Explore the vast range of titles available.

The accurate estimation of the remaining useful life (RUL) for aircraft engines is essential for ensuring safety and uninterrupted operations in the aviation industry. Numerous investigations have leveraged the success of the attention-based Transformer architecture in sequence modeling tasks, particularly in its application to RUL prediction. These studies primarily focus on utilizing onboard sensor readings as input predictors. While various Transformer-based approaches have demonstrated improvement in RUL predictions, their exclusive focus on temporal attention within multivariate time series sensor readings, without considering sensor-wise attention, raises concerns about potential inaccuracies in RUL predictions. To address this concern, our paper proposes a novel solution in the form of a two-stage attention-based hierarchical Transformer (STAR) framework. This approach incorporates a two-stage attention mechanism, systematically addressing both temporal and sensor-wise attentions. Furthermore, we enhance the STAR RUL prediction framework by integrating hierarchical encoder–decoder structures to capture valuable information across different time scales. By conducting extensive numerical experiments with the CMAPSS datasets, we demonstrate that our proposed STAR framework significantly outperforms the current state-of-the-art models for RUL prediction.

Lung adenocarcinoma (LUAD) is one of the most prevalent pathological kinds of lung cancer, which is a common form of cancer that has a high death rate. Over the past several years, growing studies have indicated that GPD1L was involved in the advancement of a number of different cancers. However, its clinical significance in LUAD has not been investigated. In this study, following an examination of the TGCA datasets, we found that GPD1L displayed a dysregulated state in a wide variety of cancers; this led us to believe that GPD1L is an essential regulator in the progression of malignancies. In addition, we found that the expression of GPD1L was much lower in LUAD tissues when compared with nontumor specimens. According to the findings of ROC tests, GPD1L was able to effectively identify LUAD specimens from nontumor samples with an AUC value of 0.828 (95% confidence interval: 0.793 to 0.863). On the basis of the clinical study, a low expression of GPD1L was clearly related with both the N stage and the clinical stage. Moreover, based on the findings of a Kaplan-Meier survival study, elevated GPD1L expression was a strong indicator of considerably improved overall survival (OS) and disease-specific survival (DSS). GPD1L expression and clinical stages were found to be independent prognostic indicators for overall survival and disease-free survival in LUAD patients, according to multivariate analyses. Based on multivariate analysis, the C-indexes and calibration plots of the nomogram demonstrated an effective prediction performance for LUAD patients. Besides, the expression of GPD1L was positively related to mast cells, eosinophils, Tcm, TFH, iDC, DC, and macrophages, while negatively associated with Th2 cells, NK CD56dim cells, Tgd, Treg, and neutrophils. Finally, qRT-PCR was able to demonstrate that GPD1L had a significant amount of expression in LUAD. Additionally, according to the results of functional tests, overexpression of GPD1L had a significant inhibiting effect on the proliferation of LUAD cells. In general, the results of our study suggested that GPD1L had the potential to serve as a diagnostic and prognostic marker for LUAD.

This paper presents a learning-assisted approach for state estimation of quadruped robots using observations of proprioceptive sensors, including multiple inertial measurement units (IMUs). Specifically, one body IMU and four additional IMUs attached to each calf link of the robot are used for sensing the dynamics of the body and legs, in addition to joint encoders. The extended Kalman filter (KF) is employed to fuse sensor data to estimate the robot’s states in the world frame and enhance the convergence of the extended KF (EKF). To circumvent the requirements for the measurements from the motion capture (mocap) system or other vision systems, the right-invariant EKF (RI-EKF) is extended to employ the foot IMU measurements for enhanced state estimation, and a learning-based approach is presented to estimate the vision system measurements for the EKF. One-dimensional convolutional neural networks (CNN) are leveraged to estimate required measurements using only the available proprioception data. Experiments on real data from a quadruped robot demonstrate that proprioception can be sufficient for state estimation. The proposed learning-assisted approach, which does not rely on data from vision systems, achieves competitive accuracy compared to EKF using mocap measurements and lower estimation errors than RI-EKF using multi-IMU measurements.

Estimating the remaining useful life (RUL) of aircraft engines holds a pivotal role in enhancing safety, optimizing operations, and promoting sustainability, thus being a crucial component of modern aviation management. Precise RUL predictions offer valuable insights into an engine’s condition, enabling informed decisions regarding maintenance and crew scheduling. In this context, we propose a novel RUL prediction approach in this paper, harnessing the power of bi-directional LSTM and Transformer architectures, known for their success in sequence modeling, such as natural languages. We adopt the encoder part of the full Transformer as the backbone of our framework, integrating it with a self-supervised denoising autoencoder that utilizes bidirectional LSTM for improved feature extraction. Within our framework, a sequence of multivariate time-series sensor measurements serves as the input, initially processed by the bidirectional LSTM autoencoder to extract essential features. Subsequently, these feature values are fed into our Transformer encoder backbone for RUL prediction. Notably, our approach simultaneously trains the autoencoder and Transformer encoder, different from the naive sequential training method. Through a series of numerical experiments carried out on the C-MAPSS datasets, we demonstrate that the efficacy of our proposed models either surpasses or stands on par with that of other existing methods.

