Search Results (3,908)

Despite the increasing use of machine learning (ML) and deep learning (DL) for leak detection and localization in water distribution networks (WDNs), standardized datasets, common evaluation protocols, and consistent reporting practices remain limited, thereby restricting meaningful comparison among studies. In this systematic review, PRISMA 2020 was followed to examine the benchmarking practices, data sources, sensing modalities, and evaluation strategies adopted in recent ML/DL-based leak-detection studies. Scopus was searched in April 2026, and 90 studies were included after screening against predefined eligibility criteria. Substantial variation was identified in dataset generation, model validation, and performance assessment. Thirty studies were assigned to the public-benchmark category, but only 23 used one of the three named water-leak resources tracked in this review; the remainder included topology-only reuse or other heterogeneous public resources. Pressure measurements were the dominant sensing modality, whereas flow, transient, and smart-meter data remained comparatively underexplored. Considerable inconsistency was also observed in performance metrics, validation procedures, and leak-scenario definitions, preventing fair comparison of detection and localization performance. Based on these findings, a practical reporting framework is proposed to improve transparency, reproducibility, and comparability. The principal recommendations include standardized dataset documentation, consistent evaluation protocols, expanded community benchmarks, uncertainty quantification, and model interpretability to support operational deployment. Full article

Reliable structural monitoring for smart buildings and construction sites requires more than sensor acquisition; it requires sensing and communication paths that remain traceable, recoverable, and compatible with platform-side data processing under heterogeneous field constraints. This study presents a dual-path IoT sensing and communication framework that deliberately separates high-data-rate vibration monitoring from low-data-rate inclination-status monitoring while maintaining common requirements for preservation of available time information, data-source identification, and backend interpretability. The smart-building path integrates an ADXL355 triaxial accelerometer, ESP32-S3, Power over Ethernet (PoE), and Message Queuing Telemetry Transport (MQTT) for 200 Hz vibration acquisition, together with a second-order 10 Hz low-pass filter, 40-record batching, and a Flash LittleFS-based store-and-recovery mechanism that interleaves live and replayed records after reconnection. The construction-site path combines an SCL3300-D01 inclinometer with LoRaWAN, baseline-referenced relative-angle estimation, and a hysteresis state machine with distinct alarm and recovery thresholds. In a 24 h validation, four vibration nodes delivered all 69,120,000 expected records, and four forced-outage trials recovered all offline records while live transmission continued. Frequency-domain analysis confirmed attenuation of high-frequency components while retaining the dominant low-frequency response. The inclination path demonstrated quantifiable angle accuracy, correct alarm/recovery transitions, continuous LoRaWAN frame delivery over the observed interval, and correct backend decoding. The results show that path-specific communication design, combined with a common traceability concept, supports prototype functionality under the reported test conditions, not immediate construction-site deployment. Full 3D visual synchronization, BIM/GIS asset mapping, and digital-twin platform interfacing were not implemented and remain future development tasks. Full article

