目的基于随机森林模型探讨中青年乳腺癌患者未成年子女养育忧虑现状及其影响因素,为临床干预提供依据。方法采用便利抽样法,选择2023年4月至12月在本市某三级甲等综合医院乳腺外科接受诊疗的275例乳腺癌患者为研究对象。采用自行设计的...目的基于随机森林模型探讨中青年乳腺癌患者未成年子女养育忧虑现状及其影响因素,为临床干预提供依据。方法采用便利抽样法,选择2023年4月至12月在本市某三级甲等综合医院乳腺外科接受诊疗的275例乳腺癌患者为研究对象。采用自行设计的一般资料问卷、中文版养育忧虑问卷(parenting concerns questionnaire,PCQ)、领悟社会支持量表(perceived social support scale,PSSS)、癌症复发担忧量表(concern about recurrence scale,CARS)、简易疾病感知量表(brief illness perception questionnaire,BIPQ)进行调查。基于随机森林模型和最小绝对收缩和选择算法(least absolute shrinkage and selection operator,LASSO)对变量进行重要性排序和变量筛选,将筛选后的变量纳入多元线性回归分析。结果260例患者完成研究。中青年乳腺癌患者养育忧虑得分为(51.1±6.4)分。将随机森林及LASSO回归确定的变量,纳入多元线性回归分析结果显示(并按影响因素重次要排序),疾病感知越高、领悟社会支持越低、癌症复发担忧越大、肿瘤分期Ⅳ期、离异/丧偶、未成年子女个数越多的中青年乳腺癌患者养育的忧虑越严重(均P<0.05),解释总变异的57.0%。结论中青年乳腺癌患者养育忧虑处于中等偏高水平,受多种因素影响,医护人员应针对性制订措施给予干预,以便降低患者养育忧虑水平。展开更多
为进一步推进塔吉克斯坦地区的地质灾害评估工作,本文采用信息量模型和随机森林模型对海东市的滑坡灾害进行易发性评价,并通过ROC曲线对这两种模型的性能进行了评估。结果表明,信息量模型与随机森林模型均表现出良好的分类能力,然而随...为进一步推进塔吉克斯坦地区的地质灾害评估工作,本文采用信息量模型和随机森林模型对海东市的滑坡灾害进行易发性评价,并通过ROC曲线对这两种模型的性能进行了评估。结果表明,信息量模型与随机森林模型均表现出良好的分类能力,然而随机森林模型的表现更优于信息量模型。信息量模型在对相关因子的分级分析中表现卓越,能够有效识别某因子分级内对滑坡影响最深的区间。而随机森林模型则在衡量因子的相对重要性方面具有优势。两种模型各具特色,结合使用能够更全面地掌握滑坡灾害的成因与易发性,为后续的地质灾害防治措施提供科学依据。To further advance the assessment of geological disasters in the Tajikistan region, this paper employs the information value model and the random forest model to evaluate the susceptibility to landslides in Haidong City, and assesses the performance of these two models using ROC curves. The results indicate that both the information value model and the random forest model demonstrate good classification capabilities;however, the random forest model outperforms the information value model. The information value model excels in the graded analysis of relevant factors, effectively identifying the intervals within a factor’s grading that have the most significant impact on landslides. In contrast, the random forest model has an advantage in measuring the relative importance of factors. Each model has its unique characteristics, and their combined use can provide a more comprehensive understanding of the causes and susceptibility of landslide disasters, offering a scientific basis for subsequent geological disaster prevention and control measures.展开更多
目的:运用随机森林算法研究大学生人格特质对抑郁水平的影响。方法:采用中国大五人格问卷极简版、抑郁自评量表对1436名大学生进行测量。使用回归模型分析大学生人格特质是否影响其抑郁水平,通过R语言构建随机森林模型分析大学生人格特...目的:运用随机森林算法研究大学生人格特质对抑郁水平的影响。方法:采用中国大五人格问卷极简版、抑郁自评量表对1436名大学生进行测量。使用回归模型分析大学生人格特质是否影响其抑郁水平,通过R语言构建随机森林模型分析大学生人格特质对抑郁水平的重要性。结果:回收到有效问卷1368份,问卷有效率为95.3%。回归模型显示,大学生人格特质对其心理健康的影响有统计学意义。随机森林模型显示,大学生人格特质对抑郁水平的影响按重要性排名分别是神经质、责任心、宜人性、开放性、外倾性。结论:人格特质是影响大学生心理健康中的抑郁水平的重要因素。测量大学生的人格特质,是识别和干预大学生抑郁水平的有效途径。