Phishing attacks represent a significant and growing threat in the digital world, affecting individuals and organizations globally. Understanding the various factors that influence susceptibility to phishing is essential for developing more effective strategies to combat this pervasive cybersecurity challenge. Machine learning has become a prevalent method in the study of phishing susceptibility. Most studies in this area have taken one of two approaches: either they explore statistical associations between various factors and susceptibility, or they use complex models such as deep neural networks to predict phishing behavior. However, these approaches have limitations in terms of providing practical insights for individuals to avoid future phishing attacks and delivering personalized explanations regarding their susceptibility to phishing. In this paper, we propose a machine-learning approach that leverages explainable artificial intelligence techniques to examine the influence of human and demographic factors on susceptibility to phishing attacks. The machine learning model yielded an accuracy of 78%, with a recall of 71%, and a precision of 57%. Our analysis reveals that psychological factors such as impulsivity and conscientiousness, as well as appropriate online security habits, significantly affect an individual’s susceptibility to phishing attacks. Furthermore, our individualized case-by-case approach offers personalized recommendations on mitigating the risk of falling prey to phishing exploits, considering the specific circumstances of each individual.

IntroductionDiarrhoea-dominant irritable bowel syndrome (IBS-D) is a disorder with multiple pathogenesis; many people with IBS-D may have psychosocial issues which can make assessment and treatment more difficult. Routine treatment procedure might not always achieve the desired outcome. Therefore, patients may not be satisfied with the conventional experience and would like to be more involved in clinical decision-making. A shared decision-making (SDM) model, that requires patient participation, has been demonstrated to have a powerful effect on the diagnosis and treatment of other diseases, which improves patients’ compliance, satisfaction, thus refining the clinical outcome. However, there is no corresponding evidence in IBS-D. Herein, we hope to verify the effect of SDM through clinical studies, and we anticipate that SDM can improve the therapeutic effect in patients with IBS-D.MethodsThe study is a prospective, randomised, single-centre trial. 166 IBS-D outpatients who attend Peking Union Medical College Hospital will be allocated into routine treatment group and SDM group. The primary endpoint is the severity of bowel symptoms, measured by the IBS symptom severity scale. Secondary endpoints include impact of disease and quality of life, negative psychology and the evaluation of diagnosis and treatment process.Ethics and disseminationEthical approval has been obtained from the research ethics committee of Peking Union Medical College Hospital (I-23PJ470). This protocol has been approved by Chinese Clinical Trial Register (ChiCTR2300073681) in July 2023. The results of this trial will be published in an open-access way and disseminated among gastrointestinal physicians.Trial registration numberChinese Clinical Trial Register (ChiCTR2300073681).

Chronic pancreatitis is a progressive fibroinflammatory disorder with no currently satisfactory treatment. Emerging evidence suggests an association between gut microbial dysbiosis and chronic pancreatitis. Although direct causative evidence is lacking, it is hypothesized that the gut microbiota may play a pivotal role in modulating pancreatic function via the gut–pancreas axis. Thus, modulating the gut microbiota through the administration of probiotics or prebiotics may alleviate pancreatic disorders. In this review, we first propose the potential mechanisms by which specific probiotics or prebiotics may ameliorate chronic pancreatitis, including the alleviation of small intestinal bacterial overgrowth (SIBO), the facilitation of short-chain fatty acids’ (SCFAs) production, and the activation of glucagon-like peptide-1 receptors (GLP-1Rs) in the pancreas. Since there are currently no probiotics or prebiotics used for the treatment of chronic pancreatitis, we discuss research in other disease models that have used probiotics or prebiotics to modulate pancreatic endocrine and exocrine functions and prevent pancreatic fibrosis. This provides indirect evidence for their potential application in the treatment of chronic pancreatitis. We anticipate that this research will stimulate further investigation into the gut–pancreas axis and the potential therapeutic value of probiotics and prebiotics in chronic pancreatitis.

