Search Results (2,159)

To address the challenge of identifying water-flooded layers in the high-porosity, high-permeability, and strongly heterogeneous reservoirs of the Guantao Formation in the Penglai 19-3 Oilfield, research on water-flooded layer identification methods was systematically conducted. The logging characteristics of oil layers and water-flooded layers at different levels overlap considerably, which limits the accuracy of traditional identification methods. Meanwhile, the Archie equation shows significantly reduced applicability during the moderate and strong water-flooding stages. A water-flooded layer identification model was constructed using HistGBDT, and performance comparison between the base model and the optimized model reveals that the latter achieves a test accuracy of 91.6%. Compared with BPNN and SVM, the optimized HistGBDT model demonstrates substantially higher test accuracy and better generalization performance. Based on six sets of logging data, the optimized HistGBDT model developed enables the accurate identification of oil layers and multi-level water-flooded layers. It provides a reliable technical approach for tapping remaining oil in the high-water-cut stage of the Penglai 19-3 Oilfield and offers a new method and engineering reference for water-flooded layer identification in similar high-porosity, high-permeability heterogeneous reservoirs in the Bohai Bay Basin. Full article

Accurate assessment of coalbed methane (CBM) content is essential for characterizing subsurface reservoir distribution, guiding well placement, and estimating reserves. Current methods for determining coal seam gas content mainly rely on direct laboratory measurements of core samples or indirect interpretations derived from well log data. However, conventional coring is costly, while log-based approaches often depend on linear empirical formulas and are restricted to near-wellbore regions. In practice, the relationships between elastic properties and gas content are highly complex and nonlinear, leading conventional linear models to produce substantial prediction errors and inadequate performance. This study introduces a novel method for predicting gas content in deep coal seams using a Conditional Generative Adversarial Network (CGAN). First, elastic parameters are obtained through pre-stack inversion. Next, sensitivity analysis and attribute optimization are applied to identify elastic attributes that are most sensitive to gas content. A CGAN is then employed to learn the nonlinear mapping between multiple fluid-sensitive seismic attributes and gas content distribution. By integrating multiple constraints to refine the discriminator and guide generator training, the model achieves accurate gas content prediction directly from seismic data. Applied to a real dataset from a CBM block in the Ordos Basin, China, the proposed CGAN-based method produces predictions that align closely with measured gas content trends at well locations. Validation at blind wells shows an average prediction error of 1.6 m³/t, with 83% of samples exhibiting errors less than 3 m³/t. This research presents an effective and innovative deep learning approach for predicting coalbed methane content. Full article

We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as a time series classification task. As financial transaction data streams grow in scale and complexity, traditional methods often require large labeled datasets and struggle with time series of irregular sampling frequencies and varying sequence lengths. To address these challenges, we extend conditional Generative Adversarial Networks (GANs) for targeted data augmentation, integrate Bayesian inference to obtain predictive distributions and quantify uncertainty, and leverage log-signatures for robust feature encoding of transaction histories. We propose a composite Wasserstein distance-based loss to align generated and real unlabeled samples while simultaneously maximizing classification accuracy on labeled data. Our approach is evaluated on the BankSim dataset, a widely used simulator for credit card transaction data, under varying proportions of labeled samples, demonstrating consistent improvements over benchmarks in both global statistical and domain-specific metrics. These findings highlight the effectiveness of GAN-driven semi-supervised learning with log-signatures for irregularly sampled time series and emphasize the importance of uncertainty-aware predictions. Full article

Benford’s law states that in many real-world datasets, the probability that the leading digit is d equals ${log}_{10}((d+1)/d)$ for all $1\le d\le 9$. We call this weak Benford behavior. A dataset is said to follow strong Benford behavior if the probability that its significand (i.e., the significant digits in scientific notation) is at most s equals ${log}_{10}\left(s\right)$ for all $s\in [1,10)$. We investigate Benford behavior in a multi-proportion stick fragmentation model, where a stick is split into m substicks according to fixed proportions at each stage. This generalizes previous work on the single proportion stick fragmentation model, where each stick is split into two substicks using one fixed proportion. We provide a necessary and sufficient condition under which the lengths of the stick fragments converge to strong Benford behavior in the multi-proportion model. Full article