Objective: The random forest algorithm was used to explore the influence of personality traits on depression level of college students. Methods: 1436 college students were measured by the Chinese Big Five Personality Questionnaire Inventory Brief 15-item Version and Self-rating Depression Scale. Regression model was used to analyze whether college students’ personality traits affected their depression level, and R language was used to construct a random forest model to analyze the importance of college students’ personality traits to depression level. Results: 1368 valid questionnaires were collected, the effective rate was 95.3%. The regression model shows that the influence of college students’ personality traits on their mental health has statistical significance. Random Forest model shows that the influence of personality traits on depression level of college students is neuroticism, conscientiousness, agreeableness, openness and extraversion. Conclusion: Personality trait is an important factor affecting the level of depression in college students’ mental health. Measuring the personality traits of college students is an effective way to identify and intervene in their levels of depression.展开更多
随着对地观测技术的飞速发展,我们能够以前所未有的精度和频率获取地球表面的各种数据,通过进行更精细的空间分析和时间序列分析,可以揭示地理环境变化的深层次规律。本文旨在建立中国降水量变化趋势及其与海拔、坡度、土地利用之间的...随着对地观测技术的飞速发展,我们能够以前所未有的精度和频率获取地球表面的各种数据,通过进行更精细的空间分析和时间序列分析,可以揭示地理环境变化的深层次规律。本文旨在建立中国降水量变化趋势及其与海拔、坡度、土地利用之间的预测模型。通过对降水量、地形因素和五种主要土地覆盖类型的相关性分析,运用Logistic回归和随机森林模型探讨了这些因素对灾害发生的共同影响机制。此外,采用ARIMA时间序列模型预测了未来2025年到2035年间的降水量和土地利用格局,并结合随机森林模型评估了此期间各地区暴雨灾害风险的空间分布。研究结果揭示了在极端天气条件下最脆弱的地区,为灾害防范和土地规划提供了重要参考。With the rapid advancement of remote sensing technologies, we are now able to obtain various data on the Earth’s surface with unprecedented accuracy and frequency. Through more refined spatial and time series analyses, the underlying patterns of geographical environmental changes can be revealed. This study aims to establish predictive models for the trends in precipitation changes in China and their relationships with elevation, slope, and land use. By analyzing the correlations between precipitation, topographic factors, and five major land cover types, the study employs Logistic regression and Random Forest models to explore the joint impact of these factors on the occurrence of disasters. Additionally, the ARIMA time series model is utilized to forecast precipitation and land use patterns from 2025 to 2035, while the Random Forest model is applied to assess the spatial distribution of rainfall disaster risks during this period. The results of the study highlight the most vulnerable regions under extreme weather conditions, providing valuable insights for disaster prevention and land planning.展开更多
Dior“文化挪用”马面裙事件引发民众热议,以“马面裙”为代表的新中式服装走进大众视野。新中式服装实现了传统文化与现代时尚的完美融合,其产业发展在经济、文化等不同维度上均具有重要价值,因而了解民众对新中式服装的情感倾向与关注...Dior“文化挪用”马面裙事件引发民众热议,以“马面裙”为代表的新中式服装走进大众视野。新中式服装实现了传统文化与现代时尚的完美融合,其产业发展在经济、文化等不同维度上均具有重要价值,因而了解民众对新中式服装的情感倾向与关注点,深入分析影响民众关于新中式服装购买意愿的影响因素对新中式服装产业的未来发展及传统文化传承具有深远意义。团队通过网络爬取进行文本分析,为问卷设计提供理论支持。基于描述性统计分析构建消费者画像,综合应用二值Logistic回归与随机森林模型确定影响消费意愿的主要因素,从消费者因素、产品因素和推广途径三个方面明确新中式服装的市场方向,以此提出有价值的结论与建议。结果表明,性别、年龄、学历、收入、地区作用的消费者自身因素是影响新中式服装购买意愿的最主要因素。