Search Results (201)

Artificial intelligence has become crucial in sports, leveraging its analytical capabilities to enhance the understanding and prediction of complex events. Machine learning algorithms in sports, especially basketball, are transforming performance analysis by identifying patterns and trends invisible to traditional methods. This technology provides in-depth insights into individual and team performance, enabling precise evaluation of strategies and tactics. Consequently, the detailed analysis of every aspect of a team’s routine can significantly elevate the level of competition in the sport. This study investigates a range of machine learning models, including Logistic Regression (LR), Ridge Regression Classifier (RR), Random Forest (RF), Naive Bayes (NB), K-Nearest Neighbors (KNNs), Support Vector Machine (SVM), Stacking Classifier (STACK), Bagging Classifier (BAG), Multi-Layer Perceptron (MLP), AdaBoost (AB), and XGBoost (XGB), as well as deep learning architectures such as Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs), to compare their effectiveness in predicting game outcomes in the NBA and WNBA leagues. The results show highly acceptable prediction accuracies of 65.50% for the NBA and 67.48% for the WNBA. This study allows us to understand the impact that artificial intelligence can have on the world of basketball and its current state in relation to previous studies. It can provide valuable insights for coaches, performance analysts, team managers, and sports strategists by using machine learning and deep learning models to predict NBA and WNBA outcomes, enabling informed decisions and enhancing competitive performance. Full article

Emerging applications like augmented reality (AR) demand efficient wireless transmission of high-resolution three-dimensional (3D) images, yet conventional systems struggle with the high data volume and vulnerability to noise. This paper proposes a novel feature-driven framework that integrates semantic source coding with deep learning-based Joint Source–Channel Coding (JSCC) for robust and efficient transmission. Instead of processing dense meshes, the method first extracts a compact set of geometric features—specifically, the ridge and valley curves that define the object’s fundamental structure. This feature representation which is extracted by the anatomical curves is then processed by an end-to-end trained JSCC encoder, mapping the semantic information directly to channel symbols. This synergistic approach drastically reduces bandwidth requirements while leveraging the inherent resilience of JSCC for graceful degradation in noisy channels. The framework demonstrates superior reconstruction fidelity and robustness compared to traditional schemes, especially in low signal-to-noise ratio (SNR) regimes, enabling practical and efficient 3D semantic communications. Full article

Digital epidermal microscopic (DEM) images offer the potential to quantitatively analyze skin aging at the microscopic level. However, stochastic complexity, local highlights, and low contrast in DEM images pose significant challenges to accurate segmentation. This study evaluated eight deep learning models to identify methods capable of accurately segmenting complex DEM images while meeting diverse performance requirements. To this end, this study first constructed a manually labeled DEM image dataset. Then, eight deep learning models (FCN-8s, SegNet, UNet, ResUNet, NestedUNet, DeepLabV3+, TransUNet, and AttentionUNet) were systematically evaluated for their performance in DEM image segmentation. Our experimental findings show that AttentionUNet achieves the highest segmentation accuracy, with a DSC of 0.8696 and an IoU of 0.7703. In contrast, FCN-8s is a better choice for efficient segmentation due to its lower parameter count (18.64 M) and efficient inference speed (GPU time 37.36 ms). FCN-8s and NestedUNet show a better balance between accuracy and efficiency when assessed across metrics like segmentation accuracy, model size, and inference time. Through a systematic comparison of eight deep learning models, this study identifies superior methods for segmenting skin furrows and ridges in DEM images. This work lays the foundation for subsequent applications, such as analyzing skin aging through furrow and ridge features. Full article

