Search Results (1,777)

Building Information Modeling (BIM) has fundamentally changed the way interdisciplinary coordination works in construction projects; however, the theoretical mechanisms underlying open collaboration standards in this field remain insufficiently explored. This article fills this gap by presenting a systematic analysis of the BIM Collaboration Format (BCF) through the lens of reification and serialization, two fundamental concepts in information systems theory. Although the BCF format is widely used in the industry and implemented in major BIM tools for clash detection and issue tracking, the existing literature treats it primarily as an operational tool, overlooking the deeper information systems principles that govern its architecture. The analysis demonstrates that BCF achieves reification by transforming informal coordination knowledge—such as verbally communicated clashes, scattered email threads, and undocumented design decisions—into first-class objects (Topic, Comment, Viewpoint) equipped with unique identifiers, typed attributes, ownership, temporal metadata, and formalized inter-object relationships. Further analysis was conducted on BCF’s serialization mechanisms, including XML encoding for file exchange, JSON for RESTful API communication, and ZIP archiving as a distribution container, each of which was selected to balance human readability, schema validation, compression, and cross-platform portability. The complementarity of these two mechanisms was examined: reification determines what to preserve and in what structure, while serialization determines how to encode and in what format, which together enable interoperable, auditable, and automatable coordination workflows in heterogeneous software environments. The analysis was illustrated with a real-world BCF example from a major infrastructure project in Poland, demonstrating practical alignment between theoretical constructs and their implementation. The research results provide both a conceptual foundation for researchers working on openBIM standards and practical guidance for practitioners seeking to optimize issue management, the implementation of a Common Data Environment (CDE), and the specification of Exchange Information Requirements (EIR). The study contributes new knowledge in three areas: (1) To the best of the authors’ knowledge, it provides the first systematic theoretical analysis of BCF through the lens of reification and serialization, filling a gap between the format’s widespread practical use and its limited theoretical understanding. (2) It demonstrates how the formal criteria of reification (unique identity, typed attributes, ownership, temporal metadata, and inter-object relationships) map onto specific BCF entities, offering a transferable analytical framework for evaluating other openBIM standards. (3) It identifies the complementarity of reification and serialization as a design principle that can guide the development of future standards for digital twins and IoT-based facility management. Full article

The incorporation of the Internet of Things (IoT) in indoor agricultural systems has become an essential tool for monitoring and analyzing environmental variables, contributing to more efficient decision-making. This article presents the design and implementation of an IoT-based digital agriculture system applied to a Plant Factory (PF) for hydroponic vegetable cultivation using the Nutrient Film Technique (NFT). The objective of this study was to develop a system capable of effectively monitoring and controlling the environmental variables that directly influence the microclimate of a closed agricultural environment. The proposed system integrates a four-layer IoT architecture based on a MODBUS RS-485 communication bus, which allows for continuous data acquisition and the operation of multiple sensors and controlled devices. Additionally, user-oriented tools such as a human–machine interface (HMI), a web application, a mobile application and an automatic alert module were incorporated, enhancing accessibility and remote supervision. Experimental results showed stable control performance of ambient temperature (TA), relative humidity (RH), photoperiod, and photosynthetic photon flux density (PPFD), along with continuous monitoring of CO₂ concentration. A 30-day validation experiment using Swiss chard (Beta vulgaris L. var. cicla) under controlled conditions was conducted. The results showed progressive plant development, with leaf area increasing from 15.17 cm² to 690.39 cm², plant height from 7 cm to 31 cm, fresh weight from 23 g to 171 g, and the number of leaves from 9 to 20. These results support the functional validity of the proposed system as a reliable platform for environmental monitoring and control in controlled-environment agriculture. Full article

Accurate air quality forecasting requires the effective integration of heterogeneous data sources that vary in spatial coverage, temporal resolution, and sensing reliability. This paper presents a unified spatio-temporal data processing framework designed to support multi-source air quality forecasting by jointly leveraging regulatory monitoring stations of the Central Pollution Control Board (CPCB) as reference-grade anchors and community-driven Internet of Things (IoT) sensing platforms for spatial densification. The proposed end-to-end workflow addresses key challenges associated with heterogeneity, data quality, and interoperability through systematic schema harmonization, multi-stage data cleaning, and robust missing data imputation using a Robocentric Iterated Extended Kalman Filter (RIEKF). The processed data are temporally aligned to a uniform sampling grid and enriched with spatial descriptors, including geospatial coordinates, administrative boundaries, and proximity-based emission features. These enriched observations are subsequently fused into a unified spatio-temporal representation that captures both spatial dependencies and temporal dynamics across the sensor network. Dynamic graphs constructed from this representation are processed using a Mobility-Aware Peripheral-Enhanced Graph Neural Network to forecast pollutant concentrations and generate categorical air quality indices. The framework is evaluated using regression metrics reported as RMSE/MAE in µg/m³ and MAPE in %, together with standard AQI classification metrics, demonstrating its effectiveness in improving predictive accuracy and robustness for real-world air quality forecasting applications. Full article

