Accurate survival prognosis is essential for personalized prognostic assessment and treatment planning in lung adenocarcinoma. This study compares non-parametric and semi-parametric statistical methods for survival prognostic modeling using clinical data from the TCGA-LUAD cohort(n=493). The Kaplan-Meier estimator and the multivariate Cox proportional hazards model were applied to evaluate the prognostic roles of tumor stage, age, and gender. The dataset was divided into a training set (70%) for model fitting and a testing set (30%) for independent validation. The results show that the Kaplan-Meier estimator provides an intuitive visualization of survival differences across tumor stages, with Log-rank tests confirming significant differences among subgroups(p<0.001). The Cox model identified tumor stage as the dominant independent prognostic factor. Compared with Stage I patients, Stage IV patients had a 3.58-fold higher hazard of death(HR = 3.58, 95% CI: 1.67–7.69, p<0.005). Although the C-index increased only slightly from 0.686 to 0.689, the Cox model offered added value through multivariate adjustment and the estimation of interpretable hazard ratios. These findings suggest that Kaplan-Meier estimation and Cox regression play complementary roles in lung cancer survival analysis.

Show more

In recent years, the rapid development of intelligent transportation systems (ITS) and autonomous driving has made human driving behavior modeling accurate and critical for improving traffic safety, efficiency, and autonomous system adaptability. Traditional rule-based or utility-centric models, however, fail to handle the complexity, randomness, and scenario dependence of real driving. Thus, our study aims to explore inverse reinforcement learning (IRL), a data-driven method, for driving behavior modeling. We first reviewed major IRL variants such as Maximum Margin IRL, MaxEnt Deep IRL, GAIL, Bayesian IRL and IAL and analyze their strengths like MaxEnt Deep IRL's adaptability to large state space and limitations in ITS. We then proposed two frameworks: 1) an AOAT strategy based on MaxEnt IRL which uses HighD data set and reduces lateral deviations by 42.91%-55.35% vs fixed-weight schemes; 2) a multi-agent framework integrating multi-modal data, using Bradley-Terry regression and PPO algorithm for real-time traffic signal optimization. Finally, we discussed IRL's challenges such as data set reliance, poor reward function interpretability, high computation and cost and proposed future directions including standardized datasets, hybrid reward structures and algorithm optimization. This study proves IRL's value for human-centric modeling, laying a foundation for safer, more adaptable ITS.

Show more

Social enterprises play an important role in public service supplementation, community development, and sustainable business practices. Their governance processes face pressures related to mission preservation, transparent resource allocation, and multi-stakeholder trust maintenance. Generative artificial intelligence can process unstructured information such as annual reports, project materials, meeting records, and stakeholder feedback, providing support for proposal generation, risk identification, and explanatory output in governance decision-making. Focusing on the governance trust mechanism of social enterprises under generative AI-assisted decision-making, this study constructs an analytical framework linking AI-assisted decision-making level, governance process quality, and governance trust outcomes. It further verifies the framework through public textual data, scenario-based experimental ratings, and a repeated-measures regression model. The results show that the AI-assisted decision-making group scores higher than the manual decision-making group in governance trust, decision transparency, and explanatory adequacy. Among the mechanism variables, explanatory adequacy makes the strongest contribution to governance trust, followed by risk controllability. The findings indicate that the value of generative AI in social enterprise governance lies mainly in improving information integration efficiency, explanatory clarity, and risk identification capability. The study also provides methodological references for building responsible AI-assisted governance mechanisms in social enterprises.

Show more

Riichi Mahjong is a difficult imperfect-information game. To improve the way Mahjong AI makes decisions, this paper proposes a hierarchical and risk-aware decision framework. Instead of choosing an action directly from the current state, the model first selects a high-level strategy and then evaluates specific actions under that strategy. A risk control head is also added so that the model can better handle dangerous situations and make a better trade-off between offense and defense. Experimental results show that this framework improves overall decision quality and gives a better balance between attack and safety. Among the tested models, the version that combines both strategy and risk performs the best overall. The latent strategy analysis also shows that the model learns different internal decision modes with different behavior patterns. This suggests that the proposed method is effective for Riichi Mahjong AI and can make the decision process more structured, stable, and easier to understand.

Show more