Search Results (2,967)

Smoking in oilfield operation areas poses a severe risk of fire and explosion accidents, threatening production safety, workers’ lives, and the surrounding ecological environment. Such behavior represents a typical preventable unsafe human action. Detecting smoking behaviors among oilfield workers can fundamentally prevent such safety incidents. To address the challenges of low detection accuracy for small objects and frequent missed or false detections under extreme industrial environments, this paper proposes a GCEA-YOLO network based on YOLOv11 for smoking behavior detection. First, a CSP-EDLAN module is introduced to enhance fine-grained feature learning. Second, to reduce model complexity while preserving critical spatial information, an ADown module is incorporated. Third, an enhanced feature fusion module is integrated to achieve effective multiscale feature aggregation. Finally, an EfficientHead module is employed to generate high-precision and lightweight detection results. The experimental results demonstrate that, compared with YOLOv11n, GCEA-YOLO achieves improvements of 20.8% in precision, 6.9% in recall, and 15.1% in mean average precision (mAP). Overall, GCEA-YOLO significantly outperforms YOLOv11n. Full article

To achieve a scientific evaluation of land ecological resilience in mining areas and promote the green transformation and sustainable development of the mining industry, this study is based on the core concept of Nature-based Solutions (NbS), coupling the “Driving force–Pressure–State–Impact–Response” (DPSIR) framework, and constructs an evaluation system for mine land ecological resilience (MLER) focusing on sustainability. This system covers multiple aspects, including natural ecology, socio-economics, and policy management, comprising 21 secondary indicators that comprehensively respond to NbS’ fundamental principles of “nature-guided, multi-party collaboration, and long-term adaptation.” In terms of evaluation methodology, this study proposes a combined weighting model that integrates AHP-CRITIC game theory with Vague sets. First, subjective expert experience and objective data variance are balanced through combined weighting. Based on game theory, the optimal combination coefficients were determined (α₁ = 0.624, α₂ = 0.376) to reconcile subjective and objective preferences. Subsequently, the three-dimensional interval structure of Vague sets is utilized to effectively accommodate fuzzy information and data gaps. By characterizing the restoration process through interval membership, the model enhances the representational capacity of the evaluation results regarding complex ecological information. Empirical research conducted in the mining areas of Gan Xian, Xing Guo, Yu Du, and Xun Wu in Jiangxi Province effectively identified differences in resilience levels: the resilience of the Xing Guo mining area was classified as I, Gan Xian and Yu Du as II, and Xun Wu as IV. These results are fundamentally consistent with the AHP-Fuzzy Comprehensive Evaluation method, verifying the robustness and reliability of the model. The NbS-guided evaluation system and model constructed in this study provide scientific tools for identifying differences in the sustainability of MLER and key constraints, promoting the transformation of restoration models from “engineering-driven” to “nature-driven, long-term adaptation” in the context of NbS in China. Full article

Accurate user positioning in 6G networks is essential for next-generation mobile services. However, classical approaches such as time-difference-of-arrival (TDoA) remain vulnerable to dense multipath and NLoS conditions commonly found in indoor and industrial environments. This paper proposes an AI-driven RF fingerprinting framework that leverages uplink channel state information (CSI) to achieve robust and privacy-preserving 2D localization. A lightweight convolutional neural network (CNN) extracts location-specific spectral–spatial fingerprints from CSI tensors, while a federated learning (FL) scheme enables distributed training across multiple gNBs without sharing raw channel data. The proposed integration of CSI tensor processing with FL and structured pruning is introduced as a novel solution for practical 6G edge positioning. To further reduce latency and communication costs, a structured pruning mechanism compresses the model by 40–60%, lowering the memory footprint with negligible accuracy loss. A performance evaluation in 3GPP-compliant indoor factory scenarios indicates a median positioning error below 1 m for over 90% of cases, significantly outperforming TDoA. Moreover, the compressed FL model reduces the FL communication load by ~38% and accelerates local training, establishing an efficient, secure, and deployment-ready positioning solution for 6G networks. Full article

