68994 research outputs found
Sort by
A novel optimal sensor placement software for supporting the development of monitoring systems in civil engineering structures
Full text linkThis paper proposes a new software for the Optimal Sensor Placement (OSP) featuring an intuitive graphical user interface that simplifies its use. The software automates OSP analyses, enhancing efficiency, reducing human error, and supporting the development of effective dynamic monitoring systems as a result. It incorporates five well-established OSP methods that allow users to explore the optimal number of sensors and their locations on a structure. Moreover, it accommodates both numerical and experimental data as input. Results are provided in both tabular and graphical format. It can be used in all types of structures, even though it was developed primarily for civil engineering applications. A key innovation of the proposed software is its ability to perform OSP analyses on multi-block, complex, and non-orthogonal buildings, increasing versatility. After a comprehensive description of the new software, its applicability and potentiality are shown through simple applications, as well as with real case studies
INNOVATIVE STRATEGIES FOR THE MANAGEMENT OF POSTHARVEST GRAY MOLD OF STRAWBERRIES AND BROWN ROT OF PEACHES
No full textUna quota significativa di perdite e sprechi alimentari è legata a malattie postraccolta di ortofrutticoli freschi. In questa ricerca sono state valutate strategie per gestire la muffa grigia su fragola ed il marciume bruno su pesca. Su fragola è stata valutata l’efficacia della fumigazione postraccolta di diversi oli essenziali per il controllo della muffa grigia e l’estensione della shelf life. L’esposizione agli OE di Origanum vulgare, Cinnamonum zeylanicum, Citrus bergamia, Thymus serpyllum, Malaleuca alternifolia, Thymus vulgaris e Rosmarinus officinalis si è rivelata efficace a concentrazioni tra 11,36 μL/L e 45,45 μL/L mentre gli OE Lavandula hybrida, Helichrysum italicum, Lavandula officinalis e Thymus capitatus non sono risultati efficaci. Tutti gli OE hanno mostrato sintomi di fitotossicità alle massime concentrazioni testate. Il panel test effettuato con le concentrazioni efficaci di O. vulgare, T. vulgaris, C. zeylanicum, M. alternifolia e C. bergamia ha mostrato che solo M. alternifolia è stato percepito in modo significativo. In un secondo esperimento sono stati messi a confronto e validati vari strumenti di supporto per il controllo del marciume bruno in relazione a tre cultivar di pesca, caratterizzate da diversi momenti di fioritura e maturazione. Dai risultati è emersa una correlazione tra i vari strumenti dimostrando la loro validità sul territorio della Regione Marche per prevenire il rischio
di malattia ed ottimizzare l’uso dei prodotti fitosanitari. In un terzo esperimento è stato valutato l’effetto dell’ozono gassoso in fase di stoccaggio per il controllo del marciume bruno correlato ad un trattamento preraccolta con due tipi di atomizzatori, uno convenzionale ed uno innovativo ed a una valutazione degli impatti ambientali del trattamento. Il trattamento alternato con ozono (50/200 ppb giorno/notte) per 10 e 20 giorni si è rivelato efficace su pesche non trattate in campo, tuttavia, sono stati osservati
effetti fitotossici sui frutti. Le pesche trattate con ozono hanno mostrato migliori prestazioni ambientali.
