This study is based on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and aims to explore early detection and disease progression in Alzheimer's disease (AD). We employ innovative data preprocessing strategies, including the use of the random forest algorithm to fill missing data and the handling of outliers and invalid data, thereby fully mining and utilizing these limited data resources. Through Spearman correlation coefficient analysis, we identify some features strongly correlated with AD diagnosis. We build and test three machine learning models using these features: random forest, XGBoost, and support vector machine (SVM). Among them, the XGBoost model performs the best in terms of diagnostic performance, achieving an accuracy of 91%. Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.

In this study, nanoscale periodic surface structures were fabricated on polyimide (PI) films using a linearly polarized KrF excimer laser with a wavelength of 248 nm. The effects of laser energy density and pulse number on the morphology and surface roughness of laser-induced periodic surface structures (LIPSSs) were systematically investigated. When the pulse width was 20 ns, the repetition rate was 10 Hz, and the beam incidence angle was normal (90°), periodic ripples with a spatial period of approximately 200 nm formed within an energy density range of 7–18 mJ/cm² and pulse number range of 6000–18,000. The most uniform and well-defined structures were achieved at 14.01 mJ/cm² and 12,000 pulses, with a ripple depth of 60 nm and surface roughness ($R_{\mathrm{a}}$) approximately 26 times greater than that of pristine PI. The ripple orientation was consistently perpendicular to the laser polarization, consistent with low-spatial-frequency LIPSS (LSFL) formation mechanisms governed by interference-induced photothermal effects. In addition, surface wettability was found to be significantly enhanced due to changes in both surface chemistry and topography, with the water contact angle decreasing from 73.7° to 19.7°. These results demonstrate the potential of UV nanosecond laser processing for the scalable fabrication of functional nanostructures on polymer surfaces for applications in surface engineering and biointerfaces.

In this study, considering the delays for a susceptible individual becoming an alcoholic and the relapse of a recovered individual back into being an alcoholic, we formulate an epidemic model for alcoholism with distributed delays and relapse. The basic reproduction number $R_0$ is calculated, and the threshold property of $R_0$ is established. By analyzing the characteristic equation, we demonstrate the local asymptotic stability of the different equilibria under various conditions: when $R_0<1$, the alcoholism-free equilibrium is locally asymptotically stable; when $R_0>1$, the alcoholism equilibrium exists and is locally asymptotically stable. Furthermore, we demonstrate the global asymptotic stability at each equilibrium using a suitable Lyapunov function. Specifically, when $R_0<1$, the alcoholism-free equilibrium is globally asymptotically stable; when $R_0>1$, the alcoholism equilibrium is globally asymptotically stable. The sensitivity analysis of $R_0$ shows that reducing exposure is more effective than treatment in controlling alcoholism. Interestingly, we found that extending the latency delay $h_1$ and relapse delay $h_2$ also effectively contribute to the control of the spread of alcoholism. Numerical simulations are also provided to support our theoretical results.

This study is based on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and aims to explore early detection and disease progression in Alzheimer's disease (AD). We employ innovative data preprocessing strategies, including the use of the random forest algorithm to fill missing data and the handling of outliers and invalid data, thereby fully mining and utilizing these limited data resources. Through Spearman correlation coefficient analysis, we identify some features strongly correlated with AD diagnosis. We build and test three machine learning models using these features: random forest, XGBoost, and support vector machine (SVM). Among them, the XGBoost model performs the best in terms of diagnostic performance, achieving an accuracy of 91%. Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.

In recent years, the rapid development of artificial intelligence (AI) technology has been driving profound transformations in higher education. As a fundamental course in science and engineering disciplines, Advanced Mathematics plays a crucial role in cultivating students’ logical thinking and innovative capabilities. However, the current teaching models exhibit significant shortcomings in fostering students’ ability to identify and solve problems, primarily reflected in the monotony of teaching content, the limitations of students’ thinking, and the constraints of instructional methods. In response to these issues, this paper proposes an AI-based teaching approach for Advanced Mathematics. By utilizing scenario simulations to guide students in discovering problems and employing modeling tools to assist them in solving problems in real time, the study constructs a comprehensive teaching model that spans the entire process from problem identification to problem resolution. Research findings indicate that the application of AI technology can effectively enhance students’ abilities in problem awareness, logical reasoning, and creative thinking. This study provides both theoretical support and practical reference for the reform of Advanced Mathematics education and the innovation of higher-level talent cultivation models.

On August 24, 2023, Japan controversially decided to discharge nuclear wastewater from the Fukushima Daiichi Nuclear Power Plant into the ocean, initiating intense domestic and global debates. This study employs a mixed-method approach, integrating quantitative evolutionary game theory and qualitative data analysis to explore the strategic dynamics among Japan, other nations, and the Japan Fisheries Association regarding this decision. The data includes international environmental reports and economic statistics, served as the basis for simulating decision-making processes under various legal, economic, and environmental pressures. The evolutionary game theory model is used to predict and analyze three evolutionarily stable strategies (ESS), detailing the transition from the initiation to cessation of wastewater discharge. These strategies highlight the necessity for international cooperation, rigorous scientific research, public education, and effective wastewater treatment methods. This study aims to provide both a theoretical framework and practical guidance to foster a global consensus on nuclear wastewater management, which is vital for marine conservation and sustainable development.