Improving alignment between timber sawmilling and prefabrication, defined as the coordination of information, materials, and decision-making across the supply chain, is critical for sustainable construction. This study examined integration through semi-structured interviews with 15 industry practitioners. Using framework analysis supported by NVivo, eight interlinked themes were identified: supply chain fragmentation and market cycles; data-driven forecasting; inventory and moisture management; digital integration; smart planning and production; quality assurance and workforce capability; circular economy and residue utilisation; and systemic enablers and constraints. The findings show that technical capabilities such as optimisation, grading, and QR-based traceability are often undermined by organisational and policy barriers, including distributor-mediated purchasing, limited interoperability, outdated standards, and uneven skills pathways. Integration was considered more feasible for mass timber prefabrication, where batch planning, tighter quality assurance, and vertical integration align with mill operations, compared with frame-and-truss networks that rely on just-in-time project workflows. The study provides empirical evidence of practitioner perspectives and identifies priorities for action that translate into sustainability gains through improved material efficiency, waste reduction, higher-value residue pathways, and supportive policy settings. Full article

The effects of extreme heat events on Surface Urban Heat Island Intensity (SUHII) were investigated in Lecce (southern Italy) during the summer months (June–August) from 2018 to 2025. The analysis began with the identification of heatwave frequency, duration, and intensity using the Warm Spell Duration Index (WSDI), based on a homogenized long-term temperature record, which indicated a progressive increase in persistent extreme events in recent years. High-resolution ECOSTRESS land surface temperature (LST) data were then processed and combined with CORINE Land Cover (CLC) information to examine the thermal response of different urban fabrics, compact residential areas, continuous/discontinuous urban fabric, and industrial–commercial zones. SUHII was derived from each ECOSTRESS acquisition and evaluated across multiple diurnal intervals to assess temporal variability under both normal and WSDI conditions. The results show a consistent diurnal asymmetry: daytime SUHII becomes more negative during WSDI periods, reflecting enhanced rural warming under dry and highly irradiated conditions, despite overall higher absolute LST during heatwaves, whereas nighttime SUHII intensifies, particularly in dense urban areas where higher thermal inertia promotes persistent heat retention. Statistical analyses confirm significant differences between normal and extreme conditions across all classes and time intervals. These findings demonstrate that extreme heat events alter the urban–rural thermal contrast by amplifying nighttime heat accumulation and reinforcing daytime negative SUHII values. The integration of WSDI-derived heatwave characterization with multi-year ECOSTRESS observations highlights the increasing thermal vulnerability of compact urban environments under intensifying summer extremes. Full article

This paper discusses the evolution of convolutional (CNN) and recurrent (RNN) artificial neural networks in applications for Building Information Modeling (BIM). The paper outlines the milestones reached in the last two decades. The article organizes the current state of knowledge and technology in terms of three aspects: (1) computer visualization coupled with BIM models (detection, segmentation, and quality verification in images, videos, and point clouds), (2) sequence and time series modeling (prediction of costs, energy, work progress, risk), and (3) integration of deep learning results with the semantics and topology of Industry Foundation Class (IFC) models. The paper identifies the most used architectures, typical data pipelines (synthetic data from BIM models, transfer learning, mapping results to IFC elements) and practical limitations: lack of standardized benchmarks, high annotation costs, a domain gap between synthetic and real data, and discontinuous interoperability. We indicate directions for development: combining CNN/RNN with graph models and transformers for wider use of synthetic data and semi-/supervised learning, as well as explainability methods that increase trust in AECOO (Architecture, Engineering, Construction, Owners & Operators) processes. A practical case study presents a new application, Bimetria, which uses a hybrid CNN/OCR (Optical Character Recognition) solution to generate 3D models with estimates based on two-dimensional drawings. A deep review shows that although the importance of attention-based and graph-based architectures is growing, CNNs and RNNs remain an important part of the BIM process, especially in engineering tasks, where, in our experience and in the Bimetria case study, mature convolutional architectures offer a good balance between accuracy, stability and low latency. The paper also raises some fundamental questions to which we are still seeking answers. Thus, the article not only presents the innovative new Bimetria tool but also aims to stimulate discussion about the dynamic development of AI (Artificial Intelligence) in BIM. Full article

