Abstract: We define the function $Col: \mathbb{N} \to \mathbb{N}$ as the Collatz function, given by $3n + 1$ if $n$ is odd and $\displaystyle\frac{n}{2}$ if $n$ is even. The conjecture postulates that for any positive integer, at some point, its iteration will reach 1, or equivalently, every orbit will fall into the periodic cycle $\{4, 2, 1\}$. Two conditions would invalidate the conjecture: The existence of a divergent orbit or the presence of another cycle. We can study the dynamics of the orbits through the density of even terms in their orbit. If all points' accumulation density exceeds the value of $\displaystyle\frac{\ln(3)}{\ln(2)}$ then the orbit is bounded. The main result of this work is to show that there are no natural numbers such that the accumulation points of the pair density are less than $\displaystyle\frac{\ln(3)}{\ln(2)}$. In other words, there are no divergent orbits.

Abstract: Benthic macroinvertebrates are widely used as bioindicators for assessing freshwater ecosystem health. This study investigated the diversity patterns and community structure of benthic macroinvertebrates across 21 sampling sites along the middle and lower reaches of the Yangtze River. A total of 74 species belonging to 3 phyla, 7 classes, 17 orders, 37 families, and 58 genera were identified, with aquatic insects dominating the assemblages. Alpha diversity indices showed no significant differences among river sections, whereas multivariate analyses (NMDS and PERMANOVA) revealed significant spatial variation in community composition, indicating that beta diversity plays a key role in structuring assemblages at the basin scale. Canonical correspondence analysis (CCA) identified nutrient variables (TN and NH₄⁺-N), as well as pH and conductivity, as the main environmental drivers influencing community distribution. The results suggest that benthic macroinvertebrate diversity patterns in large river systems are jointly shaped by regional environmental gradients and local habitat conditions. These findings provide insights into biodiversity conservation and ecological management of large river ecosystems.

Abstract: The increasing demand for sustainable and affordable smart-city infrastructure has intensified the need for low-cost, near-real-time water-quality monitoring systems. In this study, we propose Water-QI, a low-cost Internet of Things (IoT)-based environmental monitoring platform that combines budget-friendly sensors with deep learning for Water Quality Index (WQI) assessment and forecasting. The sensing platform measures five key physicochemical parameters, namely temperature, total dissolved solids (TDS), pH, turbidity, and electrical conductivity, enabling continuous multi-parameter monitoring in urban water environments. To model temporal variations in water quality under both cloud-based and edge-oriented deployment scenarios, we evaluate multiple Gated Recurrent Unit (GRU) architectures with different widths and depths. Experiments are conducted at two temporal resolutions, hourly and minute-level, in order to examine the trade-off between predictive accuracy and computational cost. In the hourly scenario, the single-layer GRU with 64 units achieved the best overall balance, reaching a validation RMSE of 0.0281 and a test R² of 0.9820, while deeper stacked GRU models degraded performance substantially. In the minute-resolution scenario, shallow wider GRU models produced the best results, with the single-layer GRU with 512 units attaining the lowest validation RMSE (0.025548) and the 256-unit variant achieving nearly identical accuracy with much lower inference cost. The results show that increasing model width can yield marginal improvements at high temporal granularity, whereas excessive recurrent depth consistently harms convergence and generalization. Overall, the findings indicate that shallow GRU architectures provide the most practical solution for accurate, low-cost, and scalable near-real-time water-quality forecasting. In particular, the 64-unit GRU is the most suitable choice for hourly low-complexity operation, while the 256-unit GRU offers the best speed--accuracy trade-off for minute-level edge inference on resource-constrained devices.

Abstract: Diabetes complications may increase frailty rates among the elderly, leading to falls, immobility, dependency, hospitalizations, and death. The study aimed to assess any association between frailty status and glycaemic control among older adults with type 2 diabetes mellitus at Kenyatta National Hospital, Kenya. We conducted a cross-sectional study of 430 older individuals aged 60+ years with type 2 diabetes at a specialized diabetes clinic using a modified FRAIL scale. Mean age was 69.1 years, with 65.7% female and 76.2% completed primary school. Frailty prevalence was 3.8%, pre-frailty 24.3%, and robust/non-frail 71.9%. It was associated with age, social status, health knowledge, duration of DM, blood pressure, body mass index, high-density lipoprotein-C, and renal failure. Mean fasting plasma glucose (FPG) was 8.7 mmol/L, with 60% having FPG>7 mmol/L; mean glycated haemoglobin (HbA1C) was 8.0%, with 41% having HbA1C>8%. Glycaemic control was correlated with number of medications, blood pressure, lipidaemia but not age, sex, social status. No correlation was found between frailty and glycaemic control: frailty versus FPG (r=0.038, P=.459; χ²=0.699, P=.705), and HbA1C (r = –0.009, P=0.877; χ²=0.046, P=.977). Low frailty prevalence was noted, with no association to glycaemic control. Our findings provide evidence for conducting frailty assessments in chronic disease care.