I risultati ottenuti possono essere utili per la messa a punto di strategie per una gestione integrata e sostenibile di queste due malattie.A significant portion of food loss and waste is linked to postharvest diseases of fresh fruit. This research evaluated different strategies for managing gray mold on strawberries and brown rot on peaches. The effectiveness of postharvest fumigation of various essential oils (EOs) in controlling gray mold and extending shelf life on strawberries was determined. Exposure EOs of Origanum vulgare, Cinnamonum zeylanicum, Citrus bergamia, Thymus serpyllum, Malaleuca alternifolia, Thymus vulgaris and Rosmarinus officinalis were found to be effective at concentrations between 11.36 μL/L and 45.45 μL/L, while EOs of Lavandula hybrida, Helichrysum italicum, Lavandula officinalis and Thymus capitatus were not effective in controlling gray mold. All EOs showed symptoms of phytotoxicity at the highest concentrations tested. The subsequent panel test carried out with the effective concentrations of the EOs of O. vulgare, T. vulgaris, C. zeylanicum, M. alternifolia and C. bergamia showed that only M. alternifolia was significantly perceived. A second set of trials was carried out to compare and validate various decision support tools for brown rot control in relations of three cultivar of peaches characterized by different flowering and ripening periods. The results showed a correlation between the tools, demonstrating their effectiveness in the Marche Region, central-eastern Italy, for preventing disease risk and optimizing the use of pesticides. In the third experiment the effects of applying gaseous ozone during storage to control brown rot were tested
as well as the impact of a preharvest treatment using two types of sprayers (one conventional and one innovative). The environmental impact of the treatment was also assessed. The alternating ozone treatment (50/200 ppb day/night) was effective in controlling brown rot on peach fruits untreated in the field. Slight phytotoxic effects were observed on fruits exposed to ozone. Peaches treated with ozone showed better environmental performance. The results can contribute to set up alternative strategies for sustainable management of these diseases
EU EMISSION TRADE SYSTEM LINEAMENTI, INTERAZIONE E CRITICITA DI UN MERCATO ANCORA IN FIERI
No full textLa presente tesi di dottorato analizza le dinamiche giuridiche, economiche e politiche dell’Emission Trading System (ETS), strumento cardine della politica climatica europea. Il lavoro esplora l’interazione tra diritto ambientale e diritto dell’energia, evidenziando come la decarbonizzazione stia ridefinendo la governance sovranazionale. Partendo dalle basi teoriche dei fallimenti di mercato e delle esternalità negative, si mostra l’evoluzione storica dell’ETS, dal periodo pilota all’attuale Fase 4, fino alla creazione dell’ETS 2 per edifici e trasporti. La tesi esamina inoltre il rapporto tra ETS e meccanismi di protezione del mercato unico, come il Carbon Border Adjustment Mechanism (CBAM), e le implicazioni settoriali e nazionali, con particolare attenzione al settore marittimo e al sistema portuale italiano. L’analisi evidenzia come l’applicazione uniforme di regole sovranazionali richieda correttivi specifici per tutelare asset strategici nazionali, suggerendo percorsi per trasformare vincoli normativi in opportunità di innovazione tecnologica e sviluppo sostenibile
Precision agriculture in support of mediterranean pastoral systems
No full textI sistemi pastorali mediterranei sono profondamente intrecciati con gli ecosistemi di prateria, e costituiscono la base della biodiversità, del funzionamento del paesaggio e della fornitura di importanti servizi ecosistemici. Tuttavia, questi sistemi sono sempre più minacciati dalle pressioni congiunte dei cambiamenti socio-economici, delle trasformazioni nell’uso del suolo e dei cambiamenti climatici. Affrontare queste sfide richiede approcci integrati capaci di sostenere una gestione adattiva e trasformativa. Questa tesi indaga come l’agricoltura di precisione, il telerilevamento e l'analisi dei servizi ecosistemici possano contribuire alla resilienza dei sistemi pastorali mediterranei nel contesto del cambiamento globale.
La ricerca si sviluppa attorno a tre obiettivi. In primo luogo, la modellazione predittiva della vegetazione è stata utilizzata per valutare gli impatti del cambiamento climatico sulla dinamica dei pascoli in scenari contrastanti di gestione e clima. Attraverso l’applicazione di quattro algoritmi di machine learning a due aree mediterranee — un sistema montano temperato e una pianura arida — le proiezioni future hanno evidenziato spostamenti altitudinali verso l’alto di arbusteti e praterie continue, con espansione delle praterie discontinue nelle aree temperate e aumento della copertura di vegetazione legnosa nelle regioni aride. L’aumento delle temperature e la diminuzione delle precipitazioni hanno ulteriormente rafforzato tali tendenze. Tra gli algoritmi testati, MaxEnt si è dimostrato particolarmente efficace con dataset limitati e basati su soli punti di presenza, confermando l’idoneità di questo algoritmo in contesti con scarsità di dati. I risultati sostengono la necessità di strategie di adattamento specifiche per sito, che spaziano dalla diversificazione delle risorse foraggere e dal miglioramento delle infrastrutture nei sistemi temperati, fino all’agroforestazione, all’impiego di razze tolleranti alla siccità e a una gestione più efficiente delle risorse nelle zone semi-aride e aride.