Digital twins (DTs) based on agent-based artificial intelligence (Agentic AI) provide a transformative framework for streamlining nondestructive testing (NDT) of 3D-printed rehabilitation equipment. This study applies a conceptual research methodology based on the integration and analysis of recent advances in Agentic AI, digital twin architectures, additive manufacturing, NDT technologies, and intelligent rehabilitation systems to establish a framework for autonomous quality monitoring and lifecycle management of 3D-printed medical devices. By creating intelligent virtual replicas of physical devices, these systems enable continuous monitoring of structural integrity, functional performance, and degradation mechanisms throughout the product lifecycle. Unlike conventional AI-based DTs, Agentic AI-driven DTs can autonomously perceive, reason, plan, and execute corrective actions based on real-time sensor data, NDT results, manufacturing information, and historical knowledge. The main conclusion of this work is that Agentic AI-enhanced DTs have the potential to transform NDT from a passive inspection approach into an intelligent, predictive, and autonomous decision-support system for rehabilitation equipment. Advanced machine learning and autonomous decision-making algorithms enable the identification of early signs of material degradation, manufacturing defects, fatigue accumulation, and performance anomalies, supporting predictive maintenance and proactive quality assurance. Integrating Agentic AI DTs with additive manufacturing processes enables real-time optimization of printing parameters, adaptive process control, and continuous refinement of inspection strategies without production interruption or destructive sampling, thereby supporting Industry 4.0 and smart manufacturing principles. The main innovation of this research lies in proposing an autonomous closed-loop framework that combines Agentic AI, DTs, additive manufacturing, and NDT into a unified system capable of continuous learning, reasoning, and operational optimization. Compared with existing studies that mainly focus on AI-assisted defect detection or static digital twin models, this approach introduces autonomous agents capable of coordinating sensing, simulation, diagnosis, prediction, and corrective actions across the entire lifecycle of 3D-printed rehabilitation devices. The proposed concept extends current digital twin applications by incorporating virtual stress testing, autonomous simulation, patient-specific customization, and adaptive device management, reducing dependence on physical prototypes, minimizing material waste, and accelerating design validation. By combining autonomous reasoning with predictive analytics, Agentic AI-based DTs represent a next-generation solution for intelligent, adaptive, and sustainable nondestructive testing, advancing both additive manufacturing technologies and personalized rehabilitation engineering. Full article

Machine learning is widely proposed as a basis for smart wastewater treatment plant (WWTP) management, yet reported performance is rarely benchmarked against trivial alternatives. This study uses six years of monitoring from a municipal WWTP in Serbia serving 18,000 population equivalents, comprising 1017 fully measured days. Total nitrogen removal falls from 79.4% outside summer to 67.4% in June to August (p = 4 × 10⁻¹⁸), in five of six years, while influent load, hydraulic flow and phosphorus removal are unchanged, which points to oxygen limitation. Four model families are benchmarked against persistence and a ten-measurement rolling mean on one chronological hold-out period. Predictive skill depends decisively on forecast horizon: at one step ahead nothing beats both baselines, whereas at five steps nitrogen reaches R² of 0.516 against 0.388 and 0.320. Chemical oxygen demand (COD) never beats a rolling mean. A random forest identifies nitrogen exceedance of 15 mg/L with an area under the curve of 0.90. Explanation of that model shows it recognises a breach already under way rather than one beginning, which sets the operating conditions for its use. Evaluating on interpolated rather than measured days raises apparent accuracy from R² of 0.34 to 0.82. Full article

Ensuring food authenticity, traceability, and quality has become a critical challenge in increasingly complex and globalized food supply chains. Conventional post-harvest analytical approaches, while powerful, often operate in isolation and fail to fully capture the influence of pre-harvest conditions on food composition. In parallel, the emergence of smart farming technologies has enabled the collection of high-resolution environmental and agronomic data, offering new opportunities to establish baseline signatures linked to geographical origin and production practices. This review explores the integration of pre-harvest data from precision agriculture with advanced post-harvest analytical techniques, focusing on spectroscopic and isotopic methods for food authentication. Recent advances in vibrational spectroscopy, including near- and mid-infrared, Fourier-transform infrared, and Raman techniques, alongside complementary methods such as nuclear magnetic resonance and fluorescence spectroscopy, have enabled rapid and non-destructive food fingerprinting. In parallel, isotope ratio mass spectrometry and compound-specific isotope analysis provide robust markers of origin, climate conditions, and agricultural inputs through the analysis of stable isotopes of carbon, hydrogen, oxygen, nitrogen, and sulfur. The combination of these analytical approaches with chemometric and machine learning tools facilitates the extraction of meaningful patterns from complex datasets. A central focus of this review is the development of integrated farm-to-fork frameworks that use multi-source data, including field sensor technologies, spectral fingerprints, and isotopic signatures, to enhance traceability and authentication. Applications across a wide range of food systems, including edible oils, beverages, plant-based products, and animal-derived foods, are critically evaluated to highlight the strengths and limitations of current methodologies. Key challenges related to data standardization, system interoperability, cost, portability, miniaturization and regulatory acceptance are discussed, alongside emerging solutions such as artificial intelligence-driven models, digital twins, and blockchain-enabled traceability systems. The review underscores a paradigm shift from reactive testing toward predictive and real-time food authentication systems, driven by the convergence of smart agriculture and advanced analytical chemistry. This integrated approach has the potential to significantly enhance transparency, trust, and sustainability in the global food system. Full article

