Explore the vast range of titles available.

Fault zones accommodate relative motion between tectonic blocks and control earthquake nucleation. Nanocrystalline fault rocks are ubiquitous in “principal slip zones” indicating that these materials are determining fault stability. However, the rheology of nanocrystalline fault rocks remains poorly constrained. Here, we show that such fault rocks are an order of magnitude weaker than their microcrystalline counterparts when deformed at identical experimental conditions. Weakening of the fault rocks is hence intrinsic, it occurs once nanocrystalline layers form. However, it is difficult to produce “rate weakening” behavior due to the low measured stress exponent, n , of 1.3 ± 0.4 and the low activation energy, Q , of 16,000 ± 14,000 J/mol implying that the material will be strongly “rate strengthening” with a weak temperature sensitivity. Failure of the fault zone nevertheless occurs once these weak layers coalesce in a kinematically favored network. This type of instability is distinct from the frictional instability used to describe crustal earthquakes. Extremely fine-grained fault rocks are intrinsically weak and behave as fluids even at low temperatures and fast deformation rates. Local production of fine-grained material during fault movement can lead to an earthquake instability.

Magnetic flux leakage testing (MFL) is the most widely used nondestructive testing technology in the safety inspection of oil and gas pipelines. The analysis of MFL test data is essential for pipeline safety assessments. In recent years, deep-learning technologies have been applied gradually to the data analysis of pipeline MFL testing, and remarkable results have been achieved. To the best of our knowledge, this review is a pioneering effort on comprehensively summarizing deep learning for MFL detection and evaluation of oil and gas pipelines. The majority of the publications surveyed are from the last five years. In this work, the applications of deep learning for pipeline MFL inspection are reviewed in detail from three aspects: pipeline anomaly recognition, defect quantification, and MFL data augmentation. The traditional analysis method is compared with the deep-learning method. Moreover, several open research challenges and future directions are discussed. To better apply deep learning to MFL testing and data analysis of oil and gas pipelines, it is noted that suitable interpretable deep-learning models and data-augmentation methods are important directions for future research.

Seismic wave arrival time measurements form the basis for numerous downstream applications. State‐of‐the‐art approaches for phase picking use deep neural networks to annotate seismograms at each station independently, yet human experts annotate seismic data by examining the whole network jointly. Here, we introduce a general‐purpose network‐wide phase picking algorithm based on a recently developed machine learning paradigm called Neural Operator. Our model, called Phase Neural Operator, leverages the spatio‐temporal contextual information to pick phases simultaneously for any seismic network geometry. This results in superior performance over leading baseline algorithms by detecting many more earthquakes, picking more phase arrivals, while also greatly improving measurement accuracy. Following similar trends being seen across the domains of artificial intelligence, our approach provides but a glimpse of the potential gains from fully‐utilizing the massive seismic data sets being collected worldwide. Plain Language Summary Earthquake monitoring often involves measuring arrival times of P‐ and S‐waves of earthquakes from continuous seismic data. With the advancement of artificial intelligence, state‐of‐the‐art phase picking methods use deep neural networks to examine seismic data from each station independently; this is in stark contrast to the way that human experts annotate seismic data, in which waveforms from the whole network containing multiple stations are examined simultaneously. With the performance gains of single‐station algorithms approaching saturation, it is clear that meaningful future advances will require algorithms that can naturally examine data for entire networks at once. Here we introduce a multi‐station phase picking algorithm based on a recently developed machine learning paradigm called Neural Operator. Our algorithm, called Phase Neural Operator, leverages the spatial‐temporal information of earthquake signals from an input seismic network with arbitrary geometry. This results in superior performance over leading baseline algorithms by detecting many more earthquakes, picking many more seismic wave arrivals, yet also greatly improving measurement accuracy. Key Points We introduce a multi‐station phase picking algorithm, Phase Neural Operator (PhaseNO), that is based on a new machine learning paradigm called Neural Operator PhaseNO can use data from any number of stations arranged in any arbitrary geometry to pick phases across the input stations simultaneously By leveraging the spatial and temporal contextual information, PhaseNO achieves superior performance over leading baseline algorithms

