Search Results (610)

The convergence of artificial intelligence (AI), explainable AI (XAI), and neuroscience is fostering new opportunities for understanding both machine and biological intelligence through interpretable and human-centered learning paradigms. In this Perspective, we introduce XAI2Brain as a conceptual framework for brain–AI alignment, positioning mechanistic interpretability as an intermediate layer connecting neural network representations, human understanding, and neuroscience-inspired AI design. Rather than viewing XAI solely as a post hoc transparency tool, we emphasize its emerging role in enabling mechanistic analysis of internal model representations, concept-level reasoning, and interactive human–AI alignment. We define XAI2Brain as a multi-level conceptual framework rather than a deployable system, explicitly aimed at structuring brain–AI alignment across representation-level, mechanism-level, and interaction-level perspectives. We survey the evolution of XAI methodologies—from feature attribution and concept-based explanations to mechanistic and human-centric interpretability approaches—and discuss how these methods may support bidirectional knowledge transfer between AI systems and cognitive neuroscience. Importantly, we adopt a cautious stance on brain–AI analogy, explicitly recognizing that artificial neural representations are not equivalent to biological neural representations, and instead focusing on functional and informational correspondences rather than structural equivalence. Unlike conventional human-in-the-loop or reinforcement learning from human feedback paradigms that primarily optimize behavioral outputs, XAI2Brain focuses on cognitively interpretable and mechanistically grounded alignment between AI systems and human reasoning processes. This alignment promotes interactive human-in-the-loop intelligence, empowering humans to comprehend, guide, and refine AI systems, while enabling AI systems to better interpret human instructions, intentions, and contextual reasoning. We further discuss the challenges of scaling explainability to large generative and multimodal models, including issues of interpretability robustness, cognitive compatibility, evaluation, and ethical accountability. We also highlight key limitations of current mechanistic interpretability methods, including explanation instability, representation superposition, and lack of causal guarantees, underscoring that these challenges remain open research problems. Rather than proposing a complete artificial brain architecture, this Perspective outlines a research roadmap toward more interpretable, adaptive, and neuroscience-inspired AI systems capable of supporting future brain–AI integration and collaborative intelligence. We additionally clarify that this work follows a narrative perspective review methodology with structured thematic synthesis of the literature. By framing explainability as a bridge between mechanistic AI understanding, cognitive science, and human-centered interaction, XAI2Brain highlights the importance of interpretable alignment for the next generation of brain-inspired AI systems. Full article

Multi-source heterogeneous data in discrete manufacturing shop floors, including vibration signals, equipment logs, visual monitoring data, and handwritten production reports, exhibit significant differences in modality and semantic representation. Traditional fusion methods often fail to bridge the semantic gap between low-level sensing signals and high-level manufacturing cognition, limiting intelligent anomaly analysis and decision-making capability. To address this issue, this paper proposes a semantic translation and fusion framework for industrial heterogeneous data based on Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs). First, a unified semantic translation mechanism is developed to convert multimodal industrial data into structured semantic representations for cross-modal alignment. Second, an industrial knowledge graph and RAG mechanism are introduced to integrate process knowledge, maintenance manuals, and historical fault records into the reasoning process. Third, an LLM-driven reasoning framework is designed for multimodal semantic fusion, anomaly identification, causal analysis, and optimization recommendation generation. In addition, a digital twin-based visualization interface is constructed to realize real-time interaction between production lines, industrial data, and intelligent cognitive reports. Experimental results demonstrate that the proposed framework significantly improves industrial reasoning accuracy, anomaly analysis correctness, and response efficiency compared with general-purpose LLMs, providing an effective solution for intelligent cognition and decision-making in discrete manufacturing systems. Full article

