Search Results (1,023)

Xyloglucan endotransglucosylase/hydrolases (XTHs) are a class of cell wall-associated enzymes involved in the construction and remodeling of cellulose/xyloglucan crosslinks. However, knowledge of this gene family in the model monocot Brachypodium distachyon is limited. A total of 29 BdXTH genes were identified from the whole genome, and these were further divided into three subgroups (Group I/II, Group III, and the Ancestral Group) through evolutionary analysis. Gene structure and protein motif analyses indicate that closely clustered BdXTH genes are relatively conserved within each group. A highly conserved amino acid domain (DEIDFEFLG) responsible for catalytic activity was identified in all BdXTH proteins. We detected three pairs of segmentally duplicated BdXTH genes and five groups of tandemly duplicated BdXTH genes, which played vital roles in the expansion of the BdXTH gene family. Cis-elements related to hormones, growth, and abiotic stress responses were identified in the promoters of each BdXTH gene, and when roots were treated with two abiotic stresses (salinity and drought) and four plant hormones (IAA, auxin; GA3, gibberellin; ABA, abscisic acid; and BR, brassinolide), the expression levels of many BdXTH genes changed significantly. Transcriptional analyses of the BdXTH genes in 38 tissue samples from the publicly available RNA-seq data indicated that most BdXTH genes have distinct expression patterns in different tissues and at different growth stages. Overexpressing the BdXTH27 gene in Brachypodium led to reduced root length in transgenic plants, which exhibited higher cellulose levels but lower hemicellulose levels compared to wild-type plants. Our results provide valuable information for further elucidation of the biological functions of BdXTH genes in the model grass B. distachyon. Full article

Candidozyma auris is a multidrug-resistant, thermo- and osmotolerant yeast capable of persisting on biotic and abiotic surfaces, attributes likely linked to its cell wall composition. Here, seven putative genes encoding yapsins, aspartyl proteases GPI-anchored to the membrane or cell wall, were identified in the genomes of C. auris CJ97 and 20-1498, from clades III and IV, respectively. The C. auris YPS1 gene is orthologous to the SAP9 of C. albicans. The YPS7 gene is orthologous to YPS7 in C. glabrata and S. cerevisiae, so that they may share similar roles. An in silico analysis suggested an interaction between pepstatin and the catalytic domain of Yps1 and Yps7. Although this inhibitor, when combined with caffeine, had a subtle effect on the growth of C. auris, it induced alterations in the cell wall. CauYPS1 and CauYPS7 expression increased under nutrient starvation and NaCl, and at 42 °C. The transcriptome of the 20-1498 strain suggests that autophagy may play a role in thermal stress, probably degrading deleterious proteins or maintaining cell wall and vacuolar homeostasis. Therefore, CauYps1 and CauYps7 may play a role in the cell wall integrity of C. auris in stress conditions, and they could be a target of new antifungal or antivirulence agents. Full article

This paper presents a novel, multi-stage modelling approach for integrating Generative AI (GenAI) tools into design-based STEM education, promoting sustainability and 21st-century problem-solving skills. The proposed methodology includes (i) a conceptual model that defines structural aspects of the domain at a high abstraction level; (ii) a contextual model for defining the internal context; (iii) a GenAI-based model for solving the STEM task, which consists of a generic model for integrating GenAI tools into STEM-driven education and a process model, presenting learning/design processes using those tools. A case study involving the design of an autonomous folkrace robot illustrates the implementation of the approach. Based on Likert-scale evaluations, quantitative results demonstrate a significant impact of GenAI tools in enhancing critical thinking, conceptual understanding, creativity, and engineering practices, particularly during the prototyping and testing phases. This paper concludes that the structured integration of GenAI tools supports personalized, inquiry-based, and sustainable STEM education, while also raising new challenges in prompt engineering and ethical use. This approach provides educators with a systematic pathway for leveraging AI to develop STEM-based skills essential for future sustainable development. Full article