Abstract: Chronic pruritus in patients with dermatological conditions causes physical discomfort, skin breakdown, sleep disturbance, and overall decline in quality of life. Persistent scratching can lead to a condition known as lichenification, which further deteriorates the skin. Lichenified skin is more susceptible to infections, which further complicates the treatment and prolongs the recovery time. This highlights the importance of accurately detecting and quantifying scratching behavior for effective management and intervention. All the existing technologies to monitor scratching involve the use of external sensor modalities such as an accelerometer and a gyroscope, followed by camera monitoring. However, such scratch detection methods are limited in their reliability in monitoring scratching intensity. This study aims to acquire muscle activity to accurately detect, quantify, and provide feedback on self-induced scratching intensity. Through a meticulous understanding of the synergies of hand muscles, three out of seven forearm muscles were identified that generate consistent and distinctive signals during scratching motion. These signals were acquired, preprocessed, segmented, and analyzed using both time and frequency domain features. The extracted 45 features of 3-Channel EMG signals were first optimized using recursive feature elimination and validated by cross-validation accuracies of the recursive feature elimination technique, with the highest optimized accuracy of 0.8628 when EMG of a complete combination of muscles is used. This study shows the promising results in facilitating enhanced diagnosis and management of scratching intensities. The model can be deployed into an embedded device for generating alerts and providing advanced therapy.

Abstract: This study examines women’s textile knowledge in Portugal as a fundamental element of cultural heritage, situating it within domestic, social, and industrial contexts, with a particular focus on Guimarães. Drawing on a multidisciplinary approach grounded in historical and documentary evidence, it analyses how female expertise in spinning, weaving, embroidery, and lacemaking contributed to the evolution of textile practices from the fifteenth century to the present day. The findings indicate that this knowledge was pivotal to the transformation of domestic textile activities into an emerging industrial sector, shaping both production methods and cultural identity. The study concludes that recognising the historical importance of women’s textile labour is essential for understanding the development of the Portuguese industry. Furthermore, this research emphasises the urgency of preserving, transmitting, and legitimising the intangible cultural heritage inextricably linked to women’s textile mastery. It argues that integrating this legacy into contemporary creative and industrial practices can foster cultural sustainability and unlock new possibilities for future innovation, ensuring that this ancestral expertise remains a living pillar of regional identity.

Abstract: A 7-year-old, 38.3 kg, male neutered Labrador retriever presented to the Teaching Hospital for a consultation of Comprehensive Oral Health Assessment and Treatment. Nine months prior to the consultation, the patient presented to the ER service due to acute right facial swelling. To further evaluate the swelling, the patient was sedated by IV administration of dexmedetomidine and fentanyl, and ventricular premature contractions (VPCs) were confirmed. The facial swelling subsided afterward, but it recurred. Therefore, a dental procedure under general anesthesia was scheduled. Although norepinephrine CRI was initiated to treat the hypotension perioperatively, VPCs were noticed a few minutes after norepinephrine CRI. After the dental procedure, a prolonged recovery was observed, and naloxone (0.01 mg/kg) was administered IV to reverse the effects of fentanyl. Before administration of naloxone, the HR was 80 bpm. Within one minute of administering naloxone, the patient was extubated. However, the HR surged to 240 bpm, and sinus tachycardia was observed. Ninety minutes after naloxone IV, the HR was 105 bpm with normal sinus rhythm, gradually approaching the pre-anesthesia HR level (110 bpm). Veterinarians should recognize that administration of naloxone could induce arrhythmias. Therefore, continuous monitoring of ECG, pulse, and blood pressure is imperative when administering naloxone.