Hydrothermal vents, widely occurring along middle-ocean ridges and volcanic arcs, have been well-studied in vent-associated microbiology, mineralogy, and geochemistry. However, there are rarely investigations regarding the detailed microbial community in the hydrothermal vent-influenced sediment. To explore hydrothermal activities on microbial diversity at the Carlsberg Ridge in the northwestern Indian Ocean, four sediment cores were sampled from the near-vent fields to distant vent sedimentary fields in the Tianxiu hydrothermal field, and the microbial community compositions were analyzed. The sediment microorganisms closest to the hydrothermal vent were primarily composed of Acidimicrobiia, Gammaproteobacteria, Anaerolineae, and Planctomycetes. The microbial communities at the depth containing extensive signals of hydrothermal activity consisted mainly of Dehalococcoidia, Aerophoria, Anaerolineae, and Gammaproteobacteria. No significant differences in microbial composition were observed between the two weak hydrothermal sediment cores, primarily composed of Nitrososphaeria, Gammaproteobacteria, Alphaproteobacteria, and Acidimicrobiia. Moreover, heterogeneous selection substantially impacted the bacterial community assembly in near-vent sediments other than stochasticity. Multivariate statistical analysis identified that environmental fluctuations accounted for 55.59% of the community variation, with hydrothermal inputs (such as Fe, Pb, Cu, and Zn) being the primary factors shaping the construction of hydrothermal sediment microbial communities. These results enhance understanding of the response of deep-sea sediments to hydrothermal activity. Full article

Boulenophrys gutu sp. nov. was described from Mt. Hengshan, and B. hengshanensis was re-described based on the holotype and newly collected specimens using phylogenetic and morphological evidence. The new species forms an independent clade, and it is diagnosed by a combination of following characters: (1) male SVL 34.4–44.7 mm (n = 7), female SVL 36.2–52.8 mm (n = 8); (2) dorsal surface of head, body, and limbs relatively smooth; (3) vomerine ridge weak, vomerine teeth absent; (4) narrow lateral fringes on toes; (5) heels moderate long, meeting when thighs are positioned at right angles to body; (6) supratympanic fold behind tympanum thick, distinctly enlarged with thickness near diameter of tympanum; (7) inner metatarsal tubercle small (IMT/SVL 4.4–5.2%); (8) several large dark brown patches along both ventrolateral sides of abdomen; (9) coloration of inner and outer metacarpal tubercle, inner metatarsal tubercle, and tip of digits ivory. Phylogenetic analyses based on 16S rRNA and COI genes revealed that B. hengshanensis is sister to B. wugongensis. Morphological comparisons showed that B. hengshanensis is diagnosed by a combination of following characters: (1) moderate body size, male SVL 34.4–38.0 mm (n = 9), female SVL 48.4 mm (n = 1); (2) weak vomerine ridge, absence of vomerine teeth; (3) tongue not notched behind; (4) a small horn-like tubercle on upper eyelid; (5) rudimentary webbing between toes; (6) narrow lateral fringes on toes; (7) heels relatively short, not meeting when thighs are positioned at right angles to body; (8) supratympanic fold behind tympanum narrow, not distinctly enlarged; (9) a pair of dark brown broad stripes along ventrolateral sides of abdomen; (10) dense creamy white dots present on lower abdomen, merge with deep brown patches without clear boundary. Full article

Deep coalbed methane development faces technical challenges, such as high in situ stress and low permeability. The dynamic evolution of fractures after hydraulic fracturing and the flowback mechanism are crucial for optimizing productivity. This paper focuses on the inversion of post-fracturing fracture volume parameters and dynamic analysis of the flowback in deep coalbed methane wells, with 89 vertical wells in the eastern margin of the Ordos Basin as the research objects, conducting systematic studies. Firstly, through the analysis of the double-logarithmic curve of normalized pressure and material balance time, the quantitative inversion of the volume of propped fractures and unpropped secondary fractures was realized. Using Pearson correlation coefficients to screen characteristic parameters, four machine learning models (Ridge Regression, Decision Tree, Random Forest, and AdaBoost) were constructed for fracture volume inversion prediction. The results show that the Random Forest model performed the best, with a test set R² of 0.86 and good generalization performance, so it was selected as the final prediction model. With the help of the SHAP model to analyze the influence of each characteristic parameter, it was found that the total fluid volume into the well, proppant intensity, minimum horizontal in situ stress, and elastic modulus were the main driving factors, all of which had threshold effects and exerted non-linear influences on fracture volume. The interaction of multiple parameters was explored by the Partial Dependence Plot (PDP) method, revealing the synergistic mechanism of geological and engineering parameters. For example, a high elastic modulus can enhance the promoting effect of fluid volume into the well and proppant intensity. There is a critical threshold of 2600 m³ in the interaction between the total fluid volume into the well and the minimum horizontal in situ stress. These findings provide a theoretical basis and technical support for optimizing fracturing operation parameters and efficient development of deep coalbed methane. Full article