Dior’s “cultural appropriation” incident involving horse-face skirts has sparked public discussion, and new Chinese-style clothing represented by the horse-face skirts has entered the public eye. This style perfectly blends traditional culture with modern fashion, and its industrial development has important value in different dimensions such as economy and culture. Therefore, understanding the emotional tendencies and concerns of the public towards the new Chinese-style clothing, and conducting a deep analysis of the factors influencing the public’s willingness to purchase such clothing have profound significance for the future development of the new Chinese-style clothing industry and the inheritance of traditional culture. The team conducted text analysis through web crawling to provide theoretical support for questionnaire design. Based on descriptive statistical analysis, a consumer portrait is constructed, and binary logistic regression and random forest models are comprehensively applied to determine the main factors affecting consumers’ willingness. Clarifying the market direction of new Chinese-style clothing from three aspects: consumer factors, product attributes, and promotional channels, in order to provide valuable conclusions and suggestions. The results indicate that consumer factors such as gender, age, education, income, and regional influence are the most significant factors affecting the willingness to purchase new Chinese-style clothing.展开更多
随着数字化转型的加速,数字经济已成为推动中国经济高质量发展的重要引擎。然而,不同区域之间数字经济的发展水平存在显著差异,对区域间差距及其演变规律的研究具有重要意义。本研究基于2000年至2022年中国八大经济区的数字经济指数数据...随着数字化转型的加速,数字经济已成为推动中国经济高质量发展的重要引擎。然而,不同区域之间数字经济的发展水平存在显著差异,对区域间差距及其演变规律的研究具有重要意义。本研究基于2000年至2022年中国八大经济区的数字经济指数数据,利用随机森林模型对全国数字经济指数进行动态预测,并分析区域间的数字经济差异及其成因。研究结果表明,未来五年(2025~2029年)全国数字经济指数将保持稳步增长。区域分析显示,东部沿海经济区的数字经济指数始终领先,大西北和黄河中游经济区则相对较低但增长势头良好。基于研究结果,本研究提出了加强中西部地区政策支持、优化数字基础设施建设、推动区域协同发展以及激发内生动力等政策建议,以促进区域间数字经济的均衡发展。本研究为理解中国数字经济发展的总体趋势与区域特征提供了重要参考,也为优化数字经济政策制定和实现高质量发展提供了科学依据。With the acceleration of digital transformation, the digital economy has become an important engine to promote the high-quality development of China’s economy. However, there are significant differences in the development level of digital economy among different regions, and it is of great significance to study the inter-regional gap and its evolution pattern. Based on the digital economy index data of China’s eight economic regions from 2000 to 2022, this study uses the Random Forest Model to dynamically forecast the national digital economy index and analyze the inter-regional digital economy differences and their causes. The results show that the national digital economy index will maintain a steady growth in the next five years (2025~2029). Regional analyses show that the Eastern Coastal Economic Zone consistently leads the Digital Economy Index, while the Great Northwest and Middle Yellow River Economic Zones have relatively low but good growth momentum. Based on the findings, this study proposes policy recommendations such as strengthening policy support in the central and western regions, optimizing digital infrastructure construction, promoting regional synergistic development, and stimulating endogenous dynamics, in order to promote balanced development of the digital economy among regions. This study provides an important reference for understanding the general trend and regional characteristics of China’s digital economy development, as well as a scientific basis for optimizing digital economy policymaking and achieving high-quality development.展开更多