Background: Rock–blast design is a canonical inverse problem that joins elastodynamic partial differential equations (PDEs), fracture mechanics, and stochastic heterogeneity. Objective: Guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol, a systematic review of mathematical methods for geomechanically informed blast modelling and optimisation is provided. Methods: A Scopus–Web of Science search (2000–2025) retrieved 2415 records; semantic filtering and expert screening reduced the corpus to 97 studies. Topic modelling with Bidirectional Encoder Representations from Transformers Topic (BERTOPIC) and bibliometrics organised them into (i) finite-element and finite–discrete element simulations, including arbitrary Lagrangian–Eulerian (ALE) formulations; (ii) geomechanics-enhanced empirical laws; and (iii) machine-learning surrogates and multi-objective optimisers. Results: High-fidelity simulations delimit blast-induced damage with ≤0.2 m mean absolute error; extensions of the Kuznetsov–Ram equation cut median-size mean absolute percentage error (MAPE) from 27% to 15%; Gaussian-process and ensemble learners reach a coefficient of determination ($R^2>0.95$) while providing closed-form uncertainty; Pareto optimisers lower peak particle velocity (PPV) by up to 48% without productivity loss. Synthesis: Four themes emerge—surrogate-assisted PDE-constrained optimisation, probabilistic domain adaptation, Bayesian model fusion for digital-twin updating, and entropy-based energy metrics. Conclusions: Persisting challenges in scalable uncertainty quantification, coupled discrete–continuous fracture solvers, and rigorous fusion of physics-informed and data-driven models position blast design as a fertile test bed for advances in applied mathematics, numerical analysis, and machine-learning theory. Full article

Introduction: Burnout syndrome, long described as an “occupational phenomenon”, now affects 15–20% of the general workforce and more than 50% of clinicians, teachers, social-care staff and first responders. Its precise nosological standing remains disputed. We conducted a mechanistic review of electroencephalography (EEG) studies to determine whether burnout is accompanied by reproducible brain-function alterations that justify disease-level classification. Methods: Following PRISMA-adapted guidelines, two independent reviewers searched PubMed/MEDLINE, Scopus, Google Scholar, Cochrane Library and reference lists (January 1980–May 2025) using combinations of “burnout,” “EEG”, “electroencephalography” and “event-related potential.” Only English-language clinical investigations were eligible. Eighteen studies (n = 2194 participants) met the inclusion criteria. Data were synthesised across three domains: resting-state spectra/connectivity, event-related potentials (ERPs) and longitudinal change. Results: Resting EEG consistently showed (i) a 0.4–0.6 Hz slowing of individual-alpha frequency, (ii) 20–35% global alpha-power reduction and (iii) fragmentation of high-alpha (11–13 Hz) fronto-parietal coherence, with stage- and sex-dependent modulation. ERP paradigms revealed a distinctive “alarm-heavy/evaluation-poor” profile; enlarged N2 and ERN components signalled hyper-reactive conflict and error detection, whereas P3b, Pe, reward-P3 and late CNV amplitudes were attenuated by 25–50%, indicating depleted evaluative and preparatory resources. Feedback processing showed intact or heightened FRN but blunted FRP, and affective tasks demonstrated threat-biassed P3a latency shifts alongside dampened VPP/EPN to positive cues. These alterations persisted in longitudinal cohorts yet normalised after recovery, supporting trait-plus-state dynamics. The electrophysiological fingerprint differed from major depression (no frontal-alpha asymmetry, opposite connectivity pattern). Conclusions: Across paradigms, burnout exhibits a coherent neurophysiological signature comparable in magnitude to established psychiatric disorders, refuting its current classification as a non-disease. Objective EEG markers can complement symptom scales for earlier diagnosis, treatment monitoring and public-health surveillance. Recognising burnout as a clinical disorder—and funding prevention and care accordingly—is medically justified and economically imperative. Full article

Artificial intelligence (AI) agents are increasingly shaping vital sectors of society, including healthcare, education, supply chains, and finance. As their influence grows, AI alignment research plays a pivotal role in ensuring these systems are trustworthy, transparent, and aligned with human values. Leveraging blockchain technology, proven over the past decade in enabling transparent, tamper-resistant distributed systems, offers significant potential to strengthen AI alignment. However, despite its potential, the current AI alignment literature has yet to systematically explore the effectiveness of blockchain in facilitating secure and ethical behavior in AI agents. While existing systematic literature reviews (SLRs) in AI alignment address various aspects of AI safety and AI alignment, this SLR specifically examines the gap at the intersection of AI alignment, blockchain, and ethics. To address this gap, this SLR explores how blockchain technology can overcome the limitations of existing AI alignment approaches. We searched for studies containing keywords from AI, blockchain, and ethics domains in the Scopus database, identifying 7110 initial records on 28 May 2024. We excluded studies which did not answer our research questions and did not discuss the thematic intersection between AI, blockchain, and ethics to a sufficient extent. The quality of the selected studies was assessed on the basis of their methodology, clarity, completeness, and transparency, resulting in a final number of 46 included studies, the majority of which were journal articles. Results were synthesized through quantitative topic analysis and qualitative analysis to identify key themes and patterns. The contributions of this paper include the following: (i) presentation of the results of an SLR conducted to identify, extract, evaluate, and synthesize studies on the symbiosis of AI alignment, blockchain, and ethics; (ii) summary and categorization of the existing benefits and challenges in incorporating blockchain for AI alignment within the context of ethics; (iii) development of a framework that will facilitate new research activities; and (iv) establishment of the state of evidence with in-depth assessment. The proposed blockchain-based AI alignment framework in this study demonstrates that integrating blockchain with AI alignment can substantially enhance robustness, promote public trust, and facilitate ethical compliance in AI systems. Full article

