Search Results (353)

Reliable in-line estimation of slurry rheology could improve the safety and control of pipeline-transfer operations, particularly in radioactive-waste processing where frequent manual sampling is undesirable. This study presents SW-RheoPINN, a physics-informed inverse pipe-rheometry framework for estimating pipe-effective yield stress and plastic viscosity from short windows of pressure-drop, mass-flow-rate, density, and pipe-geometry measurements. The framework combines a permutation-invariant sensor-window encoder with an analytical Bingham pipe-flow backbone, radial momentum balance, a regularized constitutive relation, cross-sectional mass conservation, and a tightly bounded velocity-profile correction for limited model discrepancy. SW-RheoPINN was evaluated using 20 two-state kaolin–water flow-loop experiments comprising 40 hydraulic states. In matched-physics synthetic tests with 2% multiplicative mass-flow noise, yield-stress recovery improved from $R^2=0.787$ for two-state windows to $R^2=0.923$ and $R^2=0.955$ for three- and four-state windows, respectively; plastic-viscosity recovery improved from $R^2=0.937$ to $R^2=0.967$ and $R^2=0.961$. For the experimental data, complete sensor-window reconstruction achieved a MAPE of 0.80% and $R^2=0.990$. Because measured mass flow is an encoder input in this reconstruction, these metrics characterize inverse self-consistency rather than prospective prediction. A separate target-flow-withheld evaluation, in which the withheld mass flow was not supplied to the inverse model, achieved an RMSE of $0.108$ kg.s-1, $R^2=0.790$, and a median absolute percentage error of 3.55%. Prediction was strongest for compositions with repeatable hydraulic behavior and degraded when nominally similar experiments occupied distinct response states. Ablation and sensitivity analyses showed that strongly resolved high-yield conditions were largely insensitive to composition-related regularization, Papanastasiou sharpness, and correction capacity, whereas low-yield estimates were more model dependent. Misspecified-physics tests further showed that small hydraulic residuals do not necessarily imply unbiased rheological parameters. The inferred pipe-effective yield stresses retained the broad composition-dependent trend observed by offline rheometry, although absolute cross-scale agreement was limited. These results support SW-RheoPINN as a physics-constrained inference and diagnostic framework for identifying both well-supported and weakly resolved rheological states from standard process measurements. 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

During long-term monitoring, data missing often happens due to environmental interference, sensor malfunction or transmission problems, which will threaten the effectiveness of structural health monitoring. This study proposes an anchor-constrained residual stacking method, which can improve data reconstruction performance relative to individual models across diverse missing patterns while reducing the risk of performance degradation associated with unconstrained ensemble learning. The method adopts a two-level stacking framework in which heterogeneous base learners generate candidate reconstructed data and grouped out-of-fold predictions are used to select an anchor learner for different missing patterns. A residual meta-learner then learns complementary residual information relative to the anchor learner, while validation-gated fusion regulates residual correction and final fusion based on reserved validation data, reducing unreliable fusion contributions. The effectiveness of the proposed method is verified using monitoring data with different missing patterns from a steel stringer bridge under multiple structural states. It achieves a coefficient of determination ($R^2$) of 0.9020, together with the lowest relative root mean square error (RRMSE) and mean absolute error (MAE) among the compared methods. Operational modal analysis further confirms that the method preserves the main dynamic characteristics of structural responses, supporting reliable reconstruction across diverse missing patterns and multiple structural states. Full article

Fast and accurate detection of missed and multiple seeding, followed by timely correction, is needed to maintain potato planting quality. Photoelectric, laser, capacitive, and machine vision methods have been developed for defect detection. Backup metering channels, catch-up compensation, in situ release, preparatory seed belts, and electric reseeding devices have also been used for correction. However, stable field use remains limited. Reported outcomes often cover detection accuracy, model performance, or single-action success, but end-to-end verification from defect detection through reseeding to outcome checking is not consistently available. Using a structured search of international and Chinese databases and citation screening, this review synthesized 88 publications published by 1 June 2026. The review compares the principles, reported performance, and operating conditions of the main detection methods and considers planting-quality control and reseeding in a broader agronomic context. Photoelectric and capacitive sensors generally produce clear event signals with simple processing. Machine vision provides more detailed class and position information but is more sensitive to lighting, occlusion, vibration, and computing delay. The analysis shows that high detection accuracy alone does not ensure reliable field correction. Performance also depends on sensor position, space-time matching, reseeding method, actuator response, and post-action checking. Future studies should use a wider set of metrics, conduct longer field tests under varied conditions, and improve the coordination of detection, control, actuation, and verification. These comparisons can inform sensor selection, correction-system design, and field evaluation protocols for potato seed-metering detection and reseeding systems. Full article