It is well accepted that environmental stressors experienced over a one’s life, from microbial infections to chemical toxicants to even psychological stressors, ultimately shape central nervous system (CNS) functioning but can also contribute to its eventual breakdown. The severity, timing and type of such environmental “hits”, woven together with genetic factors, likely determine what CNS outcomes become apparent. This focused review assesses the current COVID-19 pandemic through the lens of a multi-hit framework and disuses how the SARS-COV-2 virus (causative agent) might impact the brain and potentially interact with other environmental insults. What the long-term consequences of SAR2 COV-2 upon neuronal processes is yet unclear, but emerging evidence is suggesting the possibility of microglial or other inflammatory factors as potentially contributing to neurodegenerative illnesses. Finally, it is critical to consider the impact of the virus in the context of the substantial psychosocial stress that has been associated with the global pandemic. Indeed, the loneliness, fear to the future and loss of social support alone has exerted a massive impact upon individuals, especially the vulnerable very young and the elderly. The substantial upswing in depression, anxiety and eating disorders is evidence of this and in the years to come, this might be matched by a similar spike in dementia, as well as motor and cognitive neurodegenerative diseases.

Background Osteosarcoma, as the most common primary bone malignancy, is urgent to be well-studied on the biomarkers and therapeutic targets to improve the five-year survival rate. Transcriptomic analysis using single-cell RNA or bulk RNA sequencing has been developed to detect biomarkers in various cancer types. Methods and results We applied Scissor to combine single-cell RNA-seq data and bulk transcriptome data of osteosarcoma, providing cell-level information and sample phenotypes to identify the survival-associated cell subpopulations. By investigating the differences between the survival-associated cell subpopulations, we identified CCL21, CCL22, CCL24, CXCL11, CXCL12, CXCL13, GNAI2, and RAC2 in the proliferating cells that are significantly associated with osteosarcoma patient outcome. Then we assigned the risk score for each sample based on the cell proportion-normalized gene expression and validated it in the public dataset. Conclusions This study provides the clinical insight that chemokine signaling pathway genes (CCL21, CCL22, CCL24, CXCL11, CXCL12, CXCL13, GNAI2, and RAC2) in proliferating cells might be the potential biomarkers for treatment of osteosarcoma.

Adversarial training is an effective defense method for deep models against adversarial attacks. However, current adversarial training methods require retraining the entire neural network, which consumes a significant amount of computational resources, thereby affecting the timeliness of deep models and further hindering the rapid learning process of new knowledge. In response to the above problems, this article proposes an incremental adversarial training method (IncAT) and applies it to the field of brain computer interfaces (BCI). Within this method, we first propose a deep model called Neural Hybrid Assembly Network (NHANet) and then train it. Then, based on the original samples and the trained deep model, calculate the Fisher information matrix to evaluate the importance of deep neural network parameters on the original samples. Finally, when calculating the loss of adversarial samples and real labels, an Elastic Weight Consolidation (EWC) loss is added to limit the variation of important weights and bias parameters in the Neural Hybrid Assembly Network (NHANet). The above incremental adversarial training method was applied to the publicly available epilepsy brain computer interface dataset at the University of Bonn. The experimental results showed that when facing three different attack algorithms, including fast gradient sign method (FGSM), projected gradient descent (PGD) and basic iterative method (BIM), the method proposed in this paper achieved robust accuracies of 95.33%, 94.67%, and 93.60%, respectively, without affecting the accuracy of clean samples, which is 5.06%, 4.67%, and 2.67% higher than traditional training methods respectively, thus fully verifying the generalization and effectiveness of the method.