This study introduces the Machine Learning (ML)-Driven Pattern Synthesis for Digital Forensics in Synthetic Log Analysis (ML-PSDFA) framework to address critical gaps in digital forensics, including the reliance on real-world data, limited pattern diversity, and forensic integration challenges. A key innovation is the introduction of a novel temporal forensics loss ${\mathcal{L}}_{\mathrm{TFL}}$ in the Synthetic Attack Pattern Generator (SAPG), which enhances the preservation of temporal sequences in synthetic logs that are crucial for forensic analysis. The framework employs the SAPG with hybrid seed data (UNSW-NB15 and CICIDS2017) to create 500,000 synthetic log entries using Google Colab, achieving a realism score of 0.96, a temporal consistency score of 0.90, and an entropy of 4.0. The methodology employs a three-layer architecture that integrates data generation, pattern analysis, and forensic training, utilizing TimeGAN, XGBoost classification with hyperparameter tuning via Optuna, and reinforcement learning (RL) to optimize the extraction of evidence. Due to enhanced synthetic data quality and advanced modeling, the results exhibit an average classification precision of 98.5% (best fold 98.7%) 98.5% (best fold 98.7%), outperforming previously reported approaches. Feature importance analysis highlights timestamps (0.40) and event types (0.30), while the RL workflow reduces false positives by 17% over 1000 episodes, aligning with RL benchmarks. The temporal forensics loss improves the realism score from 0.92 to 0.96 and introduces a temporal consistency score of 0.90, demonstrating enhanced forensic relevance. This work presents a scalable and accessible training platform for legally constrained environments, as well as a novel RL-based evidence extraction method. Limitations include a lack of real-system validation and resource constraints. Future work will explore dynamic reward tuning and simulated benchmarks to enhance precision and generalizability. Full article

Background/Objectives: In 2019, the European Society of Gynaecological Oncology (ESGO) published a set of quality indicators (QIs) for the surgical management of cervical cancer with the aim of improving clinical practice. The objective of this study is to evaluate the influence of ESGO QIs and clinicopathological factors on progression-free survival (PFS) in patients with early-stage cervical cancer in a retrospective cohort. Methods: A retrospective study was conducted in patients with early-stage cervical cancer who underwent radical surgery with pelvic lymph node assessment at La Paz University Hospital between 2005 and 2022. The cohort was divided into two groups according to the timing of surgery (before vs. after 2010), when MRI was implemented as a standardized diagnostic tool and the multidisciplinary tumor board was established. Univariate and multivariate Cox regression analyses were performed, including demographic and histopathological variables, as well as adherence to ESGO QIs, focusing on those related to the overall management. Hazard ratios and 95% confidence intervals were estimated. Kaplan–Meier survival curves were generated and compared between groups. Results: The implementation of systematic MRI and a multidisciplinary tumor board at our center was associated with a significant reduction in positive surgical margins (p = 0.003) and parametrial invasion (p < 0.001), as well as improved diagnostic accuracy, lowering the rate of upstaging from 31.6% before 2010 to 4.4% thereafter (p < 0.001). PFS in the post-2010 cohort was significantly improved (log-rank p = 0.0408), although no differences in overall survival (OS) were observed (log-rank p = 0.2602). Additionally, cervical conization prior to radical hysterectomy was associated with a markedly reduced risk of recurrence (HR 0.12, p < 0.001), representing the most significant prognostic factor for PFS in our cohort. Conclusions: The correct application of ESGO QIs, along with appropriate staging and pathological assessment, is essential to improve prognosis in cervical cancer. Systematic implementation of these standards is recommended to optimize clinical care. Full article

