Search Results (85)

Immersive audio and vibroacoustic stimulation have gained increasing attention as non-invasive approaches for modulating human emotional and physiological states. The SonikB3D platform was previously introduced as a multisensory system combining immersive 3D audio, vibroacoustic stimulation, and physiological monitoring. Building upon this prior work, the present study advances the platform through a refined experimental protocol and a data-driven framework for the automatic assessment of relaxation using multimodal biosignals. A controlled pilot study was conducted with 20 participants exposed to 3D sound and vibroacoustic stimulation delivered through a massage table equipped with integrated transducers. Although the SonikB3D platform supports multiple stimulation scenarios, the present study focuses on a single controlled condition combining binaural 3D audio (binaural beats plus music) and vibroacoustic stimulation in order to ensure methodological consistency for multimodal modelling. Physiological responses were continuously recorded using a synchronized setup including electroencephalography (EEG), photoplethysmography (PPG), and electrodermal activity (EDA). Subjective emotional self-assessment questionnaires were collected before and after exposure to provide a multidimensional characterization of participant responses. Results show a statistically significant increase in self-reported relaxation (paired t-test = 3.05, p = 0.01), corresponding to an average 8% improvement in normalized relaxation scores. To support objective assessment, multimodal physiological features associated with autonomic and emotional regulation were extracted and used to develop a two-stage machine learning pipeline. The proposed model, combining a window-level Random Forest classifier with session-level aggregation, achieved an accuracy of 80% and an F1-score of 0.857 in classifying relaxation-related states. These findings provide preliminary evidence that combined 3D audio and vibroacoustic stimulation can produce measurable changes in subjective and physiological indicators of relaxation, while demonstrating the feasibility of automatic relaxation state inference from multimodal biosignals. Although exploratory due to the limited sample size and the absence of unimodal control conditions, this work contributes a data-driven methodology for studying human responses to multisensory sound and vibration metrics. Full article

The quest for seismic resiliency requires designing for performance objectives beyond life safety. Functional recovery is an emerging objective often defined as the time required to restore a building’s basic functionality to the pre-event level. Nevertheless, quantifying functional recovery is a complex, computationally intensive process that is challenging to integrate into a standard design workflow. This study develops a machine learning (ML) model to map design and geometric features of steel special moment-resisting frames (SMRFs) to their functional recovery under two hazard levels: design-basis (DBE) and maximum considered (MCE) earthquakes. First, functional recovery time was quantified for an inventory of 100 steel SMRFs with varying heights by integrating FEMA P-58 loss-based methodology with the ATC-138 framework. The building information and calculated recovery times were then used in a standard ML pipeline including feature selection, hyperparameter tuning, cross-validation, model evaluation, and model explainability. The results suggest that the ML model can accurately estimate functional recovery using design and geometric features, achieving R² values of 89% and 93% on the test set for DBE and MCE levels, respectively. In addition, for the studied regular SMRF buildings, the results indicate that building weight and the average strong-column weak-beam ratio are influential design parameters that govern functional recovery time, suggesting that a recovery-oriented design of steel SMRFs may benefit from minimizing building weight and avoiding overt column upsizing. Full article