In secondo luogo, la tesi esplora come le praterie contribuiscano alla fornitura di servizi ecosistemici. In sei casi di studio mediterranei, diversi tipi di pascolo hanno mostrato di fornire distinti “pacchetti” di servizi ecosistemici in funzione delle modalità di gestione, del clima e della struttura della vegetazione. A scala di paesaggio, le analisi condotte in un caso di studio montano dell’Italia centrale hanno indicato che mosaici di praterie e formazioni legnose offrono bundles di servizi ecosistemici più equilibrati, limitando al contempo i disservizi ecosistemici. Questi risultati evidenziano l’importanza di mantenere mosaici di paesaggio eterogenei per sostenere dei sistemi pastorali multifunzionali.
In terzo luogo, la tesi dimostra come approcci integrati — che combinano telerilevamento, sensori prossimali, indici di vegetazione, indicatori di servizi ecosistemici e tecniche di machine learning — possano supportare la pianificazione partecipativa. Lo studio ha evidenziato il potenziale di queste tecniche come strumenti dialogici in grado di quantificare trade-off e sinergie tra diversi pacchetti di servizi ecosistemici, che possono consentire agli stakeholder di co-progettare strategie di gestione adattiva fondate sia su evidenze ecologiche sia su priorità locali.
Nonostante i progressi presentati, permangono diverse criticità. La modellazione predittiva è sensibile alla selezione delle variabili, alla risoluzione dei dati e alle procedure di cross-validation impiegate; le analisi dei servizi ecosistemici sono limitate dalla scarsità di dati sui tratti funzionali, dalla letteratura datata e da classificazioni degli habitat incoerenti tra Paesi. Superare tali vincoli richiederà una migliore armonizzazione dei dati, l’uso di modelli ensemble, approcci alla vegetazione a livello di comunità e una maggiore integrazione delle dimensioni socio-economiche e culturali.
Nel complesso, questa tesi fornisce contributi metodologici e indicazioni pratiche per il mantenimento di sistemi pastorali mediterranei resilienti e adattivi. Collegando agricoltura di precisione, modellazione ecologica e processi partecipativi, essa delinea un quadro integrato capace di orientare le decisioni gestionali per affrontare il cambiamento globale.Mediterranean pastoral systems are deeply intertwined with grassland and rangeland ecosystems, which underpin biodiversity, landscape functioning, and the delivery of essential ecosystem services. Yet these systems are increasingly threatened by the combined pressures of socio-economic change, land-use transformations, and climate variability. Addressing these challenges requires integrative approaches capable of supporting adaptive and transformative management. This thesis investigates how precision agriculture, remote sensing, and ecosystem service (ES) assessments can contribute to the resilience of Mediterranean pastoral systems under global change.
The research is developed around three objectives. First, predictive vegetation modelling was used to assess the impacts of climate change on rangeland dynamics under contrasting management and climate scenarios. Using four machine-learning algorithms applied to two Mediterranean areas—a temperate mountain system and an arid lowland—future projections highlighted upward shifts of shrublands and continuous grasslands, expansion of discontinuous grasslands in temperate areas, and increased woody cover in arid regions. Rising temperatures and declining precipitation further reinforced these patterns. Among the tested algorithms, MaxEnt proved particularly effective with limited and presence-only datasets, confirming its suitability for data-scarce environments. The findings support the need for site-specific adaptation strategies ranging from diversified forage resources and infrastructure improvements in temperate systems to agroforestry, drought-tolerant breeds, and improved resource management in semi-arid and arid zones.
Second, the thesis explores how rangelands contribute to ES provision. Across six Mediterranean case studies, different rangeland types were shown to deliver distinct ES bundles depending on management approaches, climate, and vegetation structure. At the landscape scale, analyses from a mountain case study in central Italy indicated that mosaics of grasslands and woody formations provide the most balanced ES portfolios, while also limiting ecosystem disservices. These results highlight the importance of maintaining heterogeneous landscape structures to support multifunctional pastoral systems.
Third, the thesis demonstrates how integrated approaches—combining remote sensing, proximal sensing, vegetation indices, ES indicators, and machine-learning techniques—can support participatory planning. Case studies illustrate the potential of dialogical tools that quantify trade-offs and synergies among ES bundles, enabling stakeholders to co-design adaptive management strategies grounded in both ecological evidence and local priorities.
Despite the advances presented, several caveats remain. Predictive modelling is sensitive to variable selection, data resolution, and cross-validation procedures; ES assessments are limited by scarce trait data, outdated literature, and inconsistent habitat classifications across countries. Addressing these constraints will require improved data harmonisation, ensemble modelling, community-level vegetation approaches, and greater integration of socio-economic and cultural dimensions.
