课程文献中心 更多>>

关键词： Materials Informatics   Machine learning   graphical user interface   Feature engineering  

摘要： Designing descriptors for materials and catalysts within machine learning is a complex process. In particular, material compositions can be represented using information from the periodic table. Additionally, feature engineering and feature selection add further complexity, requiring significant programming skills and knowledge of machine learning. To address this challenge, a web-based graphical user interface (GUI) for feature assignment, feature engineering, and feature selection has been developed. This GUI is designed to facilitate materials and catalysts design using machine learning, without the need for advanced programming or machine learning expertise.

关键词： COVID-19 vaccination   elderly care facility residents   influenza vaccination   Japan   pneumococcal vaccination   vaccination rate   web-based survey  

摘要： This study evaluated pneumococcal vaccination status using evaluable data collected from 445 of 1,313 managing directors of elderly care facilities in Japan through an online survey (September 5, 2022-November 25, 2022;UMIN000048747);comparisons were made with the influenza (2021-2022 vaccination only) and coronavirus disease 2019 (COVID-19) vaccination status. Among facilities who kept pneumococcal vaccination records (n = 42), the mean pneumococcal vaccination rate was 31.1%, with the rate being higher for the influenza (93.1%;n = 234) and COVID-19 (94.3%;n = 285) vaccines. Overall, excluding facilities that answered that the corresponding vaccine status at their sites was unknown, the percentage of facilities with high vaccination rates (80% to 100%) was substantially higher for the influenza (80.5%;351/436) and COVID-19 (89.6%;396/442) vaccines than for the pneumococcal vaccine (6.5%;24/370). Multivariable analysis showed that major factors associated with a high pneumococcal vaccination rate (>= 15%) were "managing director's willingness to recommend" and "pneumococcal vaccination request from the residents." The most common reason for their willingness to recommend the pneumococcal vaccine was that it is an effective disease prevention strategy (83.3%;65/78) and for their unwillingness to recommend the pneumococcal vaccine was the inability to understand the effectiveness of the vaccine (43.6%;17/39). In conclusion, there is a need to improve pneumococcal vaccination rates in elderly care facilities in Japan. Strategies such as increasing awareness and encouraging pneumococcal vaccine recommendation among managing directors, especially for residents not eligible for the national subsidy program, and providing regular training on the pneumococcal vaccine for staff and residents are required.

关键词： Elderly patients   bowel preparation   colonoscopy   machine learning   predictive model  

摘要： BackgroundAdequate bowel preparation is crucial for effective colonoscopy, especially in elderly patients who face a high risk of inadequate preparation. This study develops and validates a machine learning model to predict bowel preparation adequacy in elderly patients before *** study adhered to the TRIPOD AI guidelines. Clinical data from 471 elderly patients collected between February and December 2023 were utilized for developing and internally validating the model, while 221 patients' data from March to June 2024 were used for external validation. The Boruta algorithm was applied for feature selection. Models including logistic regression, light gradient boosting machines, support vector machines (SVM), decision trees, random forests, and extreme gradient boosting were evaluated using metrics such as AUC, accuracy, sensitivity, and specificity. The SHAP algorithm helped rank feature importance. A web-based application was developed using the Streamlit framework to enhance clinical *** Boruta algorithm identified 7 key features. The SVM model excelled with an AUC of 0.895 (95% CI: 0.822-0.969), and high accuracy, sensitivity, and specificity. In external validation, the SVM model maintained robust performance with an AUC of 0.889. The SHAP algorithm further explained the contribution of each feature to model *** study developed an interpretable and practical machine learning model for predicting bowel preparation adequacy in elderly patients, facilitating early interventions to improve outcomes and reduce resource wastage.

关键词： Encryption   dark web   cyber terrorism   legal implications   countermeasures  

摘要： The rapid growth of digital technologies has provided new opportunities for cyber criminals, including terrorist organizations, to exploit encrypted communications and the Dark Web for illicit activities. Cyber terrorism, characterized by the use of cyber-attacks to cause fear, disrupt societies, or damage national security, has become a significant threat in the modern world. Encryption technology ensures privacy and security for legitimate users, but it is also increasingly used by terrorists to coordinate attacks and evade detection. Simultaneously, the Dark Web offers anonymity, facilitating illegal activities such as recruitment, fundraising, and the planning of cyber-attacks. This research explores the intersection of encryption, the Dark Web, and cyber terrorism, examining the Indian legal implications of these technologies in facilitating terrorist activities. Using a doctrinal research methodology, this study analyzes existing Indian legal frameworks such as the Unlawful Activities (Prevention) Act and the Information Technology Act along with international conventions addressing encryption and the Dark Web. It evaluates the challenges posed by these technologies to law enforcement and the balance between national security and individual privacy rights. It evaluates potential countermeasures, including international cooperation, advanced decryption techniques, and policy reforms aimed at striking a balance between privacy and national security. This study provides insights into the growing threat posed by cyber terrorism in India and the urgent need for comprehensive legal and technological responses.

