Search Results (9,018)

Obtaining multiple MRI contrasts for each patient prolongs scan acquisition time, increases healthcare costs, and may not always be feasible due to patient specific constraints. Deep learning-based MRI contrast synthesis offers a potential solution, yet most existing approaches are evaluated on preprocessed public benchmarks that do not reflect real-world clinical variability. In this study, we propose a fusion U-Net transformer framework for bidirectional T1-weighted ↔ T2-weighted brain MRI synthesis trained and evaluated exclusively on retrospectively acquired clinical data. The proposed architecture integrates multiscale convolutional feature extraction with axial attention mechanisms and a transformer bottleneck for efficient global context modeling. A fusion refinement block is incorporated to mitigate skip connection artifacts. An adversarial training strategy with the least squares GAN objective and a hybrid loss combining L1 reconstruction and structural similarity (SSIM) is employed to promote both pixel-level accuracy and perceptual fidelity. The model is evaluated using SSIM and PSNR metrics alongside qualitative expert assessment conducted by two board-certified radiologists. For both synthesis directions, the framework achieves competitive quantitative performance against baseline models under the challenging conditions of clinical data. Expert evaluation confirms high anatomical fidelity and clinically acceptable image quality across both synthesis directions. These results indicate that the proposed framework represents a promising approach for multi-contrast MRI synthesis in clinically heterogeneous data environments. Full article

In an era marked by rising stress-related disorders and cardiovascular morbidity, understanding how the brain and heart adapt to environmental, physiological, and social stressors has become an urgent biomedical priority. This review advances an integrative framework centered on sociostasis, defined as the dynamic regulation of physiological state through social interaction, and its intersection with hormesis, a biphasic adaptive response to controlled stress that enhances resilience. We focus on four evolutionarily conserved neuropeptides, vasopressin, oxytocin, corticotropin-releasing hormone, and the urocortins, which serve as molecular bridges linking social behavior, neuroendocrine signaling, autonomic regulation, and cardiovascular function. Operating within an organized autonomic architecture, these systems calibrate responses to acute and chronic stress. Their context-dependent synergy enables adaptive flexibility under manageable challenge but may promote maladaptive cardiovascular remodeling when chronically dysregulated. Genetic vulnerability, developmental adversity, and persistent psychosocial stress can shift neuroendocrine–autonomic set points, increasing susceptibility to hypertension, endothelial dysfunction, and stress-induced cardiomyopathy. Conditioning and preconditioning paradigms illustrate how repeated exposure to subthreshold stressors primes cardiovascular tissues for future insults, enhancing ischemic tolerance and adaptive gene expression. We propose that cardiovascular hormesis depends not only on stimulus intensity but also on the integrity of neuroautonomic regulatory mechanisms that support recovery and flexibility. Vagal efficiency, a dynamic index of cardioinhibitory regulation, is discussed as a potential translational metric of adaptive capacity. By integrating molecular, physiological, and psychosocial perspectives, this framework conceptualizes cardiovascular resilience as an emergent property of coordinated hormetic signaling, neuropeptidergic modulation, autonomic regulation, and social buffering. Translational implications include peptide-based therapies, autonomic biofeedback, and behavioral interventions designed to enhance stress adaptability. Full article

Hybrid hydro–solar microgrids offer a practical electrification option for remote and weak-grid communities by combining run-of-river hydropower with photovoltaic generation. However, their performance depends strongly on coordinated decisions across three layers: (i) system sizing and architecture, (ii) turbine selection and rating under variable river flow, and (iii) operational energy dispatch under time-varying solar resource and demand. This paper develops an optimization-driven planning framework for a run-of-river hydro–PV microgrid that co-optimizes component capacities and turbine-related design choices while enforcing time-series operational feasibility. Physics-based component models translate river discharge into hydroelectric output via turbine efficiency characteristics and operating limits, and compute PV generation and storage trajectories under dispatch and state-of-charge constraints. The planning problem is formulated as a multi-objective optimization that quantifies trade-offs among life-cycle cost, supply reliability (e.g., unmet-load metrics), and sustainability indicators (e.g., diesel-free operation or emissions when backup generation is present). A Pareto-optimal set of designs is obtained using a population-based multi-objective algorithm, and representative knee-point (balanced) solutions are selected to illustrate how turbine choice and dispatch strategy interact with seasonal hydrology and solar variability. The proposed approach supports transparent and robust design decisions for hybrid hydro–solar microgrids. Full article