In this paper, we present a unique method to determine the level of bot contamination of web-based user agents. It is common practice for bots and robotic agents to masquerade as human-like to avoid content and performance limitations. This paper continues our previous work, using over 600 million web log entries collected from over 4000 domains to derive and generalize how the prominence of specific web browser versions progresses over time, assuming genuine human agency. Here, we introduce a parametric model capable of reproducing this progression in a tunable way. This simulation allows us to tag human-generated traffic in our data accurately. Along with the highest confidence self-tagged bot traffic, we train a Transformer-based classifier that can determine the bot contamination—a botness metric of user-agents without prior labels. Unlike traditional syntactic or rule-based filters, our model learns temporal patterns of raw and heuristic-derived features, capturing nuanced shifts in request volume, response ratios, content targeting, and entropy-based indicators over time. This rolling window-based pre-classification of traffic allows content providers to bin streams according to their bot infusion levels and direct them to several specifically tuned filtering pipelines, given the current load levels and available free resources. We also show that aggregated traffic data from multiple sources can enhance our model’s accuracy and can be further tailored to regional characteristics using localized metadata from standard web server logs. Our ability to adjust the heuristics to geographical or use case specifics makes our method robust and flexible. Our evaluation highlights that 65% of unclassified traffic is bot-based, underscoring the urgency of robust detection systems. We also propose practical methods for independent or third-party verification and further classification by abusiveness. Full article

This work aims towards the automatic detection of faults in industrial air-cooling equipment used in a production line for staple fibers and ultimately provides maintenance scheduling recommendations to ensure seamless operation. In this context, various deep learning models are tested to ultimately define the most effective one for the intended scope. In the examined system, four vibration and temperature sensors are used, each positioned radially on the motor body near the rolling bearing of the motor shaft—a typical setup in many industrial environments. Thus, by collecting and using data from the latter sources, this work exhaustively investigates the feasibility of accurately diagnosing faults in staple fiber cooling fans. The dataset is acquired and constructed under real production conditions, including variations in rotational speed, motor load, and three fault priorities, depending on the model detection accuracy, product specification, and maintenance requirements. Fault identification for training purposes involves analyzing and evaluating daily maintenance logs for this equipment. Experimental evaluation on real production data demonstrated that the proposed ResNet50-1D model achieved the highest overall classification accuracy of 97.77%, while effectively resolving the persistent misclassification of the faulty impeller observed in all the other models. Complementary evaluation confirmed its robustness, cross-machine generalization, and suitability for practical deployment, while the integration of predictions with maintenance logs enables a severity-based prioritization strategy that supports actionable maintenance planning.deep learning; fault classification; industrial air-cooling; industrial automation; maintenance scheduling; vibration analysis Full article

Background: The high-precision analysis of multimode fibers (MMFs) is a critical task in numerous applications, including remote sensing, medical imaging, and environmental monitoring. In this study, we propose a novel deep interpretable network approach to reconstruct spectral images captured using CCD sensors. Methods: Our model leverages a Tiny-YOLO-inspired convolutional neural network architecture, specifically designed for spectral wavelength prediction tasks. A total of 1880 CCD interference images were acquired across a broad near-infrared range from 1527.7 to 1565.3 nm. To ensure precise predictions, we introduce a dynamic factor α and design a dynamic adaptive loss function based on Huber loss and Log-Cosh loss. Results: Experimental evaluation with five-fold cross-validation demonstrates the robustness of the proposed method, achieving an average validation MSE of 0.0149, an R² score of 0.9994, and a normalized error (μ) of 0.0005 in single MMF wavelength prediction, confirming its strong generalization capability across unseen data. The reconstructed outputs are further visualized as smooth spectral curves, providing interpretable insights into the model’s decision-making process. Conclusions: This study highlights the potential of deep learning-based interpretable networks in reconstructing high-fidelity spectral images from CCD sensors, paving the way for advancements in spectral imaging technology. Full article