This paper presents OpS-EWMA-LLM (Operational State Shifts Detection using Exponential Weighted Moving Average and Labeling using Large Language Model), a hybrid framework that combines fleet-normalized statistical shift detection with LLM-assisted diagnostics to identify and interpret operational state changes across heterogeneous fleets. First, we introduce a residual-based EWMA control chart methodology that uses deviations of each component’s sensor reading from its fleet-wide expected value to detect anomalies. This statistical approach yields near-zero false negatives and flags incipient faults earlier than conventional methods, without requiring component-specific tuning. Second, we implement a pipeline that integrates an LLM with retrieval-augmented generation (RAG) architecture. Through a three-phase prompting strategy, the LLM ingests time-series anomalies, domain knowledge, and contextual information to generate human-interpretable diagnostic insights. Finaly, unlike existing approaches that treat anomaly detection and diagnosis as separate steps, we assign to each detected event a criticality label based on both statistical score of the anomaly and semantic score from the LLM analysis. These labels are stored in the OpS-Vector to extend the knowledge base of cases for future retrieval. We demonstrate the framework on SCADA data from a fleet of wind turbines: OpS-EWMA successfully identifies critical temperature deviations in various components that standard alarms missed, and the LLM (augmented with relevant documents) provides rationalized explanations for each anomaly. The framework demonstrated robust performance and outperformed baseline methods in a realistic zero-tuning deployment across thousands of heterogeneous equipment units operating under diverse conditions, without component-specific calibration. By fusing lightweight statistical process control with generative AI, the proposed solution offers a scalable, interpretable tool for condition monitoring and asset management in Industry 4.0/5.0 settings. Beyond its technical contributions, the outcome of this research is aligned with the UN Sustainable Development Goals SDG 7, SDG 9, SDG 12, SDG 13. Full article

With the deep integration of digital technology and the tourism industry, the transformation of the spatial form of smart tourism destinations and the research on their system structure have become the focus. This study adopts a mixed research approach, taking villages in the mountainous areas of southeastern China as examples, and collects empirical data through semi-structured interviews, participant observation and literature collection. This study draws on structuralist location theory to construct a four-dimensional spatial analysis model of natural environment, production economy, social norms and cultural values and incorporates a historical perspective to make up for the limitations of this theory in explaining regional dynamic changes caused by the lack of a time dimension. This study finds that digital tourism provides external resources such as the consumer market, tourism capital and information technology prompting the reconfiguration of the rural internal system. By absorbing external resources and upgrading traditional industries, rural areas have formed a more diversified, inclusive, and dynamically balanced spatial form. Furthermore, phenomena such as villagers’ relocation, e-commerce employment and local tea-growing knowledge indicate that certain predicaments still exist in the construction of digital tourism. This research can provide practical references for the development and spatial optimization of rural digital tourism. Full article

The creation of bioenergy based on the biomass wood pellet industry, which accounts for the majority of the global biomass supply, is one of the most common and important ways to utilize waste wood, wood dust, and other byproducts of wood manufacturing, known as forestry residues. Pellet production processes might greatly benefit from fast monitoring systems that may allow for at least a semi-quantitative measurement of crucial parameters such as lignin and cellulose. The determination of lignin and cellulose is complicated and time-consuming because it usually requires time-demanding and labor-intensive sample preparation. This, however, might be a crucial problem. In this context, the application of Raman spectroscopic techniques is considered a promising approach, as it enables rapid, reliable, and label-free analysis of wood pellets, providing information about the chemical composition of the biomass, specifically lignin and cellulose. The purpose of this article is to report on the application of Raman spectroscopy exemplified by the detection of the lignin/cellulose ratio. In our methodological approach, we integrated the area under the selected Raman bands to avoid a large scatter of data when only the intensities of the bands were used. Moreover, the acquired Raman spectra displayed very strong signals from both substances, which contributes to the feasibility of the analysis even with a portable instrument. This study is expected to be of assistance in situations when the monitoring of the chemical changes and the quick inspection of pellets are required in near real time, online, and in situ. Full article

