Search Results (3,934)

This paper addresses the challenges of low accuracy and long transfer learning time in small-sample bearing fault diagnosis, which are often caused by limited samples, high noise levels, and poor feature extraction. We propose a method that combines an improved capsule network with a Siamese neural network. Multi-view data partitioning is used to enrich data diversity, and Markov transformation converts one-dimensional vibration signals into two-dimensional images, enhancing the visualization of signal features. The dynamic routing mechanism of the capsule network effectively captures and integrates key fault features, improving the model’s feature representation and robustness. The Siamese network shares weights to optimize feature matching, while SKNet dynamically adjusts feature fusion to enhance generalization performance. By integrating the Siamese neural network with SKNet, we improve transfer efficiency, reduce the number of parameters, and lighten the model to reduce complexity and shorten transfer time. Experimental results demonstrate that this method can accurately identify faults under conditions of limited samples and high noise, thereby improving diagnostic accuracy and reducing transfer time. Full article

Circulating immunoglobulin G (IgG) concentrations in newborn goat kids are not sufficient to protect the animal against external agents. Therefore, consumption of colostrum, rich in immune components, shortly after birth is crucial. Traditional laboratory methods used to measure IgG concentrations, such as ELISA or RID, are reliable but costly and impractical for many farmers. This study proposes a more accessible alternative for farmers to predict IgG concentration in goat colostrum by integrating color-based techniques with machine learning models, specifically decision trees and neural networks, through the development of two regression models based on colostrum color data from Majorera dairy goats. A total of 813 colostrum samples were collected in a previous study (June 1997–April 2003) that utilized multiple regression analysis as a reference to verify that applying data science techniques improves accuracy and reliability. The decision tree model outperformed the neural network, achieving higher accuracy and lower error rates. Both models provided predictions that closely matched IgG concentrations obtained by ELISA. Therefore, this methodology offers a practical and affordable solution for the on-farm assessment of colostrum quality (i.e., IgG concentration). This approach could significantly improve farm management practices, ensuring better health outcomes in newborn animals by facilitating timely and accurate colostrum quality evaluation. Full article

Background: Adolescents in foster care endure frequent disruptive transitions, often culminating in discharge to independent living rather than reunification or adoption. Former foster youth fare poorly once on their own, with high rates of homelessness and social disconnection. This study explored the use of the Bridges Transitions Framework near the end of placement to help youth cope with the transition to adulthood. Methods: In this exploratory study, the framework was integrated into a foster agency’s programming; then, we assessed outcomes using administrative data and youth interviews. Thirty-five youth participated. Status of employment, education, and social support was collected 18 months after exposure to the framework. Results: The participants reported moderate to high levels of social support, which is often limited or absent among foster care leavers. Relative to rates reported in state-level foster care data, participants had substantially higher rates of school enrollment after discharge. With very few empirically assessed models available for this population that specifically address internal coping with such substantial life changes, the Transitions Framework offers a tool that may help foster youth navigate aging out of care. Securing lasting and meaningful social support and employment and completing education remain elusive for former foster youth. Conclusions: To confirm the utility of the Transitions Framework, it is recommended to assess it with a large sample and matched comparison group over time. Full article

Extraction of dense 3D geographic information from ultra-high-resolution unmanned aerial vehicle (UAV) imagery unlocks a great number of mapping and monitoring applications. This is facilitated by a step called dense image matching, which tries to find pixels corresponding to the same object within overlapping images captured by the UAV from different locations. Recent developments in deep learning utilize deep convolutional networks to perform this dense pixel correspondence task. A common theme in these developments is to train the network in a supervised setting using available dense 3D reference datasets. However, in this work we propose a novel unsupervised dense point cloud extraction routine for UAV imagery, called UnDER. We propose a novel disparity-shifting procedure to enable the use of a stereo matching network pretrained on an entirely different typology of image data in the disparity-estimation step of UnDER. Unlike previously proposed disparity-shifting techniques for forming cost volumes, the goal of our procedure was to address the domain shift between the images that the network was pretrained on and the UAV images, by using prior information from the UAV image acquisition. We also developed a procedure for occlusion masking based on disparity consistency checking that uses the disparity image space rather than the object space proposed in a standard 3D reconstruction routine for UAV data. Our benchmarking results demonstrated significant improvements in quantitative performance, reducing the mean cloud-to-cloud distance by approximately 1.8 times the ground sampling distance (GSD) compared to other methods. Full article