With the development of technology, comfort has gradually developed into the main criterion for evaluating intelligent vehicle performances. In this study, a field test was carried out under five common driving conditions, and 60 participants took part. Passenger posture data, vehicle motion data and passenger subjective comfort data were collected. A paired sample T-test and a ridge regression algorithm were used to explore the relationship between passenger posture swing parameters and subjective comfort. The results show that under the same driving conditions, the speed of posture swing was significantly higher for passengers who experienced discomfort. Furthermore, we found that the change in angular velocity was the main cause of passenger discomfort under different driving conditions. This suggested that the design of intelligent vehicle algorithms should focus on the angular velocity variation among passengers. Finally, based on traditional machine learning algorithms and deep learning algorithms, this paper establishes two models for predicting comfort through passenger posture instability. The accuracy of the machine learning model in predicting passenger comfort was 87.1%, while that for the deep learning model was 89%. The findings are useful in providing a theoretical basis for improving the comfort of intelligent vehicles. Full article

Background. Orthodontic extrusion (OE), or forced eruption, is a conservative technique used to recover teeth affected by coronal fractures, traumatic intrusions, or severe caries. It involves applying light, continuous forces to induce vertical tooth movement, promoting tissue remodeling through periodontal ligament stimulation. Materials and Methods. This narrative review included studies investigating OE as a therapeutic approach for the management of deep or subgingival carious lesions, traumatic dental injuries (such as intrusion or fracture), or for alveolar ridge augmentation in implant site development. OE is typically performed using fixed appliances such as the straight-wire system or, in selected cases, clear aligners. Forces between 30 and 100 g per tooth are applied, depending on the clinical situation. In some protocols, OE is combined with fiberotomy to minimize gingival and bone migration. Results. Studies show that OE leads to significant vertical movement and increases in buccal bone height and interproximal septa. It enhances bone volume in targeted sites, making it valuable in implant site development. Compared to surgical crown lengthening, OE better preserves periodontal tissues and improves esthetics. Conclusions. In this narrative review is analized how OE is effective for managing traumatic intrusions and compromised periodontal sites, particularly when paired with early endodontic treatment. It reduces the risks of ankylosis and root resorption while avoiding invasive procedures like grafting. Although clear aligners may limit axial tooth movement, OE remains a minimally invasive, cost-effective alternative in both restorative and implant dentistry. Full article

This study addresses the critical need for accurate tourism demand (TD) forecasting in Bulgaria using economic indicators, developing robust predictive models to navigate post-pandemic market volatility. The COVID-19 pandemic exposed tourism’s vulnerability to systemic shocks, highlighting deficiencies in traditional forecasting approaches. Bulgaria’s tourism industry, characterized by strong seasonal variations and economic sensitivity, requires enhanced methodologies for strategic planning in uncertain environments. The research employs comprehensive comparative analysis of machine learning (ML) and deep machine learning (DML) methodologies. Monthly overnight stay data from Bulgaria’s National Statistical Institute (2005–2024) were integrated with COVID-19 case data, Consumer Price Index (CPI) and Bulgarian Gross Domestic Product (GDP) variables for the same period. Multiple approaches were implemented including Prophet with external regressors, Ridge regression, LightGBM, and gradient boosting models using inverse MAE weighting optimization, alongside deep learning architectures such as Bidirectional LSTM with attention mechanisms and XGBoost configurations, as each model statistical significance was estimated. Contrary to prevailing assumptions about deep learning superiority, traditional machine learning ensemble approaches demonstrated superior performance. The ensemble model combining Prophet, LightGBM, and Ridge regression achieved optimal results with MAE of 156,847 and MAPE of 14.23%, outperforming individual models by 10.2%. Deep learning alternatives, particularly Bi-LSTM architectures, exhibited significant deficiencies with negative R² scores, indicating fundamental limitations in capturing seasonal tourism patterns, probable data dependence and overfitting. The findings, provide tourism stakeholders and policymakers with empirically validated forecasting tools for enhanced decision-making. The ensemble approach combined with statistical significance testing offers improved accuracy for investment planning, marketing budget allocation, and operational capacity management during economic volatility. Economic indicator integration enables proactive responses to market disruptions, supporting resilient tourism planning strategies and crisis management protocols. Full article