Signals generated during tool wear are nonlinear, non-stationary, and easily affected by machining noise, which makes reliable tool condition monitoring difficult in intelligent manufacturing. To address this issue, this study proposes a tool wear degree classification framework, FCTrans-CA, that fuses time-domain and frequency-domain information through a lightweight cross-attention (CA) bridge. Fast Fourier transform (FFT) is first used to obtain frequency-domain representations. The raw time-domain signals are processed by a multi-scale one-dimensional convolutional neural network (MS-CNN) to extract temporal wear features, while the FFT-derived representations provide complementary spectral cues. These two feature streams are fused by an asymmetric CA module in which frequency-domain features guide the selection of wear-sensitive temporal features. K-means clustering is used to divide the measured flank wear (VB) trajectory of each tool into initial-, normal-, and severe-wear stages, thereby reducing subjectivity in label generation. Experiments on the PHM2010 milling dataset show that FCTrans-CA achieves 99.43% classification accuracy on 40,648 test samples. The results indicate that cross-domain feature interaction improves the separability of wear states and provides a reproducible data-driven route for tool wear monitoring. Full article

The integration of photovoltaic (PV) and wind turbine (WT) systems into modern power grids demands not only accurate component-level models but also a holistic understanding of their coordinated operation. This review bridges the gap between low-level device physics and high-level system coordination, offering a dual perspective often overlooked in existing surveys that treat generation and management separately. We systematically analyze PV models, from single-diode equivalent circuits to data-driven approaches, and WT models, ranging from aerodynamic and mechanical representations to simplified electrical equivalents suitable for stability studies. Critically, we then shift focus to the system level by examining energy management systems (EMS) that enable hybrid PV–WT coordination. Unlike prior reviews that emphasize either component accuracy or dispatch strategies alone, this paper highlights the emerging synergy between hybrid PV–WT modeling and EMS architectures. By identifying mismatches between model fidelity and EMS requirements, this review maps a pathway towards more integrated hybrid renewable systems. The discussion synthesizes key trade-offs in scalability, uncertainty handling, and real-time feasibility, underscoring that true potential is unlocked only through intelligent integration of component models and control architectures. Full article

Human sitting posture recognition is critical for smart seating, ergonomic monitoring, and healthcare systems. However, existing deep learning approaches typically rely on highly complex network architectures that are computationally expensive, hindering their lightweight deployment on edge devices. Furthermore, current methods frequently struggle with indistinct boundaries among multi-class postures and are highly prone to overfitting when constrained by small-sample pressure sensor datasets. To bridge this gap, this paper proposes a novel, lightweight posture recognition framework specifically tailored for pressure distribution maps. First, sitting pressure data is collected using a thin-film pressure array sensor and uniformly mapped into an [M × N] image representation, establishing an effective sample format for Convolutional Neural Network (CNN) inputs. Second, as our primary architectural contribution, we fundamentally optimize the classic LeNet-5 network to enhance complex feature representation without inflating model complexity. Specifically, the depth of the convolutional layers is increased with a progressively increasing channel configuration. Batch Normalization (BN) is introduced to accelerate convergence and ensure training stability, while a Dropout mechanism is embedded within the fully connected layers to strictly penalize overfitting under small-sample constraints. These architectural improvements are synergistically combined with targeted data augmentation strategies—including random translation, rotation, and intensity perturbation—to further strengthen the model’s generalization capability. Experimental results demonstrate that the proposed method achieves a classification accuracy of 95.5% in a five-class sitting posture recognition task, significantly outperforming baseline models such as the traditional LeNet-5, AlexNet-Lite, and VGG-Small. The findings indicate that this approach achieves an optimal balance among recognition accuracy, training stability, and low model complexity, providing a robust algorithmic baseline and proof-of-concept for smart healthcare perception systems, paving the way for future large-scale subject-independent validation. Full article

