo (first multi-egocentric dataset for 4D social scene reconstruction), and Ego-1K (large-scale 12-camera rig for dynamic 3D video synthesis) are thoroughly examined alongside an analysis of integrations with large language models (LLMs) and vision–language models that drive performance gains, typically in the 15–30% range over single-view baselines in hand tracking, HOI recognition, and reconstruction fidelity, although we show through a consolidated meta-analysis that this gain is task-dependent: larger for geometry-bottlenecked tasks such as in-hand object lifting, and smaller, method-dependent, or occasionally negative for semantic-recognition tasks such as keystep recognition under naive view fusion. These methods cover work in multi-view stereo, cross-view learning, and novel-view synthesis while addressing several real-time wearable constraints. Practical applications such as immersive Augmented Reality/Virtual Reality (AR/VR), assistive robotics, and healthcare monitoring are also discussed together with the challenges in motion calibration, benchmark diversity, and edge deployment ability. Thus, in this review, we attempt to fill a critical gap by focusing exclusively on wearable multi-view systems in an open-world setting, synthesizing the latest literature to chart future directions toward more embodied and continual learning agents. Full article

Aquaculture has rapidly expanded, surpassing capture fisheries and playing a vital role in global food security. However, this growth raises environmental concerns, especially regarding nitrogen waste accumulation in recirculating aquaculture systems (RASs). Nitrogen compounds from uneaten feed and fish excreta, mainly ammonia (NH₃) and nitrite (NO₂⁻), lead to water pollution, eutrophication, and greenhouse gas emissions. This study describes the setup and the efficiency of a new photo-electrocatalytic (PEC) system in reducing nitrogen waste in a high-density RAS for rainbow trout (30 kg/m³). The PEC system, an evolution of a pure photocatalytic system, was integrated in the units of the RAS and tested for the first time in field conditions, combining photocatalysis and electrochemical oxidation to convert toxic nitrogen species (NH₃) into less harmful nitrogen forms (NO₃⁻ and N₂), aiming to mitigate both water and atmospheric pollution. Over a 4-week period, water nitrogen compounds, ammonia and greenhouse gases (carbon dioxide, nitrous oxide and methane) emitted by water were continuously monitored in two groups of three tanks (PEC vs. control). Each tank was equipped as an independent RAS unit. PEC treatment led to significantly lower NH₃ concentrations (0.96 ± 0.2 mg/L vs. 1.78 ± 0.2 mg/L, p < 0.01), lower NO₂⁻ levels and higher NO₃⁻ levels (61.77 ± 2.14 mg/L vs. 53.10 ± 2.14 mg/L, p < 0.01) in water, indicating efficient nitrogen oxidation. Gaseous emissions were also reduced: NH₃ (1.49 vs. 2.64 mg/m²/day, p < 0.05) and N₂O (1.44 vs. 2.88 mg/m²/day, p < 0.05). These results support PEC technology as a promising solution for improving nitrogen management in intensive aquaculture. Although challenges remain in optimizing energy use and scalability, PEC offers a valuable strategy for reducing environmental impact while sustaining productivity in the aquaculture industry. Full article

Background/Objectives: Snow can disrupt emergency medical services (EMSs); however, previous studies have mainly measured snowfall or prefecture-level exposure. These measures may not capture snow remaining on the ground or conditions within ambulance operating areas. We examined whether the daily snow depth assigned at the fire department level was associated with EMS time intervals and 1-month survival after out-of-hospital cardiac arrest (OHCA). Methods: This retrospective cohort study included 7395 adults with OHCA from the Akita Prefecture Utstein-style emergency transport registry between 2019 and 2023. Daily snow depth from the nearest Automated Meteorological Data Acquisition System (AMeDAS) station was assigned to each case by the fire department. Snow exposure was analyzed as >0 cm versus 0 cm, as five depth categories, and as a continuous variable using natural splines. Multivariable models were adjusted for age, sex, cardiac origin, initial rhythm, fire department area, witnessed status, bystander cardiopulmonary resuscitation, and year. Results: Call-to-scene time and total EMS time were longer with snow cover than without snow cover (median, 9 vs. 8 min and 34 vs. 31 min, respectively; both p < 0.001). Snow cover was associated with lower 1-month survival after adjustment (odds ratio [OR], 0.73; 95% confidence interval [CI], 0.54–0.98), but this association was attenuated after additional adjustment for call-to-scene time (OR, 0.77; 95% CI, 0.57–1.03). Category-based and spline analyses showed no clear dose–response relationship. Conclusions: Daily snow depth is consistently associated with longer EMS response and transport times. However, its association with 1-month survival remains unclear. This survival association may reflect broader winter conditions rather than snow cover itself. Full article

Background: Anemia is a common systemic condition associated with adverse maternal, perioperative, and cardiovascular outcomes. Although timely screening is clinically important, diagnosis still relies on invasive blood testing. Palpebral conjunctival pallor has traditionally been used as a noninvasive indicator of anemia, but its diagnostic accuracy remains limited. This study aimed to develop and validate a deep learning system to estimate hemoglobin (Hb) concentration and screen for anemia using palpebral conjunctiva images captured with a smartphone-compatible slit-lamp microscope. Methods: In this prospective observational study, 225 Japanese participants (20–92 years) underwent conjunctival imaging and blood testing. Palpebral conjunctiva videos were obtained using the Smart Eye Camera. Video frames were processed using automated anterior-segment segmentation and conjunctiva extraction. A ConvNeXt-based regression model was trained to predict Hb values. Anemia was defined using sex-specific Hb thresholds. Results: From 225 videos, 53,776 frames were extracted, yielding 9903 quality-filtered conjunctiva images (training: 8082; test: 1821). Video-level predicted Hb values moderately correlated with measured Hb (r = 0.42). For anemia screening, frame-level analysis achieved an AUC of 0.75, with accuracy of 0.76, sensitivity of 0.71, and specificity of 0.79. Video-level aggregation achieved 69% accuracy. Conclusions: Deep learning analysis of palpebral conjunctiva images acquired with a portable slit-lamp microscope demonstrated the feasibility of non-invasive hemoglobin estimation and anemia screening. Although the proposed approach achieved moderate performance, further improvements in model accuracy and prospective multi-center validation are required before clinical implementation. Full article