Microbial contamination in aquatic environments poses severe threats to aquaculture sustainability, ecological balance and public health. Traditional culture-based detection methods, while standardized, are time-consuming and labor-intensive, often failing to meet the urgent need for rapid on-site monitoring required to prevent disease outbreaks and manage water quality effectively. By integrating latest research advances (2020–2025), this study reviews advances in rapid detection technologies for aquatic microorganisms, including the evolution of nucleic acid amplification strategies, with a focused comparison of the analytical sensitivity and field deployability of quantitative polymerase chain reaction (qPCR) and mainstream isothermal amplification techniques (loop-mediated isothermal amplification, LAMP; recombinase polymerase amplification, RPA). Furthermore, this study reports on the emergence of Clustered Regularly Interspaced Short Palindromic Repeat (CRISPR)-associated protein (Cas) systems as next-generation diagnostic tools, highlighting their integration with microfluidic Lab-on-a-Chip (LOC) platforms to achieve attomolar sensitivity. We also consider the application of portable nanopore sequencing for real-time pathogen identification and the growing role of Artificial Intelligence (AI) in analyzing complex diagnostic datasets. Advanced molecular methods have achieved significant reductions in time consumption—from days to less than one hour—while challenges regarding sample preparation and environmental matrix inhibition remain. The future of aquatic monitoring lies in integrated, automated systems that combine the specificity of CRISPR-Cas diagnostics with the connectivity of IoT-enabled biosensors. Comparative analysis indicates that isothermal amplification methods (LAMP, RPA) coupled with CRISPR-Cas systems offer the optimal balance of sensitivity, speed, and field deployability for point-of-care aquaculture diagnostics, while qPCR/dPCR remain indispensable for quantitative regulatory applications. We propose a structured technology selection framework to guide researchers and practitioners in choosing appropriate detection modalities based on specific sensitivity, cost, throughput, and deployment requirements. Full article

Tiny Machine Learning (TinyML) enables Machine Learning (ML) models to run on resource-constrained devices, which is critical for Industrial Internet of Things (IIoT) systems requiring low latency, energy efficiency, and local decision-making. Nevertheless, deploying TinyML in IIoT remains challenging due to diverse applications, hardware, frameworks, and deployment methodologies, highlighting the need for a structured and focused review. Existing review articles mainly address general IoT or edge AI, leaving a critical gap in a unified and systematic understanding of TinyML applications, system components, and methodologies within IIoT contexts. Consequently, this systematic literature review (SLR) addresses this gap by analyzing 35 peer-reviewed studies published between 2018 and 2026, offering a comprehensive and structured synthesis of TinyML-enabled IIoT systems. The selected works are synthesized across three major dimensions: applications, system components, and methodologies. In terms of applications, TinyML is primarily used for predictive maintenance, equipment monitoring, anomaly detection, energy management, and general-purpose applications. The general category captures cross-domain solutions that do not fit into a single industrial application. A comparative analysis of all application categories is conducted in terms of accuracy, latency, memory, and energy. For system components, a structured comparison shows how hardware, software, and sensing choices shape performance and applicability. Hardware platforms are grouped by microcontroller families, highlighting dominant types. Software frameworks are summarized, showing the widespread use of lightweight toolchains for on-device inference. Sensor types are categorized, with vibration sensing most common. They are supported by other sensing methods such as vision, sound (acoustic), and environmental sensors. Finally, the methodologies examined in this SLR provide a comprehensive view of the data foundations, model selection, and optimization strategies. In short, this SLR converges diverse TinyML–IIoT applications, microcontroller-based hardware, lightweight software frameworks, sensing modalities, varied datasets, and optimization strategies, while also identifying challenges and future research directions. Full article

