Search Results (977)

Continuous multi-parameter monitoring is important for characterizing environmental conditions in commercial beef cattle facilities, but sensor performance and system reliability require evaluation under production conditions. This study developed a LoRa-based multi-sensor node for air temperature, relative humidity, CO₂, NH₃, air speed, and illuminance. Field performance was evaluated at one commercial farm by synchronous comparison with commercial instruments using 1-min paired observations and regression- and agreement-based analyses. Nine prototype nodes were subsequently deployed at three sites for 14-day monitoring periods. Temperature and relative humidity showed the strongest linear relationships with the comparison instruments (R² = 0.995 and 0.994), followed by illuminance, air speed, and CO₂ (R² = 0.990, 0.863, and 0.773). NH₃ showed a weaker relationship (R² = 0.604), improving after 10-min aggregation; most application-monitoring estimates below 5 ppm were extrapolated rather than validated absolute concentrations. Overall data availability was 99.66%, and continuous monitoring captured temporal patterns in thermal conditions, air quality, local airflow, and illuminance. The evaluation focused on environmental monitoring performance rather than animal-based outcomes. These findings support parameter-specific environmental monitoring and multi-site deployment in commercial beef cattle facilities, with potential for future anomaly detection and environmental control. Full article

This study employs a multi-method, high-precision research approach to evaluate the thermal comfort performance of a window-based direct evaporative cooling (DEC) air conditioning system installed in a university dormitory building (50 rooms) in Beijing. To compensate for the insufficiency of single-day test data, the study was conducted continuously for 30 days from 1 June to 30 June 2026 (00:00–23:59 daily). Eight calibrated sensor sets were deployed in each of the 50 rooms (that is, eight fixed sensor sets per room × 50 rooms = 400 synchronously logged spatial measurement points, each integrating a fixed SHT35 temperature/humidity sensor with a matched hot-wire anemometer probe; this unusually dense, building-scale simultaneous deployment is uncommon in previous dormitory studies), recording data simultaneously across all rooms throughout the test period with the DEC units continuously operating. The research integrates field physical measurement data, standardized subjective questionnaire surveys (200 within-person paired questionnaires, each pairing a student’s retrospective recall of the pre-DEC condition with an in situ vote collected during DEC operation), and advanced computational thermophysiological modeling results based on the frameworks of ISO 7730–2021 and ASHRAE Standard 55–2023. Environmental parameters, including dry-bulb temperature (Ta), relative humidity (RH), and air velocity (Va), were monitored at eight spatially distributed points per room with a 10 Hz sampling frequency and a one-hour median resolution. The mean radiant temperature (Tr) was approximated as equal to Ta due to the absence of globe temperature measurements, and this simplification is discussed as a limitation. Simultaneously, through a single-session questionnaire (June 24–30) compliant with ISO 10551 and the Appendix B requirements of ANSI/ASHRAE Standard 55, which paired each respondent’s retrospective recall of the early-June pre-DEC (non-cooled) condition with a concurrent vote collected during DEC operation—a recalled-pre/concurrent-post design rather than two separate real-time pre-/post-intervention surveys—data on clothing ensembles, activity levels, and subjective thermal sensation votes (TSV) were collected. The acquired data were input into a customized simulation platform developed in the Fortran language (which was debugged and cross-validated against the ISO 7730/ASHRAE Standard 55 reference implementation to within 0.01 PMV scale units), which employs the Fanger two-node thermoregulation model to accurately calculate and predict the predicted mean vote (PMV), predicted percentage of dissatisfied (PPD) occupants, new effective temperature (ET*), and standard effective temperature (SET*). The results indicate that the DEC unit achieved a stable outlet temperature reduction of Δt = 3.87 °C (inlet temperature 31.72 °C, outlet temperature 27.85 °C), with an average wet-bulb air temperature of 18.66 °C and an average outlet relative humidity of 58.3% (inlet RH: 42.1%), confirming the expected humidifying effect of direct evaporative cooling while maintaining an average indoor relative humidity of 42.07%—a result particularly relevant to Beijing’s dry-to-semi-humid summer environment, where evaporative cooling is thermodynamically favorable. Because no DEC-off baseline period was monitored, the measured indoor conditions are reported as observational associations with DEC operation rather than as effects attributable exclusively to the unit; the pre-DEC satisfaction level was recalled retrospectively within the same single session and is therefore subject to recall/contrast bias; and all energy-saving figures are theoretical nameplate estimates rather than metered energy consumption. Full article