The regulatory mechanisms underlying embryogenic callus (EC) formation in polyploid bananas remain unexplored, posing challenges for genetic transformation and biotechnological applications. Here, we conducted transcriptome sequencing on cultured explants, non-embryogenic callus, EC, and browning callus in the ABB cultivar ‘MJ’ (Musa spp. cv. Bengal). Our analysis of differentially expressed genes (DEGs) revealed significant enrichment in plant hormones, MAPK, and zeatin biosynthesis pathways. Notably, most genes in the MJ variety exhibited balanced expression of the A and B alleles, but A-specific allele expression was dominant in the key signaling pathways, whereas B-specific allele expression was very rare during EC induction. In the auxin signaling pathway, six A-specific MJARF genes were markedly downregulated, underscoring their critical roles in the negative regulation of callus formation. Additionally, six A-specific MJEIN3 alleles were found to play negative regulatory roles in ethylene signaling during EC development. We also identified phenylpropanoids responsible for enzymatic browning. Furthermore, the expression patterns of transcription factors in bananas exhibited specific expression modes, highlighting the unique mechanisms of callus formation. This study enhanced our understanding of the regulatory roles of these alleles in EC induction and offers new insights into the utilization of alleles to improve the efficiency of somatic embryogenesis in bananas.

Aim: In the case under consideration, research was conducted to optimize the design process of fire protection for an underwater sea tunnel to reduce potential fire risks and enhance the resistance of fire protection pipelines to corrosion caused by seawater. Introduction: Designing intelligent fire protection systems is always a key point in the construction process of underwater sea tunnels. Taking the Karnaphuli Tunnel in Bangladesh as an example, the intelligent fire protection design of a typical offshore tunnel was examined. The commonly used fire protection schemes for tunnels were analyzed based on the characteristics of underwater tunnel fires, and a suitable intelligent fire protection system was proposed. In view of the hidden dangers from combustible gases such as CO and H2S that might cause fires in the lowest point of wastewater pumping stations, this study set up a gas detection alarm system and an automatic foam fire extinguishing system at the lowest point. Meanwhile, according to the high chloride ions in the water of the Karnaphuli River in Chittagong, the anti-corrosion problem of fire protection pipes in the underwater highway tunnels was discussed, and the selection of fire-fighting pipes was proposed. Considering the characteristics of marine corrosion, a two-layer anti-corrosion structure with epoxy zinc-based powder coating as the bottom layer and functional coating as the surface layer was adopted. Methodology: Both theoretical and practical research methods were carried out in this article. According to the chemical theory, the anaerobic environment in tunnels with seawater was to produce CO and H2S. Using the experimental analysis on practical monitoring of seawater, it could be concluded that ordinary fire protection pipelines could get corroded easily in seawater. Conclusions: Gas detection alarm and automatic foam fire extinguishing system should be added at the lowest point of the undersea highway tunnel due to the presence of some combustible gases such as CO and H2S. In view of the easy corrosion of fire system pipes in underwater highway tunnels, internal and external plastic-coated steel pipes with hot-melt epoxy powder as the inner coating and 3PE (three-layer structure) as the outer coating should be adopted in the design and construction of intelligent fire protection system in underwater tunnels.

BackgroundTo investigate the severity of hypoxemia and prevalence of pulmonary hypertension (PHTN) in patients with the overlap syndrome (OS) of restrictive ventilatory defect (RVD) and sleep apnea (SA).MethodsPatients referred for both sleep test and spirometry for suspected SA and ventilatory disorders were recruited prospectively from January 2019 to January 2020. SA was determined by an apnea-hypopnea index ≥ 5/h; average oxygen saturation during sleep (meanSaO2) and percentage of total sleep time with saturation < 90% (T90) were calculated. RVD was diagnosed in the presence of forced expiratory volume in the first second/forced vital capacity (FVC) > 0.7 and FVC < 80% predicted value. PHTN was defined by tricuspid regurgitation peak velocity ≥ 3.4 m/s, documented by noninvasive transthoracic echocardiography.ResultsPatients with OS had significantly lower meanSaO2 but higher T90 than subjects with isolated SA and isolated RVD. Patients with OS vs. those with isolated SA had higher odds of PHTN in multivariable analysis with age, sex, and body mass index adjusted for (OR 2.96, 95%CI 1.05–8.91, p = 0.040). Patients with meanSaO2 < 92% vs. meanSaO2 ≥ 92% had significantly higher odds of being diagnosed with PHTN (OR 5.40, 95%CI 2.01–15.7, p < 0.001). Similarly, T90 (≥ 4.5% versus < 4.5%) was also independently associated with the prevalence of PHTN (OR 7.21, 95%CI 2.54–23.67, p < 0.001).ConclusionPatients with OS of RVD and SA had severe hypoxemia, which is associated with the prevalence of PHTN. Further investigation is needed to discern whether therapeutic strategies toward OS might mitigate PHTN in this cohort.Trial registrationClinical Trial Registration No. ChiCTR1900027294 on 1 October 2019