Background Prediabetes is the earliest identifiable stage of glycemic dysregulation, and its progression can be delayed by effective control of risk factors. Currently, various risk factors for the progression from prediabetes to type 2 diabetes mellitus (T2DM) need to be further summarized. Objective This systematic evaluation of the risk factors for the progression of prediabetes to type 2 diabetes mellitus provides a theoretical basis for early recognition and intervention. The meta-analysis identifies the Fatty Liver Index as a significant risk factor [OR = 6.14, 95% CI (5.22, 7.22)] for the progression from prediabetes to type 2 diabetes, highlighting its predictive value. Methods PubMed, Web of Science, Embase, The Cochrane Library, CNKI, WANFANG, and VIP databases were searched to collect cohort studies on risk factors for progressing to type 2 diabetes in prediabetes from inception to February 15, 2024. STATA 17.0 was used for Meta-analysis. Results A total of 59 studies were included, all of which were of medium to high quality. The factors were categorized into four major groups: sociodemographic factors, lifestyle factors, psychosocial factors, and comorbidities and clinical indicators. Meta-analysis results showed that sociodemographic factors [age [OR = 1.03, 95% CI (1.01, 1.04)], family history [OR = 1.48, 95% CI (1.36, 1.61)], male sex [OR = 1.13, 95% CI (1.08, 1.19)], high BMI [OR = 1.21, 95% CI (1.15, 1.27)], high waist circumference [OR = 1.49, 95% CI (1.23, 1.79)], and high waist-to-hip ratio [OR = 2.44, 95% CI (2.17, 2.74)]]. Lifestyle factors included a lack of physical exercise [OR = 1.86, 95% CI (1.19, 2.88)], smoking [OR = 1.31, 95% CI (1.22, 1.41)], and moderate physical activity [OR = 0.24, 95% CI (0.09, 0.67)]. Psychosocial factors included anxiety [OR = 2.61, 95% CI (1.36, 5.00)], depression [OR = 1.88, 95% CI (1.35, 2.61)], and social deprivation level 4 [OR = 1.15, 95% CI (1.13, 1.18)]. Comorbidities and clinical indicators included hypertension [OR = 1.41, 95% CI (1.33, 1.50)], high triglycerides [OR = 1.25, 95% CI (1.10, 1.43)], high cholesterol [OR = 1.09, 95% CI (1.06, 1.12)], fatty liver index [OR = 6.14, 95% CI (5.22, 7.22)], low HDL-C [OR = 1.13, 95% CI (1.09, 1.36)], and high blood glucose levels [OR = 1.01, 95% CI (1.01, 1.02)]. Conclusions This study found that age, male sex, positive family history of type 2 diabetes, high BMI, unhealthy lifestyle, anxiety, depression, high blood pressure, high triglycerides, and a high fatty liver index are risk factors for the progression from prediabetes to type 2 diabetes and should be given sufficient attention. Moderate physical activity and Low HDL-C are protective factors. Future studies should also increase follow-up, explore the best diagnostic criteria for prediabetes, and fully consider the definitions of various factors. The study was registered in PROSPERO (CRD42024513931).

A network ultrasonic Wasserstein generative adversarial network (US-WGAN), which can generate ultrasonic guided wave signals, is proposed herein to solve the problem of insufficient datasets for pipe ultrasonic nondestructive testing based on deep neural networks. This network was trained with pre-enhanced and US-WGAN-enhanced datasets with 3000 epochs; the ultrasound signals generated by the US-WGAN were proved to be of high quality (peak signal-to-noise ratio scores in the range of 30–50 dB) and belong to the same population distribution as the original dataset. To verify the effectiveness of the US-WGAN, a fully connected neural network with seven layers was established, and the performances of the network after data enhancement using the US-WGAN and popular virtual defects were verified for the same network parameters and structures. The results show that adoption of the US-WGAN effectively suppresses the overfitting phenomenon while training the network and increases the dataset size, thereby improving the training and testing accuracies (>97%). Additionally, we noted that a simple, fully connected shallow neural network was sufficient for achieving high-accuracy defect classification using the US-WGAN data enhancement method.

Explainability is a very active area of research in machine learning and image processing. This paper aims to investigate the explainability of visible light and infrared image fusion technology in order to enhance the credibility of model understanding and application. Firstly, a multimodal image fusion model was proposed based on the advantages of convolutional neural networks (CNN) for local context extraction and Transformer global attention mechanism. Secondly, to enhance the explainability of the model, the Delta Debugging Fuse Image (DDFImage) algorithm was employed for generating local explanatory information. Finally, we gain deeper insights into the internal workings of the model through feature importance analysis of the generated explanatory fusion images. Comparative analysis with other explainability algorithms demonstrates the superior performance of our algorithm. This comprehensive approach not only improves the explainability of the model but also provides more reference for practical application of the model.

High-strength bolts are crucial load-bearing components of wind turbine towers. They are highly susceptible to fatigue cracks over long-term service and require timely detection. However, due to the structural complexity and hidden nature of the cracks in wind turbine tower bolts, the small size of the cracks, and their variable propagation directions, detection signals carrying crack information are often drowned out by dense thread signals. Existing non-destructive testing methods are unable to quickly and accurately characterize small cracks at the thread roots. Therefore, we propose an ultrasonic phased array element arrangement method based on the Fermat spiral array. This method can greatly increase the fill rate of the phased array with small element spacing while reducing the effects of grating and sidelobes, thereby achieving high-energy excitation and accurate imaging with the ultrasonic phased array. This has significant theoretical and engineering application value for ensuring the safe and reliable service of key wind turbine components and for promoting the technological development of the wind power industry.