The unhygienic practices in retail poultry meat shops adversely affect chicken meat quality and shelf life. To address this issue, a meat-surface-decontaminating wipe was developed. Deionized water, jamun leaf (Syzygium cumini) extracts, and other generally recognized as safe ingredients were used to prepare a decontamination solution. A sterile non-woven cloth soaked in the solution was applied over the meat surface as a decontamination wipe. Treated and untreated meat samples were stored at 4 ± 1 °C under aerobic packaging conditions, and various meat quality parameters were evaluated at every 1-day interval until the onset of spoilage. It was observed that the wipe could significantly reduce 2.31 log microbial loads (p = 0.00005, CI-95%, 1.85, 2.77) over the meat surface. With the increasing storage intervals, the meat quality parameters changed significantly (p < 0.05), and the treated chicken samples spoiled on day 6, whereas the control spoiled on day 5. The meat spoilage was confirmed by the evaluation of quality changes in the stored meat. Additionally, the wipe could cause 1.14 (p = 0.00000, CI-95%, 1.01, 1.25) and 1.03 (p = 0.00005, CI-95%, 0.90, 1.16) log reductions of E. coli and S. aureus, respectively. Based on the results, it was concluded that the decontamination wipe could improve the meat quality and shelf life of retail chicken meat without affecting the sensory quality attributes. Full article

Parkinson’s disease (PD), a progressive neurodegenerative disorder affecting over 10 million people worldwide, necessitates continuous symptom monitoring to optimize treatment and enhance quality of life. Effective communication between patients and healthcare providers (HCPs) is vital but often hindered by fragmented data and cognitive impairments. PARKA AI, a novel iOS application, leverages Apple Watch HealthKit data (e.g., tremor detection, mobility metrics, heart rate, and sleep patterns) and integrates it with self-reported logs (e.g., mood, medication adherence) to empower PD self-management and improve patient–HCP interactions. Employing a human-centered design approach, we developed a high-fidelity prototype using a large language model (LLM)— Google Gemini 1.5 Flash—to process and analyze self-reports and objective sensor-derived data from Apple Healthkit to generate patient-friendly summaries and concise HCP reports. PARKA AI provides accessible data visualizations, personalized self-management tools, and streamlined HCP reports to foster engagement and communication. This paper outlines the derived design requirements, prototype features, and illustrative use cases to show how LLMs can be used in digital health tools. Future work will focus on real-world usability testing to validate the application’s efficacy and accessibility. Full article

The rapid growth of Large Language Models (LLMs) has generated massive amounts of high-dimensional feature vectors extracted from diverse datasets. Efficient storage and retrieval of such data are critical for enabling accurate and fast query responses. Vector databases (Vector DBs) provide efficient storage and retrieval for high-dimensional vectors. These systems rely on Approximate Nearest Neighbor Search (ANNS) indexes, such as HNSW, to handle large-scale data efficiently. However, the original HNSW is implemented on DRAM, which is both costly and vulnerable to crashes. Therefore, we propose P-HNSW, a crash-consistent HNSW on persistent memory. To guarantee crash consistency, P-HNSW introduces two logs, NLog and NlistLog. We describe the logging process during the operation and the recovery process in the event of system crashes. Our experimental results demonstrate that the overhead of the proposed logging mechanism is negligible, while P-HNSW achieves superior performance compared with SSD-based recovery mechanisms. Full article

The Gaussian Mixture Model (GMM) is commonly used to formulate the probabilistic model for quantifying uncertainties in renewable generation. However, traditional static probabilistic models may not efficiently adapt and learn from newly forecasted and measured data. In this paper, we propose a recursively updated probabilistic model that leverages a recursive estimation method to update the parameters of the GMM based on continuously arriving data of renewable generation. This recursive modeling approach effectively incorporates new observations while discarding outdated samples, enabling the tracking of time-varying uncertainties in renewable generation in an incremental manner. Furthermore, we introduce an extra calibration stage to enhance the long-term accuracy of the probabilistic model after a large number of incremental updates. The main contribution is to address the potential degradation of performance caused by suboptimal incremental updates accumulated over time. Numerical tests demonstrate that the proposed model achieves 5–10% higher log likelihood in characterizing renewable generation uncertainties compared to purely recursive models, while reducing computational time by three to four orders of magnitude (1000 to 10,000 times) relative to conventional EM. These results highlight the proposed model’s suitability for real-time probabilistic modeling of renewable generation, with potential applications in system operation. Full article