Taiwan’s strategic focus in digital healthcare has been officially integrated into national industrial policy and identified as a crucial application area for artificial intelligence (AI) and next-generation communication technologies. As the healthcare sector undergoes rapid digital transformation, digital healthcare technologies have emerged as essential tools for improving medical quality and efficiency. Leveraging the extensive coverage of its National Health Insurance (NHI) system and its strengths in Information and Communications Technology (ICT), Taiwan also benefits from the robust research capacity of universities and hospitals. Government-driven regulatory reforms and infrastructure initiatives are further accelerating the advancement of the NHI MediCloud system and the broader digital healthcare ecosystem. This article provides a comprehensive overview of smart healthcare development, highlighting government policy support and the R&D capabilities of universities, research institutes, and hospitals. It also examines the ICT industry’s participation in the development of smart healthcare ecosystems, such as Foxconn, Quanta, Acer, ASUS, Wistron, Qisda, etc. With strong data assets, technological expertise, and policy backing, Taiwan demonstrates significant potential in both AI innovation and smart healthcare applications, steadily positioning itself as a key player in the global healthcare market. Full article

The exponential growth in the usage of textual data across industries and data sharing across institutions underscores the critical need for frameworks that effectively balance data utility and privacy. This paper proposes an innovative agentic AI-based framework specifically tailored for textual data, integrating user-driven qualitative inputs, differential privacy, and generative AI methodologies. The framework comprises four interlinked topics: (1) A novel quantitative approach that translates qualitative user inputs, such as textual completeness, relevance, or coherence, into precise, context-aware utility thresholds through semantic embedding and adaptive metric mapping. (2) A differential privacy-driven mechanism optimizing text embedding perturbations, dynamically balancing semantic fidelity against rigorous privacy constraints. (3) An advanced generative AI approach to synthesize and augment textual datasets, preserving semantic coherence while minimizing sensitive information leakage. (4) An adaptable dataset-dependent optimization system that autonomously profiles textual datasets, selects dataset-specific privacy strategies (e.g., anonymization, paraphrasing), and adapts in real-time to evolving privacy and utility requirements. Each topic is operationalized via specialized agentic modules with explicit mathematical formulations and inter-agent coordination, establishing a robust and adaptive solution for modern textual data challenges. Full article

Industrial Control Systems (ICS) and Cyber–Physical Systems (CPS) are critical infrastructures supporting national sectors, where cyberattacks can directly cause physical process disruptions and safety incidents. Following PRISMA 2020 guidelines, we systematically searched Web of Science, Scopus, IEEE Xplore, and the ACM Digital Library for studies published between 1 January 2021 and 31 October 2025, and finally included 89 primary studies. The literature is categorized into five data modalities—network traffic, operational data, simulation data, hybrid data, and other auxiliary data—and compared in terms of detection objectives, learning paradigms, model families, attack types, and datasets. The analysis shows that network data are effective for detecting cyber-layer attacks such as reconnaissance, DoS, and MITM, while operational data are suited for physical-layer anomalies including process disturbances, FDI, and stealth deviations. Simulation and hybrid data further support rare-scenario generation and cyber–physical consistency checking. However, limitations remain, including reliance on few benchmarks, lack of realistic multi-domain datasets, label sparsity, concept drift, and insufficient consideration of real-time and resource-constrained OT environments. Based on these findings, this review highlights future directions such as multi-domain dataset development, physics- and control-informed model design, hybrid-data-driven integrated detection, and lightweight edge deployment. Full article

The integration of operational technology (OT) and information technology (IT) within the Industrial Internet of Things (IIoT) has posed prominent security challenges for resource-constrained devices. Existing authentication architectures often suffer from critical vulnerabilities: one is their reliance on centralized trusted third parties, which creates single points of failure; the other is their use of static credentials like biometrics, which pose severe privacy risks if compromised. To address these limitations, this paper proposes DLR-Auth, which combines chaotic synchronization of semiconductor superlattice physically unclonable functions (SSL-PUFs) with Shamir’s secret sharing (SSS) to enable decentralized registration and revocable templates. Notably, DLR-Auth is a two-party authentication framework that removes the need for a separate online registration authority that operates directly between a user device ($U{D}_i$) and a server (S). In our setting, the server S still acts as the central relying party and hardware authority embedding the matched SSL-PUF module. The protocol also includes an efficient multi-access mechanism optimized for high-frequency interactions. Formal security analysis with the Real-or-Random (ROR) model proves the semantic security of the session key, while performance evaluations demonstrate that DLR-Auth has significant advantages in computational and communication efficiency. DLR-Auth thus offers a robust, scalable, lightweight solution for next-generation secure IIoT systems. Full article