Olive flounder (Paralichthys olivaceus) is a key aquaculture species in South Korea, but its production has been challenged by rising mortality under environmental stress from key environmental factors such as water temperature, dissolved oxygen, and feeding conditions. To support adaptive management, this study proposes a Bayesian Deep Kernel Machine Regression (BDKMR) model that integrates Gaussian process regression with neural network-based feature learning. Using longitudinal data from commercial farms, we model fish growth as a function of water temperature, dissolved oxygen, and feed quantity. Model performance is assessed via Leave-One-Out Cross-Validation and compared against kernel ridge regression and Bayesian kernel machine regression. Results show that BDKMR achieves substantially lower prediction errors, indicating superior accuracy and robustness. These findings suggest that BDKMR offers a flexible and effective framework for predictive modeling in aquaculture systems. Full article

Deep learning has excelled in image classification largely due to large, professionally labeled datasets. However, in the field of medical images data annotation often relies on experienced experts, especially in tasks such as white blood cell classification where the staining methods for different cells vary greatly and the number of samples in certain categories is relatively small. To evaluate leukocyte classification performance with limited labeled samples, a few-shot learning method based on Feature Reconstruction Network with Improved EfficientNetV2 (FRNE) is proposed. Firstly, this paper presents a feature extractor based on the improved EfficientNetv2 architecture. To enhance the receptive field and extract multi-scale features effectively, the network incorporates an ASPP module with dilated convolutions at different dilation rates. This enhancement improves the model’s spatial reconstruction capability during feature extraction. Subsequently, the support set and query set are processed by the feature extractor to obtain the respective feature maps. A feature reconstruction-based classification method is then applied. Specifically, ridge regression reconstructs the query feature map using features from the support set. By analyzing the reconstruction error, the model determines the likelihood of the query sample belonging to a particular class, without requiring additional modules or extensive parameter tuning. Evaluated on the LDWBC and Raabin datasets, the proposed method achieves accuracy improvements of 3.67% and 1.27%, respectively, compared to the method that demonstrated strong OA performance on both datasets among all compared approaches. Full article

Plastic debris has become a persistent feature of deep-sea ecosystems, yet its role as a habitat for calcifying organisms remains poorly understood. Foraminifera colonization has been observed in significant numbers on plastic surfaces, suggesting that these materials serve as novel and significant deep-sea colonization sites for these abundant calcifying organisms. This study uses deep-sea experimental plastic substrates to examine the colonization and reproductive morphology of the benthic foraminifera Lobatula wuellerstorfi across three locations: Station M (4000 m), Oregon OOI (575 m), and Southern Hydrate Ridge (774 m). A total of 482 individuals were analyzed for morphometric traits, including proloculus diameter, to investigate reproductive morphotypes. The Oregon samples displayed a clear bimodal proloculus size distribution, consistent with alternating reproductive strategies, while Station M populations exhibited a broader, less defined bimodal distribution skewed toward megalospheric forms. A weak but significant increase in proloculus diameter over deployment duration was observed at Station M, suggesting a possible influence of experiment duration and/or substrate maturity and environmental conditions. These findings demonstrate that plastics can serve as persistent colonization sites for deep-sea foraminifera, offering a unique experimental platform to investigate benthic population dynamics, ecological plasticity, and potential geochemical implications, as well as the broader impacts of foraminifera on deep-sea biodiversity and biogeochemical cycling. Full article