Background/Objectives: The RTK-RAS signaling cascade is a central axis in colorectal cancer (CRC) pathogenesis, governing cellular proliferation, survival, and therapeutic resistance. Somatic alterations in key pathway genes—including KRAS, NRAS, BRAF, and EGFR—are pivotal to clinical decision-making in precision oncology. However, the integration of these genomic events with clinical and demographic data remains hindered by fragmented resources and a lack of accessible analytical frameworks. To address this challenge, we developed AI-HOPE-RTK-RAS, a domain-specialized conversational artificial intelligence (AI) system designed to enable natural language-based, integrative analysis of RTK-RAS pathway alterations in CRC. Methods: AI-HOPE-RTK-RAS employs a modular architecture combining large language models (LLMs), a natural language-to-code translation engine, and a backend analytics pipeline operating on harmonized multi-dimensional datasets from cBioPortal. Unlike general-purpose AI platforms, this system is purpose-built for real-time exploration of RTK-RAS biology within CRC cohorts. The platform supports mutation frequency profiling, odds ratio testing, survival modeling, and stratified analyses across clinical, genomic, and demographic parameters. Validation included reproduction of known mutation trends and exploratory evaluation of co-alterations, therapy response, and ancestry-specific mutation patterns. Results: AI-HOPE-RTK-RAS enabled rapid, dialogue-driven interrogation of CRC datasets, confirming established patterns and revealing novel associations with translational relevance. Among early-onset CRC (EOCRC) patients, the prevalence of RTK-RAS alterations was significantly lower compared to late-onset disease (67.97% vs. 79.9%; OR = 0.534, p = 0.014), suggesting the involvement of alternative oncogenic drivers. In KRAS-mutant patients receiving Bevacizumab, early-stage disease (Stages I–III) was associated with superior overall survival relative to Stage IV (p = 0.0004). In contrast, BRAF-mutant tumors with microsatellite-stable (MSS) status displayed poorer prognosis despite higher chemotherapy exposure (OR = 7.226, p < 0.001; p = 0.0000). Among EOCRC patients treated with FOLFOX, RTK-RAS alterations were linked to worse outcomes (p = 0.0262). The system also identified ancestry-enriched noncanonical mutations—including CBL, MAPK3, and NF1—with NF1 mutations significantly associated with improved prognosis (p = 1 × 10⁻⁵). Conclusions: AI-HOPE-RTK-RAS exemplifies a new class of conversational AI platforms tailored to precision oncology, enabling integrative, real-time analysis of clinically and biologically complex questions. Its ability to uncover both canonical and ancestry-specific patterns in RTK-RAS dysregulation—especially in EOCRC and populations with disproportionate health burdens—underscores its utility in advancing equitable, personalized cancer care. This work demonstrates the translational potential of domain-optimized AI tools to accelerate biomarker discovery, support therapeutic stratification, and democratize access to multi-omic analysis. Full article