Early non-invasive correction of neonatal auricular deformities is highly dependent on timely and precise diagnosis. However, clinical practice is often compromised by the subjectivity of visual assessments and the lack of objective tracking metrics, which frequently leads to missed optimal treatment windows. To address these challenges, we developed an interpretable deep learning-based diagnostic system for the automated screening and fine-grained classification of these deformities. Methodologically, a large-scale, multi-source dataset (n = 4644) was curated to support model training. The system pairs an automated object detector (YOLOv11) for background-reduced region-of-interest isolation with a cascaded classification pipeline optimized via ConvNeXt-Tiny. Crucially, we introduced a supervised contrastive learning module to project high-dimensional morphological features into a continuous severity score, enabling quantitative longitudinal tracking of therapeutic efficacy. To evaluate generalization and robustness, the framework underwent rigorous evaluation across three independent real-world cohorts and one controlled synthetic stress test. The system achieved 88.2% accuracy (Area Under the Curve (AUC): 0.949) in binary screening and 87.4% accuracy (macro-AUC: 0.976) in multi-class subtyping on the internal baseline. To enhance interpretability and build clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to explore the spatial distribution of the model’s attention, which frequently aligned with key anatomical landmarks. Furthermore, the learned severity scores robustly quantified post-intervention improvements (p = 0.0004), effectively capturing subtle anatomical normalization. While validation for rare subtypes remains underpowered, and the severity score currently functions mainly as a learned morphological similarity index requiring future clinical calibration, this study ultimately provides an objective and standardized web-based tool to facilitate the early intervention and precision management of neonatal auricular anomalies. Full article

Carbon capture and utilization (CCU) is imperative for industrial decarbonization. However, current life cycle assessment (LCA) methodologies often apply a static, one-size-fits-all approach, assuming a 99% CO₂ purity standard for all utilization pathways. This ignores the thermodynamic limits of capture technologies and the tolerance of certain endpoints for coarse gas, leading to severe over-purification energy penalties. To bridge this gap, we developed a quality-matched dynamic LCA framework targeting steam methane reforming (SMR) tail gas in industrial parks. A superstructure matrix was constructed, coupling 16 capture configurations (spanning chemical absorption to cryogenic separation across 85–99% purities) with five utilization pathways, under a dynamic grid decarbonization model (2024–2060). The baseline scenario shows that methanol is the most carbon-intensive pathway at 16.88 kg CO₂-eq per kg CO₂ utilized, whereas mineralization and concrete curing remain near break-even at 0.221 and 0.010 kg CO₂-eq, respectively. When low-purity demand is matched with PSA capture at 85–90% purity, the net GWP of mineralization and concrete curing decreases to 0.134 and 0.005 kg CO₂-eq, corresponding to capture-stage penalty reductions exceeding 60% relative to unnecessary 99% purification. Under the dynamic electricity scenario, concrete curing reaches the net-zero tipping point around 2031, and the coupled mineralization substitution strategy ultimately achieves −0.046 kg CO₂-eq per kg CO₂ utilized. These findings provide a compelling scientific basis for policymakers to design dual-grade CO₂ pipeline networks and prioritize low-purity, high-circularity building materials over carbon-intensive chemical synthesis in near-term industrial transitions. Full article

Intelligent detection in modern manufacturing, healthcare, process industries, and structural monitoring is fundamentally enabled by heterogeneous sensor systems. Rather than being viewed as a purely image-centered recognition task, intelligent detection is more appropriately formulated as a sensor-driven state inference problem in which sensing physics, signal quality, temporal synchronization, modality availability, and deployment conditions jointly determine what can be reliably detected, localized, interpreted, and acted upon. Against this background, this review provides a structured synthesis of the field through three coupled dimensions, namely methods, systems, and governance, and organizes the literature around four recurring engineering components: signal unification, representation unification, alignment mechanisms, and robustness mechanisms. Using a structured review protocol with explicit source selection, screening, and study coding, the paper traces the methodological evolution from traditional feature-engineering and model-based pipelines to deep learning for visual, temporal, multimodal, generative, and mechanism-constrained sensing, and further to foundation-model-based and multimodal sensor intelligence. Cross-domain evidence is synthesized from industrial defect detection, fault diagnosis, remaining useful life prediction, non-destructive testing, structural health monitoring, medical lesion analysis, and process monitoring. The review argues that recent progress has substantially strengthened learned representations, multimodal interaction, and semantic extensibility, but has not removed persistent constraints arising from domain shift, missing modalities, calibration instability, privacy-preserving collaboration, and edge-side resource limits. Accordingly, the central challenge is no longer how to optimize isolated detection models, but how to build sensor-enabled intelligent systems that remain physically grounded, trustworthy, transferable, and maintainable under real operational conditions. On this basis, the paper concludes by identifying future directions in mechanism-aware modeling, trustworthy evaluation, missing-modality-robust multimodal systems, privacy-preserving cross-site collaboration, and edge-native lifecycle-aware deployment. Full article