Petri nets represent a highly versatile mathematical formalism for modeling discrete event and hybrid systems. For the development of modern complex production processes for Industry 4.0, integrating these formal models with industrial communication standards is an appropriate and effective option. The main aim of the proposed article is to design a new web-based software tool for the modeling, simulation, and control of mechatronic systems with OPC Unified Architecture support. To accomplish this task, an original software solution called PetriLink is proposed. This platform leverages an intuitive graphical interface and significantly expands the formalism by combining hybrid Petri nets with Colored Petri Nets (CPN) data extensions and a reactive OPC UA subscription model. These new features greatly expand the area of systems that can be modeled and controlled, bridging the gap between theoretical academic tools and practical industrial automation. Furthermore, the structural flexibility of the implemented Petri net models enables the explicit representation of symmetric cyber-physical architectures, as well as the design of asymmetric, event-driven control strategies (e.g., using inhibitor and reset arcs) for enhanced system robustness. The platform was evaluated on a reference net of 5000 places and 2500 transitions, where an incremental dirty-flag evaluation mechanism keeps the per-step engine cost below 1 ms for sparse industrial markings and at about 350 µs for a moderate workload of one hundred concurrent tokens, yielding a speed-up of up to roughly three orders of magnitude over naive full re-evaluation and confirming consistent soft real-time behavior on commodity hardware. Offering a graphical environment for the design of discrete event and hybrid system control algorithms, it can be used for education, research and practice in cyber-physical systems (Industry 4.0). Full article

Accurate identification of pathogenic yeasts is essential for clinical diagnosis and effective antifungal therapy. However, current approaches predominantly rely on microscopy-based models, which require large-scale annotated datasets and exhibit limited generalization across morphologically similar species. In contrast, light-scattering (LS) imaging captures the diffraction patterns generated by internal cellular structures, providing volumetric biophysical cues that extend beyond surface morphology, yet its indirect representations pose major challenges for feature discrimination. Our objective is to develop fast and accurate methods to detect various species of yeasts. We propose FPA-YeastNet, which is a frequency-enhanced single-modality deep learning architecture that improves yeast classification in LS images by leveraging discriminative frequency-domain features. Building upon this enhanced modality, we further propose FGCA-YeastNet, a frequency-guided cross-attention network designed to integrate LS and microscopy information for complementary representation learning. The proposed multimodal model facilitates synergistic interactions between volumetric scattering structures and fine-grained cellular textures through adaptive fusion and bidirectional attention, leading to improved robustness and interpretability. Comprehensive classification experiments conducted on a multimodal yeast dataset demonstrate that FGCA-YeastNet effectively bridges the performance gap between LS and microscopy modalities, achieving significant improvements over both unimodal and multimodal baselines. The FPA-YeastNet yields an average accuracy improvement of 6.26% compared with LS-only models, and FGCA-YeastNet further provides mean gains of 19.97% and 7.67% over unimodal and multimodal baseline models, respectively. Experimental results demonstrate the diagnostic potential of light scattering and microscopic imaging and underscore the effectiveness of frequency-guided multimodal collaboration for reliable and interpretable yeast classification in clinical microbiology. Full article

This study addresses the fragmented understanding of tourist responses to AI-generated content (AIGC) in tourism and hospitality by developing a process-oriented systematic review. While prior studies have examined AIGC-related trust, authenticity, credibility, and adoption, these constructs have often been treated separately, limiting theoretical understanding of how tourists evaluate and rely on AI-generated tourism content. Based on a systematic review of 98 peer-reviewed journal articles retrieved from Scopus and the Web of Science Core Collection and published between January 2023 and March 2026, this study synthesizes the literature around four connected stages: perceived AIGC attributes, evaluative judgments, trust calibration, and behavioral responses. The findings show that tourist responses to AIGC are not direct reactions to technological exposure, but emerge through a layered process in which tourists assess content quality, credibility, authenticity, and contextual appropriateness before deciding whether and how far to rely on AI-generated outputs. The review contributes by reconceptualizing trust as a dynamic calibration mechanism, distinguishing authenticity from credibility and trust, and identifying reliance as a key bridge between evaluation and behavior. The study offers a process-oriented framework and a future research agenda for advancing more theoretically integrated and context-sensitive research on AIGC in sustainable digital tourism. By clarifying how tourists evaluate, trust, verify, and rely on AI-generated tourism content, the review contributes to sustainable tourism development by highlighting the conditions under which AIGC can support more responsible, transparent, and human-centered tourism communication. These insights are relevant to destination sustainability because trustworthy and context-sensitive AIGC can improve information quality, reduce misleading representations, and support more informed tourist decision-making. Full article