本研究基于无人机影像数据和随机森林模型,探讨了农作物提取的方法与效果。通过对无人机获取的高分辨率影像进行处理和分析,结合机器学习算法,实现了对农作物种植区域的自动提取和分类。研究结果表明,结合无人机影像和随机森林模型能够...本研究基于无人机影像数据和随机森林模型,探讨了农作物提取的方法与效果。通过对无人机获取的高分辨率影像进行处理和分析,结合机器学习算法,实现了对农作物种植区域的自动提取和分类。研究结果表明,结合无人机影像和随机森林模型能够有效地提高农作物提取的准确性和效率,为农业生产提供了重要的技术支持。Based on UAV (Unmanned Aerial Vehicle) image data and the random forest model, this study explored the methods and effects of crop extraction. By processing and analyzing the high-resolution images obtained by UAVs and combining with machine learning algorithms, the automatic extraction and classification of crop planting areas were achieved. The research results show that the combination of UAV images and the random forest model can effectively improve the accuracy and efficiency of crop extraction, providing important technical support for agricultural production.展开更多
文摘目的基于随机森林模型探讨中青年乳腺癌患者未成年子女养育忧虑现状及其影响因素,为临床干预提供依据。方法采用便利抽样法,选择2023年4月至12月在本市某三级甲等综合医院乳腺外科接受诊疗的275例乳腺癌患者为研究对象。采用自行设计的一般资料问卷、中文版养育忧虑问卷(parenting concerns questionnaire,PCQ)、领悟社会支持量表(perceived social support scale,PSSS)、癌症复发担忧量表(concern about recurrence scale,CARS)、简易疾病感知量表(brief illness perception questionnaire,BIPQ)进行调查。基于随机森林模型和最小绝对收缩和选择算法(least absolute shrinkage and selection operator,LASSO)对变量进行重要性排序和变量筛选,将筛选后的变量纳入多元线性回归分析。结果260例患者完成研究。中青年乳腺癌患者养育忧虑得分为(51.1±6.4)分。将随机森林及LASSO回归确定的变量,纳入多元线性回归分析结果显示(并按影响因素重次要排序),疾病感知越高、领悟社会支持越低、癌症复发担忧越大、肿瘤分期Ⅳ期、离异/丧偶、未成年子女个数越多的中青年乳腺癌患者养育的忧虑越严重(均P<0.05),解释总变异的57.0%。结论中青年乳腺癌患者养育忧虑处于中等偏高水平,受多种因素影响,医护人员应针对性制订措施给予干预,以便降低患者养育忧虑水平。
文摘为进一步推进塔吉克斯坦地区的地质灾害评估工作,本文采用信息量模型和随机森林模型对海东市的滑坡灾害进行易发性评价,并通过ROC曲线对这两种模型的性能进行了评估。结果表明,信息量模型与随机森林模型均表现出良好的分类能力,然而随机森林模型的表现更优于信息量模型。信息量模型在对相关因子的分级分析中表现卓越,能够有效识别某因子分级内对滑坡影响最深的区间。而随机森林模型则在衡量因子的相对重要性方面具有优势。两种模型各具特色,结合使用能够更全面地掌握滑坡灾害的成因与易发性,为后续的地质灾害防治措施提供科学依据。To further advance the assessment of geological disasters in the Tajikistan region, this paper employs the information value model and the random forest model to evaluate the susceptibility to landslides in Haidong City, and assesses the performance of these two models using ROC curves. The results indicate that both the information value model and the random forest model demonstrate good classification capabilities;however, the random forest model outperforms the information value model. The information value model excels in the graded analysis of relevant factors, effectively identifying the intervals within a factor’s grading that have the most significant impact on landslides. In contrast, the random forest model has an advantage in measuring the relative importance of factors. Each model has its unique characteristics, and their combined use can provide a more comprehensive understanding of the causes and susceptibility of landslide disasters, offering a scientific basis for subsequent geological disaster prevention and control measures.