Deploying artificial intelligence models on low-cost edge devices requires balancing predictive accuracy with strict constraints on computational resources, such as inference latency and memory footprint. Despite growing interest in TinyML systems, limited empirical evidence exists on how these factors interact across different embedded hardware platforms. This study presents a systematic multi-objective evaluation of three lightweight AI architectures—multinomial logistic regression (MLR), multilayer perceptron (MLP), and a reduced convolutional neural network (CNN)—implemented natively on three representative platforms: ESP32-S3, Raspberry Pi Pico, and Raspberry Pi Zero W. The models were evaluated on three image classification datasets of increasing complexity (Synthetic Geometric Figures, MNIST, and Fashion-MNIST), measuring classification accuracy, inference latency, and peak memory footprint under real execution conditions. Pareto-front analysis was used to identify efficient model–platform configurations and characterize the trade-offs between predictive performance and computational resources. The results provide quantitative insight into accuracy–resource trade-offs and establish a reproducible framework for evaluating lightweight AI models on resource-constrained edge devices, supporting informed design decisions in TinyML applications. Full article

DNA mixture interpretation remains one of the most technically demanding challenges in forensic genetics. While probabilistic genotyping (PG) systems have substantially advanced likelihood ratio (LR) evaluation, comparatively less attention has been devoted to the systematic reconstruction of contributor genotypes, particularly in no-suspect and database-search contexts. This review synthesizes recent developments in DNA mixture deconvolution through a four-strategy framework: (i) physical and biological separation, (ii) high-information genetic markers, (iii) continuous probabilistic algorithms, and (iv) integration with database searching infrastructures. Upstream approaches, including single-cell isolation and sequencing, reduce mixture complexity at the molecular level. Marker innovations such as microhaplotypes, MiniHaps and DIP-STRs increase per-locus information content and enhance resistance to degradation. Downstream probabilistic models—extended from STRs to SNPs and microhaplotypes—leverage quantitative signal data to infer contributor genotypes, with recent advances in Hamiltonian Monte Carlo, variational inference, and deep learning improving inferential stability and reconstruction accuracy. Importantly, genotype deconvolution and LR evaluation represent mathematically distinct objectives, requiring different validation metrics and potentially separate architectural optimization. The convergence of molecular innovation, algorithmic refinement, and LR-based database searching is progressively transforming mixture interpretation from a purely evidential assessment into an integrated investigative framework. Future progress will depend on standardized marker panels, deconvolution-specific performance metrics, and scalable LR-enabled database infrastructures. Full article

Cerium dioxide (CeO₂) has emerged as a structurally versatile oxide for dye-wastewater purification because its architecture, porosity, and surface accessibility can be tuned over a wide range while maintaining good chemical stability and environmental compatibility. Recent studies show that template-free or low-template routes can generate porous, mesoporous, multilayered, and flower-like CeO₂ architectures with rapid dye uptake and, in some systems, adsorption-assisted photocatalytic removal. However, CeO₂-based dye removal has often been discussed either within broad surveys of environmental applications or from composition-centered viewpoints, whereas the more fundamental question is how synthesis route controls architecture formation and how architecture, in turn, governs adsorption and subsequent removal behavior. This mini-review addresses that question from a morphology-centered perspective. It first examines template-free and low-template routes for constructing structured CeO₂, then discusses how porosity, hierarchical assembly, and surface accessibility regulate adsorption kinetics and equilibrium capacity in dye-containing aqueous systems. It further considers adsorption-assisted photocatalytic removal and argues that dark adsorption should be regarded as the structural first step rather than a secondary contribution. On this basis, the review shows that rare-earth doping in these systems is most usefully understood as a secondary tuning strategy that refines an already favorable host architecture by modifying surface interaction, optical response, or reactive-species generation. Overall, the available evidence indicates that CeO₂-based dye-wastewater purification is most meaningfully interpreted through a route–architecture–function framework in which morphology defines the host, adsorption organizes the local reaction environment, and doping serves mainly as structure-assisted tuning. This perspective shifts the design logic of CeO₂ from empirical performance optimization toward rational structure-directed construction of integrated removal platforms. Full article