Micro-crack defects on the surfaces of plate heat exchanger sheets often exhibit a linear grayscale pattern when clustered. In defect detection, traditional methods are more suitable than deep learning models in controlled production environments with limited computing resources to meet stringent national standards, which require low miss rates. However, deep learning models commonly suffer feature loss when detecting individual, small-scale defects, leading to higher leak detection rates. Moreover, in grayscale image line detection using traditional methods, the varying direction, width, and asymmetric grayscale profiles of defects can result in filled grayscale valleys due to width-adaptive smoothing coefficients, complicating accurate defect extraction. To address these issues, this study establishes a theoretical foundation for parameter selection in variable-width defect detection. We propose a directional gradient-based algorithm that mathematically constrains the Gaussian template width to cover variable-width defects with a fixed σ, reframing the detection defect from ridge edges to centrally symmetric double-ridge edges in gradient images. Experimental results show that, when tested in the defective boards library and under simulated factory CPU conditions, this algorithm achieves a miss detection rate of 14.55%, a false detection rate of 21.85%, and an 600 × 600 pixel image detection time of 0.1402 s. Compared to traditional line detection and deep learning object detection methods, this algorithm proves advantageous for detecting micro-crack defects on plate heat exchanger sheets in industrial production, particularly in data-scarce and resource-limited scenarios. Full article

Linear models are not always able to sufficiently capture the structure of a dataset. Sometimes, combining predictors in a non-parametric method, such as deep neural networks (DNNs), would yield a more flexible modeling of the response variables in the predictions. Furthermore, the standard statistical classification or regression approaches are inefficient when dealing with more complexity, such as a high-dimensional problem, which usually suffers from multicollinearity. For confronting these cases, penalized non-parametric methods are very useful. This paper proposes two heuristic approaches and implements new shrinkage penalized cost functions in the DNN, based on the elastic-net penalty function concept. In other words, some new methods via the development of shirnkaged penalized DNN, such as ${\mathrm{DNN}}_{\mathrm{elastic-net}}$ and ${\mathrm{DNN}}_{\mathrm{ridge}\&\mathrm{bridge}}$, are established, which are strong rivals for ${\mathrm{DNN}}_{\mathrm{Lasso}}$ and ${\mathrm{DNN}}_{\mathrm{ridge}}$. If there is any dataset grouping information in each layer of the DNN, it may be transferred using the derived penalized function of elastic-net; other penalized DNNs cannot provide this functionality. Regarding the outcomes in the tables, in the developed DNN, not only are there slight increases in the classification results, but there are also nullifying processes of some nodes in addition to a shrinkage property simultaneously in the structure of each layer. A simulated dataset was generated with the binary response variables, and the classic and heuristic shrinkage penalized DNN models were generated and tested. For comparison purposes, the DNN models were also compared to the classification tree using GUIDE and applied to a real microbiome dataset. Full article

Based on the new high-resolution multibeam bathymetry data collected by the “Dongfanghong 3” vessel in 2023 in the Parece Vela Basin (PVB) and previous magnetic anomaly data, we systematically analyze the seafloor topographical changes of abyssal hills and oceanic core complexes (OCCs) in the “Chaotic Terrain” region, and the revised seafloor spreading model is constructed in the PVB. Using detailed analysis of the seafloor topography, we identify typical geomorphological features associated with seafloor spreading, such as regularly aligned abyssal hills and OCCs in the PVB. The direction variations of seafloor spreading in the PVB are closely related to mid-ocean ridge rotation and propagation. The formation of OCCs in the “Chaotic Terrain” can be explained by links to the continuous and persistent activity of detachment faults and dynamic adjustments controlled by variations of deep magma supply in the different segments in the PVB. We use 2D discrete Fourier image analysis of the seafloor topography to calculate the aspect ratio (AR) values of abyssal hills in the western part of the PVB. The AR value variations reveal a distinct imbalance in magma supply across various regions during the basin spreading process. Compared to the “Chaotic Terrain” area, the region with abyssal hills indicates a higher magma supply and greater linearity on seafloor topography. AR values fluctuated between 2.1 and 1.7 of abyssal hills in the western segment, while in the “Chaotic Terrain”, they dropped to 1.3 due to the lower magma supply. After the formation of the OCC-1, AR values increased to 1.9 in the eastern segment, and this shows the increase in magma supply. Based on changes in seafloor topography and variations in magma supply across different segments of the PVB, we propose that the seafloor spreading process in the magnetic anomaly linear strip 9-6A of the PVB mainly underwent four formation stages: ridge rotation, rift propagation, magma-poor supply, and the maturation period of OCCs. Full article