Soilless systems are increasingly important in protected horticulture because they improve water and nutrient-use efficiency, support year-round production, and reduce dependence on field conditions. However, the root zone is still commonly managed as a passive nutrient reservoir using mainly electrical conductivity and pH set points. This review presents the root zone as an actively engineered biological environment in which dissolved oxygen, root-zone temperature, nutrient-solution chemistry and hydraulics, microbiomes and biofilms, and sensor-guided control interact to determine crop performance. These domains converge on root respiration and ATP production, membrane transport, aquaporin activity, hydraulic conductance, calcium delivery, oxidative balance, and microbial or pathogen selection. Their combined effects influence fresh mass, tissue hydration, nutrient uptake, phytochemical composition, tipburn incidence, disease resilience, and overall system stability. Recent evidence indicates that active aeration, targeted root-zone heating or cooling, optimized flow scheduling, and calcium-focused interventions can improve the yield and quality of leafy vegetables, although responses vary with crop species, cultivar, developmental stage, and production-system architecture. Current evidence also indicates important uncertainties, including crop- and cultivar-specific response thresholds, architecture-dependent performance, energy and resource costs, and the still-limited predictability of microbiome manipulation. Emerging sensing, machine learning, digital-twin, and predictive-control approaches could enable a transition from threshold-based correction to physiology-informed root-zone state management. Nevertheless, wider commercial translation is constrained by inconsistent reporting of sensor location, hydraulic conditions, nutrient composition, microbial status, and resource use. We therefore propose a minimum reporting framework and research priorities for developing reproducible, energy-aware, microbiologically robust, and crop-specific root-zone management strategies for closed soilless horticulture. Full article

Mobile self-reports provide subjective and contextual information that passive sensors cannot recover, but frequent prompts compete with everyday activities and are often answered late. Here, we show that situational context and recent response history predict whether an ecological momentary assessment response begins within 15 min. We analyzed 70,375 records from 170 participants in the Italian arm of DiversityOne; 43.19% met the operational timeliness criterion. Participant-clustered generalized estimating equations identified associations with activity, social setting, location, mood, weekday, hour and survey day, with corrected Cramér’s V values of 0.044–0.175. In leakage-resistant evaluation, gc-Forest achieved an accuracy of 0.719 for personalized forward prediction, whereas history-augmented LightGBM achieved an accuracy of 0.704 and area under the receiver operating characteristic curve of 0.779 when participants were held out. Retrospectively ranking ten candidate moments increased the participant-balanced timely-response rate from 44.60% to 51.43%. These results establish prompt timeliness as a learnable scheduling outcome, while distinguishing it from content accuracy or cognitive effort. Full article

In the present study, the structural, electronic, optical, adsorption and sensitivity properties of BN and AlN nanoribbons towards nitrogen dioxide (NO₂) gas molecules were investigated via density functional theory (DFT), DFT-D3 dispersion correction and time-dependent DFT (TD-DFT). Six different NO₂ adsorption configurations were taken into account to evaluate the interaction between NO₂ molecules and the BN and AlN nanoribbon surface. Three adsorption configurations were considered for each nanoribbon, resulting in six adsorption configurations in total. The adsorption energy calculations indicated stronger chemosorption on the AlN nanoribbon surface than the BN nanoribbon surface, while BN nanoribbons gave a stronger optical response than AlN. The charge transfer (CT) results conclude that the NO₂ gas molecule acts like an electron donor, while it behaves like an electron acceptor on the AlN nanoribbon surface. The sensitivity (S) values confirm that the BN nanoribbon exhibits high sensing performance across all adsorption configurations, while the AlN nanoribbon shows the highest sensitivity for the H3 configuration. Furthermore, due to the chemisorption nature between BN and AlN nanoribbons’ surfaces, the band gap energy becomes narrower after interaction. For example, the band gap of the BN nanoribbons decreases from 6.2 eV to around 0.5 eV after NO₂ adsorption, showing electron excitation and improving the electron sensing performance. Overall, the evaluated results indicate that AlN nanoribbons are promising candidates for adsorption-based NO₂ gas sensors, while BN nanoribbons show superior potential for optical NO₂ sensing applications. Full article