Physical sensor deployments in ground-based environmental monitoring networks are frequently constrained by high installation costs, hardware failures, and limited spatial coverage, resulting in incomplete observational datasets and degraded sensing capacity across monitoring stations. Data-driven virtual sensing offers a cost-effective alternative by estimating target environmental parameters through machine learning models trained on correlated sensor measurements, reducing dependency on dense physical infrastructure. This paper presents VS-DCFF, an applied virtual sensing framework for dual-target estimation of near-surface air temperature and relative humidity from ground-based sensor network data. VS-DCFF integrates: (i) a deterministic pipeline applying temporal encoding, rolling-window statistics, and mutual information-based feature selection to capture a linear trend/seasonal component and to select features predictive of the residual signal; (ii) a probabilistic pipeline employing a Gaussian copula model to generate statistically consistent synthetic residual samples preserving inter-variable dependencies; and (iii) an early feature-level fusion strategy feeding a copula-augmented XGBoost residual-boosting stage, whose output is combined with the linear trend component for the final prediction. Under a strict chronological evaluation protocol, VS-DCFF is benchmarked against persistence, linear and ensemble regression baselines, and a same-protocol re-implementation of the statistical core of the VSG-SGL framework, and achieves near-surface air temperature $\mathrm{RMSE}=0.7791{}^{\circ }$C, $R^2=0.9735$, and relative humidity $\mathrm{RMSE}=3.7747\%$, $R^2=0.9701$, outperforming all tested baselines. The framework is further validated through leave-one-station-out spatial generalization, robustness evaluation under simulated sensor faults and target-history loss, copula-variant and synthetic-data fidelity diagnostics, and a lightweight edge-deployment ablation. All findings, including cases where tested extensions such as spatial context features did not yield a robust improvement, are reported transparently. Results indicate that the proposed architecture provides a computationally efficient, extensively validated approach to dual-target environmental virtual sensing under realistic deployment conditions. Full article

Air pollution data processing is a relevant aspect of urban-life-quality monitoring. This study relates the values of air pollutants to meteorological factors with prediction models created with multiple linear regression (MLR) in the R program. Fragmented data were obtained in the years 2023/24 from the heaviest-urban-traffic location in Belgrade, Serbia. A Serbian-comparable list of air pollutants (PM₁₀, PM_2.5, SO₂, NO₂, CO, and O₃) was created according to an analysis of sensor availability at monitoring stations. With the prediction models and seasonally clustered data (spring and summer data clusters were incomplete), each of these pollutants (except O₃) was related to all measurable meteorological factors (atmospheric pressure, wind speed, relative humidity, and temperature). All independent (meteorological) factors showed a moderate level (Multiple R² < 0.7) of impact on the prediction of air pollutant values (dependent factors). The second group of prediction models related pollutant triplets, and fourteen of the created models reached R² > 0.7. The prediction model with the highest relevant R² value (CO~PM₁₀ + NO₂) was used for CO pollutant prediction and in-sample fit analysis. The obtained mean absolute error is ~0.13 mg/m³. This case study contributes to the examination of the role of meteorological factors in urban-traffic air-quality monitoring within a seasonal context. Full article