Background/Objectives: Heart rate variability (HRV) has been widely investigated as a predictor of disease and mortality across diverse patient populations; however, there remains no consensus on the optimal set or combination of time and frequency domain nor on nonlinear features for reliable prediction across clinical contexts. Given the relevance of the COVID-19 pandemic and the unique clinical profiles of these patients, this retrospective observational study explored the potential of HRV analysis for early prediction of in-hospital mortality using ECG signals recorded during the initial moments of ICU admission in COVID-19 patients. Methods: HRV indices were extracted from four ECG leads (I, II, III, and aVF) using sliding windows of 2, 5, and 7 min across observation intervals of 15, 30, and 60 min. The raw data posed significant challenges in terms of structure, synchronization, and signal quality; thus, from an original set of 381 records from 321 patients, after data pre-processing steps, a final dataset of 82 patients was selected for analysis. To manage data complexity and evaluate predictive performance, two feature selection methods, four feature reduction techniques, and five classification models were applied to identify the optimal approach. Results: Among the feature aggregation methods, compiling feature means across patient windows (Method D) yielded the best results, particularly for longer observation intervals (e.g., using LDA, the best AUC of $0.82\pm 0.13$ was obtained with Method D versus $0.63\pm 0.09$ with Method C using 5 min windows). Linear Discriminant Analysis (LDA) was the most consistent classification algorithm, demonstrating robust performance across various time windows and further improvement with dimensionality reduction. Although Gradient Boosting and Random Forest also achieved high AUCs and F1-scores, their performance outcomes varied across time intervals. Conclusions: These findings support the feasibility and clinical relevance of using short-term HRV as a noninvasive, data-driven tool for early risk stratification in critical care, potentially guiding timely therapeutic decisions in high-risk ICU patients and thereby reducing in-hospital mortality. Full article

Thyroid hormones (thyroxine, T₄, and triiodothyronine, T₃) are indispensable for sustaining vertebrate life, and their deficiency gives rise to a wide range of symptoms characteristic of hypothyroidism, affecting 5–10% of the world’s population. The precursor for thyroid hormone synthesis is thyroglobulin (Tg), a large iodoglycoprotein consisting of upstream regions I-II-III (responsible for synthesis of most T₄) and the C-terminal CholinEsterase-Like (ChEL) domain (responsible for synthesis of most T₃, which can also be generated extrathyroidally by T₄ deiodination). Using CRISPR/Cas9-mediated mutagenesis, we engineered a knock-in of secretory ChEL into the endogenous TG locus. Secretory ChEL acquires Golgi-type glycans and is properly delivered to the thyroid follicle lumen, where T₃ is first formed. Homozygous knock-in mice are capable of thyroidal T₃ synthesis but largely incompetent for T₄ synthesis such that T₄-to-T₃ conversion contributes little. Instead, T₃ production is regulated thyroidally by thyrotropin (TSH). Compared to cog/cog mice with conventional hypothyroidism (low serum T₄ and T₃), the body size of ChEL-knock-in mice is larger; although, these animals with profound T₄ deficiency did exhibit a marked elevation of serum TSH and a large goiter, despite normal circulating T₃ levels. ChEL knock-in mice exhibited a normal expression of hepatic markers of thyroid hormone action but impaired locomotor activities and increased anxiety-like behavior, highlighting tissue-specific differences in T₃ versus T₄ action, reflecting key considerations in patients receiving thyroid hormone replacement therapy. Full article

Background and Objectives: Uterine cancer is the most common gynaecologic malignancy in developed countries, yet the psychosocial sequelae of treatment are incompletely described. This prospective, single-centre study quantified six-month changes in the quality of life (QoL) and perceived stress in women with newly diagnosed uterine cancer and explored clinical moderators of change. Methods: Participants completed four validated self-report questionnaires: the 36-item Short-Form Health Survey (SF-36), the 26-item World Health Organization Quality-of-Life-BREF (WHOQOL-BREF), the 30-item EORTC QLQ-C30 and the 10-item Perceived Stress Scale (PSS-10) before therapy and again six months after surgery ± adjuvant chemoradiation. Subgroup analyses were performed for stage (FIGO I–II vs. III–IV). Results: Mean SF-36 Physical Functioning improved from 58.7 ± 12.1 to 63.1 ± 12.6 (Δ = +4.4 ± 7.3; p = 0.000, d = 0.36). PSS declined from 24.1 ± 5.6 to 20.8 ± 5.4 (Δ = −3.3 ± 5.0; p < 0.001, d = 0.66). The WHOQOL-BREF Physical and Psychological domains rose by 4.4 ± 6.9 and 3.5 ± 7.3 points, respectively (both p < 0.01). EORTC QLQ-C30 Global Health increased 5.1 ± 7.6 points (p < 0.001) with parallel reductions in fatigue (−5.4 ± 9.0) and pain (−4.8 ± 8.6). Advanced-stage patients showed larger reductions in stress (ΔPSS −3.5 ± 2.5 vs. −2.3 ± 2.3; p = 0.036) but similar QoL gains. ΔPSS correlated inversely with ΔWHOQOL Psychological (r = −0.53) and ΔSF-36 Mental Health (r = −0.49) and positively with ΔEORTC Global Health (r = −0.42) (all p < 0.001). Conclusions: Over six months, multimodal uterine cancer treatment was associated with clinically meaningful QoL improvements and moderate stress reduction. Greater stress relief paralleled superior gains in psychological and global health indices, highlighting the importance of integrative survivorship care. Full article