The rapid growth of renewable energy sources, particularly solar and wind power, has increased the demand for efficient and reliable battery energy storage systems (BESSs) to address intermittency, enhance grid stability, and improve energy management. In recent years, artificial intelligence (AI) has emerged as a transformative technology for optimizing the operation, control, monitoring, and maintenance of battery storage systems. This review provides a comprehensive overview of AI-driven BESS technologies for renewable energy applications. The study examines recent advances in machine learning, deep learning, reinforcement learning, and hybrid intelligent algorithms applied to battery state estimation, energy management, fault diagnosis, predictive maintenance, thermal management, and lifetime prediction. Furthermore, the integration of AI-based BESSs with photovoltaic systems, wind farms, microgrids, and smart grids is critically analyzed. The review highlights the advantages of AI techniques in improving system efficiency, reliability, adaptability, and decision-making capabilities under uncertain operating conditions. Current challenges, including data quality, model interpretability, computational requirements, cybersecurity concerns, and real-time implementation issues, are also discussed. Finally, emerging research directions such as digital twins, explainable artificial intelligence, federated learning, and edge intelligence are explored to provide insights into the future development of intelligent battery storage systems. This review aims to serve as a valuable reference for researchers, engineers, and practitioners working at the intersection of artificial intelligence, battery technologies, and renewable energy systems. Full article

The Internet of Vehicles (IoV) is revolutionizing intelligent transportation systems by ubiquitous connectivity of vehicles, roadside infrastructure, pedestrians, edge/cloud platforms, and smart-city services. With the IoV evolving towards highly connected, autonomous and data-driven mobility ecosystems, it needs to meet challenging requirements for low latency, scalability, interoperability, security, privacy and trust. This paper presents a comprehensive cross-layer approach for intelligent, secure and privacy-preserving IoV systems. It is built upon an analytical framework and systematically studies the perception, communication, edge/cloud computing, blockchain-enabled trust and application layers of IoV technologies. In addition, the paper presents an in-depth review of the enabling techniques such as machine learning (ML), deep learning (DL), reinforcement learning (RL), federated learning (FL), blockchain, cybersecurity mechanisms, digital twins, edge computing, 6G integration, and resource allocation. Moreover, it discusses the interplay and trade-offs between intelligence, security, privacy, computation, latency, and scalability. The survey also covers other significant challenges like intrusion detection, decentralized authentication, privacy-preserving learning, blockchain overhead, semantic interoperability, post-quantum security, and standardized datasets. This study is intended to serve as a structured reference for the development of scalable, trustworthy, and intelligent IoV systems by highlighting state-of-the-art techniques, open research gaps, and future directions. Full article