Precise monitoring of ammonia (NH₃) in humid agricultural environments is essential for livestock management and environmental protection. However, conventional metal oxide semiconductor sensors often suffer from signal attenuation and baseline instability because of competitive water adsorption under room-temperature, high-humidity conditions. Here, a non-annealed Sn/Ce-containing polyacrylonitrile (PAN) nanofiber membrane was fabricated by electrospinning for room-temperature NH₃ sensing. The resulting Sn/Ce/PAN membrane exhibits an amorphous hybrid structure formed through interactions between the metal species and the PAN matrix. The Sn/Ce/PAN membrane-based sensor delivers a response of 90% toward 100 ppm NH₃ at 80% RH, with a response time of 16 s and a recovery time of 37 s. The sensing response increases with relative humidity and reaches its maximum at 80% RH, demonstrating excellent sensing performance under high-humidity conditions. Combined experimental and theoretical investigations reveal that the outstanding sensing performance originates from humidity-mediated proton conduction enabled by enhanced water adsorption and the formation of a continuous hydrogen-bond network, whereas excessive water accumulation suppresses charge transport under excessively humid conditions. This work provides mechanistic insights into room-temperature NH₃ sensing under high humidity and offers a promising strategy for developing high-performance gas sensors for practical humid environments. Full article

Leaf-level vapor pressure deficit ($VP{D}_{\mathrm{leaf}}$) depends on the temperature of the leaf surface as well as the temperature and humidity of the surrounding air. Therefore, instruments that estimate $VP{D}_{\mathrm{leaf}}$ from a fixed leaf–air temperature offset may introduce condition-dependent errors. This paper presents the development, uncertainty analysis, and validation of a low-cost, single-housing, portable sensor platform that directly measures air temperature ($T_{\mathrm{air}}$), relative humidity ($RH$), and leaf surface temperature ($T_{\mathrm{leaf}}$) via an SHT35 and an MLX90614 infrared thermometer, and computes $VP{D}_{\mathrm{leaf}}$ on-board in real time using an ATmega328-based microcontroller. The platform was validated against a Testo 610 thermo-hygrometer and a FLIR E4 thermal camera on two lettuce (Lactuca sativa L.) cultivars grown at 20–26 °C and 40–70 %RH. Coefficients of determination were $R^2=0.9607$ for $T_{\mathrm{air}}$ and $R^2=0.9382$ for $RH$ ($n=1017$). Leaf temperature and the on-board $VP{D}_{\mathrm{leaf}}$ output itself were validated against reference readings taken during randomly timed site visits on three separate days ($n=250$ after excluding apparent misreads): $T_{\mathrm{leaf}}$ showed $R^2=0.8852$ against the FLIR E4, and the device-computed $VP{D}_{\mathrm{leaf}}$ showed $R^2=0.9100$ against a reference $VP{D}_{\mathrm{leaf}}$ computed from the same reference readings, with a mean bias of $+0.008$ kPa and an RMSE of $0.046$ kPa. A propagation-of-error analysis separately yielded a worst-case $VP{D}_{\mathrm{leaf}}$ uncertainty of $\pm 0.153$ kPa under representative conditions ($T_{\mathrm{air}}=25$ °C, $T_{\mathrm{leaf}}=24$ °C, $RH=65\%$), mainly driven by the $\pm 0.5$ °C infrared sensor tolerance; the empirically observed error was well within this conservative bound. With a cost of USD 83.28, this platform provides a practical and economically accessible tool for real-time monitoring and VPD-informed decision making in vertical farms and greenhouses. Full article

