Search Results (6,374)

Background: Advanced glycation end products (AGEs), a group of food processing byproducts, have been implicated in the development of various diseases. However, the relationship between circulating AGEs and sleep disorders remains uncertain. Methods: This cross-sectional study elucidated the association of plasma AGEs with sleep disorders among 1732 Chinese adults who participated in the initial visit (2019–2020) of the Tongji–Shenzhen Cohort (TJSZC). Sleep behavior was assessed using self-reported questionnaires and precise accelerometers. Plasma levels of AGEs, including Nε-(Carboxymethyl)lysine (CML), Nε-(Carboxyethyl)lysine (CEL), and Nδ-(5-hydro-5-methyl-4-imidazolone-2-yl)-ornithine (MG-H1), were quantified by ultra-high performance liquid chromatography–tandem mass spectrometry (UPLC-MS/MS). Results: In logistic regression, per IQR increment in individual AGEs was associated with an increased odds ratio of short sleep duration (CML: 1.11 [1.00, 1.23]; CEL: 1.16, [1.04, 1.30]), poor sleep quality (CML: 1.33 [1.10, 1.60]; CEL: 1.53, [1.17, 2.00]; MG-H1: 1.61 [1.25, 2.07]), excessive daytime sleepiness (CML: 1.33 [1.11, 1.60]; MG-H1: 1.39 [1.09, 1.77]), and insomnia (CML: 1.29 [1.05, 1.59]). Furthermore, in weighted quantile sum regression and Bayesian kernel machine regression analyses, elevated overall exposure levels of plasma AGEs were associated with an increased risk of sleep disorders, including short sleep duration, poor sleep quality, excessive daytime sleepiness, and insomnia, with CML being identified as the leading contributor. Insufficient vegetable intake and higher dietary fat intake was associated with an increase in plasma CEL. Conclusions: These findings support a significant association between plasma AGEs and sleep disorders, indicating that AGEs may adversely influence sleep health and reducing the intake of AGEs may facilitate preventing and ameliorating sleep disorders. Full article

The detection of ship fires is a critical aspect of maritime safety and surveillance, demanding high accuracy in both identification and response mechanisms. However, the scarcity of ship fire images poses a significant challenge to the development and training of effective machine learning models. This research paper addresses this challenge by exploring advanced data augmentation techniques aimed at enhancing the training datasets for ship and ship fire detection. We have curated a dataset comprising ship images (both fire and non-fire) and various oceanic images, which serve as target and source images. By employing diverse image blending methods, we randomly integrate target images of ships with source images of oceanic environments under various conditions, such as windy, rainy, hazy, cloudy, or open-sky scenarios. This approach not only increases the quantity but also the diversity of the training data, thus improving the robustness and performance of machine learning models in detecting ship fires across different contexts. Furthermore, we developed a Gradio web interface application that facilitates selective augmentation of images. The key contribution of this work is related to object extraction-based blending. We propose basic and advanced data augmentation techniques while applying blending and selective randomness. Overall, we cover eight critical steps for dataset creation. We collected 9200 ship fire and 4100 ship non-fire images. From the images, we augmented 90 ship fire images with 13 background images and achieved 11,440 augmented images. To test the augmented dataset performance, we trained Yolo-v8 and Yolo-v10 models with “Fire” and “No-fire” augmented ship images. In the Yolo-v8 case, the precision-recall curve achieved 96.6% (Fire), 98.2% (No-fire), and 97.4% mAP score achievement in all classes at a 0.5 rate. In Yolo-v10 model training achievement, we got 90.3% (Fire), 93.7 (No-fire), and 92% mAP score achievement in all classes at 0.5 rate. In comparison, both trained models’ performance is outperforming other Yolo-based SOTA ship fire detection models in overall and mAP scores. Full article