Human presence detection is critical when building smart cities with use cases in sectors like smart homes, emergency evacuation, health-care monitoring and others. Existing human detection systems predominantly rely on camera-based imaging, raising privacy concerns. Moreover, conventional FMCW radar approaches are primarily motion-based, thus often failing to detect the presence of unconscious individuals, as in the case of search and rescue (SAR) operations. Some radar approaches use Doppler or spectral peak analysis to estimate respiration but fail to exploit phase coherence to resolve sub-millimeter chest displacement and higher-order physiological harmonics. This paper presents an interferometric radar framework that models multi-feature vital-sign signatures for human detection under controlled clinical settings using respiratory harmonic relationships, inter-harmonic consistency, chest-displacement spectral characteristics, and radar-derived cardiac mechanical signatures. Physiological relationships are used to establish the expected structure of the extracted features, while subject-to-subject variability and measurement uncertainty are used to determine practical acceptance regions from the training cohort. Experimental data from 30 healthy subjects were analyzed using a single interferometric radar sensor under controlled clinical conditions. The resulting signatures were subsequently evaluated using a machine-learning validation pipeline. With 243 test cases, the proposed framework achieved 89.71% accuracy, 95.26% precision, 94.15% F1-score, and 93.06% sensitivity. The study demonstrates that interferometric chest-displacement sensing can provide a privacy-preserving physiological feature space for human presence detection, while also identifying the limitations associated with unresolved multi-person signal superposition and hardware-induced phase uncertainty. Moreover, interferometric sensing by principle will work better than conventional radar approaches for SAR operations. Although validated in a controlled clinical environment, the framework establishes a foundational pathway towards future research for eventual deployment in next-generation smart systems. Full article

Water quality monitoring is important for protecting aquatic life and supporting informed water quality assessment and environmental decision support. However, many existing systems mainly focus on data collection and threshold-based alerts, without connecting prediction, diagnosis, and intelligent assessment within a unified workflow. This paper proposes an integrated smart aquatic monitoring system using Southeast Texas (SETX) water quality data, advanced machine learning models, large language models (LLMs), and an agentic n8n workflow. Firstly, SETX water quality data are extracted, cleaned, and converted into a structured CSV format. Important water features such as pH, dissolved oxygen, temperature, conductivity, and total dissolved solids are used to train and evaluate four different machine learning models, including Transformer, Quantum Neural Network (QNN), XGBoost, and Random Forest. The ML model is then deployed to a backend system for use inside the n8n automation workflow. For simulation, a Python script is designed to emulate an IoT water quality sensor by reading dataset records, converting valid records into JSON objects, and sending them to an agentic n8n webhook. The n8n workflow receives the sensor data and forwards it to the deployed model to predict surface water quality status. Across three simulations with three different datasets, the ML models demonstrate strong performance in classifying safe and unsafe water conditions. On the SETX dataset, Random Forest achieved the best performance, with 99.97% accuracy and a 99.95% macro F1-score. XGBoost also performed strongly, achieving 99.91% accuracy and a 99.86% macro F1-score. The Transformer model achieved 95.98% accuracy and a 94.00% macro F1-score, while the QNN model achieved 94.78% accuracy and a 92.24% macro F1-score. These results demonstrate that the processed SETX dataset supports reliable water quality prediction and can be integrated into the proposed n8n-based intelligent monitoring workflow. The prediction results are subsequently analyzed by an LLM-based diagnosis agent to generate an LLM-based water quality assessment, risk classification, and assessment summary that explain the prediction and highlight the most influential water quality parameters. The proposed system demonstrates a practical framework for combining sensor simulation, predictive modeling, LLM-based decision support, and agentic workflow automation for intelligent water quality assessment and smart environmental monitoring. Full article

Artificial intelligence (AI) is embedded in healthcare through decision support, imaging, documentation, monitoring, digital twins, and smart-hospital infrastructures. This scoping review mapped technologies, healthcare contexts, socio-technical dimensions, governance mechanisms, and implementation conditions of AI-enabled healthcare systems. The review followed PRISMA-ScR. Scopus, Web of Science Core Collection, PubMed, and IEEE Xplore were searched on 1 July 2026 for English-language sources published from 2021 to 2026. All four authors participated in source selection; each record was assessed by two reviewers, and disagreements were resolved by consensus. Data were charted in matrices and synthesized descriptively and thematically. Of 2422 records, 426 duplicates were removed and 1996 were screened. Among 185 full-text reports, 124 were excluded, including 18 for insufficient methodological or empirical information, and 61 were included. Included sources then underwent a complementary seven-criterion cross-design appraisal scored from 1 to 3, without altering the final corpus. Technologies included machine learning, deep learning, decision support, explainable AI, natural language processing, large language models, interoperability frameworks, blockchain/IoMT, and digital twins. Challenges involved validation, data quality, interoperability, accountability, privacy, security, explainability, trust, bias, equity, and workforce readiness. Reported implementation facilitators included interoperable infrastructure, participatory design, lifecycle governance, continuous validation, and context-sensitive implementation. Full article