文摘目的:运用随机森林算法研究大学生人格特质对抑郁水平的影响。方法:采用中国大五人格问卷极简版、抑郁自评量表对1436名大学生进行测量。使用回归模型分析大学生人格特质是否影响其抑郁水平,通过R语言构建随机森林模型分析大学生人格特质对抑郁水平的重要性。结果:回收到有效问卷1368份,问卷有效率为95.3%。回归模型显示,大学生人格特质对其心理健康的影响有统计学意义。随机森林模型显示,大学生人格特质对抑郁水平的影响按重要性排名分别是神经质、责任心、宜人性、开放性、外倾性。结论:人格特质是影响大学生心理健康中的抑郁水平的重要因素。测量大学生的人格特质,是识别和干预大学生抑郁水平的有效途径。Objective: The random forest algorithm was used to explore the influence of personality traits on depression level of college students. Methods: 1436 college students were measured by the Chinese Big Five Personality Questionnaire Inventory Brief 15-item Version and Self-rating Depression Scale. Regression model was used to analyze whether college students’ personality traits affected their depression level, and R language was used to construct a random forest model to analyze the importance of college students’ personality traits to depression level. Results: 1368 valid questionnaires were collected, the effective rate was 95.3%. The regression model shows that the influence of college students’ personality traits on their mental health has statistical significance. Random Forest model shows that the influence of personality traits on depression level of college students is neuroticism, conscientiousness, agreeableness, openness and extraversion. Conclusion: Personality trait is an important factor affecting the level of depression in college students’ mental health. Measuring the personality traits of college students is an effective way to identify and intervene in their levels of depression.
文摘随着对地观测技术的飞速发展,我们能够以前所未有的精度和频率获取地球表面的各种数据,通过进行更精细的空间分析和时间序列分析,可以揭示地理环境变化的深层次规律。本文旨在建立中国降水量变化趋势及其与海拔、坡度、土地利用之间的预测模型。通过对降水量、地形因素和五种主要土地覆盖类型的相关性分析,运用Logistic回归和随机森林模型探讨了这些因素对灾害发生的共同影响机制。此外,采用ARIMA时间序列模型预测了未来2025年到2035年间的降水量和土地利用格局,并结合随机森林模型评估了此期间各地区暴雨灾害风险的空间分布。研究结果揭示了在极端天气条件下最脆弱的地区,为灾害防范和土地规划提供了重要参考。With the rapid advancement of remote sensing technologies, we are now able to obtain various data on the Earth’s surface with unprecedented accuracy and frequency. Through more refined spatial and time series analyses, the underlying patterns of geographical environmental changes can be revealed. This study aims to establish predictive models for the trends in precipitation changes in China and their relationships with elevation, slope, and land use. By analyzing the correlations between precipitation, topographic factors, and five major land cover types, the study employs Logistic regression and Random Forest models to explore the joint impact of these factors on the occurrence of disasters. Additionally, the ARIMA time series model is utilized to forecast precipitation and land use patterns from 2025 to 2035, while the Random Forest model is applied to assess the spatial distribution of rainfall disaster risks during this period. The results of the study highlight the most vulnerable regions under extreme weather conditions, providing valuable insights for disaster prevention and land planning.