Reward processing is a vital function for health and survival and is impaired in various psychiatric and neurological disorders. Using a monetary gambling task, the current study aims to elucidate neural substrates in the reward network underlying the evaluation of win versus loss outcomes and their association with behavioral characteristics, such as impulsivity and task performance, and neuropsychological functioning. Functional MRI was recorded in thirty healthy, male community volunteers (mean age = 27.4 years) while they performed a monetary gambling task in which they bet with either 10 or 50 tokens and received feedback on whether they won or lost the bet amount. Results showed that a set of key brain structures in the reward network, including the putamen, caudate nucleus, superior and inferior parietal lobule, angular gyrus, and Rolandic operculum, had greater blood oxygenation level-dependent (BOLD) signals during win relative to loss trials, and the BOLD signals in most of these regions were highly correlated with one another. Furthermore, exploratory bivariate analyses between these reward-related regions and behavioral and neuropsychological domains showed significant correlations with moderate effect sizes, including (i) negative correlations between non-planning impulsivity and activations in the putamen and caudate regions, (ii) positive correlations between risky bets and right putamen activation, (iii) negative correlations between safer bets and right putamen activation, (iv) a negative correlation between short-term memory capacity and right putamen activity, and (v) a negative correlation between poor planning skills and left inferior occipital cortex activation. These findings contribute to our understanding of the neural underpinnings of monetary reward processing and their relationships to aspects of behavior and cognitive function. Future studies may confirm these findings with larger samples of healthy controls and extend these findings by investigating various clinical groups with impaired reward processing. Full article

As a plant-specific peroxidase family, class III peroxidase (PRX) plays an important role in plant growth, development, and stress response. In this study, a preliminary functional analysis of CqPRX9L1 was conducted. Bioinformatics analysis revealed that CqPRX9L1 encodes a 349-amino acid protein belonging to the plant-peroxidase-like superfamily, featuring a transmembrane domain and cytoplasmic localization. The promoter region of CqPRX9L1 harbors various cis-acting elements associated with stress responses, hormone signaling, light regulation, and meristem-specific expression. The tissue-specific expression pattern of the CqPRX9L1 gene and its characteristics in response to different stresses were explored using subcellular localization, quantitative real-time PCR (qRT-PCR), and heterologous transformation into Arabidopsis thaliana. The results showed that CqPRX9L1, with a transmembrane structure, was localized in the cytoplasm, which encodes 349 amino acids and belongs to the plant-peroxisome-like superfamily. The promoter region contains stress-response elements, hormone-response elements, light-response elements, and meristem expression-related elements. The expression of CqPRX9L1 was relatively higher in ears and roots at the panicle stage than in stems and leaves. CqPRX9L1 showed a dynamic expression pattern of first decreasing and then increasing under abiotic stresses such as 15% PEG 6000, low temperature, and salt damage, with differences in response time and degree. CqPRX9L1 plays an important role in response to abiotic stress by affecting the activity of antioxidant enzymes such as superoxide dismutase (SOD) and peroxidase (POD), as well as the synthesis and decomposition of proline (Pro). CqPRX9L1 also affects plant bolting and flowering by regulating key flowering genes (such as FT and AP1) and gibberellin (GA)-related pathways. The results establish a foundation for revealing the functions and molecular mechanisms of the CqPRX9L1 gene. Full article

As an auxin-responsive gene, Gretchen Hagen 3 (GH3) maintains hormonal homeostasis by conjugating excess auxin with amino acids in plant stress-related signaling pathways. GH3 genes have been characterized in many plant species, but the characteristics of pepper (Capsicum annuum L.) GH3 (CaGH3) gene family members in response to multiple stimulants are largely unknown. In this study, we systematically identified the CaGH3 gene family at the genome level and identified eight members on four chromosomes in pepper. CaGH3s were divided into two groups (I and III) and shared conserved motifs, domains, and gene structures. Moreover, CaGH3s had close evolutionary relationships with tomato (Solanum lycopersicum L.), and the promoters of most CaGH3 genes contained hormone and abiotic stress response elements. A protein interaction prediction analysis demonstrated that the CaGH3-3/3-6/3-7/3-8 proteins were possibly core members of the CaGH3 family interaction. In addition, qRT-PCR results showed that CaGH3 genes were differentially expressed in pepper tissues and could be induced by phytohormones (IAA, ABA, and MeJA) and abiotic stresses (salt, low temperature, and drought) with different patterns. In addition, CaGH3-5 and CaGH3-7 were cloned, and the sequences showed a high degree of conservation. Moreover, the results of subcellular localization indicated that they were located in the membrane and chloroplast. Notably, after overexpressing CaGH3-7 in tomato, RNA-seq was performed on wild-type and transgenic lines, and the differentially expressed genes were mainly enriched in response to external stimuli. This study not only lays the foundation for a comprehensive understanding of the function of the CaGH3 gene family during plant growth and stress responses but also provides potential genetic resources for pepper resistance breeding. Full article