The sustainable management of energy sources such as wind plays a crucial role in supplying electricity for both residential and industrial purposes. For this, accurate wind data are essential to bring sustainability in energy output estimations for wind stations. The choice of an appropriate distribution function significantly affects the actual wind data, directly influencing the estimated energy output. While the Weibull function is commonly used to describe wind speed at various locations worldwide, the variability of weather information across wind sites varies significantly. Probabilistic forecasting offers comprehensive probability information for renewable generation and load, assisting decision-making in power systems under uncertainty. Traditional probabilistic forecasting techniques based on machine learning (ML) rely on prediction uncertainty derived from previous distributional assumptions. This study utilized a Bayesian Recurrent Neural Network (BNN-RNN), incorporating prior distributions for weight variables in the RNN network layer and extending the Bayesian networks. Initially, a periodic RNN processes data for wind energy prediction, capturing trends and correlation characteristics in time-series data to enable more accurate and reliable energy production forecasts. Subsequently, the wind power meteorological dataset was analyzed using the reciprocal entropy approach to reduce dimensionality and eliminate variables with weak connections, thereby simplifying the structure of the prediction model. The BNN-RNN prediction model integrates inputs from RNN-transformed time-series data, dimensionality-reduced weather information, and time categorization feature data. The Winkler index is lower by 3.4%, 32.6%, and 7.2%, respectively, and the overall index of probability forecasting pinball loss is reduced by 51.2%, 22.3%, and 10.7%, respectively, compared with all three approaches. The implications of this study are significant, as they demonstrate the potential for more accurate wind energy forecasting through Bayesian optimization. These findings contribute to more precise decision-making and bring sustainability to the effective management of energy systems by proposing a Bayesian Recurrent Neural Network (BNN-RNN) to improve wind energy forecasts. The model further enhances future estimates of wind energy generation, considering the stochastic nature of meteorological data. The study is crucial in increasing the understanding and application of machine learning by establishing how Bayesian optimization significantly improves probabilistic forecasting models that would revolutionize sustainable energy management. Full article

Early hospital readmission refers to unplanned emergency admission of patients within 30 days of discharge. Predicting early readmission risk before discharge can help to reduce the cost of readmissions for hospitals and decrease the death rate for Intensive Care Unit patients. In this paper, we propose a novel approach for prediction of unplanned hospital readmissions using discharge notes from the MIMIC-III database. This approach is based on first extracting relevant information from clinical reports using a pretrained Named Entity Recognition model called BioMedical-NER, which is built on Bidirectional Encoder Representations from Transformers architecture, with the extracted features then used to train machine learning models to predict unplanned readmissions. Our proposed approach achieves better results on clinical reports compared to the state-of-the-art methods, with an average precision of 88.4% achieved by the Gradient Boosting algorithm. In addition, explainable Artificial Intelligence techniques are applied to provide deeper comprehension of the predictive results. Full article

The early detection accuracy of early gastric cancer (EGC) determines the choice of the optimal treatment strategy and the related medical expenses. We aimed to develop a simple, affordable, and time-saving diagnostic model using six machine learning (ML) algorithms for the diagnosis of EGC. It is based on the endoscopy-based Kyoto classification score obtained after the completion of endoscopy and other clinical features obtained after medical consultation. We retrospectively evaluated 1999 patients who underwent gastrointestinal endoscopy at the China Beijing Hospital. Of these, 203 subjects were diagnosed with EGC. The data were randomly divided into training and test sets (ratio 4:1). We constructed six ML models, and the developed models were evaluated on the testing set. This procedure was repeated five times. The Kolmogorov–Arnold Networks (KANs) model achieved the best performance (mean AUC value: 0.76; mean balanced accuracy: 70.96%; mean precision: 58.91%; mean recall: 70.96%; mean false positive rate: 26.11%; mean false negative rate: 31.96%; and mean F1 score value: 58.46). The endoscopy-based Kyoto classification score was the most important feature with the highest feature importance score. The results suggest that the KAN model, the optimal ML model in this study, has the potential to identify EGC patients, which may result in a reduction in both the time cost and medical expenses in clinical practice. Full article

This paper introduces a single LED and four photodetectors (PDs) as a visible light system structure and collects the received signal strength values and corresponding physical coordinates at the PD receiving end, establishing a comprehensive dataset. The K-means clustering algorithm is employed to separate the room into center and boundary areas through the fingerprint database. The bald eagle search (BES) algorithm is employed to optimize the initial parameters, specifically the weights and thresholds, in the extreme learning machine (ELM) neural network, and the BES–ELM indoor positioning model is established by region to improve positioning accuracy. Due to the impact exerted by the ambient environment, there are fluctuations in the positioning accuracy of the center and edge regions, and the positioning of the edge region needs to be further improved. To address this, it is proposed to use the enhanced weighted K-nearest neighbor (EWKNN) algorithm based on the BES–ELM neural network to correct the prediction points with higher-than-average positioning errors, achieving precise edge positioning. The simulation demonstrates that within an indoor space measuring 5 m × 5 m × 3 m, the algorithm achieves an average positioning error of 2.93 cm, and the positioning accuracy is improved by 86.07% relative to conventional BP neural networks. Full article