Sugarcane wax-derived policosanol (POL) is well recognized for its multifaceted biological activities, particularly in dyslipidemia management, whereas sugar cane extract powder (SEP), prepared from whole sugar juice blended with supplementary components, has not been thoroughly investigated for its biological activities and potential toxicities. Herein, the comparative dietary effect of four distinct SEPs (SEP-1 to SEP-4) and Cuban sugarcane wax extracted POL were examined to prevent the pathological events in high-cholesterol diet (HCD)-induced hyperlipidemic zebrafish. Among the SEPs, a 14-week intake of SEP-2 emerged with the least zebrafish survival probability (0.75, log-rank: χ² = 14.1, p = 0.015), while the POL supplemented group showed the utmost survival probability. A significant change in body weight and morphometric parameters was observed in the SEP-2 supplemented group compared to the HCD group, while non-significant changes had appeared in POL, SEP-1, SEP-3, and SEP-4 supplemented groups. The HCD elevated total cholesterol (TC) and triglyceride (TG) levels were significantly minimized by the supplementation of POL, SEP-1, and SEP-2. However, an augmented HDL-C level was only noticed in POL-supplemented zebrafish. Likewise, only the POL-supplemented group showed a reduction in blood glucose, malondialdehyde (MDA), AST, and ALT levels, and an elevation in sulfhydryl content, paraoxonase (PON), and ferric ion reduction (FRA) activity. Also, plasma from the POL-supplemented group showed the highest antioxidant activity and protected zebrafish embryos from carboxymethyllysine (CML)-induced toxicity and developmental deformities. POL effectively mitigated HCD-triggered hepatic neutrophil infiltration, steatosis, and the production of interleukin (IL)-6 and inhibited cellular senescence in the kidney and minimized the ROS generation and apoptosis in the brain. Additionally, POL substantially elevated spermatozoa count in the testis and safeguarded ovaries from HCD-generated ROS and senescence. The SEP products (SEP-1, SEP-3, and SEP-4) showed almost non-significant protective effect; however, SEP-2 exhibited an additive effect on the adversity posed by HCD in various organs and biochemical parameters. The multivariate examination, employing principal component analysis (PCA) and hierarchical cluster analysis (HCA), demonstrates the positive impact of POL on the HCD-induced pathological events in zebrafish, which are notably diverse, with the effect mediated by SEPs. The comparative study concludes that POL has a functional superiority over SEPs in mitigating adverse events in hyperlipidemic zebrafish. Full article

To investigate the flow characteristics of movable water in coal under the influence of micro-nano pore fractures with multiple fractal structures, this study employed nuclear magnetic resonance (NMR) and multifractal theory to analyze gas–water seepage under different injection pressures. Then, the scale threshold for mobile water entering coal pores and fractures was determined by clarifying the relationship among “injection pressure-T₂ dynamic multiple fractal parameter seepage resistance-critical pore scale”. The results indicate that coal samples from Yiwu (YW) and Wuxiang (WX) enter the nanoscale pore size range at an injection pressure of 8 MPa, while the coal sample from Malan (ML) enters the nanoscale pore size range at an injection pressure of 9 MPa. During the water injection process, there is a significant linear relationship between the multiple fractal parameters log X(q, ε) and log(ε) of the sample. The generalized fractal dimension D(q) decreases monotonically with increasing q in an inverse S-shape. This decrease occurs in two distinct stages: D(q) decreases rapidly in the low probability interval q < 0; D(q) decreases slowly in the high probability interval q > 0. The multiple fractal singularity spectrum function f(α) has an asymmetric upward parabolic convex function relationship with α, which is divided into a rapidly increasing left branch curve and a slowly decreasing right branch curve with α₀ as the boundary. Supporting evidence indicates the feasibility of a methodology for identifying the variation in multiple fractal parameters of gas–water NMR seepage and the critical scale transition conditions. This investigation establishes a methodological foundation for analyzing gas–water transport pathways within porous media materials. Full article