Overall, this thesis provides methodological contributions and practical insights for supporting resilient and adaptive Mediterranean pastoral systems. By bridging precision agriculture, ecological modelling, and participatory processes, it outlines an integrative framework capable of informing management decisions to cope global change
Development of Algorithms for the Processing of Data from Contactless Sensors
No full textQuesta tesi presenta algoritmi innovativi per il processamento dei dati acquisiti con sensori senza contatto, che hanno il vantaggio della non invasività rispetto ai sensori indossabili. In particolare, la tesi esplora come algoritmi per l'elaborazione di segnali radar e video possano essere impiegati per il monitoraggio dei comportamenti e dei segnali fisiologici di un soggetto in ambienti indoor, con applicazioni negli ambienti di vita assistita e nella sanità. L'obiettivo finale è creare un sistema che rilevi e monitori il movimento di un soggetto e il suo segnale di respirazione. Di conseguenza, vengono sviluppate e discusse quattro linee di ricerca; la prima linea nel Capitolo 3 descrive algoritmi basati su algoritmi You-Only-Look-Once (YOLO) per la localizzazione e il tracciamento di un soggetto in un ambiente interno con un radar Multiple-Input-Multiple-Output (MIMO) ed una telecamera di profondità, ottenendo errori di localizzazione tra 0,16 e 0,72 m per il radar e tra 0,08 e 0,31 m per la telecamera di profondità; una volta che un soggetto è localizzato nell'ambiente, è possibile estrarre informazioni sul suo movimento e sulla sua attività e per questo motivo vengono sviluppate le due successive linee di ricerca: il Capitolo 4 descrive uno studio sugli algoritmi per il riconoscimento delle attività umane da video, utilizzando l'estrazione delle posa basata su MediaPipe e classificatori di machine learning "lightweight" per identificare attività legate all'igiene su RaspBerry Pi, con F1-score superiori al 94%; successivamente, il Capitolo 5 presenta algoritmi per il riconoscimento di traccie micro-Doppler con un radar a singolo chip; il capitolo inizia da uno studio di fattibilità sull'estrazione di parametri spazio-temporali dell'andatura attraverso segnali micro-Doppler e si conclude con metodi basati su machine learning e deep learning per classificare sei diverse camminate, raggiungendo fino al 95,6% di accuratezza. Come ultima linea di ricerca, nel Capitolo 6 viene condotto uno studio sugli algoritmi per il monitoraggio respiratorio con radar MIMO e telecamere di profondità; il capitolo introduce un nuovo indice di qualità del segnale basato sull'analisi in frequenza e descrive algoritmi per l'estrazione della frequenza respiratoria da soggetti in movimento acquisiti con una telecamera di profondità ed un radar MIMO ottenendo errori vicino a 1 respiro al minuto. Infine, gli approcci proposti sono analizzati nel Capitolo 7 nel contesto del monitoraggio e della prevenzione della fragilità come applicazione o caso d'uso, discutendo le possibili implicazioni delle linee di ricerca nell'identificazione di indicatori comuni di fragilità.This thesis presents novel algorithms for processing data acquired through contactless sensors, which have seen an increased interest due to their non-invasiveness compared to wearable sensors. In particular, the thesis examines how algorithms processing radar and depth camera signals can provide adequate monitoring of a subject’s behavior and physiology in indoor settings, with applications in ambient assisted living and healthcare. The ultimate goal is to create a system within an environment that detects and monitors a subject's motion and the respiration signal. As a consequence, four lines of research are developed and discussed; the first line in Chapter 3 is the starting point and describes algorithms, based on You-Only-Look-Once (YOLO) detectors for the localization and tracking of a subject in an indoor environment with a Multiple-Input-Multiple-Output (MIMO) radar and a depth camera, obtaining localization errors between 0.16 and 0.72 m for the radar and within 0.08 and 0.31 m for the depth camera; once a subject is located in the environment it is possible to extract information about the movement and activity performed and for this reason, the two following research lines are developed: Chapter 4 describes a study on algorithms for human activity recognition from video camera, using MediaPipe-based pose extraction and lightweight machine learning classifiers to identify hygiene-related activities on embedded platforms, with weighted F1-scores higher than 94% under real-time constraints; then, Chapter 5 presents algorithms for micro-Doppler recognition with a single-chip radar, starting from a feasibility study for the extraction of gait spatio-temporal parameters and concluding with methods based on machine learning and deep learning to discriminate between micro-Doppler signatures to classify six walking patterns, reaching up to 95.6% accuracy. As the last research line, a study on algorithms for respiratory monitoring with MIMO radars and depth cameras is conducted in Chapter 6, introducing a novel frequency-based signal quality index and extracting the respiration rate from moving subjects recorded with a depth camera and a MIMO radar with errors close to 1 breath per minute. Eventually, Chapter 7 discusses the proposed approaches analyzed in the context of frailty monitoring and prevention as an application or use case, providing possible implications of the research line in identifying common frailty indicators
Metataxonomic Exploration of Non‐Korean Kimchi Made With Sea Fennel (Crithmum maritimum L.)