As freshwater supplies decrease, adopting sustainable practices like water- and energy-efficient irrigation is crucial, particularly in resource-constrained regions. Here, farmers often cannot purchase precision irrigation equipment, which achieves high water and energy efficiencies via full automation. Currently, no irrigation methods exist that combine automatic scheduling of events with manual operation of valves, familiar hardware on low-income farms. This work synthesizes functional requirements for a tool that could address efficiency needs while integrating into current manual practices. Then, a design concept for an automatic scheduling and manual operation (AS-MO) human–machine interaction (HMI) that meets these requirements is proposed. Two design stages of the AS-MO HMI were evaluated by farmers and market stakeholders in three countries. Results show that farmers in Kenya and Jordan valued the proposed AS-MO HMI because they could increase efficiency on their farms without the cost or complexity of automatic valves. In Morocco, a possible market was found, but a majority of participants preferred full automation. Interviewees provided feedback on how to improve the tool’s design in future iterations. If adopted at scale, the proposed AS-MO tool could increase efficiency on farms that otherwise cannot afford current precision irrigation technology, improving sustainable agriculture worldwide. Full article

Additive Manufacturing (AM) is a pivotal technology for transforming complex geometries with minimal tooling requirements. Among the several AM techniques, Wire Arc Additive Manufacturing (WAAM) is notable for its ability to produce large metal components, which makes it particularly appealing in the aerospace sector. However, precise control of the bead geometry, specifically bead width and height, is essential for maintaining the structural integrity of WAAM-manufactured parts. This paper introduces a methodology using a Deep Neural Network (DNN) model for forecasting the bead geometry in the WAAM process, focusing on gas metal arc welding cold metal transfer (GMAW-CMT) WAAM. This study addresses the challenges of bead geometry prediction by developing a robust predictive framework. Key process parameters, such as the wire travel speed, wire feed rate, and bead dimensions of the previous layer, were monitored using a Coordinate Measuring Machine (CMM) to ensure precision. The collected data were used to train and validate various regression models, including linear regression, ridge regression, regression, polynomial regression (Quadratic and Cubic), Random Forest, and a custom-designed DNN. Among these, the Random Forest and DNN models were particularly effective, with the DNN showing significant accuracy owing to its ability to learn complex nonlinear relationships inherent in the WAAM process. The DNN model architecture consists of multiple hidden layers with varying neuron counts, trained using backpropagation, and optimized using the Adam optimizer. The model achieved mean absolute percentage error (MAPE) values of 0.014% for the width and 0.012% for the height, and root mean squared error (RMSE) values of 0.122 for the width and 0.153 for the height. These results highlight the superior capability of the DNN model in predicting bead geometry compared to other regression models, including the Random Forest and traditional regression techniques. These findings emphasize the potential of deep learning techniques to enhance the accuracy and efficiency of WAAM processes. Full article

Pine wilt disease (PWD) is a severe forest disease caused by the invasion of pine wood nematode (Bursaphelenchus xylophilus), which has caused significant damage to China’s forestry resources due to its short disease cycle and strong infectious ability. Benefiting from the development of unmanned aerial vehicle (UAV)-based remote sensing technology, the use of UAV images for the detection of PWD-infected trees has become one of the mainstream methods. However, current UAV-based detection studies mostly focus on multispectral and hyperspectral images, and few studies have focused on using red–green–blue (RGB) images for detection. This study used UAV-based RGB images to extract feature information using different color space models and then utilized semantic segmentation techniques in deep learning to detect individual PWD-infected trees. The results showed that: (1) The U-Net model realized the optimal image segmentation and achieved the highest classification accuracy with F1-score, recall, and Intersection over Union (IoU) of 0.9586, 0.9553, and 0.9221, followed by the DeepLabv3+ model and the feature pyramid networks (FPN) model. (2) The RGBHSV feature scheme outperformed both the RGB feature scheme and the hue saturation value (HSV) feature scheme, which were unrelated to the choice of the semantic segmentation techniques. (3) The semantic segmentation techniques in deep-learning models achieved superior model performance compared with traditional machine-learning methods, with the U-Net model obtaining 4.81% higher classification accuracy compared with the random forest model. (4) Compared to traditional semantic segmentation models, the newly proposed segment anything model (SAM) performed poorly in identifying pine wood nematode disease. Its success rate is 0.1533 lower than that of the U-Net model when using the RGB feature scheme and 0.2373 lower when using the HSV feature scheme. The results showed that the U-Net model using the RGBHSV feature scheme performed best in detecting individual PWD-infected trees, indicating that the proposed method using semantic segmentation technique and UAV-based RGB images to detect individual PWD-infected trees is feasible. The proposed method not only provides a cost-effective solution for timely monitoring forest health but also provides a precise means to conduct remote sensing image classification tasks. Full article