Abstract: Rapid urbanization and stringent ecological protection policies in China have intensified spatial competition among Urban–Agricultural–Ecological (UAE) spaces. However, existing studies often overlook how this competition evolves across different slope structures. To address this, this study establishes a fine-scale analytical framework using H3 hexagonal grids and slope spectrum analysis to investigate the slope structure evolution and spatial competition mechanisms from 1990 to 2023. The results reveal a distinct topographic stratification of competitive niches: urban space dominates low-slope regions (< 6°) but exhibits a pervasive "upslope expansion" trend, with its average slope increasing from 1.81° to 2.07°. Agricultural space characterizes the transition zones (6°–15°), showing an "upslope migration" in the Southeastern Hills driven by urban squeeze. Ecological space functions as a stable barrier in steep terrains (> 15°) but faces encroachment in transition zones. Furthermore, cluster analysis identifies significant regional heterogeneity aligning with China’s macro-topography: the Eastern Plains are characterized by "low-slope agglomeration," where urban–agricultural conflict is most intense; the Southern Hilly Regions display an "interwoven upslope" pattern; while the Western Highlands maintain absolute ecological dominance. Mechanism analysis using GeoDetector and Multiscale Geographically Weighted Regression (MGWR) indicates that competition intensity is predominantly driven by human activity factors (e.g., human footprint, nighttime lights, q > 0.29), yet significantly modulated by topographic constraints (e.g., elevation), creating a nonlinear enhancement effect. Crucially, this study challenges the traditional flat-projection planning model. We propose a transition to "three-dimensional topographic regulation," advocating for differentiated management strategies—such as strict "slope redlines" for urban–agricultural transition zones—to resolve the intensifying spatial conflicts in complex terrains and safeguard agricultural sustainability.

Abstract: The development of remote blood pressure (BP) measurement algorithms using remote photoplethysmography (rPPG) has significant limitations, including the small size of publicly available datasets, privacy concerns regarding facial videos, and a lack of diverse, realistic datasets associated with actual BP measurements. To address these challenges, this study aimed to provide comprehensive, simultaneous recordings of participants' faces, along with reference physiological measurements, for 300 adult participants aged 18–65 years. For each imaging session, systolic and diastolic blood pressure and reference heart rate (HR) were recorded using clinical electronic BP monitors in addition to recording illuminance (lux) values for indoor and outdoor environments. The collected data, called CLBP-300, is a crucial resource for developing and evaluating remote vital signs from facial rPPG signals. A sample of videos is publicly available to demonstrate data quality, while academic researchers can access the complete dataset under a strict data use agreement. The data and python code presented in this study are available on https://sites.google.com/view/clbp-300?usp=sharing.

Abstract: Occlusion is strongly related to oral health and is a key factor for the successful outcome in dental restorations, because prosthetic restorations must not only be harmoniously integrated, but also balanced in terms of occlusion and articulation. The current study aims to establish the reproducibility of tooth contacts in central occlusion using a prototype of a new dental articulator and compare the results with the T-Scan and Medit i500 systems. Materials and Methods: We applied two different types of laboratory methods, digital and conventional, with digital registration being carried out with the T-Scan and Medit i500 systems, and the conventional one—with articulating paper. The R software environment (version 4.2.2, R Core Team, 2022) was employed to carry out the statistical analysis and produce the graphical visualizations. The methods used were: descriptive statistics, stacked paired t-test to test the presence of a statistically significant difference in the mean values of overlap, with the adopted significance level being α=0.05; two-way and three-way analysis of variance (two-way ANOVA); Fisher's post-hoc analysis; graphical analysis for data visualization. Results: The 40μm articulating paper established more common contacts than the digital devices. The three-way ANOVA analysis, used to compare the applied methods, reported good overlap, with statistically significant differences found only in the colors of the occlusal coating at 95% confidence interval, which gives us reason to conclude that there is no difference between the methods used, confirming the reliability of the new device. Conclusion: Despite the remarkable evolution of digital dentistry, still no single flawless occlusal analysis method exists. Both conventional and digital systems have their advantages and disadvantages, and the clinician must use them in a complementary manner for accurate analysis.