Existing Environmental, Social, and Governance (ESG) monitoring approaches rely primarily on static reports and dashboard-based interfaces, limiting real-time analysis and interactive exploration of sustainability data in complex built environments. In addition, current digital twin systems often lack integration with IoT-based sensing or depend on cloud-based rendering infrastructures, increasing deployment complexity and restricting accessibility. This study proposes a lightweight Web3D-based digital twin framework for real-time ESG monitoring in smart buildings. The system integrates an independently developed IoT sensor network with a browser-native 3D visualization platform, enabling real-time monitoring of ESG indicators—including electricity consumption—without requiring proprietary software or dedicated rendering hardware. ESG indicators are derived using a rule-based classification aligned with the WELL Building Standard v1. The framework was validated through a 12-month real-world deployment involving 60 IoT sensors. Results demonstrate stable performance, achieving 66 FPS rendering, 78 ms system latency, and 98% sensor data consistency based on cross-sensor agreement. The system also enabled timely detection of environmental anomalies, leading to measurable improvements in air quality and lighting conditions. Unlike prior digital twin systems, the proposed framework delivers a fully browser-native, lightweight architecture that integrates real-time IoT sensing, adaptive Web3D visualization, and structured ESG monitoring within a single deployable system. This approach provides a practical solution with potential for broader deployment in real-time sustainability monitoring for smart buildings. Full article

Modular integrated construction (MiC) is an innovative construction method that shifts on-site activities to a controlled factory environment, thereby offering sustainability benefits. However, current carbon management relies on labor-intensive manual data collection, causing delayed and inaccurate carbon accounting that increases greenwashing risks. Existing approaches lack real-time, automated, and trustworthy carbon tracking capabilities across fragmented supply chains. This study develops and validates the Blockchain-enabled IoT-BIM Platform (BIBP), which combines Internet of Things (IoT), Building Information Modeling (BIM), and blockchain for real-time carbon monitoring. IoT sensors automate data capture from construction equipment and BIM provides spatial visualization of carbon at the module and building levels. A Hyperledger Fabric blockchain ensures the authenticity, immutability, and traceability of carbon records. Validated on a 15-story MiC project in Hong Kong, BIBP established a cradle-to-end-of-construction baseline of 949.84 kgCO_2e/m², identifying steel and concrete as the primary hotspots (80% of material emissions). Real-time analytics demonstrated that combining high-volume ground granulated blast furnace slag (GGBS) concrete substitution, new energy sea–land multimodal transport, and 10% steel waste reduction achieves over 20% carbon savings. Furthermore, the BIBP automated data acquisition and calculation, improving assessment efficiency by 92.4%. The platform demonstrates the potential to transform carbon management from a static, retrospective evaluation into a proactive, data-driven monitoring process, equipping stakeholders with a tool to dynamically track emissions and make timely interventions toward carbon reduction targets. Full article

As industries deploy more connected devices in factories, warehouses, and smart facilities, the need for artificial intelligence (AI) systems that can operate securely in distributed, data-intensive environments is growing. Traditional centralized learning and online education platforms struggle when students and systems have to process real-time streams (sensors, video, text) with strict latency and privacy requirements. To address this challenge, a blockchain-secured, edge-enabled multimodal federated learning framework tailored for Industrial IoT (IIoT) environments is proposed. The model integrates four key layers: (i) a blockchain layer that provides credentialing, transparency, and token-based incentives; (ii) a multimodal community layer that supports group formation, peer consensus, and cross-modal learning across text, images, audio, and sensor data; (iii) an edge computing layer that enables low-latency task offloading and secure training within Intel SGX enclaves; and (iv) a data layer that applies pre-processing, differential privacy, and synthetic augmentation to safeguard sensitive information. Experiments on industrial multimodal datasets demonstrate 42% faster model aggregation, 78.9% multimodal accuracy, and 1.9% accuracy loss under ε = 1.0 differential privacy. This shows a scalable and practical path for decentralized AI training in next-generation IIoT systems, confirming the possibility of technical support for educational processes. However, the conducted research requires a validation of pedagogical effectiveness. Full article

Agriculture, as a basis of sustainable development, faces increasing pressure to meet rising global food demands while confronting the increasing impacts of climate change. Precision agriculture offers a data-driven approach to address these challenges by optimizing input use, improving productivity, and reducing environmental impacts. Sensor technologies play a critical role in smart and precision agriculture, offering high-resolution spatial and temporal insights into soil conditions, plant development and environmental conditions. This review highlights the current state and future potential of various sensor and imaging systems, particularly their role in monitoring soil properties, crop nutrition, plant health and detecting biotic and abiotic stressors. Special attention is given to accessible paper-based and printed electrochemical devices for on-site soil and plant analysis, as well as active handheld multispectral sensors designed for real-time canopy assessment. The integration of sensor-derived data with predictive models, IoT networks and decision-support tools enables more precise, site-specific management, improves input efficiency and supports climate-resilient agricultural practices. By examining the capabilities, limitations and future potential of these sensing platforms, this review highlights their growing importance in advancing sustainable intensification and strengthening crop production. Full article

