Search Results (871)

Mycotoxin contamination in maize poses significant food and feed safety risks, particularly in regions with variable climatic conditions like Serbia. This study investigated the occurrence of regulated mycotoxins in maize harvested across the Republic of Serbia from 2021 to 2023, emphasizing the impact of climatic factors. A total of 548 samples of unprocessed maize grains were analysed for the presence of key mycotoxins, including aflatoxins, ochratoxin A, zearalenone, deoxynivalenol, fumonisins, and trichothecenes type A (T-2 and HT-2 toxins), using validated analytical methods. The results revealed high contamination frequencies, with aflatoxins and fumonisins being the most prevalent. The results revealed substantial temporal variability and frequent co-contamination of mycotoxins. Aflatoxin B₁ (AFB₁) was the most concerning contaminant, with 73.2% of the samples in 2022 exceeding the European regulatory limit for human consumption (5 µg/kg) for un processed maize grains, reaching peak concentrations of 527 µg/kg, which is 105.4 times higher than the allowed limit. For animal feed, the limit of 20 µg/kg was exceeded in 40.5% of the samples, with the highest concentration being 26.4 times greater than the maximum allowable level. In 2021, the non-compliance rates for AFB₁ in food and feed were 8.3% and 2.3%, respectively, while in 2023, they were 23.2% and 12.2%, respectively. Fumonisins contamination was also high, particularly in 2021, with fumonisin B₁ (FB₁) detected in 87.1% of samples and average concentrations reaching 4532 µg/kg. Although levels decreased in 2023 (70.7% occurrence, average 885 µg/kg), contamination remained significant. Deoxynivalenol (DON) contamination was consistently high (>70% of samples), with peak concentrations of 606 µg/kg recorded in 2021. Zearalenone (ZEN) and ochratoxin A (OTA) occurred less frequently, but ZEN levels peaked in 2022 at 357.6 µg/kg, which is above the regulatory limit of 350 µg/kg for food. Trichothecenes (HT-2 and T-2 toxins) were detected sporadically, with concentrations well below critical thresholds. Co-occurrence of mycotoxins was frequent, with significant mixtures detected, particularly between aflatoxins and fumonisins, as well as other fusarial toxins. The analysis demonstrated that temperature, humidity, and rainfall during both the growing and harvest seasons strongly influenced mycotoxin levels, with the most severe contamination occurring under specific climatic conditions. Notably, the highest mycotoxin levels, like aflatoxins, were linked to warmer temperatures and lower rainfall. The high non-compliance rates for aflatoxins and fumonisins and co-contamination pose significant food and feed safety risks. From a public health perspective, chronic exposure to contaminated maize increases the likelihood of carcinogenesis and reproductive disorders. Reduced productivity and bioaccumulation in animal tissues/products represent serious economic and safety concerns for livestock. This study provides insights into the potential risks to food and feed safety and the need for enhanced regulatory frameworks, continuous monitoring, and mitigation strategies in Serbia as well as other geographical regions. Full article

This study presents a novel method for detecting sleep posture changes—specifically tossing and turning—by monitoring variations in humidity using an array of humidity sensors embedded at regular intervals within a memory-foam pillow. Unlike previous approaches that rely primarily on temperature or pressure sensors, our method leverages the observation that humidity fluctuations are more pronounced during movement, enabling the more sensitive detection of posture changes. We demonstrate that dynamic patterns in humidity data correlate strongly with physical motion during sleep. To identify these transitions, we applied the Pruned Exact Linear Time (PELT) algorithm, which effectively segmented the time series based on abrupt changes in humidity. Furthermore, we converted humidity fluctuation curves into image representations and employed a transfer-learning-based model to classify sleep postures, achieving accurate recognition performance. Our findings highlight the potential of humidity sensing as a reliable modality for non-invasive sleep monitoring. In this study, we propose a novel method for detecting tossing and turning during sleep by analyzing changes in humidity captured by a linear array of sensors embedded in a memory foam pillow. Compared to temperature data, humidity data exhibited more significant fluctuations, which were leveraged to track head movement and infer sleep posture. We applied a rolling smoothing technique and quantified the cumulative deviation across sensors to identify posture transitions. Furthermore, the PELT algorithm was utilized for precise change-point detection. To classify sleep posture, we converted the humidity time series into images and implemented a transfer learning model using a Vision Transformer, achieving a classification accuracy of approximately 96%. Our results demonstrate the feasibility of a sleep posture analysis using only humidity data, offering a non-intrusive and effective approach for sleep monitoring. Full article