Forecasting power consumption is essential for intelligent power management in IoT-enabled smart environments, where heterogeneous behaviors appear from diverse building usages. University campuses are considered environments that share similarities with smart cities, making them suitable for power dynamics analysis. We build upon an IoT-based Advanced Metering Infrastructure (AMI) we deployed at our Engineering School’s Campus (INPT, Morocco), and an optimized XGBoost pipeline enhanced via Genetic Algorithms. Limited modeling granularity is addressed in heterogeneous consumption patterns. We propose and justify a cluster-aware approach partitioning data $\left(D\right)$ into K regimes such that $D={\bigcup }_{c=1}^K{C}_c$. Each cluster is treated as a homogeneous behavioral profile and modeled using a GA-XGBoost model, enabling an intermediate granularity between global and meter-level learning. Experiments on real-world campus AMI data show that our proposed GA-XGBoost model consistently outperforms SVR and LSTM baselines across all clusters. In addition, cluster-specific models further improve performance compared to a single GA-XGBoost model trained without clustering, achieving a 48.42% improvement in MASE. Overall, beyond improving forecasting accuracy, cross-cluster generalization shows performance degradation and distributional shift when models are transferred across clusters, while residual diagnostics reveal differences in variance, temporal dependence, and non-Gaussianity. Full article

The maintenance and repair of industrial equipment is a process whose automation can improve the efficiency and safety of industrial production. This paper presents a software service that recognizes service engineer actions from video captured during equipment maintenance. The development stages of this service are described, along with the key features selected for training the machine learning model and their use in implementation. Experiments were conducted to test the software service under laboratory conditions, using the disassembly of a centrifugal oil pump and the replacement of a device in a smart panel for electricity distribution and metering as case studies. The trained model recognizes the required actions with at least 87% accuracy. Finally, the paper describes the testing and hardware requirements, the main functionality, and the advantages of using the service. The results show that identifying the actions of a service engineer requires only the position of their hands in two coordinates, x and y. Dimensionality reduction methods require the extraction of three types of features—geometric, angular, and distance—as well as the use of statistical parameters of time series data in conjunction with the energy and entropy of the wavelet transform coefficients of the time series data. These transformations enable the use of simplified machine learning methods and do not require high-powered devices on-site. It is shown that the presented method allows for a significant reduction in the incoming information for the service to operate (by 31.72 times), which is expressed by storing the coordinates of the hands instead of the video (5.9 MB versus 186 KB). Full article

Patient recovery prediction and hospital length of stay estimation remain critical challenges in healthcare resource allocation and clinical decision-making. Inaccurate discharge planning drives substantial avoidable hospital costs, while existing machine learning models remain limited by narrow, single-domain data that fail to capture the multimodal complexity of modern smart ward environments. This study proposes IoT-ClinXAI, an explainable multimodal framework that fuses IoT environmental data, wearable physiological signals, and clinical records for accurate and transparent patient recovery prediction in smart hospital wards. A Multi-domain Hierarchical Consensus Feature-Selection method groups features into structured domains, applies Borda–Kemeny weighted consensus within each domain, and reduces cross-domain redundancy while preserving complementary information. A Snake Optimization–tuned Random Forest Regressor optimizes predictive performance through adaptive hyperparameter search, while a multi-scale SHAP framework provides global and patient-level explanations for transparent clinical inference. Experiments were conducted on a real-world IoT-enabled smart ward dataset comprising patient data and recovery duration. The proposed framework achieved strong predictive performance on the held-out test set, with $R^2$ of 0.964, RMSE of 0.476 days, MAE of 0.342 days, and MAPE of 3.13%, yielding a 23.3% RMSE reduction over the unselected baseline and outperforming all feature-selection methods by 10.9–17.6% in RMSE. Statistical superiority was consistently confirmed across all pairwise comparisons using Wilcoxon signed-rank tests with Bonferroni correction ($p<0.001$). SHAP analysis identified ward allocation, respiratory rate, and oxygen saturation as the dominant recovery predictors, while environmental IoT variables showed minimal predictive contribution. These results highlight IoT-ClinXAI as a reliable and useful framework for supporting bed management, discharge planning, and hospital resource optimization in resource-constrained healthcare settings. Full article