Molybdenum is an important material in modern industry, widely used in extreme environments such as rocket engine nozzles and microelectrodes due to its high melting point, excellent mechanical properties, and thermal conductivity. However, as a difficult-to-machine metal, traditional machining methods struggle to achieve the desired microstructures in molybdenum. Electrochemical machining (ECM) offers unique advantages in manufacturing fine structures from hard-to-machine metals. Studies have shown that molybdenum exhibits a fast corrosion rate in alkaline or acidic solutions, posing significant environmental pressure. Therefore, this study investigates the electrochemical machining of molybdenum in neutral salt solutions to achieve high-precision microstructure fabrication. First, the polarization curves and electrochemical impedance spectroscopy (EIS) of molybdenum in NaNO3 solutions of varying concentrations were measured to determine its electrochemical reaction characteristics. The results demonstrate that molybdenum exhibits good electrochemical reactivity in NaNO3 solutions, leading to favorable surface erosion morphology. Subsequently, a mask electrochemical machining technique was employed to fabricate arrayed microstructures on the molybdenum surface. To minimize interference between factors, an orthogonal experiment was used to optimize the parameter combination, determining the optimal machining process parameters. Under these optimal conditions, an array of micro-groove structures was successfully fabricated with an average groove width of 110 μm, a depth-to-width ratio of 0.21, an aspect ratio of 9000, and a groove width error of less than 5 μm. Full article

Fractional vegetation cover (FVC) is an essential metric forvaluating ecosystem health and soil erosion. Traditional ground-measuring methods are inadequate for large-scale FVC monitoring, while remote sensing-based estimation approaches face issues such as spatial scale discrepancies between ground truth data and image pixels, as well as limited sample representativeness. This study proposes a method for FVC estimation integrating uncrewed aerial vehicle (UAV) and satellite imagery using machine learning (ML) models. First, we assess the vegetation extraction performance of three classification methods (OBIA-RF, threshold, and K-means) under UAV imagery. The optimal method is then selected for binary classification and aggregated to generate high-accuracy FVC reference data matching the spatial resolutions of different satellite images. Subsequently, we construct FVC estimation models using four ML algorithms (KNN, MLP, RF, and XGBoost) and utilize the SHapley Additive exPlanation (SHAP) method to assess the impact of spectral features and vegetation indices (VIs) on model predictions. Finally, the best model is used to map FVC in the study region. Our results indicate that the OBIA-RF method effectively extract vegetation information from UAV images, achieving an average precision and recall of 0.906 and 0.929, respectively. This method effectively generates high-accuracy FVC reference data. With the improvement in the spatial resolution of satellite images, the variability of FVC data decreases and spatial continuity increases. The RF model outperforms others in FVC estimation at 10 m and 20 m resolutions, with R² values of 0.827 and 0.929, respectively. Conversely, the XGBoost model achieves the highest accuracy at a 30 m resolution, with an R² of 0.847. This study also found that FVC was significantly related to a number of satellite image VIs (including red edge and near-infrared bands), and this correlation was enhanced in coarser resolution images. The method proposed in this study effectively addresses the shortcomings of conventional FVC estimation methods, improves the accuracy of FVC monitoring in soil erosion areas, and serves as a reference for large-scale ecological environment monitoring using UAV technology. Full article