Ensuring rapid and efficient evacuation in high-density environments, such as stadiums, is critical for public safety during fire emergencies. Traditional fire alarm systems rely on reactive detection mechanisms, often resulting in delayed response times, increased panic, and overcrowding. This study introduces an AI-driven predictive fire alarm and evacuation model that leverages machine learning algorithms and real-time environmental sensor data to anticipate fire hazards before ignition, improving emergency response efficiency. To detect early fire risk indicators, the system processes data from 62,630 sensor measurements across 15 ecological parameters, including temperature, humidity, total volatile organic compounds (TVOC), CO₂ levels, and particulate matter. A comparative analysis of six machine learning models—Logistic Regression, Support Vector Machines (SVM), Random Forest, and proposed EvacuNet—demonstrates that EvacuNet outperforms all other models, achieving an accuracy of 99.99%, precision of 1.00, recall of 1.00, and an AUC-ROC score close to 1.00. The predictive alarm system significantly reduces false alarm rates and enhances fire detection speed, allowing emergency responders to take preemptive action. Moreover, integrating AI-driven evacuation optimization minimizes bottlenecks and congestion, reduces evacuation times, and improves structured crowd movement. These findings underscore the necessity of intelligent fire detection systems in high-occupancy venues, demonstrating that AI-based predictive modeling can drastically improve fire response and evacuation efficiency. Future research should focus on integrating IoT-enabled emergency navigation, reinforcement learning algorithms, and real-time crowd management systems to further enhance predictive accuracy and minimize casualties. By adopting such advanced technologies, large-scale venues can significantly improve emergency preparedness, reduce evacuation delays, and enhance public safety. Full article

Flood incidents occur annually in Taman Negara Endau Rompin Selai Bekok due to continuous substantial rains during the rainy period. The absence of a structured flood tracking and detection system limits effective information dissemination regarding flooding to the public; currently, visitors are only informed at office counters. This inefficient conventional method should be upgraded to a real time flood monitoring and alert system utilizing Internet of things (IoT) technology. UTHM personnel have requested the development of an easily accessible flood detection system via tablets or smartphones to efficiently relay flood information to visitors. Consequently, a flood detection system called “Floodwatch” was developed. The prototype provides live water level readings, air temperature, humidity, and flood images to users. The prototype has undergone rigorous testing to ensure stability, consistency, and accuracy, enabling its effective utilization. The Floodwatch system aims to enhance safety and awareness during flood events in the Taman Negara Endau Rompin Selai Bekok area. Full article