Asphalt pavements undergo progressive mechanical changes during service life due to traffic loading, temperature variations, moisture and material ageing. Embedded strain sensors can support in-situ pavement performance monitoring, but their response is strongly affected by experimental variables that must be identified before reliable long-term ageing indicators can be established. This study establishes an in-situ baseline mechanical monitoring framework for asphalt pavements using embedded resistive strain transducers. KM-100HAS sensors were installed in an asphalt test section and evaluated through controlled field campaigns. A 17-point cross-pattern loading procedure was used to validate sensor location and orientation after construction. Load-free monitoring windows were analysed to estimate strain–temperature sensitivity and assess thermal correction of static loading–recovery tests. The results showed that loading position strongly conditions the measured strain response. Passive monitoring indicated that strain–temperature sensitivity depends on both temperature level and sensor location. In the mechanical tests, normalization of the recovery branch and logarithmic fitting over the first 200 s provided a consistent recovery-shape descriptor. The resulting slope, $b_{\mathrm{l}\mathrm{o}\mathrm{g}200}$, showed a strong linear relationship with the recovery percentage after 10 min (R² = 0.855). The proposed workflow provides a standardized baseline protocol for asphalt pavement monitoring and its mechanical evolution. Full article

Red–green–blue and depth (RGB-D) semantic segmentation combines appearance cues from RGB images with geometric information from depth maps, but sensor noise, missing measurements, and boundary-inconsistent depth responses can introduce conflicting evidence during cross-modal fusion. We propose the Structure-Prior-Guided Network (SPGNet), a dual-branch, multi-stage framework that follows a correction-before-fusion strategy. At each feature scale, SPGNet estimates a learned structure prior from cross-modal agreement and discrepancy. The Cross-Modal Correction Module (CCM) uses this prior to regulate bidirectional information transfer, suppressing unreliable responses while retaining complementary cues. The Dual-branch Enhancement Fusion Module (DEF) then enhances the corrected RGB and depth features and integrates them through shared-representation-guided interaction, after which a lightweight multi-scale decoder produces the segmentation output. Under a unified training and evaluation protocol, SPGNet achieved three-run mean Intersection over Union (mIoU) scores of 50.845% on NYU Depth V2 and 48.457% on SUN RGB-D. Compared with the best reproduced baseline on each dataset, SPGNet improved mean mIoU by 2.111 and 0.899 percentage points, respectively. These results suggest that separating reliability-oriented correction from multimodal fusion can limit the propagation of unreliable cross-modal responses and improve indoor RGB-D semantic segmentation performance. Full article

Blade-tip timing (BTT) sensor technology is widely used for non-contact blade vibration measurement. However, conventional BTT methods mainly rely on sparse time-of-arrival (TOA) information, which limits continuous sensor-domain characterization of blade vibration. To address this limitation, this paper proposes a dynamic voltage-response estimation framework combining an Elite Harris Hawks Optimization-based backpropagation neural network (EHHO-BP) with waveform mapping. Zero-speed static calibration experiments are used to establish the nonlinear relationships among blade-tip radial clearance, relative angular position, and sensor voltage, and the EHHO-BP model is employed to estimate the calibration response. Blade vibration displacement obtained from numerical models or reconstructed from BTT TOA measurements is then mapped to a continuous dynamic voltage response under a quasi-static transfer assumption. Single-harmonic and multi-harmonic simulations demonstrate the response-estimation process. In the static calibration comparison, EHHO-BP achieves a median RMSE of 8.92 mV, CVRMSE of 0.56%, MAE of 6.34 mV, and R² of 0.99982. Rotating experiments at 400, 600, 800, 1200, and 1500 rpm further evaluate the transferability of the zero-speed calibration model without retraining or speed-dependent correction. Across the tested speed range, the correlation coefficient remains between 0.9868 and 0.9989 and R² remains between 0.952 and 0.997; however, the FWHM error increases from 1.469% at 400 rpm to 22.662% at 1500 rpm. These results demonstrate the good transferability of the proposed quasi-static mapping at low-to-moderate rotational speeds while revealing a progressive deterioration in temporal waveform consistency at higher speeds. The proposed framework, therefore, provides a continuous sensor-domain representation of BTT-derived blade vibration displacement and an experimentally supported assessment of its speed-dependent applicability. Full article