Understanding advanced pre-tertiary mathematics, particularly three-dimensional vectors, demands robust spatial reasoning skills that many students find challenging to develop through traditional pedagogical methods. This study proposes and evaluates an innovative educational tool that leverages large vision models to automate the conversion of handwritten vector equations into accurate 3D graphical representations. By interpreting students’ handwritten input using advanced computer vision, the system provides immediate, interactive visual feedback to bridge the cognitive gap between abstract symbolic notation and tangible geometric concepts. We evaluated the system using a dataset of 1000 handwritten vector equations typical of the Singapore-Cambridge GCE ‘A’ Level H2 Mathematics syllabus. Our findings demonstrate that while GPT-4o serves as a capable baseline, achieving 84.6% accuracy with multi-shot prompting, newer variants such as GPT-4.1-mini offer superior performance, reaching 91.4% accuracy with significantly higher computational efficiency. The results confirm that AI-powered visualisation tools can effectively interpret complex spatial mathematical layouts when guided by optimal prompt engineering. Implementing such technology in educational settings presents a viable, scalable, and cost-effective method to democratise learning support, fostering independent study and enhancing students’ conceptual comprehension of spatial mathematics. Full article

Water plays a fundamental role in countless natural and technological systems, where its unique properties are connected with those of the surrounding environment. The water’s anomalous behaviors arise from the directional nature of hydrogen bonding between molecules. To understand these anomalies, numerous molecular models have been developed, ranging from detailed atomistic descriptions to coarse-grained, conceptually simple representations. Among the latter, the two-dimensional Rose model offers a minimal yet physically meaningful framework that reproduces key thermodynamic and structural anomalies of real water while remaining analytically tractable. In this work, we present a comprehensive review and comparison of results obtained for the Rose water model using Monte Carlo and molecular dynamics simulations, thermodynamic perturbation theory, integral equation theory (both orientation-averaged and orientation-dependent), and an analytical model. The study encompasses the thermodynamic and structural properties of pure Rose water and of systems containing nonpolar solutes. Moreover, the anomalous regions and phase behavior of the model are systematically explored. The combined results demonstrate that the Rose model successfully captures the essential physics of water’s anomalies within a simple and computationally efficient framework, providing a valuable bridge between theory and simulation. Full article

Urban traffic congestion remains a persistent global challenge, contributing to significant economic inefficiencies, elevated greenhouse gas emissions, and diminished quality of life. This paper presents a real-world video-based traffic monitoring study combined with a proposed adaptive signal control framework. In the monitoring component, YOLOv11 object detection was applied directly to footage recorded from an overhead bridge position on a 40 km/h road. The model successfully detected and tracked multiple road-user categories, including cars, trucks, buses, motorcycles, cyclists, and pedestrians, yielding 1041 vehicle detections across 25 unique tracked objects. Vehicle speeds were estimated from inter-frame centroid displacement, and a Region of Interest (ROI) occupancy model was used to classify congestion states as High, Medium, or Free Flow using thresholds grounded in Highway Capacity Manual (HCM) level-of-service criteria. The system detected 11 high-congestion frames (3.8%), 184 medium-congestion frames (63.9%), and 93 free-flow frames (32.3%), consistent with moderate congestion observed during the recording period. In the proposed control component, a Proximal Policy Optimisation (PPO)-based reinforcement learning signal controller is designed around the YOLOv11 detection outputs as its state representation. Based on comparable adaptive traffic signal control studies in the literature, the proposed framework is projected to achieve approximately 25% higher peak-hour throughput, 35% shorter queue lengths, and 32% lower average waiting times relative to a fixed-time signal baseline. The detection accuracy (mAP@0.5 = 93.2%) and inference speed (32 FPS) cited are published YOLOv11 benchmarks used as indicative performance references. This work bridges real-world perception and proposed intelligent control, providing a transparent and reproducible methodology for next-generation smart city traffic management. Full article