To address the technical limitations of traditional pavement performance prediction models in capturing temporal features and analyzing multi-factor coupling, this study proposes a Bayesian Optimization Dual-Layer Feature Fusion Model (BO-DLFF). The framework integrates heterogeneous data streams from embedded strain sensors, temperature/humidity monitoring nodes, and weigh-in-motion (WIM) systems, combined with pavement distress detection and historical maintenance records. A dual-stage feature selection mechanism (BP-MIV/RF-RFECV) is developed to identify 12 critical predictors from multi-modal sensor measurements, effectively resolving dimensional conflicts between static structural parameters and dynamic operational data. The model architecture adopts a dual-layer fusion design: the lower layer captures statistical patterns and temporal–spatial dependencies from asynchronous sensor time-series through Local Cascade Ensemble (LCE) ensemble learning and improved TCN-Transformer networks; the upper layer implements feature fusion using a Stacking framework with logistic regression as the meta-learner. BO is introduced to simultaneously optimize network hyperparameters and feature fusion coefficients. The experimental results demonstrate that the model achieves a prediction accuracy of R² = 0.9292 on an 8-year observation dataset, effectively revealing the non-linear mapping relationship between the Pavement Condition Index (PCI) and multi-source heterogeneous features. The framework demonstrates particular efficacy in correlating high-frequency strain gauge responses with long-term performance degradation, providing mechanistic insights into pavement deterioration processes. This methodology advances infrastructure monitoring through the intelligent synthesis of IoT-enabled sensing systems and empirical inspection data. Full article

The detection of hydrogen gas is crucial for both industrial fields, as a green energy carrier, and biomedical applications, where it is a biomarker for diagnosis. TiO₂ nanomaterials are stable and sensitive to hydrogen gas, but their gas response can be negatively affected by external factors such as humidity. Therefore, a strategy is required to mitigate these influences. The utilization of organic–inorganic hybrid gas sensors, specifically metal oxide gas sensors coated with ultra-thin copolymer films, is a relatively novel approach in this field. In this study, we examined the performance and long-term stability of novel TiO₂-based sensors that were coated with poly(trivinyltrimethylcyclotrisiloxane-co-tetrafluoroethylene) (P(V3D3-co-TFE)) co-polymers. The P(V3D3-co-TFE)/TiO₂ hybrid sensors exhibit high reliability even for more than 427 days. They exhibit excellent hydrogen selectivity, particularly in environments with high humidity. An optimum operating temperature of 300 °C to 350 °C was determined. The highest recorded response to H₂ was approximately 153% during the initial set of measurements at a relative humidity of 10%. The developed organic–inorganic hybrid structures open wide opportunities for gas sensor tuning and customization, paving the way for innovative applications in industry and biomedical fields, such as exhaled breath analysis, etc. Full article

The temperature and humidity profiles within the planetary boundary layer (PBL) are crucial for Earth’s climate research. The Atmospheric Sounder Spectrometer by Infrared Spectral Technology (ASSIST) measures downward thermal radiation in the atmosphere with high temporal and spectral resolution continuously during day and night. The physics-based retrieval method, utilizing iterative optimization, can obtain solutions that align with the true atmospheric state. However, the retrieval is typically an ill-posed problem and is affected by noise, necessitating the introduction of regularization. To achieve high-precision detection, a systematic evaluation was conducted on the retrieval performance of temperature and humidity profiles using ASSIST by regularization methods based on the Gauss–Newton framework, which include Fixed regularization factor (FR), L-Curve (LC), Generalized Cross-Validation (GCV), Maximum Likelihood Estimation (MLE), and Iterative Regularized Gauss–Newton (IRGN) methods, and the Levenberg–Marquardt (LM) method based on a damping least squares strategy. A five-day validation experiment was conducted under clear-sky conditions at the Anqing radiosonde station in China. The results indicate that for temperature profile retrieval, the IRGN method demonstrates superior performance, particularly below 1.5 $\mathrm{k}\mathrm{m}$ altitude, where the mean BIAS, mean RMSE, mean Degrees of Freedom for Signal (DFS), and mean residual reach 0.42 $\mathrm{K}$, 0.80 $\mathrm{K}$, 3.37, and $3.01\times {10}^{-13}$ $\left(\mathrm{W}/{\mathrm{c}\mathrm{m}}^2 \mathrm{s}\mathrm{r} {\mathrm{c}\mathrm{m}}^{-1}\right)$, respectively. In contrast, other regularization methods exhibit over-regularization, leading to degraded information content. For humidity profile retrieval, below 1.5 $\mathrm{k}\mathrm{m}$ altitude, the LM method outperforms all regularization-based methods, with the mean BIAS, mean RMSE, mean DFS, and mean residual of 3.65$\%$, 5.62$\%$, 2.05, and $4.36\times {10}^{-12}$ $\left(\mathrm{W}/{\mathrm{c}\mathrm{m}}^2 \mathrm{s}\mathrm{r} {\mathrm{c}\mathrm{m}}^{-1}\right)$, respectively. Conversely, other regularization methods exhibit strong prior dependence, causing retrieval to converge results toward the initial guess. Full article