Multi-sensor data fusion is essential for accurate target tracking and trajectory reconstruction. However, common forms of systematic error in multi-sensor observations, including constant biases, linear drifts, and saturating exponential drifts, can degrade measurement consistency and trajectory estimation accuracy. Within the B-spline-constrained Error Model Best Estimate of Trajectory (EMBET) framework, B-spline coefficients and systematic-error parameters may produce similar observation responses, allowing part of the systematic-error response to be absorbed into the spline-coefficient correction and thereby weakening the identifiability of the systematic-error parameters. To avoid the weak-identifiability mechanism associated with the joint parametric estimation of trajectory and systematic-error terms, a residual-driven ResCompFormer method is proposed for systematic-error compensation and target trajectory reconstruction. First, a B-spline-constrained EMBET model is established to analyze the coupling between B-spline coefficients and systematic-error parameters. Systematic-error estimation is then removed from the joint EMBET parameter-estimation problem and reformulated as observation-domain error-sequence prediction, and ResCompFormer is employed to capture temporal dependencies and cross-channel correlations in multi-sensor residuals. The predicted errors are fed back to correct the observations, followed by iterative trajectory re-estimation. Simulation results confirm the systematic-error absorption mechanism and show that the proposed method outperforms the considered model-driven and data-driven methods in both systematic-error compensation and trajectory reconstruction, including iterative and stepwise EMBET variants. Additional experiments demonstrate the robustness of the proposed method to variations in systematic-error characteristics and sensor availability. Full article

Brushless DC (BLDC) motors are now the dominant propulsion choice for electric vehicles (EVs) because of their high torque density, efficiency and reliability, but their nonlinear dynamics, electronic commutation, and wide load and speed range make fixed-gain control difficult. A single set of proportional–integral–derivative (PID) gains tuned at one operating point degrades when inertia, back-EMF, or load torque change. This paper presents a hybrid adaptive PID speed controller for a BLDC EV drive that couples an online PID auto-tuner that re-estimates the gains from a frequency response estimate of the plant, with a fast fixed-structure PID that supplies the rapid corrective action that the auto-tuner cannot provide during its estimation interval. The novelty of this work is this explicit two-element decomposition operating on a cascaded speed/voltage loop driven by Hall sensor feedback, which removes the need for an exact analytical feedback model while retaining the transparency of classical PID. A full analytical model of the BLDC machine and the closed-loop transfer functions is derived and implemented in MATLAB/Simulink. Across step references of 1000–1800 rpm and load steps to 10 N·m, and against a conventional fixed-gain PID and a Flower Pollination Algorithm (FPA)-tuned PID, the proposed controller holds overshoot below 1% at low-to-mid speed and a consistently lower torque ripple, while a 12.4% transient undershoot at 1800 rpm under sudden load identifies the present operating limit and a direction for future work. Full article