The accurate calibration of snow parameters is necessary to establish an accurate simulation model of snow, which is generally used to study tire–snow interaction. In this paper, an innovative parameter inversion method based on in situ test results is proposed to calibrate the snow parameters, which avoids the damage to the mechanical properties of snow when making test samples using traditional test methods. A coupled Eulerian–Lagrangian (CEL) model of plate loading in snow was established; the sensitivity of snow parameters to the macroscopic load–sinkage relationship was studied; a plate-loading experiment was carried out; and the parameters of snow at the experimental site were inverted. The parameter inversion results from the snow model were verified by the experimental test results of different snow depths and different plate sizes. The results show the following: (1) The material cohesive, angle of friction, and hardening law of snow have great influence on the load–sinkage relationship of snow, the elastic modulus has a great influence on the unloading/reloading stiffness of snow, and the influence of density and Poisson’s ratio on the load–sinkage relationship can be ignored. (2) The correlation coefficient between the inversion result and the matching test data is 0.979, which is 0.304 higher than that of the initial inversion curve. (3) The load–sinkage relationship of snow with different snow depths and plate diameters was simulated by using the model parameter of inversion, and the results were compared with the experimental results. The minimum correlation coefficient was 0.87, indicating that the snow parameter inversion method in this paper can calibrate the snow parameters of the test site accurately. Full article

Urban forests, as vital components of green infrastructure, provide essential ecosystem services (ESs) that support urban sustainability. However, rapid urban expansion and increased density threaten these forests, creating significant imbalances between the supply and demand for these services. Understanding the characteristics of ecosystem services and reasonably dividing ecological management zones are crucial for promoting sustainable urban development. This study introduces an innovative ecological management zoning framework based on the matching degree and synergies relationships of ESs. Focusing on Fuzhou’s fourth ring road area in China, data from 1038 urban forest sample plots were collected using mobile LIDAR. By integrating the i-Tree Eco model and Kriging interpolation, we assessed the spatial distribution of four key ESs—carbon sequestration, avoided runoff, air purification, and heat mitigation—and analyzed their supply–demand relationships and synergies. Based on these ecological characteristics, we employed unsupervised machine learning classification to identify eight distinct ecological management zones, each accompanied by targeted recommendations. Key findings include the following: (1) ecosystem services of urban forests in Fuzhou exhibit pronounced spatial heterogeneity, with clearly identifiable high-value and low-value areas of significant statistical relevance; (2) heat mitigation, avoided runoff, and air purification services all exhibit synergistic effects, while carbon sequestration shows trade-offs with the other three services in high-value areas, necessitating targeted optimization; (3) eight ecological management zones were identified, each with unique ecological characteristics. This study offers precise spatial insights into Fuzhou’s urban forests, providing a foundation for sustainable ecological management strategies. Full article

Leaf chlorophyll content (LCC) and leaf area index (LAI) are crucial for rice growth and development, serving as key parameters for assessing nutritional status, growth, water management, and yield prediction. This study introduces a novel canopy radiative transfer model (RTM) by coupling the radiation transfer model for rice leaves (RPIOSL) and unified BRDF model (UBM) models, comparing its simulated canopy hyperspectra with those from the PROSAIL model. Characteristic wavelengths were extracted using Sobol sensitivity analysis and competitive adaptive reweighted sampling methods. Using these wavelengths, rice phenotype estimation models were constructed with back propagation neural network (BPNN), extreme learning machine (ELM), and broad learning system (BLS) methods. The results indicate that the RPIOSL-UBM model’s hyperspectra closely match measured data in the 500–650 nm and 750–1000 nm ranges, reducing the root mean square error (RMSE) by 0.0359 compared to the PROSAIL model. The ELM-based models using the RPIOSL-UBM dataset proved most effective for estimating the LAI and LCC, with RMSE values of 0.6357 and 6.0101 μg · cm⁻², respectively. These values show significant improvements over the PROSAIL dataset models, with RMSE reductions of 0.1076 and 6.3297 μg · cm⁻², respectively. The findings demonstrate that the proposed model can effectively estimate rice phenotypic parameters from UAV-measured hyperspectral data, offering a new approach to assess rice nutritional status and enhance cultivation efficiency and yield. This study underscores the potential of advanced modeling techniques in precision agriculture. Full article