This study examines runoff variations and their drivers in the Buha and Shaliu Rivers of the Qinghai Lake Basin (1960–2016), a key ecological area in China. Abrupt changes were detected using the Mann–Kendall and cumulative anomaly methods, while the Budyko framework attributed runoff variations to dominant factors. Correlation and grey relational analyses assessed multicollinearity, and a lake water balance model with climate elasticity theory quantified the effects of climate and land surface changes on runoff components and lake levels. Results indicate that the Buha River experienced an abrupt runoff change in 2004, while the Shaliu River exhibited a change beginning in 2003. Based on the trends and abrupt change points of each factor, the study period was divided into four segments: 1960–1993, 1994–2016, 1960–2003, and 2004–2016. The correlation coefficients are significantly different in different periods. The climate elasticity coefficients were as follows: P (precipitation), 1.98; ET₀ (potential evapotranspiration), −0.98; Rn (net radiation), 0.66; T (average temperature), 0.02; U₂ (wind speed at 2 m height), 0.16; RHU (relative umidity), −0.56. The elasticity coefficient of runoff with respect to precipitation is significantly higher than that for other climate variables. Net radiation and relative humidity contribute equally to runoff, while wind speed and temperature have relatively smaller effects. In the Qinghai Lake Basin, runoff is sensitive to precipitation (0.38), potential evapotranspiration (−0.07), and the underlying surface parameter ω (−98.32). Specifically, a 1 mm increase in precipitation raises runoff by 0.38 mm, while a 1 mm rise in potential evapotranspiration reduces it by 0.07 mm. A one-unit increase in ω leads to a significant runoff decrease of 98.32 mm. According to the lake water balance model, climate contributes 88.43% to groundwater runoff, while land surface changes contribute −11.57%. Climate change and land surface changes contribute 93.02% and 6.98%, respectively, to lake water levels. This study quantitatively evaluates the impacts of climate and land surface changes on runoff, providing insights for sustainable hydrological and ecological management in the Qinghai Lake Basin. Full article

Tungsten disulfide (WS₂) is attractive for the development of chemiresistive sensors due to its favorable band gap, as well as its mechanical strength and chemical stability. In this work, we elaborate a procedure for the synthesis of thin films consisting of vertically and/or horizontally oriented WS₂ nanoparticles by sulfurizing nanometer-thick tungsten layers deposited on oxidized silicon substrates using magnetron sputtering. According to X-ray photoelectron spectroscopy and Raman scattering data, WS₂ films grown in an H₂-containing atmosphere at 1000 °C are almost free of tungsten oxide. The WS₂ film’s thickness is controlled by varying the tungsten sputtering duration from 10 to 90 s. The highest response to nitrogen dioxide (NO₂) at room temperature was demonstrated by the film obtained using a tungsten layer sputtered for 30 s. The increased sensitivity is attributed to the high surface-to-volume ratio provided by the horizontal and vertical orientation of the small WS₂ nanoparticles. Based on density functional calculations, we conclude that the small in-plane size of WS₂ provides many high-energy sites for NO₂ adsorption, which leads to greater charge transfer in the sensor. The detection limit of NO₂ calculated for the best sensor (WS₂-30s) is 15 ppb at room temperature and 8 ppb at 125 °C. The sensor can operate in a humid environment and is significantly less sensitive to NH₃ and a mixture of H₂, CO, and CO₂ gases. Full article