Coordinate measuring machines (CMMs) are utilized to acquire coordinate data from manufactured surfaces for inspection reasons. These data are employed to gauge the geometric form errors associated with the surface. An optimization procedure of fitting a substitute surface to the measured points is applied to assess the form error. Since the traditional least-squares approach is susceptible to overestimation, it leads to unreasonable rejections. This paper implements a modified differential evolution (DE) algorithm to estimate the minimum zone femoral head sphericity. In this algorithm, opposition-based learning is considered for population initialization, and an adaptive scheme is enacted for scaling factor and crossover probability. The coefficients of the correlation factor and the uncertainty propagation are also measured so that the result’s uncertainty can be determined. Undoubtedly, the credibility and plausibility of inspection outcomes are strengthened by evaluating measurement uncertainty. Several data sets are used to corroborate the outcome of the DE algorithm. CMM validation shows that the modified DE algorithm can measure sphericity with high precision and consistency. This algorithm allows for an adequate initial solution and adaptability to address a wide range of industrial problems. It ensures a proper balance between exploitation and exploration capabilities. Thus, the suggested methodology, based on the computational results, is feasible for the online deployment of the sphericity evaluation. The adopted DE strategy is simple to use, has few controlling variables, and is computationally less expensive. It guarantees a robust solution and can be used to compute different form errors. Full article

Novel cancer biomarkers discoveries are driven by the application of omics technologies. The vast quantity of highly dimensional data necessitates the implementation of feature selection. The mathematical basis of different selection methods varies considerably, which may influence subsequent inferences. In the study, feature selection and classification methods were employed to identify six signature gene sets of grade 2 and 3 astrocytoma samples from the Rembrandt repository. Subsequently, the impact of these variables on classification and further discovery of biological patterns was analysed. Principal component analysis (PCA), uniform manifold approximation and projection (UMAP), and hierarchical clustering revealed that the data set (10,096 genes) exhibited a high degree of noise, feature redundancy, and lack of distinct patterns. The application of feature selection methods resulted in a reduction in the number of genes to between 28 and 128. Notably, no single gene was selected by all of the methods tested. Selection led to an increase in classification accuracy and noise reduction. Significant differences in the Gene Ontology terms were discovered, with only 13 terms overlapping. One selection method did not result in any enriched terms. KEGG pathway analysis revealed only one pathway in common (cell cycle), while the two methods did not yield any enriched pathways. The results demonstrated a significant difference in outcomes when classification-type algorithms were utilised in comparison to mixed types (selection and classification). This may result in the inadvertent omission of biological phenomena, while simultaneously achieving enhanced classification outcomes. Full article

This paper comprehensively explores the development of a standalone and compact microwave sensing system tailored for automated radio frequency (RF) scattered parameter acquisitions. Coupled with an emitting RF device (antenna, resonator, open waveguide), the system could be used for non-invasive monitoring of external matter or latent environmental variables. Central to this design is the integration of a NanoVNA and a Raspberry Pi Zero W platform, allowing easy recording of S-parameters (scattering parameters) in the range of the 50 kHz–$4.4$ GHz frequency band. Noteworthy features include dual recording modes, manual for on-demand acquisitions and automatic for scheduled data collection, powered seamlessly by a single battery source. Thanks to the flexibility of the system’s architecture, which embeds a Linux operating system, we can easily embed machine learning (ML) algorithms and predictive models for information detection. As a case study, the potential application of the integrated sensor system with an RF patch antenna is explored in the context of greenwood hydration detection within the field of smart agriculture. This innovative system enables non-invasive monitoring of wood hydration levels by analyzing scattering parameters (S-parameters). These S-parameters are then processed using ML techniques to automate the monitoring process, enabling real-time and predictive analysis of moisture levels. Full article

This study develops a hybrid machine learning (ML) algorithm integrated with IoT technology to improve the accuracy and efficiency of soil monitoring and tomato crop disease prediction in Anakapalle, a south Indian station. An IoT device collected one-minute and critical soil parameters—humidity, temperature, pH values, nitrogen (N), phosphorus (P), and potassium (K), during the vegetative growth stage, which are essential for assessing soil health and optimizing crop growth. Kendall’s correlations were computed to rank these parameters for utilization in hybrid ML techniques. Various ML algorithms including K-nearest neighbors (KNN), support vector machines (SVM), decision tree (DT), random forest (RF), and logistic regression (LR) were evaluated. A novel hybrid algorithm, ‘Bayesian optimization with KNN’, was introduced to combine multiple ML techniques and enhance predictive performance. The hybrid algorithm demonstrated superior results with 95% accuracy, precision, and recall, and an F1 score of 94%, while individual ML algorithms achieved varying results: KNN (80% accuracy), SVM (82%), DT (77%), RF (80%), and LR (81%) with differing precision, recall, and F1 scores. This hybrid ML approach proved highly effective in predicting tomato crop diseases in natural environments, underscoring the synergistic benefits of IoT and advanced ML techniques in optimizing agricultural practices. Full article