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.

This paper proposes a dynamic portfolio allocation framework that integrates deep reinforcement learning (DRL) with classical portfolio optimization to enhance rebalancing strategies and risk–return management. Within a unified reinforcement-learning environment for portfolio reallocation, we train actor–critic agents (Proximal Policy Optimization (PPO) and Advantage Actor–Critic (A2C)). These agents learn to select both the risk-aversion level—positioning the portfolio along the efficient frontier defined by expected return and a chosen risk measure (variance, Semivariance, or CVaR)—and the rebalancing horizon. An ensemble procedure, which selects the most effective agent–utility combination based on the Sharpe ratio, provides additional robustness. Unlike approaches that directly estimate portfolio weights, our framework retains the optimization structure while delegating the choice of risk level and rebalancing interval to the AI agent, thereby improving stability and incorporating a market-timing component. Empirical analysis on daily data for 12 U.S. sector ETFs (2003–2023) and 28 Dow Jones Industrial Average components (2005–2023) demonstrates that DRL-guided strategies consistently outperform static tangency portfolios and market benchmarks in annualized return, volatility, and Sharpe ratio. These findings underscore the potential of DRL-driven rebalancing for adaptive portfolio management.

This study proposes a hierarchical signal-to-policy learning framework for risk-aware portfolio optimization that integrates model-based return forecasting, explainable machine learning, and deep reinforcement learning (DRL) within a unified architecture. In the first stage, next-period returns are estimated using gradient-boosted tree models, and SHAP-based feature attributions are extracted to provide transparent, factor-level explanations of the predictive signals. In the second stage, a Proximal Policy Optimization (PPO) agent incorporates both predictive forecasts and explanatory signals into its state representation and learns dynamic allocation policies under a mean–CVaR reward function that explicitly penalizes tail risk while controlling trading frictions. By separating signal extraction from policy learning, the proposed architecture allows the use of economically interpretable predictive signals to incorporate into the policy’s state representation while preserving the flexibility and adaptability of reinforcement learning. Empirical evaluations on U.S. sector ETFs and Dow Jones Industrial Average constituents show that the hierarchical framework delivers higher and stable out-of-sample risk-adjusted returns relative to both a single-layer DRL agent trained solely on technical indicators, a mean–CVaR optimized portfolio using the same parameters used in the proposed hierarchical model and standard equal weight as well as index-based benchmarks. These results demonstrate that integrating explainable predictive signals with risk-sensitive reinforcement learning improves the robustness and stability of data-driven portfolio strategies.

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.

We propose a portfolio rebalance framework that integrates machine learning models into the mean-risk portfolios in multi-period settings with risk-aversion adjustment. In each period, the risk-aversion coefficient is adjusted automatically according to market trend movements predicted by machine learning models. We employ Gini's Mean Difference (GMD) to specify the risk of a portfolio and use a set of technical indicators generated from a market index (e.g., S&P 500 index) to feed the machine learning models to predict market movements. Using a rolling-horizon approach, we conduct a series of computational tests with real financial data to evaluate the performance of the machine learning integrated portfolio rebalance framework. The empirical results show that the XGBoost model provides the best prediction of market movement, while the proposed portfolio rebalance strategy generates portfolios with superior out-of-sample performances in terms of average returns, time-series cumulative returns, and annualized returns compared to the benchmarks.

Mutations of the Gon4l / udu gene in different organisms give rise to diverse phenotypes. Although the effects of Gon4l/Udu in transcriptional regulation have been demonstrated, they cannot solely explain the observed characteristics among species. To further understand the function of Gon4l/Udu, we used yeast two-hybrid (Y2H) screening to identify interacting proteins in zebrafish and mouse systems, confirmed the interactions by co-immunoprecipitation assay, and found four novel Gon4l-interacting proteins: BRCA1 associated protein-1 (Bap1), DNA methyltransferase 1 (Dnmt1), Tho complex 1 (Thoc1, also known as Tho1 or HPR1), and Cryptochrome circadian regulator 3a (Cry3a). Furthermore, all known Gon4l/Udu-interacting proteins—as found in this study, in previous reports, and in online resources—were investigated by Phenotype Enrichment Analysis. The most enriched phenotypes identified include increased embryonic tissue cell apoptosis, embryonic lethality, increased T cell derived lymphoma incidence, decreased cell proliferation, chromosome instability, and abnormal dopamine level, characteristics that largely resemble those observed in reported Gon4l / udu mutant animals. Similar to the expression pattern of udu , those of bap1 , dnmt1 , thoc1 , and cry3a are also found in the brain region and other tissues. Thus, these findings indicate novel mechanisms of Gon4l/Udu in regulating CpG methylation, histone expression/modification, DNA repair/genomic stability, and RNA binding/processing/export.