Against the background of highly interconnected global capital markets and rapidly propagating cross-lingual information streams, traditional anomaly detection paradigms based solely on single-modality numerical time-series sensors are insufficient for forward-looking risk sensing. From the perspective of artificial intelligence-driven sensing, this study proposes a multilingual semantic–numerical collaborative Transformer framework to construct a unified multimodal financial sensing architecture for intelligent anomaly sensing and risk perception. Within the proposed sensing paradigm, multilingual texts are conceptualized as semantic sensors that continuously emit event-driven sensing signals, while market prices, trading volumes, and order book dynamics are modeled as heterogeneous numerical sensor streams reflecting behavioral market sensing responses. These heterogeneous sensors are jointly integrated through a cross-modal sensor fusion architecture. A cross-modal temporal alignment attention mechanism is designed to explicitly model dynamic lag structures between semantic sensing signals and numerical sensor responses, enabling temporally adaptive sensor-level alignment and fusion. To enhance sensing robustness, a multilingual semantic noise-robust encoding module is introduced to suppress unreliable textual sensor noise and stabilize cross-lingual semantic sensing representations. Furthermore, a semantic–numerical collaborative risk fusion module is constructed within a shared latent sensing space to achieve adaptive sensor contribution weighting and cross-sensor feature coupling, thereby improving anomaly sensing accuracy and robustness under complex multimodal sensing environments. Extensive experiments conducted on real-world multi-market financial sensing datasets demonstrate that the proposed artificial intelligence-driven sensing framework significantly outperforms representative statistical and deep learning baselines. The framework achieves a Precision of $0.852$, Recall of $0.781$, F1-score of $0.815$, and an AUC of $0.892$, while substantially improving early warning time in practical risk sensing scenarios. In cross-market transfer settings, the proposed sensing architecture maintains stable anomaly sensing performance under bidirectional domain shifts, with AUC consistently exceeding $0.86$, indicating strong structural generalization across heterogeneous sensing environments. Ablation analysis further verifies that temporal sensor alignment, semantic sensor denoising, and collaborative cross-sensor risk coupling contribute independently and synergistically to the overall sensing performance. Overall, this study establishes a scalable multimodal intelligent sensing framework for dynamic financial anomaly sensing, providing an effective artificial intelligence-driven sensing solution for cross-market risk surveillance and adaptive financial signal sensing. Full article

The increasing need for energy-efficient and environmentally friendly electricity generation has led to the extensive use of hybrid electric systems. These systems integrate different energy sources in an effort to take advantage of the positives of each technology, as using a single source of energy comes with many limitations and disadvantages; hence, the popularity of hybrids has increased in recent times. In this regard, this paper proposes a lithium-ion battery (LIB) and ultracapacitor (UC)-based hybrid architecture considering an optimal energy management framework. In the transportation sector, hybrid vehicles (LIB and UC-based vehicles) effectively utilize the high energy density and power density of LIBs and UCs. This LIB and UC-based hybrid architecture provides an efficient power management solution considering the high power density of the LIB for smooth road profiles, and the high power density of the UC is driven during sudden spikes in load demand because the LIB will not function optimally during the sudden spikes due to lower power density. Furthermore, in order to achieve efficient utilization of the proposed hybrid system, an optimal energy management framework is used. In this regard, in this study, a fractional-order proportional–integral–derivative (FOPID) controller has been designed for effective and optimal energy management. Furthermore, the designed FOPID has been optimized using a metaheuristic technique, namely particle swarm optimization (PSO), to enhance LIB and UC-based hybrid electric vehicle energy management performance. Employing dynamic and optimal energy flow control, the FOPID-based system improves energy consumption, extends LIB life, and improves overall system performance and reliability. Full article

Laser powder bed fusion (LPBF) can fabricate intricate metal components but is prone to defects, such as porosity and cracks, that degrade performance. We present an in situ monitoring framework that fuses structure-borne acoustic emission (AE) and coaxial two-color pyrometry acquired synchronously at 1 MHz. Modality-specific encoders are pretrained separately, their latent representations are exported, and a lightweight feature-level fusion classifier with two binary heads predicts crack-like and porosity-like indications. Evaluation uses a held-out grouped experiment/build-machine-part split with independent Archimedes density and micro-CT ground truth. On the held-out test set, the fused model achieved F1 = 0.974 for crack-like detection and F1 = 0.987 for porosity-like detection, with AUROC = 0.998 and 0.993, respectively. Recall was 1.00 for both heads, corresponding to false-positive rates of 11.18% for crack-like and 0.945% for porosity-like indications. These results support synchronized AE-pyrometry fusion as a promising high-sensitivity in situ screening approach for LPBF. A later matched within-framework ablation campaign was also performed under stricter checkpoint-screening rules to compare AE + PY + Aux, AE + PY, AE-only, and PY-only variants under a common grouped-split protocol. Together, these results support multimodal monitoring while highlighting the need for explicit coupon/geometry-stratified reporting and for separately architecture-optimized unimodal baselines. Full article