The work presented in this study uses Bond Graphs to model and simulate complex urban traffic flow systems consisting of three interconnected, traffic-light-controlled crossroads with heavy traffic demand. Bond Graph models are highly versatile for modeling multi-domain systems and provide a convenient bridge between analytical representations and numerical implementations. In this paper, we exploit Bond Graph model theory and digital logic concepts to develop a structured methodology for deriving Bond Graph switching network models applied to urban traffic flow. A simple traffic-light-controlled crossroad is then modeled and analyzed. Moreover, the application of Bond Graph modeling to traffic flow, illustrated through a real case study of a street network in Sofia, Bulgaria, validates the proposed model-based approach. The obtained results demonstrate the relevance and effectiveness of the proposed Bond Graph model-based macroscopic traffic modeling framework in capturing the fundamental dynamics of traffic flow under signalized control. Beyond the specific case study considered, these results highlight the potential of the approach as a general and extensible tool for modeling more complex urban traffic networks. They open perspectives for future work aimed at assessing the flexibility, scalability, and generalization capability of the framework for heterogeneous intersections and large-scale traffic systems. Full article

The dual-active-bridge series resonant converter (DBSRC) is attractive for bidirectional DC conversion, but its output voltage may respond slowly and exhibit overshoot during start-up, load-step, and reference-step transients when conventional controllers are designed mainly from steady-state or small-signal models. This paper addresses the problem of improving the large-signal transient regulation of a DBSRC while avoiding undesired charging and discharging of the switching capacitor and output capacitor. A finite-state-machine-based state-trajectory control method is proposed. Thus, the converter consists of two full-bridge circuits, each with four switches. The proposed technique enhances the dynamic response of output voltage regulation. By examining the system dynamics in two state-plane domains, the switching behavior of the converter can be clearly characterized, enabling an accurate geometric representation of its operating mechanism. Consequently, a finite-state machine controller is designed based on state-trajectory planning. Switching conditions are utilized to achieve fast start-up and step-load transient responses. Finally, experiments are conducted to validate the effectiveness of the proposed control method. Full article

Digital Twin (DT) research in civil infrastructure has expanded rapidly, yet its practical maturity in bridge engineering remains uneven. This review examines sensor-driven DT research in bridge infrastructure through a combined bibliometric and systematic approach, with particular emphasis on implementation logic and operational maturity. First, a broad bibliometric analysis was conducted to map the thematic directions, technological clusters, and infrastructure domains structuring DT research across civil infrastructure. Second, a bridge-specific systematic review of implemented and sensor-supported cases was performed to characterize their dominant application domains, technological components, integration logic, and maturity level. The broader civil-infrastructure literature is organized around structural monitoring, lifecycle information management, cyber–physical connectivity, AI-enabled analytics, and digital representation. By contrast, the bridge-specific literature narrows toward model-asset coupling, structural health monitoring, response-based interpretation, and implementation-oriented integration. Across the reviewed bridge cases, the most recurrent layers correspond to sensing, communication, digital representation, and analytical modelling, whereas the decisive features of robust operational twins, namely continuous or recurrent physical coupling, structured data fusion, effective update logic, and explicit decision-support use, remain less consistently implemented and documented. In this sense, the study provides a more discriminating maturity-oriented interpretation of current bridge DT research by connecting bibliometric evolution, architectural configuration, and bridge-specific implementation evidence. Full article

Circular RNAs (circRNAs) are key regulators in the onset and progression of complex diseases, offering promise as diagnostic and prognostic biomarkers. However, most putative circRNA–disease associations remain experimentally unverified, largely due to the cost and time demands of wet-lab approaches. To bridge this gap, we present STRCDA (Sparse Topological Representation learning for CircRNA–Disease Associations). The pipeline first constructs fused similarity profiles for circRNAs and diseases by integrating diverse biological attributes. These initial matrices are then refined via random walk with restart to capture local features. Subsequently, a sparse-constrained dual-branch graph autoencoder extracts holistic topological embeddings from the refined local features and the known interaction network. Finally, an XGBoost classifier scores potential circRNA–disease pairs. On the CircR2Disease dataset, STRCDA achieves an AUC of 0.9771 and an AUPR of 0.9826 under five-fold cross-validation. Notably, 18 of the top 20 predicted associations were confirmed by independent experimental evidence, highlighting STRCDA’s efficacy as a robust tool for uncovering circRNA function in disease. Full article