Precision agriculture increasingly requires intelligent systems capable of integrating multimodal sensing with transparent decision support to enable timely and reliable crop management. This study proposes a hybrid intelligent IoT framework integrating environmental monitoring, wearable plant physiological sensing, AI-based pest-monitoring, machine-learning-based prediction of crop physiological stress, and explainable fuzzy rule-based decision support into a unified architecture for crop stress assessment. A novel Physiological Stress Index (PSI) was developed by combining vapor pressure deficit, relative humidity, Delta-T, leaf capacitance, and relative irradiance to provide an interpretable indicator of crop physiological stress. The proposed framework was experimentally validated under real field conditions using a commercial environmental monitoring station, wearable leaf sensors, AI-enabled pest-monitoring devices, and cloud-based analytics. Correlation analysis confirmed strong relationships between PSI and the principal environmental variables (VPD: r = 0.980, Delta-T: r = 0.990, RH: r = −0.961), demonstrating the internal consistency and sensitivity of the proposed index. At the 15 min forecasting horizon, Linear Regression and Gradient Boosting demonstrated virtually identical performance: Gradient Boosting achieved a marginally lower RMSE and higher R² (RMSE = 0.0273; R² = 0.9810), whereas Linear Regression achieved a slightly lower MAE (MAE = 0.0186). At the 1 h forecasting horizon, Gradient Boosting achieved the strongest performance (R² = 0.9034), indicating increasing relevance of nonlinear modelling at longer prediction horizons. The proposed framework demonstrates the feasibility of combining multimodal sensing, machine learning, explainable artificial intelligence, and edge-enabled IoT technologies to support proactive, transparent, and intelligent precision agriculture. Full article

This paper presents the metrological characterization of low-cost sensors integrated into a multi-sensor system for Indoor Environmental Quality monitoring, developed within the MIRABLE project. The analysis focuses on two domains: the thermal domain, using Sensirion SHT45 and SEN55 temperature sensors; and the Indoor Air Quality (IAQ) domain, using an Infineon photoacoustic spectroscopy (PAS)-based sensor for carbon dioxide (CO₂). All tests were conducted under controlled laboratory conditions using calibrated reference instruments. In the thermal domain, the influence of sensor integration within the device case was investigated at temperature (T) between 15 °C and 35 °C and relative humidities (RH) between 30 %rh and 60 %rh. The results revealed self-heating effects in the desk unit, causing temperature biases of up to 0.6 °C. In the IAQ domain, the repeatability and the impact of T and RH on CO₂ measurements were evaluated. T was identified as the main influencing factor; whereas, RH had a negligible effect. These results were supported by statistical analysis ANOVA. A correction strategy based on concentration intervals is proposed for operation between 15 °C and 25 °C, with an expanded uncertainty (k = 2) of (3.26–6.42) ppm for the with-case configuration. These results support the reliable use of the MIRABLE system. Full article

Hydrogen (H₂) detection under practical operating conditions requires sensing materials that simultaneously provide accessible reaction sites, efficient gas diffusion pathways, and fast interfacial charge transfer. Here, a hierarchical star-sphere ZnCo₂O₄ (ZC) architecture was integrated with graphene oxide (GO) and Pt supported on graphitized carbon (Pt/C) to develop hybrid chemiresistive sensing layers for low-temperature hydrogen detection. The synthesized ZC-based material exhibited a hierarchical morphology consisting of porous microspheres and star-shaped assemblies, providing a multiscale framework for gas access and surface reactions. By varying the GO content from 0.1 to 1 wt% at a fixed Pt/C loading, the ZC-0.5G composite achieved the most balanced structure, with well-distributed GO sheets, preserved star–sphere morphology, the highest specific surface area (53.6 m²/g), and the largest pore volume (0.09 cm³/g). The optimized sensor gave responses of 12.96%, 19.20%, 22.87%, and 26.43% for 500, 4000, 8000 and 10,000 ppm H₂ concentrations, respectively, with measurable response down to 50 ppm. The highest sensing performance was achieved at 50 °C and 60% relative humidity (RH), where the hierarchical oxide framework, GO-assisted interfacial pathways, and Pt catalytic sites acted in concert. The sensor also showed repeatable cyclic behavior and preferential response to H₂ compared to methanol, isopropanol, ethanol, acetone, and dimethylformamide. The improved sensing performance is attributed to the synergistic combination of the hierarchical ZC framework, GO-assisted interfacial pathways, and Pt-assisted catalytic activation, which together facilitate gas diffusion, surface reactions, and resistance modulation. Full article