The ventriculo‐arterial coupling (VAC) and left ventricle (LV) mechanics are crucial and play an important role in the pathophysiology of aortic stenosis (AS). The pressure‐volume (PV) analysis is a powerful tool to study VAC and LV mechanics. We proposed a novel minimally‐invasive method for PV analysis in patients with severe AS receiving transcatheter aortic valve implantation (TAVI). Patients with severe AS were prospectively enrolled in a single center. LV pressure and cardiac output were recorded before and after TAVI. We constructed the PV loop for analysis by analyzing LV pressure and the assumed flow. 26 patients were included for final analysis. The effective arterial elastance (Ea) decreased after TAVI (3.7 ± 1.3 vs. 2.9 ± 1.1 mmHg/mL, p < 0.0001). The LV end‐systolic elastance (Ees) did not change immediately after TAVI (2.4 ± 1.3 vs. 2.6 ± 1.1 mmHg/mL, p = 0.3670). The Ea/Ees improved after TAVI (1.8 ± 0.8 vs. 1.2 ± 0.4, p < 0.0001), demonstrating an immediate improvement of VAC. The stroke work (SW) did not change (7669.6 ± 1913.8 vs. 7626.2 ± 2546.9, p = 0.9330), but the pressure‐volume area (PVA) decreased (14469.0 ± 4974.1 vs. 12177.4 ± 4499.9, p = 0.0374) after TAVI. The SW/PVA increased after TAVI (0.55 ± 0.12 vs. 0.63 ± 0.08, p < 0.0001) representing an improvement of LV efficiency. We proposed a novel minimally invasive method for PV analysis in patients with severe AS receiving TAVI. The VAC and LV efficiency improved immediately after TAVI. Reconstructed pressure volume loop by LV pressure and cardiac output.

BackgroundRestless legs syndrome is a highly prevalent comorbidity of migraine; however, its genetic contributions remain unclear.ObjectivesTo identify the genetic variants of restless legs syndrome in migraineurs and to investigate their potential pathogenic roles.MethodsWe conducted a two-stage genome-wide association study (GWAS) to identify susceptible genes for restless legs syndrome in 1,647 patients with migraine, including 264 with and 1,383 without restless legs syndrome, and also validated the association of lead variants in normal controls unaffected with restless legs syndrome (n = 1,053). We used morpholino translational knockdown (morphants), CRISPR/dCas9 transcriptional knockdown, transient CRISPR/Cas9 knockout (crispants) and gene rescue in one-cell stage embryos of zebrafish to study the function of the identified genes.ResultsWe identified two novel susceptibility loci rs6021854 (in VSTM2L) and rs79823654 (in CCDC141) to be associated with restless legs syndrome in migraineurs, which remained significant when compared to normal controls. Two different morpholinos targeting vstm2l and ccdc141 in zebrafish demonstrated behavioural and cytochemical phenotypes relevant to restless legs syndrome, including hyperkinetic movements of pectoral fins and decreased number in dopaminergic amacrine cells. These phenotypes could be partially reversed with gene rescue, suggesting the specificity of translational knockdown. Transcriptional CRISPR/dCas9 knockdown and transient CRISPR/Cas9 knockout of vstm2l and ccdc141 replicated the findings observed in translationally knocked-down morphants.ConclusionsOur GWAS and functional analysis suggest VSTM2L and CCDC141 are highly relevant to the pathogenesis of restless legs syndrome in migraineurs.

Portfolio optimization and quantitative risk management have been studied extensively since the 1990s and began to attract even more attention after the 2008 financial crisis. This disastrous occurrence propelled portfolio managers to reevaluate and mitigate the risk and return trade-off in building their clients' portfolios. The advancement of machine-learning algorithms and computing resources helps portfolio managers explore rich information by incorporating macroeconomic conditions into their investment strategies and optimizing their portfolio performance in a timely manner. In this paper, we present a simulation-based approach by fusing a number of macroeconomic factors using Neural Networks (NN) to build an Economic Factor-based Predictive Model (EFPM). Then, we combine it with the Copula-GARCH simulation model and the Mean-Conditional Value at Risk (Mean-CVaR) framework to derive an optimal portfolio comprised of six index funds. Empirical tests on the resulting portfolio are conducted on an out-of-sample dataset utilizing a rolling-horizon approach. Finally, we compare its performance against three benchmark portfolios over a period of almost twelve years (01/2007-11/2019). The results indicate that the proposed EFPM-based asset allocation strategy outperforms the three alternatives on many common metrics, including annualized return, volatility, Sharpe ratio, maximum drawdown, and 99% CVaR.