Adolescent vaping has become a persistent health and behavioural challenge in schools, yet many institutions lack reliable tools to detect and respond to concealed e-cigarette use. This study addresses this problem by evaluating the real-world performance of a low-cost “Internet of Things” (IoT) vape detection system deployed across 37 high-risk restroom and change-room locations at a large Australian Independent school. The aim was to determine whether an IoT-based environmental monitoring platform could accurately identify vaping events, support timely staff intervention, and provide actionable insights into student behaviour patterns. A longitudinal case study design was used, collecting continuous particulate matter (PM_2.5 and PM₁₀) data at one-minute intervals over an 18-month period, where PM_2.5 and PM₁₀ refer to particulate matter with aerodynamic diameters ≤ 2.5 µm and ≤10 µm, respectively, reported in micrograms per cubic metre (µg/m³. Threshold-based alerting, cloud-based data processing, and school-led Closed-circuit television (CCTV) verification were combined to assess detection accuracy, temporal trends, and operational responses. The system recorded more than 300 vaping-related incidents, with clusters aligned to predictable times of day and higher prevalence among senior students. Operational detection performance was high, with alert events characterised by rapid, concurrent PM_2.5 and PM₁₀ excursions consistent with vaping-related aerosol profiles, although staff responsiveness declined over time due to alert fatigue and competing priorities. A major environmental smoke event demonstrated the need for context-aware logic to reduce false positives. The findings demonstrate that real-time aerosol monitoring is not only technically reliable but also highly effective in detecting vaping within school environments. These perspectives help explain why user engagement, alert fatigue, and institutional follow-through are as critical as sensor accuracy itself. Ultimately, the effectiveness of vape detection relies on strong organisational commitment, well-defined response workflows, and alignment with broader wellbeing and policy strategies. When these elements are in place, such systems can evolve from simple detection tools into intelligent, integrated components of school health governance. Full article

The increasing scarcity of urban water resources, particularly in regions with intermittent supply and household water storage tanks, demands monitoring approaches capable of identifying end-use consumption patterns beyond aggregated volume measurements. Framed primarily as a feasibility study, this research presents an IoT-based framework for the automated classification of residential water consumption activities using water-level dynamics and supervised machine learning. A non-intrusive sensing architecture based on hydrostatic pressure measurements was deployed in a domestic water tank and integrated with a cloud-based data acquisition and processing platform. Five representative household states and activities were considered: tank refilling, stable state, toilet flushing, washing clothes, and taking a bath. A labeled dataset comprising 4396 consumption events was used to train and evaluate Decision Tree, Random Forest, Support Vector Machine (SVM), k-Nearest Neighbors, and Recurrent Neural Network (LSTM) models using features derived from water-level variations. All models achieved high performance, with accuracies above 0.92 and weighted F1-scores up to 0.93. The evaluated models showed highly comparable results, with the SVM (RBF) achieving a slightly higher accuracy (0.9307) in this evaluation setting, while ROC analysis showed AUC values between 0.97 and 1.00 across all classes, indicating strong discriminative capability. Additionally, specific activities such as washing clothes and tank refilling achieved precision and recall values above 0.95. These findings confirm that hydrostatic pressure-based sensing, combined with machine learning, enables reliable identification of domestic water-use events under intermittent supply conditions. The proposed approach provides actionable insights for demand management, leak detection, and user awareness, supporting more efficient and sustainable residential water consumption strategies. Full article

The development of effective Intrusion Detection Systems (IDS) for Internet of Things (IoT) environments is constrained by the absence of realistic, large-scale datasets, particularly for the Message Queuing Telemetry Transport (MQTT) protocol, which is prevalent in industrial IoT. Existing datasets are frequently limited in scope, imbalanced, or do not capture MQTT-specific attack patterns, thereby impeding the training of accurate machine learning models. To address this gap, the extensible Message Queuing Telemetry Transport (eMQTT) Traffic Generator is introduced as a modular platform capable of simulating both legitimate MQTT communication and targeted denial-of-service (DoS) attacks. The framework features a scalable and reproducible architecture that incorporates protocol-aware attack modeling, automated traffic labeling, and direct export of datasets suitable for machine learning applications. The system produces standardized, configurable, repeatable, and publicly accessible datasets, thereby facilitating reproducible research and scalable experimentation. Experimental validation demonstrates that the simulated traffic aligns with established DoS behavior models. Two high-volume datasets were generated: one representing normal MQTT traffic and another emulating CONNECT-flooding attacks. Machine learning classifiers trained on these datasets exhibited strong performance, with gradient boosting models achieving over 95% accuracy in distinguishing benign from malicious traffic. This work offers a practical solution to the scarcity of datasets in IoT security research. By providing a controlled, extensible, and reproducible traffic-generation platform alongside validated datasets, eMQTT enables systematic experimentation, supports the advancement of IDS solutions, and enhances MQTT security for critical IoT infrastructures. Full article