Irrigation scheduling plays a pivotal role in bridging water resource allocation and farmland production management. For decades, scheduling in irrigation districts has predominantly relied on operators’ experience and relatively rigid water delivery plans, making it difficult to simultaneously meet the demands for timely responsiveness and precise water allocation under the combined influence of meteorological variability, changing crop water requirements, and the dynamic adjustments of water conveyance and distribution systems. The advancement of digital technologies, such as the Internet of Things, machine learning, deep reinforcement learning, and digital twins, has opened new technical pathways for optimizing irrigation scheduling. Focusing on the development of smart irrigation and scheduling optimization in irrigation districts, this paper systematically reviews the relevant literature published from January 2000 to June 2026 and delineates its evolution into three stages. Early-stage research was grounded in physical models, empirical rules, and hydraulic simulations, establishing fundamental methods for evapotranspiration estimation, crop water requirement calculation, and canal water delivery simulation. The middle stage, marked by the introduction of the Internet of Things and machine learning, enabled real-time monitoring of hydrological conditions, soil moisture, and meteorological data and promoted a data-driven transformation of water demand forecasting methods. The recent stage is characterized by the integration of deep reinforcement learning, digital twins, and knowledge graphs, which extends irrigation district scheduling from isolated single-point optimization toward multi-agent coordination and closed-loop management. Existing evidence confirms that digital technologies have yielded water-saving and yield-increasing benefits at the field scale and improved water distribution efficiency in several demonstration irrigation districts; however, their wider deployment at the district scale still faces bottlenecks such as inadequate sensing of physical execution processes, underdeveloped multi-objective trade-off mechanisms, and limited model transferability and long-term operational sustainability. To address these challenges, this paper proposes future research directions oriented toward real-time perception of water delivery and distribution status, multi-objective robust optimization, explainable artificial intelligence, and human–machine collaborative decision-making, thereby providing a reference for the theoretical development, engineering deployment, and operational management of smart irrigation district scheduling systems. Full article

The harvesting of fruit and vegetable crops has long been plagued by prominent issues such as high labor costs, low harvesting efficiency, and high fruit damage rates. The application of object recognition technology has enabled harvesting robots to identify, detect, and locate crops in certain agricultural scenarios, achieving a degree of automated harvesting. However, these systems still suffer from shortcomings such as poor robustness in complex environments, insufficient generalization ability, and high model deployment costs, which significantly limit their large-scale application in agricultural harvesting equipment. This paper comprehensively reviews recent literature in the field of fruit and vegetable target recognition. It summarizes how current research focuses on the implementation principles and directions for the improvement of mainstream methods—including digital image processing, traditional machine learning, and deep learning—while also identifying the remaining issues and challenges facing current technology in terms of algorithmic model real-time performance, robustness, and generalization ability. In the future, target recognition technology is expected to achieve breakthroughs through approaches such as multimodal feature fusion, large-scale models, and semi-supervised learning, evolving toward higher accuracy, faster processing speeds, and easier deployment, thereby providing technical support for the large-scale implementation of smart agriculture. Full article