Objective: Polycystic ovary syndrome (PCOS) is a prevalent metabolic disorder with an increased risk for cardiovascular disease (CVD) that is enhanced by obesity. This study sought to determine whether a panel of cardiovascular risk proteins (CVRPs) would be dysregulated in overweight/obese PCOS patients, highlighting potential biomarkers for CVD in PCOS. Methods: In this exploratory cross-sectional study, plasma levels of 54 CVRPs were analyzed in women with PCOS (n = 147) and controls (n = 97). CVRPs were measured using the SOMAscan proteomic platform (version 3.1), with significant proteins identified through linear models, regression analysis, and receiver operating characteristic (ROC) analysis. Analysis on BMI-matched subsets of the cohort were undertaken. Functional enrichment and protein–protein interaction analyses elucidated the pathways involved. Results: Eleven CVRPs were dysregulated in PCOS (whole set, without matching for body mass index (BMI) or insulin resistance (IR)): leptin, Interleukin-1 receptor antagonist protein (IL-1Ra), polymeric immunoglobulin receptor (PIGR), interleukin-18 receptor (IL-18Ra), C-C motif chemokine 3 (MIP-1a), and angiopoietin-1 (ANGPT1) were upregulated whilst advanced glycosylation end product-specific receptor, soluble (sRAGE), bone morphogenetic protein 6 (BMP6); growth/differentiation factor 2 (GDF2), superoxide dismutase [Mn] mitochondrial (MnSOD), and SLAM family member 5 (SLAF5) were downregulated versus the controls. In BMI-matched (overweight/obese, BMI ≥ 26 kg/m²) subset analysis, six CVRPs were common to the whole set: ANGPT1 and IL-1Ra were upregulated; and sRAGE, BMP6, GDF2, and Mn-SOD were downregulated. In addition, lymphotactin (XCL1) was upregulated and placenta growth factor (PIGF), alpha-L-iduronidase (IDUA), angiopoietin-1 receptor, and soluble (sTie-2) and macrophage metalloelastase (MMP12) were downregulated. A subset analysis of BMI-matched plus insulin resistance (IR)-matched women revealed only upregulation of tissue factor (TF) and renin in PCOS, potentially serving as biomarkers for cardiovascular risk in overweight/obese women with PCOS. Conclusions: A combination of upregulated obesity-related CVRPs (ANGPT1/IL/1Ra/XCL1) and downregulated cardioprotective proteins (sRAGE/BMP6/Mn-SOD/GDF2) in overweight/obese PCOS women may contribute to the increased risk for CVD. TF and renin upregulation observed in the BMI- and IR-matched limited sample PCOS subgroup indicates their potential risk of CVD. Full article

We tested a scanning electron microscope equipped with the newly developed Unity-BEX detector (SEM-BEX) system to study thirty-nine samples of the testate amoeba Difflugia. This produces fast single-scan backscattered (BSE) and combined elemental X-ray maps of selected areas, resulting in high-resolution data-rich composite colour X-ray and combined BSE maps. Using a suitably user-defined elemental X-ray colour palette, minerals such as orthoclase, albite, quartz and mica were highlighted in blue, purple, magenta and green, respectively. Imaging was faster than comparable standard energy dispersive X-ray (EDX) analysis, of high quality, and did not suffer from problems associated with the analysis of rough surfaces by EDX, such as shadowing effects or working distance versus X-ray yield artifacts. In addition, we utilised the AZtecMatch v.6.1 software package to test its utility in identifying the mineral phases present on the Difflugia tests. Significantly, it was able to identify many minerals present but would require some further development due to the small size/thinness of many of the minerals analysed. The latter would also be further improved by the development of a bespoke mineral library based on actual collected X-ray data rather than based simply on stoichiometry. The investigation illustrates that in the case of the current material, minerals are preferentially selected and arranged on the test based upon their mineralogy and size, and likely upon inherent properties such as structural strength/flexibility and specific gravity. As with previous studies, mineral usage is ultimately controlled by source availability and therefore may be of limited taxonomic significance, although of value in areas such as palaeoenvironmental reconstruction. Full article