Sixth-generation (6G) networks are expected to provide ubiquitous connectivity, AI-native orchestration, and seamless integration across terrestrial and non-terrestrial infrastructures. However, these capabilities introduce new privacy challenges related to the classification and protection of personal, quasi-personal, and non-personal data in complex data-driven environments. This paper presents a systematic review of 78 peer-reviewed studies published between 2019 and 2025. Following a PRISMA-based methodology, this review analyzes privacy-enhancing technologies (PETs), regulatory compliance frameworks, and architectural patterns for privacy preservation in 6G networks. The findings show that differential privacy (DP) and federated learning (FL) dominate current research, accounting for nearly 52% of the reviewed studies. Blockchain auditing and zero-knowledge proofs (ZKPs) collectively represent approximately 30%, while the remaining mechanisms, including physical-layer security (PLS), trusted execution environments (TEEs), homomorphic encryption (HE), secure multi-party computation (SMPC), and anonymization, account for roughly 18%. These mechanisms exhibit varying levels of privacy strength, utility preservation, latency, and energy cost. At the same time, evolving regulatory frameworks, including GDPR, PDPL, CCPA/CPRA, LGPD, and PIPL, increasingly extend privacy obligations to quasi-personal and aggregated data. Building on these findings, this paper proposes a unified taxonomy that clarifies the boundary between personal and non-personal data. It also provides a cross-layer mapping between PETs and compliance requirements across the Core/SBA, RAN, Edge/MEC, and NTN layers. Finally, this paper presents a forward-looking roadmap for 2025–2030, highlighting hybrid PET pipelines, post-quantum auditability, and AI-driven compliance automation as key directions for privacy-preserving 6G standardization. Full article

Pipe networks are essential components of modern building infrastructure, including heating, ventilation, and air conditioning (HVAC) water systems, water distribution networks (WDNs), and district heating and cooling (DHC) systems. Leakage in these systems can lead to increased energy consumption, loss of thermal efficiency, and unstable system operation, thereby affecting indoor environmental quality and overall building performance. Despite differences in scale and application, similar leakage mechanisms are also observed in other pipe network systems, such as oil and gas pipelines and liquid cooling networks. These shared characteristics motivate a unified analytical perspective across different applications. This review provides a systematic analysis of leakage diagnosis methods, with a focus on machine learning (ML) approaches. The results indicate that ML methods have become a dominant research direction due to their ability to capture nonlinear relationships and process high-dimensional data. However, their effectiveness is often constrained by the limited availability of labeled leakage data, sensitivity to dynamic operating conditions, and insufficient physical interpretability. This review provides a structured framework for understanding ML-based leakage diagnosis and offers insights into the integration of data-driven and physics-based approaches for pipe network systems. In addition, the potential role of reinforcement learning (RL) is briefly discussed as an emerging direction for handling dynamic and adaptive scenarios. Compared with ML-based methods, RL has not yet been systematically explored in leakage diagnosis and remains at an early stage of development. This review synthesizes current methodologies, identifies key challenges, and outlines future research directions. Full article