No full textIn this study, a non-Korean kimchi formulated with the unconventional ingredient sea fennel ( Crithmum maritimum L.) was investigated under both spontaneous and starter-driven fermentation to assess microbial composition and dynamics. Metatax- onomic analyses revealed significant differences between starter-inoculated and control (spontaneously fermented) kimchi. Weissella koreensis and members of the genus Companilactobacillus dominated the control samples, whereas Levilactobacillus spp., Lactiplantibacillus plantarum , and Pediococcus pentosaceus prevailed in the starter-inoculated kimchi. Fungal community profiling consistently showed the dominance of the genus Alternaria throughout fermentation in both prototypes. Kazachstania servazzi became abundant at late fermentation in both kimchi types, while Saccharomyces cerevisiae appeared exclusively in the control samples during mid-fermentation. Isolation of lactic acid bacteria provided further insights into active microbial populations across fermentation stages. W. koreensis and Leuconostoc mesenteroides were the most frequently detected species. The isolates displayed considerable heterogeneity in enzymatic activity profiles: strong leucine arylamidase and β-glucosidase activities were identified, both potentially influencing kimchi’s sensory traits. Importantly, no β-glucuronidase activity was detected, suggesting safety of the isolates with respect to cancer-associated risks. Conversely, three isolates carried the hdcA gene, and none exhibited bacteriocin activity against Listeria innocua (used as a surrogate for Listeria monocytogenes ). Most isolates demonstrated robust growth and activity in a kimchi-like medium, underscoring their performance as starter or adjunct cultures for guided fermentation of kimchi
Navigating the Tensions of Sustainable Business Model Innovation: Antecedents, Enablers, Barriers and Supporting Tools
No full textGrowing environmental and social challenges have progressively called into question the adequacy of conventional business models, prompting organizations to reconsider how value is created, delivered, and captured. In this context, Sustainable Business Model Innovation (SBMI) has emerged as a research domain of increasing relevance. Despite the consolidation of the literature on sustainable business models, a systematic understanding of the conditions preceding SBMI processes, the factors that enable or hinder their development, and the tools that support such transformation processes remains limited. The thesis is structured around three interrelated studies. The first study consists of a cross-sectional field study conducted across eight German organizations and analyzes the antecedents that orient transformation processes toward sustainable business models, with particular attention to motivations, objectives, organizational levers, critical challenges, and dynamic adaptive capabilities. The second study adopts a grounded-theory literature review to systematize the fragmented literature on SBMI enablers and barriers, identifying five main categories: market and customer acceptance, value chain, organizational aspects, regulation and policy, and financial factors. The third study provides a critical review of thirteen SBMI tools, assessing their conceptual foundations and their capacity to support sustainability-oriented business model innovation processes. Overall, the thesis conceptualizes SBMI as a dynamic and processual phenomenon, embedded in organizational contexts and characterized by tensions and equilibria, thereby contributing to a more nuanced understanding of how organizations initiate and manage sustainability-oriented business model transformations
Machine learning-based prediction of passive gears from vessel tracking data in small-scale multi-gear fisheries
No full textSmall-scale fisheries (SSF) play a crucial role in the Mediterranean Sea, contributing significantly to coastal livelihoods, employment, food security, and local economies. These fisheries are highly diverse and often operate with multiple passive gears within a single trip, targeting different species based on season, market demand, and fisher preference. This gear diversity, combined with the absence of trip-level gear reporting, poses a challenge for accurate monitoring, gear-specific effort estimation, and sustainable management. This study presents a Machine Learning-based approach to predict the type of fishing gear used during individual hauling events from high frequency vessel tracking data. Tracking data were collected from 10 SSF multi-gear vessels based in Ancona (Italy) between January 2023 and March 2024, and over 7000 hauling events were detected from a total of 1634 trips. Each event was labelled through fisher validation and expert-informed spatial analysis. Predictive models – Ridge Classifier, Logistic Regression, Decision