Cardiovascular diseases remain the leading global cause of mortality, necessitating continuous monitoring solutions that extend beyond clinical settings. This paper proposes a real-time, end-to-end Edge-IoT framework for cardiovascular risk assessment that integrates biomedical signal acquisition, edge processing, and interpretable deep learning. The system includes a three-tier architecture: (i) physiological signal acquisition using AD8232 ECG, MAX30102 photoplethysmography, DS18B20 temperature, and NEO-6M GPS sensors interfaced with an ESP32 microcontroller; (ii) real-time signal preprocessing, including digital filtering, normalisation, and PQRST feature extraction performed at the edge; and (iii) cloud-based analytics using an Enhanced TabNet classifier with modified attention mechanisms for cardiovascular risk prediction. The Enhanced TabNet architecture incorporates Entmax-based sparse attention and modified Gated Linear Units to improve predictive performance and clinical interpretability. Signal quality enhancement using Kalman filtering and class imbalance correction using SMOTE further support robust model performance. The Enhanced TabNet model achieves 97.43% accuracy, 96.18% precision, and 97.24% recall on the combined Cleveland, Hungarian, Switzerland, Long Beach VA, and Statlog heart disease datasets ($n=1190$). The developed Edge-IoT prototype maintains an end-to-end communication and processing latency below 200 ms. The framework also includes automated risk alert generation via SMS when the predicted cardiovascular risk probability exceeds a predefined threshold (e.g., 0.85), including the patient’s vital information and geolocation to support emergency response. The integrated edge-cloud architecture with attention-based feature selection provides interpretable cardiovascular risk predictions while maintaining the computational efficiency required for potential continuous patient monitoring outside hospital settings. Full article

Leakage identification in water distribution networks must estimate leak locations and magnitudes under demand fluctuations, similar adjacent-node responses, and superimposed multiple-leak signals. This study combines physics-based joint inversion with ExtraTrees candidate re-ranking. Using an EPANET model of the Hanoi network, emitter candidates were placed at pipe midpoints, and scenarios were generated across demand periods, global demand factors, and four regional demand fluctuations. Sixteen pressure residuals and 22 flow residuals formed the observation vector. The physical stage enumerated zero- to three-leak combinations and used bounded least squares to estimate leakage flows and demand corrections; standardized pressure-flow residuals and penalty terms produced the candidate pool. ExtraTrees then re-ranked candidates using candidate structure, physical scores, flow statistics, and operating-period features. In 2000 independent blind-test scenarios, complete localization accuracy, leak-number identification accuracy, and total leakage-flow MAE were 90.55%, 97.10%, and 0.841 L/s; for 1500 leakage scenarios, they were 87.53%, 96.27%, and 1.117 L/s. Re-ranking increased leakage-scenario complete localization from 76.13% to 87.53%, while final candidate-pool recall reached 99.15%. Robustness tests involving measurement noise, hydraulic-model mismatch, sensor density, computational time, and Net1 indicated that the method improves candidate discrimination under simulation, although roughness bias and weak multiple-leak signals remain challenging. Full article

Mass concentrations of particulate matter are a fundamental metric for air quality and health impact assessment; however, they are insufficient for accurately characterizing exposure. They do not capture particle size distribution or number concentration. Therefore, aerosol assessment should include particle number concentration (PNC), which better represents toxicologically relevant fractions and enables more precise source identification. The aim of this study was to conduct a comprehensive evaluation of particle number concentration (PNC) measurements in the 0.3–10 µm size range obtained using three low-cost Sensirion SPS30 particle sensors under field conditions in an urban environment. The analyses included an assessment of agreement between the SPS30 sensors, an evaluation of their measurement performance against the OPS 3330 optical particle spectrometer, and the development of calibration models. The SPS30 sensors showed high inter-device repeatability for PNC in the 0.3–1.0 µm range (CV_d < 2%). However, measurement performance declined with increasing particle size, with the index of agreement (IOA) decreasing from 0.8 (0.3–0.5 µm) to −0.5 (2.5–10 µm). Sensor accuracy was influenced by meteorological conditions: relative humidity primarily affected short-term variability (precision and dynamic agreement), while temperature controlled systematic bias. Although incorporating these variables into advanced calibration models improved performance, SPS30 sensors remained unsuitable for PNC measurements in the 2.5–10 µm range, exhibiting systematic errors of ~25% even after nonlinear correction. The findings support the responsible use of low-cost particle sensors for supplementary air quality monitoring, contributing to accessible environmental data and sustainable urban air quality management. Full article