Semiconductor wafer manufacturing is one of the most complex and data-intensive processes in the industry, encompassing the front-end (FEOL), middle-end (MOL), and back-end (BEOL) stages, involving thousands of interdependent processes. Each stage can introduce potential variability, thereby reducing yield, making metrology and inspection crucial for process control. However, due to capacity, cost, and destructive testing constraints, exhaustive metrology for every wafer or die is impractical. Therefore, this study aims to introduce sampling strategies that have evolved to balance the accuracy, risk, and efficiency of measurement allocation. This review presents a literature review of static, adaptive, and dynamic sampling and discusses recent intelligent sampling techniques. The results show that traditional static sampling provides fixed, rule-based inspection schemes that ensure comparability and compliance but lack responsiveness to process variations. Adaptive sampling introduces flexibility, allowing measurement density to be adjusted based on detected drift, anomalies, or statistical control limits. Building on this, dynamic sampling represents a paradigm shift towards predictive, real-time decision-making driven by machine learning, risk analysis, and digital twin integration. The dynamic framework continuously assesses process uncertainties and prioritizes metrology to maximize information gain, thereby significantly reducing metrology workload without impacting yield or quality. Static, adaptive, and dynamic sampling together constitute a continuous evolution from deterministic control to self-optimizing intelligence. As semiconductor nodes move towards sub-3 nm, this intelligent sampling technology is crucial for maintaining yield, cost competitiveness, and process flexibility in autonomous, data-centric wafer fabs. Full article

Accurately forecasting the operating temperature of lithium-ion batteries (LIBs) is essential for preventing thermal runaway, extending service life, and ensuring the safe operation of electric vehicles and stationary energy-storage systems. This work introduces a unified, physics-informed, and data-driven temperature-prediction framework that integrates mathematically governed preprocessing, electrothermal decomposition, and sequential deep learning architectures. The methodology systematically applies the governing relations to convert raw temperature measurements into trend, seasonal, and residual components, thereby isolating long-term thermal accumulation, reversible entropy-driven oscillations, and irreversible resistive heating. These physically interpretable signatures serve as structured inputs to machine learning and deep learning models trained on temporally segmented temperature sequences. Among all evaluated predictors, the Bidirectional Long Short-Term Memory (BiLSTM) network achieved the highest prediction fidelity, yielding an RMSE of 0.018 °C, a 35.7% improvement over the conventional Long Short-Term Memory (LSTM) (RMSE = 0.028 °C) due to its ability to simultaneously encode forward and backward temporal dependencies inherent in cyclic electrochemical operation. While CatBoost exhibited the strongest performance among classical regressors (RMSE = 0.022 °C), outperforming Random Forest, Gradient Boosting, Support Vector Regression, XGBoost, and LightGBM, it remained inferior to BiLSTM because it lacks the capacity to represent bidirectional electrothermal dynamics. This performance hierarchy confirms that LIB thermal evolution is not dictated solely by historical load sequences; it also depends on forthcoming cycling patterns and entropic interactions, which unidirectional and memoryless models cannot capture. The resulting hybrid physics-data-driven framework provides a reliable surrogate for real-time LIB thermal estimation and can be directly embedded within BMS to enable proactive intervention strategies such as predictive cooling activation, current derating, and early detection of hazardous thermal conditions. By coupling physics-based decomposition with deep sequential learning, this study establishes a validated foundation for next-generation LIB thermal-management platforms and identifies a clear trajectory for future work extending the methodology to module- and pack-level systems suitable for industrial deployment. Full article