Peptide therapeutics occupy a unique chemical space between small molecules and biologics, combining high target specificity with structural programmability and favorable safety profiles. Recent regulatory approvals and expanding clinical pipelines underscore the growing therapeutic and commercial relevance of peptide-based drugs. This review outlines chemical modification approaches and contemporary design strategies, and evaluates their impact on proteolytic stability, pharmacokinetics, membrane permeability, and target engagement. We then highlight recent advances in artificial intelligence (AI)-guided peptide drug design, including machine learning models, protein language models, and generative architectures that enable high-throughput activity prediction, property optimization, and de novo sequence generation. These approaches collectively accelerate the traditional discovery–design–validation cycle while reducing experimental attrition through data-driven, structure-informed modeling frameworks. Among these applications, AI also enables the rational design of cell-penetrating peptides (CPPs) to enhance intracellular delivery and biological activity. Building on these methodological advances, we further examine their application to peptide therapeutics, with particular emphasis on AI-based predictive models for CPPs as well as on therapeutic applications within the central nervous and pulmonary systems. We conclude by outlining future perspectives and emphasize that the systematic integration of AI-enabled sequence design with rational chemical engineering and advanced delivery technologies, supported by rigorous experimental validation, will be critical for developing robust and clinically durable peptide-based medicines. Full article

Last-mile delivery companies can face demand surges where large-volume order requests exceed daily courier capacity. In such cases fast and robust feasibility-first planning becomes more practical and valuable than building optimal routes. This paper proposes a hierarchical, computationally feasible decomposition pipeline that produces shift-feasible clusters under a strict shift-duration limit using travel-time-based duration estimates. While decomposition methods for large-scale VRPs are well established, they typically remain oriented toward route-construction quality within a single operational day or toward balancing customer counts, demand, or Euclidean territory partitions. In contrast, the proposed method targets a different decision problem: rapid feasibility-first strategic capacity planning for one-time extreme demand surges, where the primary requirement is to estimate, within seconds, a conservative upper bound on the number of courier shifts under a strict shift-duration limit. When end-to-end latency is evaluated from raw geographic points, including distance-matrix preparation for monolithic baselines, the proposed pipeline becomes 187 to 1315 times faster than matrix-based monolithic optimization on the common benchmark sizes. Methodologically, the contribution lies in combining (i) topology-preserving spatial linearization with a Hilbert Space-Filling Curve, (ii) adaptive greedy microclustering driven by empirical travel-time quantiles, and (iii) lexicographic dynamic-programming merge that minimizes the number of shifts first and total travel time second. This yields a planning-oriented decomposition mechanism that is distinct from classical route-quality-centered hierarchical VRP approaches. Full article

Urban mobility is a central challenge for sustainable and inclusive cities, as climate change, congestion, and spatial inequality increasingly reveal mobility patterns as expressions of deeper social and spatial structures. Inclusive urban mobility examines whether transport systems equitably support the everyday movements and accessibility needs of historically marginalized and underserved populations. The integration of artificial intelligence with geographic information science, combined with multimodal geospatial data fusion, provides powerful tools to diagnose and address these disparities by integrating heterogeneous data sources such as satellite imagery, GPS trajectories, transit records, volunteered geographic information, and social sensing data into scalable, high-resolution urban mobility analytics. This paper presents a systematic survey of recent GeoAI studies that fuse multiple geospatial data modalities for key urban mobility tasks, including accessibility mapping, demand forecasting, and origin–destination flow prediction, with particular emphasis on inclusive and equity-oriented applications. The review examines 18 multimodal GeoAI studies identified through a PRISMA-ScR screening process from 57 candidate publications between 2019 and 2025. The survey synthesizes methodological trends across data-, feature-, and decision-level fusion strategies, highlights the growing use of deep learning architectures, and examines emerging techniques such as knowledge graphs, federated learning, and explainable AI that support equity-relevant insights across diverse urban contexts. Building on this synthesis, the review identifies persistent gaps in population coverage, multimodal integration, equity optimization, explainability, validation, and governance, which currently constrain the inclusiveness and robustness of GeoAI applications in urban mobility research. To address these challenges, the paper proposes a structured research roadmap linking these gaps to concrete methodological and governance directions including equity-aware loss functions, adaptive multimodal fusion pipelines, participatory and human-in-the-loop workflows, and urban data trusts to better align multimodal GeoAI with the goals of inclusive, just, and sustainable urban mobility systems. Full article