Safe and sustainable water sources are a serious global concern because of growing population, urbanization, industrialization, and climate change. The conventional water surveillance systems that rely on periodic sampling and laboratory analysis fail to provide time-sensitive and high-resolution data utilized for proactive water management. Artificial Intelligence of Things (AIoT) offers a viable solution, as they can provide tools of constant active monitoring and predictive analytics. The integration of IoT sensor networks with machine learning (ML) methods enables real-time data-driven water resource monitoring and intelligent decision-making, enhances water quality assessment, supports early detection of anomalies, improves predictive capabilities for floods and droughts, and facilitates efficient irrigation and reservoir management, ultimately leading to sustainable and resilient water management systems. The paper presents an extensive overview of AIoT solutions for water quality monitoring and water resource management, including IoT sensor networks for real-time data acquisition, machine learning methods for prediction, classification, anomaly detection, and edge computing platforms for data processing and decision support. This study also highlights existing possibilities, obstacles, and research gaps identified through a review of the recent literature. Key challenges reported across multiple studies include limited data availability, sensor calibration bias, integration of heterogeneous data, and insufficient model interpretability. Advanced paradigms such as digital twin systems, TinyML, federated learning, and explainable AI (XAI) are examined as enabling technologies to enhance system efficiency, flexibility, and transparency. Future research directions are outlined to develop scalable, interpretable, and real-time water management solutions. Full article

This article compares selected fire safety regulatory systems in Japan, China, the United States, and the EU/UK, interpreted through the lens of responsive architecture and the implementation of digital technologies—building information modelling (BIM), digital twins (DTs), artificial intelligence (AI), and the Internet of Things (IoT). The study adopts a qualitative approach based on a structured review of legal acts, technical standards, public-sector reports, and the scientific and professional literature, organised using a common analytical framework. First, the analysis identifies shared foundations across regimes: the primacy of life safety, mandatory detection and alarm functions, fire compartmentation, requirements for protected means of exit, and the increasing importance of documenting the operational status of protection measures. Then, it contrasts key differences, including the permissibility of performance-based design (PBD), the degree to which digital documentation is formally recognised, organisational enforcement models, and cybersecurity approaches for integrated fire alarm/voice alarm/building management/IoT ecosystems. Japan and selected Chinese cities combine stringent requirements with openness to dynamic solutions and urban-scale data platforms. The USA relies on a decentralised code-based ecosystem with a strong role for professional and industry bodies, while the EU/UK continues to strengthen harmonised standards and digital building registers, reinforced by lessons after the Grenfell Tower fire. Against this background, Poland is discussed as broadly aligned in goals and baseline technical requirements yet lagging behind in implementing PBD pathways, digital registers, formal BIM/DT integration, and minimum cybersecurity requirements. The proposed directions for change aim to create a more predictable regulatory and technical framework for the development of responsive architecture and dynamic fire safety systems in Poland. The study contributes to the sustainability literature by framing regulatory readiness for digital fire safety as a lifecycle resilience strategy, directly relevant to safe, resource-efficient, and inclusive built environments. Full article

The rapid growth of Internet of Things (IoT) deployments in hybrid terrestrial/non-terrestrial networks (TN/NTN) faces a major bottleneck: the verbosity of standard data formats like JSON. This is critical for large-scale M2M systems tracking and monitoring multimodal dry containers, where devices must comply with the strict message-size limits of commercial satellite IoT (around 160 bytes per message). We present a comparative evaluation of four device-friendly binary serialization protocols (CBOR, MessagePack, Protocol Buffers, and a custom Struct+Zlib hybrid) targeted at battery-powered microcontrollers. Using a horizontally scalable testbed with up to 2000 concurrent devices and the oneM2M standard framework, we assess payload efficiency, throughput, latency, and maintainability. Only Protocol Buffers and Struct+Zlib meet NTN message-size limits, with Protocol Buffers providing the best trade-off between performance and long-term maintainability. Real-world validation with the Astrocast LEO satellite platform and the oneM2M Mobius framework confirms these results. Cost analysis suggests potential savings exceeding €62,000 per month for a 10,000-device maritime fleet, demonstrating both technical feasibility and economic viability. This study provides a methodological framework for designing efficient, scalable IoT systems in hybrid TN/NTN networks, offering practical guidance for global container tracking and monitoring deployments. Full article