Greenhouse microclimates exhibit substantial spatial heterogeneity. Conventional evaluations based on average measurements cannot adequately describe the environmental conditions experienced by crops. This study developed a spatial frequency analysis method to quantify long-term temperature and relative humidity heterogeneity. This method was coupled with cucumber yield and downy mildew models to evaluate the biological consequences of environmental variability. Environmental conditions in four representative greenhouse structures were monitored using distributed sensor networks under different weather conditions. The proposed method successfully identified persistent environmental hotspots. The spatial distribution of environmental heterogeneity differed among greenhouse structures, whereas solar radiation primarily controlled its intensity. Long-season monitoring data indicate that the maximum spatial variations in temperature and relative humidity within the brick-wall solar greenhouse, the assembled greenhouse, the glass greenhouse, and the plastic multi-span greenhouse reach up to 10 °C and 46%, 8.5 °C and 46%, 12 °C and 50%, and 7 °C and 32%, respectively. The assembled solar greenhouse and plastic greenhouse exhibited higher environmental uniformity, while the brick-wall solar greenhouse and glass multi-span greenhouse showed pronounced spatial gradients. Environmental heterogeneity resulted in significant within-greenhouse differences in simulated cucumber yield, with the smallest variation occurring in the assembled solar greenhouse (5.3%) and the largest in the glass multi-span greenhouse (39.2%). Disease simulations further revealed clear spatial aggregation of cucumber downy mildew risk, with the southern region of the solar greenhouse exhibiting 17–67% higher cumulative infection risk than other positions. This study establishes an integrated framework linking greenhouse environmental heterogeneity with crop productivity and disease risk, providing a practical basis for spatially differentiated precision greenhouse management and greenhouse structural optimization. Full article

During coal mine roof fracturing drilling, vibration signals from the drilling tool can reflect both the drilling state and the structural response of the roof. However, traditional vibration sensors generally depend on batteries or wired power delivery, which hinders their long-term deployment in underground monitoring environments. To overcome this limitation, a self-powered vibration sensor featuring a wedge-shaped column array structure was developed, enabling vibration-induced electrical signal generation through the triboelectric effect. The sensor utilizes drilling-induced vibration to trigger cyclic contact–separation between the nanolayers, thereby converting vibration energy into electrical signals associated with the vibration frequency. In this way, the sensor can achieve both vibration frequency measurement and energy harvesting. The sensor was experimentally verified to enable reliable frequency detection across the 0–9 Hz range, with a measurement error of less than 3%. It also retained stable operational performance under temperatures up to 100 °C and relative humidity below 90%. Moreover, the output power reached a maximum value of 8 × 10⁻⁷ W with an external load of 10⁸ Ω. The developed sensor enables self-powered vibration frequency measurement, while its redundant vibration structure enhances operational reliability. These features make it suitable for underground coal mine drilling environments characterized by limited space and strong mechanical vibration. Full article

This study addresses the challenge of incomplete indoor environmental monitoring data under alternate-floor sensor deployment in multi-story residential buildings. To enable cost-effective environmental sensing, a Building Environmental Data Reconstruction Framework (EDRF) is proposed for estimating unmonitored floor conditions. The EDRF integrates a convolutional neural network (CNN) for spatial feature extraction, a temporal convolutional network (TCN) for temporal dependency modeling, residual connections for stable feature propagation, and a multi-task learning (MTL) strategy for simultaneous reconstruction of multiple environmental variables. The model is trained and validated using real-world data collected from Floors 2–10 of a residential building, focusing on illuminance, temperature, and relative humidity. Experimental results demonstrate that the proposed framework achieves high reconstruction accuracy, with average R² values of 0.992 for temperature and 0.988 for relative humidity. Even under a reduced sensor deployment rate of 33.3%, the model maintains robust performance with an overall R² of 0.987. Ablation studies further confirm the effectiveness of each component in improving reconstruction accuracy. The proposed method provides a practical and scalable solution for reconstructing missing indoor environmental data and supports low-density sensor deployment in building monitoring systems. Full article