Abstract: A substantial share of reinforced-concrete infrastructure assets has reached an age where deterioration mechanisms such as cracking, delamination, and voiding may develop, potentially increasing safety risks and maintenance demands. Conventional condition assessment commonly relies on localized intrusive testing (e.g. coring) and manual sounding, which can be disruptive, labour-intensive, and partly subjective. Vibration-based non-destructive testing (NDT) provides an alternative by exciting the structure and evaluating changes in its dynamic response. In contrast to previous studies, which typically assess a single excitation method in isolation, this study provides a systematic side-by-side comparison of three vibration-based NDT excitation approaches: mechanical impact using a custom compressed-air impact device, acoustic excitation, and shaker excitation. All three methods were evaluated under identical measurement conditions. The vibration response is measured using laser Doppler vibrometry (LDV), enabling non-contact acquisition of frequency-response signatures. A custom mechanical excitation device was developed and evaluated, and the results indicate that it provides stable and repeatable excitation with good defect discrimination. Experiments on specimens with representative defect types show that mechanical impact and shaker excitation yield the most repeatable and discriminative response features, whereas acoustic excitation provides insufficient signal-to-noise ratio (SNR) for the smallest tested specimens (150 x 150 x 150 mm). Among the evaluated setups, the electrodynamic shaker and the compressed-air impact device offer the most promising low-noise measurements. The goal is to enable efficient and scalable inspection methods for safer and more reliable monitoring of reinforced-concrete infrastructure.

Abstract: Accurate delineation of buried slip surfaces remains a major uncertainty in landslide hazard assessment, especially where subsurface data are limited. This study evaluates a displacement-based approach to estimate quasi-three-dimensional (quasi-3D) slip surfaces using ground-surface displacement vector gradients derived from multi-temporal UAV-based LiDAR data. Two landslides in Japan (Jimba and Kamitokitozawa), representing contrasting scales, were analyzed to assess the method’s applicability and limitations. Two-dimensional (2D) slip-surface profiles were derived through group-wise median grouping of displacement gradients and weighted non-uniform rational B-spline fitting along longitudinal sections. Transverse profiles were constrained using side-scarp gradients and depths estimated from longitudinal profiles. These profiles were integrated into quasi-3D surfaces and validated against borehole-derived slip surfaces. At the Jimba landslide, characterized by relatively coherent movement, the estimated surfaces closely match borehole data in both depth and geometry. At the larger Kamitokitozawa landslide, the method reproduces first-order geometry and extent but shows larger local deviations, particularly in a graben-like subsidence zone. Nevertheless, the estimated displaced volume reaches 96% of that derived from borehole data. These results demonstrate that the method provides useful first-order constraints on slip-surface geometry for preliminary hazard assessment, borehole planning, and 3D stability analysis.

Abstract: Generalized geometric frameworks can admit enlarged kinematical structure without thereby specifying a physical observable sector. In such settings, physical observability cannot be identified naively with the full kinematical space, because normalization, expectation values, conserved transport, and admissible evolution require a controlled criterion of physical sector selection. This paper formulates PT-symmetric quaternionic spacetime (PTQ) as a projection-defined physical framework built around that requirement. We state the minimal principles of PTQ, argue that physicality is defined only after projection onto an admissible observable sector, and show how the physical inner product, probability/current structure, and observable dynamics are to be understood at the framework level only after that projection has been imposed. Probability is treated as an induced structure of the projected sector rather than as a primitive assignment on unrestricted kinematics, while dynamics are formulated as constrained projected geometric evolution compatible with admissibility, metric consistency, and continuity. We also state a framework-level notion of falsifiability, centered on the requirement that a single projection-induced residual structure remain consistent across distinct observational regimes. The scope of the paper is deliberately limited: it does not present a full cosmological model, does not provide a full replacement for quantum theory, and does not claim a universal closed dynamical system. Its purpose is to supply a foundational statement of the PTQ program on which later technical, probabilistic, and empirical developments can be assessed.

Abstract: Sustainable manufacturing increasingly requires production schedules that balance environmental responsibility with delivery reliability. In flexible job shop environments, this challenge is especially difficult because machine assignment and sequencing decisions affect both the carbon footprint of production and the risk of missing job due dates. Motivated by this trade-off, this paper studies the Carbon-Aware Flexible Job Shop Scheduling Problem with Tardiness Penalty (CAFJSP-T), a flexible job shop formulation in which total carbon emissions and total tardiness penalty are treated as the two primary objectives, while energy consumption and makespan are retained as supporting performance indicators. To solve this problem, we propose a Policy-based Rough Optimization with Large Neighborhood Search (Pro-LNS) framework that combines Proximal Policy Optimization for fast, policy-guided construction of feasible schedules with an adaptive large neighborhood search procedure for targeted refinement. The two phases are aligned through a normalized scalarized objective that balances carbon emissions and tardiness penalty while preserving all precedence, eligibility, and machine-capacity constraints. Computational experiments on benchmark instances spanning small, medium, and large workcenter categories show that Pro-LNS produces high-quality schedules with strong due-date performance and controlled carbon emissions. Under equal objective weighting, the method achieves a median optimality gap of 6.12% relative to the exact formulation, with all reported instances remaining within 14%, while requiring only 4.08 seconds on average and at most 10.51 seconds. These results indicate that Pro-LNS is an effective and computationally practical approach for carbon-aware, tardiness-sensitive flexible job shop scheduling.