文摘Dior“文化挪用”马面裙事件引发民众热议,以“马面裙”为代表的新中式服装走进大众视野。新中式服装实现了传统文化与现代时尚的完美融合,其产业发展在经济、文化等不同维度上均具有重要价值,因而了解民众对新中式服装的情感倾向与关注点,深入分析影响民众关于新中式服装购买意愿的影响因素对新中式服装产业的未来发展及传统文化传承具有深远意义。团队通过网络爬取进行文本分析,为问卷设计提供理论支持。基于描述性统计分析构建消费者画像,综合应用二值Logistic回归与随机森林模型确定影响消费意愿的主要因素,从消费者因素、产品因素和推广途径三个方面明确新中式服装的市场方向,以此提出有价值的结论与建议。结果表明,性别、年龄、学历、收入、地区作用的消费者自身因素是影响新中式服装购买意愿的最主要因素。Dior’s “cultural appropriation” incident involving horse-face skirts has sparked public discussion, and new Chinese-style clothing represented by the horse-face skirts has entered the public eye. This style perfectly blends traditional culture with modern fashion, and its industrial development has important value in different dimensions such as economy and culture. Therefore, understanding the emotional tendencies and concerns of the public towards the new Chinese-style clothing, and conducting a deep analysis of the factors influencing the public’s willingness to purchase such clothing have profound significance for the future development of the new Chinese-style clothing industry and the inheritance of traditional culture. The team conducted text analysis through web crawling to provide theoretical support for questionnaire design. Based on descriptive statistical analysis, a consumer portrait is constructed, and binary logistic regression and random forest models are comprehensively applied to determine the main factors affecting consumers’ willingness. Clarifying the market direction of new Chinese-style clothing from three aspects: consumer factors, product attributes, and promotional channels, in order to provide valuable conclusions and suggestions. The results indicate that consumer factors such as gender, age, education, income, and regional influence are the most significant factors affecting the willingness to purchase new Chinese-style clothing.
文摘随着数字化转型的加速,数字经济已成为推动中国经济高质量发展的重要引擎。然而,不同区域之间数字经济的发展水平存在显著差异,对区域间差距及其演变规律的研究具有重要意义。本研究基于2000年至2022年中国八大经济区的数字经济指数数据,利用随机森林模型对全国数字经济指数进行动态预测,并分析区域间的数字经济差异及其成因。研究结果表明,未来五年(2025~2029年)全国数字经济指数将保持稳步增长。区域分析显示,东部沿海经济区的数字经济指数始终领先,大西北和黄河中游经济区则相对较低但增长势头良好。基于研究结果,本研究提出了加强中西部地区政策支持、优化数字基础设施建设、推动区域协同发展以及激发内生动力等政策建议,以促进区域间数字经济的均衡发展。本研究为理解中国数字经济发展的总体趋势与区域特征提供了重要参考,也为优化数字经济政策制定和实现高质量发展提供了科学依据。With the acceleration of digital transformation, the digital economy has become an important engine to promote the high-quality development of China’s economy. However, there are significant differences in the development level of digital economy among different regions, and it is of great significance to study the inter-regional gap and its evolution pattern. Based on the digital economy index data of China’s eight economic regions from 2000 to 2022, this study uses the Random Forest Model to dynamically forecast the national digital economy index and analyze the inter-regional digital economy differences and their causes. The results show that the national digital economy index will maintain a steady growth in the next five years (2025~2029). Regional analyses show that the Eastern Coastal Economic Zone consistently leads the Digital Economy Index, while the Great Northwest and Middle Yellow River Economic Zones have relatively low but good growth momentum. Based on the findings, this study proposes policy recommendations such as strengthening policy support in the central and western regions, optimizing digital infrastructure construction, promoting regional synergistic development, and stimulating endogenous dynamics, in order to promote balanced development of the digital economy among regions. This study provides an important reference for understanding the general trend and regional characteristics of China’s digital economy development, as well as a scientific basis for optimizing digital economy policymaking and achieving high-quality development.
文摘本研究基于无人机影像数据和随机森林模型,探讨了农作物提取的方法与效果。通过对无人机获取的高分辨率影像进行处理和分析,结合机器学习算法,实现了对农作物种植区域的自动提取和分类。研究结果表明,结合无人机影像和随机森林模型能够有效地提高农作物提取的准确性和效率,为农业生产提供了重要的技术支持。Based on UAV (Unmanned Aerial Vehicle) image data and the random forest model, this study explored the methods and effects of crop extraction. By processing and analyzing the high-resolution images obtained by UAVs and combining with machine learning algorithms, the automatic extraction and classification of crop planting areas were achieved. The research results show that the combination of UAV images and the random forest model can effectively improve the accuracy and efficiency of crop extraction, providing important technical support for agricultural production.