The retail industry faces increasing challenges in matching supply with demand due to evolving consumer behaviors, market volatility, and supply chain disruptions. While existing approaches employ statistical and machine learning methods for demand forecasting, they often fail to capture complex temporal dependencies and lack the ability to simultaneously optimize inventory decisions. This paper proposes a novel multi-agent deep reinforcement learning framework that jointly optimizes demand forecasting and inventory management in retail supply chains, leveraging data from IoT sensors, RFID tracking systems, and smart shelf monitoring devices. Our approach combines transformer-based sequence modeling for demand patterns with hierarchical reinforcement learning agents that coordinate inventory decisions across distribution networks. The framework integrates both historical sales data and real-time sensor measurements, employing attention mechanisms to capture seasonal patterns, promotional effects, and environmental conditions detected through temperature and humidity sensors. Through extensive experiments on large-scale retail datasets incorporating sensor network data, we demonstrate that our method achieves 18.2% lower forecast error and 23.5% reduced stockout rates compared with state-of-the-art baselines. The results show particular improvements in handling promotional events and seasonal transitions, where traditional methods often struggle. Our work provides new insights into leveraging deep reinforcement learning for integrated retail operations optimization and offers a scalable solution for modern sensor-enabled supply chain challenges. Full article

Gold nanoparticles–cuprous oxide/reduced graphene oxide/polypyrrole (AuNPs-Cu₂O/rGO/PPy) hybrid nanocomposites were synthesized for surface acoustic wave (SAW) sensors, achieving high sensitivity (2 Hz/ppb), selectivity, and fast response (~2 min) at room temperature. The films, deposited via spin-coating, were characterized by SEM, EDS, and XRD, revealing a rough, wrinkled morphology beneficial for gas adsorption. The sensor showed significant frequency shifts to NH₃, enhanced by AuNPs, Cu₂O, rGO, and PPy. It had a 6.4-fold stronger response to NH₃ compared to CO₂, H₂, and CO, confirming excellent selectivity. The linear detection range was 12–1000 ppb, with a limit of detection (LOD) of 8 ppb. Humidity affected performance, causing negative frequency shifts, and sensitivity declined after 30 days due to resistivity changes. Despite this, the sensor demonstrated excellent NH₃ selectivity and stability across multiple cycles. In simulated breath tests, it distinguished between healthy and patient-like samples, highlighting its potential as a reliable, non-invasive diagnostic tool. Full article

Air quality significantly impacts the environment and human living conditions, with direct and indirect effects on the economy. Precise and prompt detection of air pollutants is crucial for mitigating risks and implementing strategies to control pollution within acceptable thresholds. One of the common pollutants is nitrogen dioxide (NO₂), high concentrations of which are detrimental to the human respiratory system and may lead to serious lung diseases. Unfortunately, reliable NO₂ detection requires sophisticated and expensive apparatus. Although cheap sensors are now widespread, they lack accuracy and stability and are highly sensitive to environmental conditions. The purpose of this study is to propose a novel approach to precise calibration of the low-cost NO₂ sensors. It is illustrated using a custom-developed autonomous platform for cost-efficient NO₂ monitoring. The platform utilizes various sensors alongside electronic circuitry, control and communication units, and drivers. The calibration strategy leverages comprehensive data from multiple reference stations, employing neural network (NN) and kriging interpolation metamodels. These models are built using diverse environmental parameters (temperature, pressure, humidity) and cross-referenced data gathered by surplus NO₂ sensors. Instead of providing direct outputs of the calibrated sensor, our approach relies on predicting affine correction coefficients, which increase the flexibility of the correction process. Additionally, a calibration stage incorporating global correlation enhancement is developed and applied. Demonstrative experiments extensively validate this approach, affirming the platform and calibration methodology’s practicality for reliable and cost-effective NO₂ monitoring, especially keeping in mind that the predictive power of the enhanced sensor (correlation coefficient nearing 0.9 against reference data, RMSE < 3.5 µg/m³) is close to that of expensive reference equipment. Full article