Abstract: Restless legs syndrome (RLS) is traditionally conceptualised as a dopamine-responsive sensorimotor disorder; however, new evidence suggests a more complex and heterogeneous neurobiological basis. Findings from neuroimaging, genetic studies, circadian biology, and clinical research indicate that dopaminergic dysfunction occurs within a broader context of neuromodulatory imbalance involving iron metabolism, adenosinergic signalling, glutamatergic excitability, and, potentially, noradrenergic pathways. In parallel, quantitative susceptibility mapping and related approaches have provided indirect evidence of altered brain iron distribution, although results remain variable across studies. Clinically, RLS extends beyond nocturnal discomfort and is associated with sleep fragmentation, impaired quality of life, and neuropsychiatric comorbidity, as well as treatment-related complications such as augmentation. However, current diagnostic frameworks remain predominantly phenomenological, and available biomarkers lack sufficient validation for routine clinical use. In this narrative review, the available clinical, genetic, and neuroimaging evidence is synthesized to propose an integrative, network-based model in which iron-dependent neuromodulatory processes influence excitability across cortico–striatal–thalamo–limbic circuits. This framework is intended as a hypothesis-generating model rather than a definitive explanation of disease mechanisms. Substantial heterogeneity across studies, together with variability in clinical presentation and limited reproducibility of candidate biomarkers, underscores the need for standardised methodologies and longitudinal, multimodal investigations. Future work should aim to test this model empirically, refine biological stratification, and determine whether network-informed approaches can improve diagnosis and therapeutic targeting in RLS.

Abstract: Long-term Holter analysis requires software tools capable of automating signal preprocessing, temporal segmentation, probabilistic computation, and result visualization in a reproducible and interpretable manner. In this research, a modular software system for automated analysis of cardiac dynamics was developed following a software engineering perspective and an iterative lifecycle based on Scrum, including requirements definition, sprint planning, development, integration, testing, review with a medical specialist, and refinement. The platform was designed to analyze standardized temporal windows of 12, 14, and 18 h extracted from original 24 h Holter-ECG recordings and integrates a frontend, a backend, and a Python® analytical engine within a unified client–server framework. It processes Excel or CSV files containing hourly average heart-rate values, performs structural validation, discretizes the data into 10 beats-per-minute intervals, constructs empirical probability distributions, identifies recurrent dynamic patterns, and generates structured JSON outputs for web-based visualization. A complementary preprocessing module was also implemented for raw PhysioNet ECG signal records, enabling the loading of .hea and .dat files, automated R-peak detection, and extraction of hourly average heart-rate values. The system was evaluated on 113 Holter records from three open-access databases: 85 from SHDB-AF, 19 from the Long-Term ST Database, and 9 from the MIT-BIH Normal Sinus Rhythm Database. Overall structural agreement at the record level was 58.4% (66/113). To conclude, this system provides a reproducible web application pipeline for Holter signal data processing and probabilistic cardiac dynamics analysis, integrating software development, preprocessing, classification, and interpretable visualization within a modular framework.

Abstract: This study develops a mobile-supported system that local governments can use in their irregular waste collection services within the scope of smart cities. Irregular waste refers to waste that individuals or organizations produce non-periodically, which arises unexpectedly or in an unusual manner. This waste can accumulate within the city and cause environmental pollution if it is not notified to the municipality or local government for collection. Unlike small-volume household waste collected at routine times, irregular waste is generally large-volume waste such as construction rubble, vegetable oil, mineral oil, and garden waste. Municipalities have different collection vehicles with varying capacities to suit different waste types and quantities. To increase efficiency in the waste collection process, waste locations should be sequenced and vehicles appropriate to the waste type should be allocated in planning. In the irregular waste collection system developed in this study, waste locations are marked on the map applications running on mobile devices, and notifications are sent to the municipality. This provides a faster, more traceable, and effortless service compared to traditional telephone or petition-based notification methods. The Google Maps API was used for processing and visualizing the notification locations on the map. Notification data is recorded in a database by municipality, and daily or 4-hour planning is done using this data. In this study, genetic algorithm and differential evolution algorithm were used for vehicle routing and vehicle type optimization. To compare the efficiency of both methods, 4 different scenarios were designed with different numbers of waste locations and different types and quantities of waste, and the successes of the methods were compared. Route optimization is calculated not statically, however, using real-time traffic data with Google Distance Matrix API integration, generating the shortest and most economical travel route between waste locations. In this way, efficiency is increased for densely populated city centers while providing citizens with an innovative irregular waste collection infrastructure using more up-to-date technologies.