Cloud and quality screening removes approximately 65% of daily TROPOMI tropospheric NO₂ pixels, creating structured data gaps that coincide with meteorological conditions driving pollution extremes. Standard gap-filling methods—kriging, Random Forests and other machine learning methods—act as statistical smoothers that systematically suppress extreme concentrations and ignore the Missing Not At Random (MNAR) character of cloud-induced missingness. Here we present a physically informed framework that treats urban NO₂ as a forced nonlinear dynamical system and reconstructs missing satellite observations through geometric navigation on a shadow manifold rather than statistical interpolation. The framework integrates five components: (i) Multivariate State-Space Reconstruction (MSSR) using multiview embeddings of continuous ground-based NO₂, O₃, and ERA5 meteorology, grounded in Stark’s forced-system embedding theorem; (ii) Short-Time Regime-Conditioned Convergent Cross Mapping (ST-RC-CCM) with a spatial-mismatch negative control for falsifiable causal validation; (iii) Inverse Probability Weighting (IPW) to correct the clear-sky sampling bias; (iv) trajectory-matrix denoising via Singular Spectrum Analysis (SSA) and Robust PCA; (v) topology-inspired fidelity metrics—Manifold Overlap Ratio (MOR) and Dynamic Trend Capture (DTC)—that penalize smoothing artefacts. The physical basis for this coupling is the shared dynamical history of surface and column NO₂: tropospheric NO₂ has a photochemical lifetime of 1–4 h near urban emission sources, comparable to the boundary layer mixing timescale, ensuring that surface and column concentrations are jointly governed by the same emission–photolysis–transport attractor. The planetary boundary layer height (PBLH), solar zenith angle (SZA), and surface O₃—all included as MSSR coordinates—are the dominant physical drivers of the instantaneous surface-to-column scaling, and their joint trajectory in state space constitutes the physically grounded basis for analogue selection. The framework is validated on a synthetic forced Lorenz-96 system, then applied to five European primary cities spanning contrasting regimes (Sofia, Milano, Stuttgart, Kraków, Hamburg) plus five N1 spatial-mismatch control stations (Plovdiv, Genova, Frankfurt, Warszawa, Berlin)—ten urban-background stations across four countries—with structured ablations (A0-A4V-A4K). Across >3600 evaluations, MOR_ext distributions for EDM and non-EDM methods are non-overlapping by a factor exceeding 5× (EDM minimum 0.59 vs. non-EDM maximum 0.10; median non-EDM MOR_ext ≤ 0.05 at every city × mask combination), while EDM achieves MOR_ext up to 0.915 (Milano Po Valley). Under a fair-comparison benchmark that withholds ground-level NO₂ from Random Forest, EDM’s RMSE advantage remains robust at a median of 3.9× (RF_FULL) and increases to 4.2× (RF_METEO), confirming that the performance gap is physical rather than an information artefact. A three-level temporal validation—within-window pseudo-cloud masking, cross-year transfer (full 2022 holdout and DJF 2023/24), and a COVID-19 out-of-distribution test—demonstrates robustness beyond standard train/test splits, with CCM library-length convergence confirmed for 60/60 ablations (p < 0.001) across all ten stations. Spatial-mismatch tests confirm local dynamical specificity at all five primary–control pairs (Δρ = 0.090–0.210), with seasonal modulation driven by orographic and synoptic mechanisms. These results establish manifold-based gap filling as a dynamically informative complement to statistical approaches, particularly in topographically confined, stagnation-prone basins where preserving extreme-event geometry is essential for exposure assessment. Full article

Electrochemical Impedance Spectroscopy (EIS) is a non-destructive technique for characterizing the battery behavior for estimating the state of health (SOH). EIS provides frequency-domain information on key parameters, including solid electrolyte interphase (SEI) resistance, charge-transfer (CT) resistance, and ohmic resistance, which are sensitive to battery degradation mechanisms. In an EIS test, a sinusoidal excitation signal is applied to the battery, and the corresponding voltage response is analyzed to extract the impedance spectrum. The reliability of SOH estimation therefore depends critically on the accurate and repeatable extraction of impedance features. This paper investigates the variability in impedance spectra arising from the state of charge (SOC), temperature, rest time, and repeated measurements under nominally identical conditions. This variability is identified as drift and represents previously underexplored variations in the impedance spectrum. To quantify these variations, this work proposes a normalized resistance-based index that captures changes in the impedance spectrum using estimated equivalent circuit model (ECM) parameters. The proposed index is applicable across battery chemistries, sizes, and operating conditions. It is evaluated using published datasets spanning different chemistries, SOC levels, and temperatures, as well as laboratory data collected from repeated EIS experiments. The results show that even at fixed SOC and temperature, repeated measurements can produce measurable bias and variance in ECM parameters. These findings highlight the importance of accounting for drift in EIS analysis and motivate uncertainty-aware battery diagnostics for practical SOH monitoring systems. Full article