The advancement of generative artificial intelligence (GAI) in healthcare is driving a transition from dialogue-based medical chatbots to workflow-embedded clinical AI agents. These agentic systems incorporate persistent state management, coordinated tool invocation, and bounded autonomy, enabling multi-step reasoning within institutional processes. As a result, traditional response-level evaluation frameworks are insufficient for understanding system behavior. This review provides a conceptual synthesis of the evolution from conversational systems to agentic architectures and proposes a system-level modeling framework for ethical clinical AI agents. We identify core architectural dimensions, including autonomy gradients, state persistence, tool orchestration, workflow coupling, and human–AI co-agency, and examine how these features reshape bias propagation pathways, error cascade dynamics, trust calibration, and accountability structures. Emphasizing that ethical risks emerge from longitudinal system interactions rather than isolated outputs, we argue for embedding fairness constraints, transparency mechanisms, and lifecycle governance directly within AI design. By outlining trajectory-level evaluation strategies, equity-aware development approaches, collaborative oversight models, and adaptive regulatory frameworks, this paper establishes a foundation for the responsible and trustworthy integration of agentic AI in healthcare. Full article

The rational design of electrode materials with tailored composition and architecture is crucial for advancing high-capability electrochemical energy storage systems. This study reports that gadolinium-modified NiFe₂O₄ nanosheet electrodes were effectively synthesized on nickel foam via a hydrothermal approach followed by thermal treatment. A series of compositions (NiFe, NiFe–Gd1, NiFe–Gd2, and NiFe–Gd3) were prepared to systematically examine the effect of Gd incorporation on structural features and electrochemical properties. X-ray diffraction (XRD) analysis confirmed the formation of the cubic spinel NiFe₂O₄ phase without detectable secondary phases, indicating that the crystal structure remains intact after Gd introduction. X-ray photoelectron spectroscopy (XPS) further verified the presence of Ni²⁺, Fe³⁺, and Gd³⁺ species within the lattice environment. Morphological analysis using field-emission scanning electron microscopy (FESEM) revealed a nanosheet-based architecture, where the optimized NiFe–Gd2 electrode exhibited a porous and interconnected nanosheet framework with abundant exposed edges. This structural configuration improves electrolyte penetration and facilitates efficient ion transport during charge storage processes. Electrochemical measurements demonstrated that the NiFe–Gd2 electrode delivers an areal capacitance of 5235 mF cm⁻² at 10 mA cm⁻², along with improved reaction kinetics and low internal resistance. An asymmetric supercapacitor assembled using NiFe–Gd2 as the positive electrode and activated carbon as the negative electrode operated stably within a 0–1.5 V potential window, achieving an energy density of 0.136 mWh cm⁻² and a power density of 3.14 mW cm⁻², while retaining 86.55% of its initial capacitance after 7000 cycles. These results highlight the potential of rare-earth engineering as a viable strategy for designing advanced spinel ferrite electrodes and pave the way for the development of high-performance, durable, and scalable supercapacitor systems for practical energy storage applications. Full article

Consumer wellbeing systems are characterized by conceptual fragmentation, heterogeneous data sources, and multilevel interactions across economic, psychological, social, and environmental domains. Existing monitoring approaches remain largely unidimensional and lack integrative system architectures capable of supporting real-time, adaptive analysis. This paper proposes a Federated Digital Twin (FDT) framework for Consumer Wellbeing Systems, designed to integrate decentralized, multimodal data while preserving autonomy and privacy. The proposed architecture builds on a five-dimensional digital twin model and extends it through federated interoperability, data fusion, adaptive learning, simulation capabilities, and human-in-the-loop mechanisms. The framework enables the synchronization of observed, self-reported, contextual, and synthetic data across distributed environments, supporting system-level modeling, prediction, and optimization. As an illustrative application, the paper examines Shopping Wellbeing and Shopping–Life Balance as sub-systems within broader wellbeing ecosystems, demonstrating how federated digital twins can unify fragmented theoretical constructs into a coherent, dynamic monitoring structure. The study contributes a system-oriented conceptual architecture for modeling complex human-centric wellbeing ecosystems and outlines implications for systems design, governance, and future interdisciplinary research. Full article