Abstract: Tsunami fragility modeling plays a central role in probabilistic coastal risk assessment; however, representing structural vulnerability under near-field tsunami conditions remains challenging due to complex hydrodynamic loading, strong spatial variability, and the presence of pre-existing earthquake damage. This paper provides a compre-hensive review and synthesis of current approaches for modeling near-field tsunami impacts on infrastructure, with a particular focus on bridging simulation-based meth-ods and empirical damage survey observations. The discussion highlights how succes-sive hazard simulations can be used to capture coupled earthquake–tsunami effects, while damage surveys offer critical insights into observed relationships between structural damage, hydrodynamic intensity measures, and spatial characteristics such as coastal proximity. Special attention is given to the role of momentum flux as a physically meaningful predictor of damage and to the systematic differences between near-field and far-field fragilities. Building on these insights, the paper outlines practical strategies for adapting baseline fragility relationships to near-field conditions, including the use of spatially dependent intensity adjustments informed by empirical data. Rather than proposing a single methodology, this work aims to provide a structured perspec-tive on existing knowledge and to guide researchers and practitioners in developing more physically consistent and data-informed fragility models for near-field tsunami risk and resilience assessments.

Abstract: Sign language translation (SLT) aims to convert sign language videos into spoken language text, serving as a critical bridge for communication between the Deaf and hearing communities. While recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in gloss-free SLT, existing methods typically rely on single-modality visual features, failing to fully exploit the complementary nature of appearance and structural cues inherent in sign language. In this architectural proposition paper, we introduce SignFuse, a novel dual-stream cross-modal fusion framework that synergistically combines CNN-based visual features with Graph Convolutional Network (GCN)-based skeletal features for gloss-free sign language translation. Our framework introduces three key innovations: (1) a Cross-Modal Fusion Attention (CMFA) module that performs bidirectional cross-attention between visual and skeletal modalities to produce enriched multimodal representations; (2) a Hierarchical Temporal Aggregation (HTA) mechanism that captures sign language dynamics at multiple temporal scales—frame-level, segment-level, and sequence-level; and (3) a Progressive Multi-Stage Training blueprint that systematically aligns visual-skeletal features with the LLM’s linguistic space through contrastive pre-training, feature alignment, and LoRA-based fine-tuning. We provide the complete mathematical formulation, detailed architectural specifications, and a fully implemented PyTorch codebase. As the computational barriers to training MLLMs remain high, we formalize the experimental methodology required to validate this framework on standard benchmarks (PHOENIX-14T, CSL-Daily, How2Sign) and extend an open invitation to the broader research community to conduct empirical validation and advance this architectural paradigm through collaboration. This work is presented as a concept and architectural framework paper, aiming to establish a theoretical foundation and encourage future empirical validation by the research community.

Abstract: Intensive salmon farming is associated with high mortality rates, highlighting the need for new welfare indicators that can detect adverse conditions earlier and less invasively than many current approaches. Existing animal-based indicators used in the industry typically depend on subjective scoring and provide information mostly after welfare problems have already developed, such as emaciation, wounds, or scale loss. Preliminary data and ongoing investigation suggest that melanin-based skin pigmentation may change dynamically with stress and condition in salmonid fishes. In this study, we present a semi-automated methodology for assessing changes in the grayscale intensity of melanin-based skin spots within the operculum region of adult Atlantic salmon (Salmo salar) kept in sea water. The pipeline combines computer vision models to detect the operculum, segment individual spots, and extract grayscale-based features for spot-level analysis over time. The method was applied to out-of-water images collected before and after exposure to a confinement episode. The results showed an overall shift in grayscale intensity from black to pigmentation fading after the challenge, although responses varied among individuals. These findings indicate that the proposed methodology can detect temporal changes in opercular melanin-based spots under applied experimental conditions. We therefore present this work as proof of principle for using computer vision to quantify changes in melanin-based skin spots as a potentially useful, non-invasive indicator of stress and welfare in Atlantic Salmon.