Background: Temporomandibular disorders (TMDs) represent a significant public health issue, among which masticatory muscle pain is the most common. Current publications increasingly indicate surface electromyography (sEMG) as an effective diagnostic tool for muscle dysfunctions that may be employed in TMDs recognition. The objective of this study was to establish reference ranges for TMDs patients with masticatory muscle pain and healthy individuals in the electromyographic Functional Clenching Index (FCI) for the temporalis muscles (TAs) and masseter muscles (MMs). This research aimed to provide an additional diagnostic tool for TMDs patients. Methods: A total of 48 individuals (n = 30 women and n = 18 men) with the muscular painful form of TMDs were recruited alongside a numerically and gender-matched control group—healthy, pain-free controls. The Functional Clenching Indexwas calculated for both groups. Results: Data analysis revealed statistically significant differences with a very large effect size. Healthy individuals had higher FCI scores compared to those with TMDs. The healthy group exhibited higher threshold values compared to the TMDs group. Conclusions: For healthy individuals, the FCI ranges for TAs were between 58 and 145, while for MMs, between 72 and 210. Lower values may indicate muscle activation disorders and occur in patients with the painful, muscular form of TMDs. This is the first study to define reference ranges for electromyographic indices; therefore, caution is recommended, and the replication of this study on a larger and more culturally diverse sample is advised. Full article

Background and Objectives: The relationship between pregnancy complications and the risk of gynecological and breast cancer remains inconclusive, with limited research available. This study aimed to determine whether pregnancy complications, including preeclampsia, gestational diabetes mellitus (GDM), large for gestational age (LGA), or intrauterine growth restriction (IUGR) are associated with the development of endometrial cancer (EC), ovarian cancer (OC), or breast cancer (BC). Materials and Methods: This was a population-based case–control study linked to the National Health Insurance Research Database from 2008 to 2020, using ICD codes to identify parous gynecological cases (n = 6714). The propensity score matching method was used to match control groups (n = 1,153,346). Multivariable logistic regression models were used to determine the association between EC, OC, BC risk and pregnancy complications. Results: In adjusted multivariable logistic regression models, women with a history of preeclampsia did not have a significantly increased risk of endometrial, ovarian, or breast cancer compared to controls. Although women with GDM complications had a significantly increased risk of breast cancer, the increased risk of EC or OC was not significant. The risk of BC in women with a history of IUGR or LGA was not significant, whereas risk statistics for EC or OC in women with a history of IUGR or LGA could not be shown because of the small sample size. Conclusions: GDM is associated with BC risk. Future studies should aim to determine whether there is a causal relationship. Therefore, cancer screening is warranted in women with GDM. Full article

Candlestick charts provide a visual representation of price trends and market sentiment, enabling investors to identify key trends, support, and resistance levels, thus improving the success rate of stock trading. The research presented in this paper aims to overcome the limitations of traditional candlestick pattern analysis, which is constrained by fixed pattern definitions, quantity limitations, and subjectivity in pattern recognition, thus improving its effectiveness in dynamic market environments. To address this, a two-layer clustering method based on a candlestick sequence simlarity matching model is proposed for identifying valid candlestick patterns and constructing a pattern library. First, the candlestick sequence similarity matching model is used to address the pattern matching issue; then, a two-layer clustering method based on the K-means algorithm is designed to identify valid candlestick patterns. Finally, a valid candlestick pattern library is built, and the predictive ability and profitability of some patterns in the library are evaluated. In this study, ten stocks from different industries and of various sizes listed on the Shanghai Stock Exchange were selected, using nearly 1000 days of their data as the test set. The predictive ability of some patterns in the library was evaluated using out-of-sample data from the same period. This selection method ensures the diversity of the dataset. The experimental results show that the proposed method can effectively distinguish between bullish and bearish patterns, breaking through the limitations of traditional candlestick pattern classification methods that rely on predefined patterns. By clearly distinguishing these two patterns, it provides clear buy and sell signals for investors, significantly improving the reliability and profitability of trading strategies. Full article