关键词： 新工科   环境工程   水文学   水文地质学   教学改革  

摘要： 传统的高校人才培养模式使学生普遍缺乏工程实践和创新能力,与企业的实际需求存在较大差异。水文学与水文地质学是高校环境工程专业一门重要的专业基础课,具有学科交叉性强、内容多和应用实践性强等特点。该文以塔里木大学环境工程专业的该门课程教学为例,分析当前教学过程中存在的问题,探讨在新工科背景下该门课程的教学优化改革途径。该途径从合理选取教学内容、教学方式和方法的灵活应用、理论教学与实践教学相结合、综合运用多种教学方法和完善课程考核方式五个方面进行改革与实践,激发学生的学习兴趣,提高教学质量,可为其他课程的教学改革提供参考。

关键词： 急性心肌梗死   中性粒细胞   生物标志物   差异分析   WGCNA   机器学习算法   免疫浸润分析   S100A12   PTCH1   LOC400499  

摘要： 背景:精确的早期诊断和及时的再灌注治疗是挽救急性心肌梗死患者的生命并改善预后的重要前提条件。因此,寻找能够早期诊断急性心肌梗死的理想生物标志物尤为重要。目的:拟通过生物信息学和机器学习分析急性心肌梗死与中性粒细胞相关的关键基因,以探寻新的生物标志物。方法:基于GEO数据库和limma包鉴定急性心肌梗死的差异表达基因。使用反卷积算法探究免疫细胞浸润情况,然后结合加权基因共表达网络分析(Weighted gene co-expression network analysis,WGCNA)、蛋白互作网络和机器学习筛选急性心肌梗死与中性粒细胞相关的特征基因,并进行功能富集分析。用ROC曲线评估特征基因对急性心肌梗死的诊断价值。通过STITCH和Herb数据库筛查生物标志物的靶向药物。最后将在2023年3-6月于贵州医科大学附属医院心内科首次诊断为急性心肌梗死的住院患者作为实验组,同期心电图无缺血性改变、冠状动脉造影无狭窄的住院患者作为对照组,收集两组患者外周血,通过RT-qPCR验证基因在人外周血样本中的相对表达量。结果与结论:(1)共获得差异表达基因2 349个,免疫浸润分析发现B cells memory,NK cells resting和Neutrophils等免疫细胞评分在疾病和正常组之间存在差异;(2)使用WGCNA发现ME green和ME turquoise这两个基因模块与中性粒细胞与急性心肌梗死表现出最高的相关性;(3)与差异表达基因相交后获得24个差异模块基因,功能富集分析发现其与先天免疫反应、细菌的防御反应等多种过程相关;KEGG结果显示其主要与肿瘤坏死因子信号通路有关。(4)机器学习算法挖掘到的基因取交集后得到的特征基因为S100A12,PTCH1和LOC400499,在GSE48060和GSE66360数据集中的ROC曲线下面积均大于0.7,将其视为潜在的生物标志物。(5)基于STITCH和Herb数据库发现S100A12有11种靶向药物,PTCH1共发现6种靶向药物。(6)RT-qPCR结果显示,与对照组相比,急性心肌梗死患者中S100A12,PTCH1和LOC400499表达具有显著差异性(P<0.05)。(7)S100A12,PTCH1和LOC400499可能是急性心肌梗死潜在的诊断生物标志物,但是其与急性心肌梗死相关的特异性尚需进一步研究,其中S100A12可能是调控急性心肌梗死的潜在靶点。

关键词： 智能网联   数字孪生   资源重构   教学模式   先进制造  

摘要： 该文基于智能网联数字技术,将先进制造专业群各专业离散型实践中心教仪进行数字孪生,实现专业群各数字资源的重构、整合、联接和集成,打通专业群中各专业物理壁垒,实现专业群教仪数据和资源共建、共管、共用和共享,促进专业群教学模式的改革,实现教学管理、教学过程、教学评价的数据量化,助推教育教学数字化转型升级。

关键词： 高质量发展   高职教育   地区   经济发展   教育模式改革  

摘要： 党的二十大提出,当前社会重要目标之一是要促进社会高质量发展,提高综合实力。紧紧贴合所研究地区的经济产业实际情况,以及高职教育与社会发展的内在关系等,研究促进地区经济发展的高职教育新模式。通过查阅资料文献,调研数据收集,高职教育助力地区经济发展在“一带一路”、乡村振兴等渠道有较为深入的开展,实际帮助地区社会质量提升。在探索研究高职教育助力地区发展的过程中,要从高职教育与地区经济两者的内在本质联系出发,才能有效探索出助力发展途径。