Cultivated lettuce (Lactuca sativa L.) is a major leafy crop and an emerging model for functional genomics within the Asteraceae family, supported by high-quality reference genomes and efficient transformation systems. Although CRISPR/Cas technology offers powerful opportunities for crop improvement, editing efficiency depends on optimized construct architecture and reliable guide RNA (gRNA) validation. However, a rapid platform for evaluating CRISPR reagents in lettuce is still lacking. Here, we developed an efficient hairyroot-based system to accelerate CRISPR/Cas genome editing optimization in L. sativa. Four Agrobacterium rhizogenes strains were compared for hairy root induction in two cultivars, ‘Saladin’ and ‘Osiride’, identifying strain ATCC15834 as the most effective based on transformation frequency and root production. Using this platform, we evaluated multiple CRISPR construct configurations, including alternative promoters for nuclease and gRNA expression. A plant-derived promoter combined with At-pU6-26 variant significantly improved editing efficiency. As a proof of concept, we targeted LsHB2, the putative ortholog of Arabidopsis thaliana ATHB2, a key regulator of the shade avoidance response using SpCas9, SaCas9, and LbCas12a nucleases. The system enabled rapid genotyping and quantitative indel profiling. Overall, this workflow provides a robust framework for efficient guide selection and construct optimization in lettuce genome editing. Full article

The rapid proliferation of text-to-image generative systems has transformed visual content production, yet the structural characteristics embedded in their compositional outputs remain insufficiently understood. Rather than approaching human–AI differentiation as a purely classification problem, this study investigates whether a controlled set of AI-generated and human-designed posters exhibits measurable structural divergence under thematically matched conditions. A dataset of jazz festival posters was analyzed using interpretable geometric and information-theoretic descriptors, including spatial density (padding ratio), edge density, chromatic dispersion, and entropy-based measures. Instead of relying on deep neural detection architectures, we employed a transparent machine-learning framework to examine intrinsic structural separability within feature space. Results demonstrated highly stable group separation (ROC-AUC = 0.99; 95% CI: 0.978–0.999) under cross-validated evaluation. Distributional analysis further revealed a pronounced divergence in spatial density allocation (Kolmogorov–Smirnov statistic = 0.76, p < 10⁻²⁸), accompanied by a very large effect size (Cohen’s d = 1.365). While padding ratio emerged as the dominant discriminative factor, additional entropy- and chromatic-based descriptors contributed to group separation even when spatial density was excluded (AUC = 0.903). These findings indicate that AI-generated and human-designed posters can diverge in negative space allocation and chromatic organization under controlled thematic and platform-specific conditions. The study contributes to the explainable analysis of generative visual systems by reframing human–AI differentiation as a structural divergence problem grounded in interpretable image statistics rather than as a model-specific artifact detection task. Full article

Photoplethysmography (PPG) has emerged as an attractive modality for non-invasive cardiovascular monitoring due to its low cost, unobtrusive nature, and ubiquity in consumer wearable devices. Despite its potential, existing PPG-based arrhythmia detection systems remain limited in scope: (i) most target only atrial fibrillation, (ii) temporal localization of abnormal segments is rarely provided, and (iii) deep learning models lack explainability, hindering adoption in clinical workflows. We present a comprehensive and fully integrated framework for multi-class arrhythmia detection, segmentation, and explainability based on PPG waveforms, Heart Rate Variability (HRV), and structured clinical metadata. The proposed system introduces a CLIP-style contrastive learning module aligning PPG waveforms with clinical variables and rhythm-state textual descriptions using BioBERT; a multitask U-Net architecture performing 4-class classification and 1D segmentation; a Retrieval-Augmented Generation (RAG) pipeline leveraging Gemini Flash large language models to produce guideline-grounded diagnostic reports; and a real-time Streamlit-based web platform supporting inference, visualization, and database storage. The system significantly improves classification accuracy (from 86.27% to 91.19%) and segmentation Dice (from 0.5815 to 0.7167). These results demonstrate the feasibility of a robust, multimodal, and explainable PPG-based arrhythmia monitoring system for real-world applications. Full article