The retrieval of global significant wave height (SWH) data is crucial for maritime navigation, aquaculture safety, and oceanographic research. Leveraging the high temporal resolution and spatial coverage of Cyclone Global Navigation Satellite System (CYGNSS) data, machine learning models have shown promise in SWH retrieval. However, existing models struggle with accuracy under high-SWH conditions and discard a significant number of such observations due to low quality, which limits their effectiveness in global SWH retrieval, particularly for monitoring tropical cyclone (TC) events. To address this, this study proposes a daily global SWH retrieval framework through the enhanced eXtreme Gradient Boosting model (XGBoost-SC), which incorporates Cumulative Distribution Function (CDF) matching to introduce prior distribution information and reduce errors for SWH values exceeding 3 m. An enhanced loss function is employed to improve accuracy and mitigate the distribution bias in low-SWH retrieval induced by CDF matching. The results were tested over one million sample points and validated against the European Centre for Medium-Range Weather Forecasts (ECMWF) SWH product. With the help of CDF matching, XGBoost-SC outperformed all models, significantly reducing RMSE and bias while improving the retrieval capability for high SWHs. For SWH values between 3–6 m, the RMSE and bias were 0.94 m and −0.44 m, and for values above 6 m, they were 2.79 m and −2.0 m. The enhanced performance of XGBoost-SC for large SWHs was further confirmed in TC conditions over the Western North Pacific and in the Western Atlantic Ocean. This study provides a reference for large-scale SWH retrieval, particularly under TC conditions. Full article

The use of smartphones is widespread among adolescents and can affect various cognitive processes. However, the effects of smartphone use on sensory processing, particularly among individuals with attention deficit hyperactivity disorder (ADHD), remain largely unknown. The present study investigated the relationship between smartphone use intensity and sensory processing in adolescents with typical development and those with ADHD. The sample included 184 adolescents aged 14 to 18 years (M = 16.56; SD = ±1.87), with 92 diagnosed with ADHD and 92 with typical development, matched for age, gender, and IQ. Participants completed a self-report questionnaire to measure smartphone use intensity, while sensory processing was assessed using the Adolescent Sensory Profile (ASP). The results revealed a significant association between the intensity of smartphone use and heightened sensory responses in adolescents with typical development. However, this relationship was not observed in participants with ADHD. These preliminary findings suggest that smartphone use may influence sensory processing differently depending on neurotypical development or the presence of ADHD, potentially contributing to the promotion or mitigation of sensory dysfunctions. Future studies are needed to further explore the mechanisms underlying these differences and to better understand the impact of digital technologies on sensory functioning. Full article

Background: Endometrial proliferative lesions (EPLs) encompass endometrial hyperplasia (EH) and endometrial carcinoma (EC). Atypical endometrial hyperplasia (AEH) is associated with an elevated risk of progression to EC. Patients with polycystic ovarian syndrome (PCOS) exhibit higher serum levels of anti-Müllerian hormone (AMH) and a correspondingly increased incidence of EPLs. AMH has the capacity to inhibit the cell proliferation of EPLs derived from Müllerian duct tissue through the AMH-AMH receptor (AMHR) signaling pathway. Methods: Pairs of samples matched by preference scores were randomly selected. Immunohistochemistry was employed to assess the expression levels of AMHR type II (AMHR2) in endometrial tissue. A comparative analysis was performed between tissues from individuals with PCOS and those without, as well as between a normal endometrium and endometrial tissue from individuals with EPLs. This study aimed to elucidate differences in AMHR2 expression among these tissue types. By focusing on AMHR2 expression, the impact of the PCOS-related background on the endometrial AMH-AMHR cascade signaling pathway was initially investigated. Results: The AMHR2 protein was expressed in the endometrium of both the PCOS group and the non-PCOS group during the reproductive age (20–39 years). The expression of the AMHR2 protein in the AEH endometrium of PCOS patients did not differ significantly from that in the normal endometrium of PCOS patients; however, it was significantly higher than in the AEH endometrium of non-PCOS patients (p = 0.011). Conversely, the expression of the AMHR2 protein in the AEH endometrium of non-PCOS patients was significantly lower than that in the normal endometrium of non-PCOS patients (p = 0.021). Notably, there was no significant difference in AMHR2 protein expression in a normal endometrium between PCOS and non-PCOS patients. Conclusions: The involvement of the endometrial AMH-AMHR cascade signaling pathway and its biological effects in the pathogenesis of AEH are evident. The pathophysiological conditions associated with PCOS, such as elevated serum AMH levels and other pathological states, may directly or indirectly influence the AMH-AMHR cascade signaling pathway in the endometrium. This influence could contribute to the progression of AEH. Full article