Search

The ongoing digitalization enables stable control processes and smooth operations of Industrial Control Systems (ICSs). A direct consequence of the highly interconnected architecture of ICSs is the introduced cyber vulnerability and increasing cyber security threats to ICSs. Numerous researches pay attention to the security problem of ICSs. However, most current studies face two challenges. First, the interaction problem between the cyber layer and the physical layer of ICSs may result in incorrect attack response strategies. Second, ICSs are real-time systems, but existing defense decision algorithms based on game theory or reinforcement learning techniques have high computational complexity, which prevents them from making decisions quickly. In this paper, we design a new multi-attribute based method for quantifying rewards and propose a multi-attribute based Q-learning algorithm to resolve the interaction problem. In addition, to overcome the limitation of slow convergence, we develop an effective parallel Q-learning (PQL) algorithm to quickly find the optimal strategy. The experimental results show the effectiveness of the PQL algorithm. Compared with the Q-learning algorithm (QL) and the deep Q-network (DQN) algorithm, our proposed solution can reduce the average completion time by 12.5 to 37 percent. [ABSTRACT FROM AUTHOR]

Background: Studying the relationship between strenuous sports or other exercises (SSOE) and lung cancer risk remains underexplored. Traditional observational studies face challenges like confounders and inverse causation. However, Mendelian randomization (MR) provides a promising approach in epidemiology and genetics, using genetic variants as instrumental variables to investigate causal relationships. By leveraging MR, we have scrutinized the causal link between SSOE and lung cancer development., Methods: Twelve single-nucleotide polymorphisms (SNPs) associated with SSOE, as identified in previously published genome-wide association studies, were utilized as instrumental variables in our investigation. Summary genetic data at the individual level were obtained from relevant studies and cancer consortia. The study encompassed a total of 11,348 cases and 15,861 controls. The statistical technique of inverse variance-weighting (IVW), commonly employed in meta-analyses and MR studies, was employed to assess the causal relationship between SSOE and lung cancer risk., Results: The MR risk analysis indicated a causal relationship between SSOE and the incidence of lung cancer, with evidence of a reduced risk for overall lung cancer [odds ratio (OR) =0.129; 95% confidence interval (CI): 0.021-0.779; P=0.03], lung adenocarcinoma (OR =0.161; 95% CI: 0.012-2.102; P=0.16) and squamous cell lung cancer (OR =0.045; 95% CI: 0.003-0.677; P=0.03). The combined OR for lung cancer from SSOE (controlling for waist circumference and smoking status) was 0.054 (95% CI: 0.010-0.302, P<0.001)., Conclusions: Our MR analysis findings indicate a potential correlation between SSOE and a protective effect against lung cancer development. Further investigation is imperative to uncover the precise mechanistic link between them., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://tlcr.amegroups.com/article/view/10.21037/tlcr-23-810/coif). The authors have no conflicts of interest to declare., (2024 Translational Lung Cancer Research. All rights reserved.)