Current security solutions predominantly rely on cloud-based implementations, often neglecting computational resource constraints and operational efficiency. While contemporary methodologies typically require additional training, the few that operate without retraining frequently yield suboptimal performance. To address these limitations, this work leverages a pre-trained MTCNN architecture to detect faces of copyright-protected individuals. We construct a facial landmark database comprising five critical fiducial points, which serves as a supplementary module integrated into the stable diffusion framework, enabling real-time security filtering for synthesized video content. The proposed system utilizes MTCNN models pre-trained in the cloud to build a repository of copyrighted facial signatures, generating a geometric parameter database of facial landmarks. This database, coupled with a parallel verification unit, functions as a plugin within the standard Stable Diffusion pipeline. By leveraging Stable Diffusion’s native decoder, we decode stochastic frames from the U-Net latent representations and perform real-time comparative analysis to identify potential copyright violations in generated video sequences. Upon detecting an infringement, an on-screen display (OSD) alert notifies the user and immediately halts the text-to-video (T2V) generation process. Experimental evaluations demonstrate that our framework effectively mitigates the resource constraints and latency issues inherent in edge deployment scenarios of prior security implementations. Leveraging MTCNN’s proven robustness and extensive edge compatibility for facial recognition, the proposed detection and obfuscation plugin integrates seamlessly with Stable Diffusion while preserving generation quality. Full article

This study develops and applies an integrated methodology that combines deep learning-based computer vision and spatial statistics to automate the large-scale identification and analysis of morphological features in vernacular courtyard dwellings. Focusing on Liangshuaixiu dwellings in Wu’an, southern Hebei, we trained an HRNetV2 semantic segmentation model on high-resolution satellite imagery to identify and extract contours for 134,280 courtyard spaces. Core morphological parameters (area, orientation) were calculated and analyzed using GIS spatial statistics and the geographic detector model. The results show that (1) the computer vision pipeline achieved efficient recognition with satisfactory accuracy (~10% mean error); (2) spatial autocorrelation and hotspot analysis revealed distinct regional patterns, including a west–east increase in average courtyard area; and (3) geographic detector analysis demonstrated that courtyard morphology is shaped by complex interactions between natural and socio-economic factors. While average area and orientation were primarily governed by climate (air pressure, wind, temperature) and topography (elevation), diversity and internal variation were strongly influenced by nonlinear interactions, particularly between natural factors (e.g., wind–aspect) and between natural and human factors (e.g., population–climate). This work provides a scalable, data-driven framework for the quantitative spatial analysis of vernacular architectural heritage, advancing the understanding of building morphology as an outcome of coupled human–environment systems. Full article

Artificial intelligence (AI) has been increasingly applied to leukemia research, spanning diagnostic, prognostic, therapeutic, and translational domains. However, the rapid growth and methodological diversity of this literature present challenges for existing reviews, which are often constrained by limited scope, narrow clinical focus, or reliance on either manual or purely bibliometric approaches. As a result, cross-domain relationships, evolving methodological trends, and the interaction between data modalities and clinical objectives remain insufficiently understood. This paper presents a systematic, AI-assisted literature analysis of AI applications in leukemia, combining scalable machine-driven discovery with author-led qualitative interpretation. Using a PRISMA-guided screening process, a corpus of 2338 peer-reviewed publications retrieved from Scopus (1990–2024) is analyzed through semantic text representation and unsupervised clustering. An iterative human–machine process is employed to identify and refine 23 analytical parameters grouped into five macro-parameters, enabling structured organization of the research landscape across diagnostic, prognostic, therapeutic, genetic, and methodological dimensions. Building on this structured representation, in-depth qualitative analysis is conducted by the authors across parameters and macro-parameters, synthesizing methodological developments, data usage patterns, application domains, and commonly used datasets. The resulting analysis provides a coherent, interpretable mapping of AI-driven leukemia research, supporting cross-domain comparison and identification of research concentrations, fragmentation, and emerging directions. By integrating large-scale automation with domain-informed qualitative analysis in a reusable analytical pipeline, this work contributes a rigorous and transferable framework for structured literature analysis in leukemia and related biomedical domains. Full article