Background and Objectives: Epithelial ovarian cancer (EOC) remains the deadliest gynecologic malignancy, yet the psychosocial dynamics of early survivorship are inadequately described. We prospectively quantified six-month trajectories in the quality of life in a consecutive cohort of 88 women newly diagnosed with EOC and explored clinical moderators of change. Methods: Eighty-eight consecutive patients (mean age 59.1 ± 10.7 years) completed the SF-36, WHOQOL-BREF, EORTC QLQ-C30, and 10-item Perceived Stress Scale (PSS-10) at baseline (pre-therapy) and six months after cytoreductive surgery ± platinum-based chemotherapy. Stage (FIGO I–II vs. III–IV) and treatment pathway (primary debulking surgery, neoadjuvant chemotherapy plus interval debulking, chemotherapy only) data were recorded. Results: Global QoL improved significantly (EORTC Global Health +5.9 ± 7.7 points; p < 0.001) while perceived stress declined (ΔPSS −3.6 ± 5.1; p < 0.001). SF-36 Physical Functioning rose 4.7 ± 7.9 points (p < 0.001) and Mental Health 4.4 ± 7.9 points (p = 0.004). The WHOQOL Physical and Psychological domains gained 4.7 ± 7.1 and 4.3 ± 7.4 points, respectively (both p < 0.01). Advanced-stage patients experienced larger stress reductions than early-stage patients (−4.1 ± 2.7 vs. −2.9 ± 2.2; p = 0.028) but comparable QoL gains. Greater stress relief correlated with greater mental-health improvement (r = −0.51) and global-health gains (r = −0.45) (all p < 0.001). Treatment pathway did not significantly influence trajectories. Conclusions: Early survivorship after first-line ovarian-cancer therapy was characterized by the clinically meaningful recovery of physical and emotional functioning together with the moderate alleviation of perceived stress. Improvements were observed irrespective of stage and treatment strategy, suggesting that contemporary multimodal regimens do not inevitably compromise patient-reported outcomes. Our estimates provide preliminary effect sizes that should be validated in multi-center cohorts with longer follow-up. Full article

Generalising deep-learning models to perform well on unseen data domains with minimal retraining remains a significant challenge in computer vision. Even when the target task—such as quantifying the number of elements in an image—stays the same, data quality, shape, or form variations can deviate from the training conditions, often necessitating manual intervention. As a real-world industry problem, we aim to automate stock level estimation in retail cabinets. As technology advances, new cabinet models with varying shapes emerge alongside new camera types. This evolving scenario poses a substantial obstacle to deploying long-term, scalable solutions. To surmount the challenge of generalising to new cabinet models and cameras with minimal amounts of sample images, this research introduces a new solution. This paper proposes a novel ensemble model that combines DenseNet-201 and Vision Transformer (ViT-B/8) architectures to achieve generalisation in stock-level classification. The novelty aspect of our solution comes from the fact that we combine a transformer with a DenseNet model in order to capture both the local, hierarchical details and the long-range dependencies within the images, improving generalisation accuracy with less data. Key contributions include (i) a novel DenseNet-201 + ViT-B/8 feature-level fusion, (ii) an adaptation workflow that needs only two images per class, (iii) a balanced layer-unfreezing schedule, (iv) a publicly described domain-shift benchmark, and (v) a 47 pp accuracy gain over four standard few-shot baselines. Our approach leverages fine-tuning techniques to adapt two pre-trained models to the new retail cabinets (i.e., standing or horizontal) and camera types using only two images per class. Experimental results demonstrate that our method achieves high accuracy rates of 91% on new cabinets with the same camera and 89% on new cabinets with different cameras, significantly outperforming standard few-shot learning methods. Full article