The accuracy of ultrasonic rangefinders is crucial for mobile robotic navigation systems, yet environmental factors such as temperature, humidity, atmospheric pressure, and wind conditions can influence ultrasonic speed in the air. The primary objective is to investigate how environmental factors influence the output signal of an ultrasonic emitter and to develop a method for improving the accuracy of distance measurements in both outdoor and indoor settings. The research employs a combination of theoretical modeling, statistical analysis, and experimental validation. The research employs an ultrasonic rangefinder integrated with environmental sensors (BME280, Bosch Sensortec GmbH, Kusterdingen, Germany) and wind sensors (WMT700, WINDCAP^®, Vaisala Oyj, Vantaa, Finland) to account for environmental influences. Experimental studies were conducted using a prototype ultrasonic rangefinder, and statistical analysis (Student’s t-test) was performed on collected data. The results of estimation by Student’s t-test for 256 measurements demonstrate the maximum effect of air temperature and the minimum effect of relative air humidity on a piezoelectric emitter output signal both outdoors and indoors. In addition, wind parameters affect the rangefinder’s operation. The maximum range of obstacle detection depends on the reflection coefficient of the material that covers the obstacle. The results align with theoretical expectations for highly reflective surfaces. A cascade-forward artificial neural network model was developed to refine distance estimations. This study demonstrates the importance of considering environmental factors in ultrasonic rangefinder systems for mobile robots. By integrating environmental sensors and using statistical analysis, the accuracy of distance measurements can be significantly improved. The results contribute to the development of more reliable navigation systems for mobile robots operating in diverse environments. Full article

This study proposes a novel Transformer-based multimodal fusion framework for grape disease detection, integrating RGB images, hyperspectral data, and environmental sensor readings. Unlike traditional single-modal approaches, the proposed method leverages a Transformer-based architecture to effectively capture spatial, spectral, and environmental dependencies, improving disease detection accuracy under varying conditions. A comprehensive dataset was collected, incorporating diverse lighting, humidity, and temperature conditions, and enabling robust performance evaluation. Experimental results demonstrate that the proposed method outperforms state-of-the-art (SOTA) models, achieving an mAP@50 of 0.94, an mAP@75 of 0.93, Precision of 0.93, and Recall of 0.95, surpassing leading detection baselines. The results confirm that the integration of multimodal information significantly enhances disease detection robustness and generalization, offering a promising solution for real-world vineyard disease management. Full article

As an important means to monitor atmospheric vertical temperature and humidity, the ground-based microwave radiometer has been widely used in environmental monitoring, climate prediction, and other fields, but its application in desert areas is particularly limited. At Minfeng Station on the southern edge of the Taklimakan Desert, Global Telecommunications System (GTS) detection technology was used to evaluate the microwave radiometer observations under different weather conditions and at different altitudes. The planetary boundary layer height (PBLH) was calculated using the potential temperature gradient method, and the planetary boundary layer results were calculated by analyzing dust and rainfall events. The results show that the determination coefficients (R²) of the overall observed temperature (T), specific humidity (q), and water vapor density (${\rho }_v$) of the microwave radiometer are all above 0.8 under different weather conditions. When the relative humidity is 0–10%, the temperature is the best, and the R² is 0.9819. When the relative humidity is 70–80%, the R² of q and ${\rho }_v$ is the best, and the R² is 0.9630 and 0.9777, respectively. This is in good agreement with the temperature observed by the FY–4A satellite; the observation effect is the best in May, and its R² is 0.9142. Under the conditions of clear sky, precipitation day, and dusty weather, the R² of the atmospheric boundary layer height calculated by the microwave radiometer is greater than 0.7 compared to the GTS sounding calculation results. These results demonstrate the reliability of microwave radiometry in extremely arid environments, providing valuable insights for boundary layer studies in desert regions. Full article