Environmental regulation in caged broiler houses requires strict control of temperature, relative humidity, and ventilation, as abnormal indoor conditions may adversely affect broiler health and productive performance. However, existing research has paid insufficient attention to environmental changes at multiple spatial locations within broiler houses, and some studies have focused solely on a single rearing cycle without seasonal differences in the indoor rearing environment. Therefore, this study proposes a GRU–Transformer prediction model based on task-adaptive fusion. By integrating data from multiple indoor temperature sensors, central relative humidity, outdoor environmental conditions, broiler age, and control signals from environmental control devices, the model predicts central temperature, central relative humidity, and temperatures at six specific locations within the house, namely the front, rear, left, right, upper, and lower positions. Additionally, the model calculates the temperature–humidity index (THI) using the predicted central temperature and central relative humidity. The model was trained using environmental data spanning multiple complete rearing cycles across four seasons and validated on four independent test sets. The validation results show that the proposed model achieved the lowest mean absolute error (MAE) in 10 out of 12 single-step tasks for central temperature, central relative humidity, and THI. Additionally, the model demonstrated relatively stable predictive performance in multi-point predictions. Furthermore, multi-step prediction tasks, ablation experiments, and random seed experiments were conducted to further verify the model’s cross-seasonal generalization capability, robustness, and tracking performance. In the future, the developed model can serve as a predictive basis to support intelligent environmental regulation using MPC (Model Predictive Control) or RL (Reinforcement Learning) frameworks. 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

The Internet of Plants (IoP) represents the convergence of Artificial Intelligence (AI), Big Data analytics, and the Internet of Things (IoT) within protected agricultural systems. This study presents an IoP platform designed to collect, process, and analyze real-time environmental data using specialized IoT sensors capable of monitoring critical variables, including carbon dioxide concentration (CO₂), pH, air temperature, and relative humidity in hydroponic production systems. The proposed framework integrates advanced machine-learning algorithms, including Random Forest Regressor and Long Short-Term Memory (LSTM) neural networks, to process large volumes of environmental data and support crop management. In addition, the platform incorporates Vapor Pressure Deficit (VPD) and Growing Degree Days (GDD) analyses to provide crop-specific recommendations and support informed decision-making. This platform establishes a benchmark for smart agriculture in Mexico’s Laja–Bajío region, facilitating informed decision-making and maximizing the sustainability of food systems. Experimental validation was conducted under both controlled and semi-controlled environments using Swiss chard (Beta vulgaris subsp. cicla L.) and lettuce (Lactuca sativa L.) cultivated in hydroponic systems. These environments represented contrasting climatic conditions, allowing evaluation of platform stability and forecasting performance under varying thermal regimes. The Random Forest Regressor model, trained using growth chamber data consisting of 19,836 valid observations, reproduced the deterministic VPD relationship with a coefficient of determination (R²) of 0.90 and a root mean square error (RMSE) of 0.08 kPa, confirming internal consistency and identifying temperature as the dominant contributing variable rather than predicting an independent outcome. The dynamic alarm system, integrated with crop phenological stages, demonstrated greater effectiveness than conventional static-threshold approaches by generating alerts according to crop developmental requirements. Furthermore, the web-based visualization platform enabled users to interpret environmental conditions through intuitive graphical representations, facilitating decision-making without requiring specialized technical expertise. The results demonstrate the feasibility of the IoP platform as a comprehensive environmental management tool for protected agricultural systems. The proposed framework provides a scalable solution for precision agriculture applications in the Laja–Bajío region of Mexico and in other regions with similar production systems. Full article