Tree, Random Forest, and Extreme Gradient Boosting – were trained and tested using various sets of predictors. Two classification levels were explored: i) gear categories (nets vs. pots) and ii) specific gear types (i.e., gillnets, trammel nets, and three types of pots). With fewer predictors and optimized tuning, Random Forest reached 95% test accuracy for gear category and Extreme Gradient Boosting achieved 86% for specific gear type classification, successfully maintaining low levels of overfitting. The shared, reproducible hauling event-level approach offers a scalable tool for automated gear classification in multi-gear fisheries and contributes to more precise monitoring, management, and traceability in small-scale coastal systems
The impact of sex and gender on Fibromyalgia Syndrome: data from the Italian Fibromyalgia Registry
No full textMost fibromyalgia (FM) patients are women, with a female-to-male ratio of 3:1. While sex differences in pain perception and description have been reported, the impact of sex and gender on FM severity remains controversial. Additionally, sex-related differential item functioning (DIF) in FM assessment tools has not yet been explored. The primary aim of this study was to analyze sex- and gender-related differences in FM severity using data from a web-based FM registry. The secondary aim was to assess sex-related DIF in three commonly used questionnaires: the Polysymptomatic Distress Scale (PDS), the modified Fibromyalgia Assessment Status (ModFAS), and the revised Fibromyalgia Impact Questionnaire (FIQR). Data from 331 male and 331 female patients, matched for age and body mass index (BMI) and fulfilling ACR 2010/2011 criteria, were retrospectively collected from the Italian Fibromyalgia Registry. Multivariate analyses were conducted on the overall and sex-stratified populations. Sex-related DIF was assessed using a hybrid Ordinal Logistic Regression/Item Response Theory method. Female sex was significantly associated with greater physical impairment, despite no differences in overall disease severity. In stratified analyses, married status influenced disease impact and burden in women, whereas BMI was associated with higher disability in men. Significant sex-related DIF was detected in one item of the Symptom Severity Scale of the PDS. Women with FM experience greater physical impairment than men, despite similar disease severity. Sociodemographic factors influence FM differently across sexes. Despite minor DIF, the three FM-specific questionnaires appear valid for use in both male and female patients
Behavioral Engagement in VR-Based Sign Language Learning: Visual Attention as a Predictor of Performance and Temporal Dynamics
No full textUnderstanding how learners engage with immersive sign language training environments is essential for advancing virtual reality-based education and inclusion. This study analyzes behavioral engagement in SONAR, a virtual reality application designed for sign language training and validation. We focus on three automatically derived engagement indicators (Visual Attention (VA), Video Replay Frequency (VRF), and Post-Playback Viewing Time (PPVT)) and examine their relationship with learning performance in a sample of 117 university students. Participants completed a self-paced Training phase with 12 sign language instructional videos, followed by a Validation quiz assessing retention. We employed Pearson correlation analysis to examine the relationships between engagement indicators and quiz performance, followed by binomial Generalized Linear Model (GLM) regression to assess their joint predictive contributions. Additionally, we conducted temporal analysis by aggregating moment-to-moment VA traces across all learners to characterize engagement dynamics during the learning session. Results show that VA exhibits a strong positive correlation with quiz performance (r = 0.76), followed by PPVT (r = 0.66), whereas VRF shows no meaningful association. A binomial GLM confirms that VA and PPVT are significant predictors of learning success, jointly explaining a substantial proportion of performance variance (pseudo−R2 = 0.83). Going beyond outcome-oriented analysis, we characterize temporal engagement patterns by aggregating moment-to-moment VA traces across all learners. The temporal profile reveals distinct attention peaks aligned with informationally dense segments of both training and validation videos, as well as phase-specific engagement dynamics, including initial acclimatization, oscillatory attention cycles during learning, and pronounced attentional peaks during assessment. Together, these findings highlight the central role of sustained and strategically allocated visual attention in VR-based sign language learning and demonstrate the value of behavioral trace data for understanding and predicting learner engagement in immersive environments