The assessment of Industrialized Building System (IBS) adoption in construction projects—a critical metric for evaluating prefabrication levels and construction modernization—remains largely manual, time-intensive, and prone to inconsistencies, with practitioners typically requiring 4–8 h to evaluate a single building using spreadsheet-based frameworks and visual documentation review. This paper presents a novel AI-enhanced workflow architecture that automates IBS scoring through systematic processing of Industry Foundation Classes (IFC) building information models—the first documented integration of web-based IFC processing, visual workflow automation (n8n), and large language model (LLM) reasoning specifically for construction industrialization assessment. The proposed system integrates a web-based frontend for IFC file upload and configuration, an n8n workflow automation backend orchestrating data transformation pipelines, and an Azure OpenAI-powered scoring engine (GPT-4o-mini and GPT-5-0-mini) that applies Construction Industry Standard (CIS) 18:2023 rules to extracted building data. Experimental validation across 136 diverse IFC building models (ranging from 0.01 MB to 136.26 MB) achieved a 100% processing success rate with a median processing duration of 61.62 s per model, representing approximately 99% time reduction compared to conventional manual assessment requiring 4–8 h of expert practitioner effort. The system demonstrated consistent scoring performance with IBS scores ranging from 31.24 to 100.00 points (mean 37.14, SD 8.84), while GPT-5-0-mini exhibited 71% faster inference (mean 23.4 s) compared to GPT-4o-mini (mean 80.2 s) with no significant scoring divergence, validating prompt engineering robustness across model generations. Processing efficiency scales approximately linearly with file size (0.67 s per megabyte), enabling real-time design feedback and portfolio-scale batch processing previously infeasible with manual methods. Unlike prior rule-based compliance checking systems requiring extensive manual programming, this approach leverages LLM semantic reasoning to interpret ambiguous construction classifications while maintaining deterministic scoring through structured prompt engineering. The system addresses key interoperability challenges in IFC data heterogeneity while maintaining traceability and compliance with established scoring methodologies. This research establishes a replicable architectural pattern for BIM-AI integration in construction analytics and positions LLM-enhanced IFC processing as a practical, accessible approach for industrialization evaluation that democratizes advanced assessment capabilities through open-source workflow automation technologies. Full article

Reliable and up-to-date measurements of public space remain scarce in small and medium-sized towns (SMSTs), where conventional geospatial datasets are often outdated, inconsistent, or inaccessible. This study presents a low-cost and fully reproducible computational pipeline that integrates nadir RGB imagery captured by a DJI Mini 3 UAV with a lightweight instance-segmentation model (Ultralytics YOLOv12-seg) and GIS-based post-processing to derive class-specific surface indicators at the neighborhood scale. The workflow consists of four components: autonomous UAV acquisition over three representative zones of Sesquilé, Colombia; planar mosaic generation and georeferencing using ad hoc ground control points; fine-tuning of a YOLOv12-seg model trained on locally annotated images; and transformation of predicted masks into OSM and GeoPackage geometries for metric analysis. The trained model achieved stable convergence with mask mAP50 ≈ 0.85 and mAP50–95 ≈ 0.70, supported by balanced precision–recall behavior across classes. Spatial outputs exhibit coherent morphological contrasts between the analyzed zones. Buildings occupy 48.17% of the mapped area, vegetation 25.88%, and transport- and plaza-related public space (roadways, sidewalks, and hardscape areas) 25.95%. These proportions capture a clear gradient from a dense urban core to less consolidated peripheral sectors. Results demonstrate that very-high-resolution UAV imagery, combined with open-source deep-learning tools and structured GIS post-processing, can reliably produce operational public-space indicators for SMSTs at low cost. The methodology provides an accessible and scalable framework for evidence-based urban assessment in municipalities with limited technical and financial resources. Full article