针对传统方法在运动鞋用户评论的感性因子提取中存在的效率低下、维度冗余问题,提出一种结合大语言模型(large language model,LLM)与主成分分析(principal component analysis,PCA)的自动化提取方法。以亚马逊电商平台的8680条运动鞋...针对传统方法在运动鞋用户评论的感性因子提取中存在的效率低下、维度冗余问题,提出一种结合大语言模型(large language model,LLM)与主成分分析(principal component analysis,PCA)的自动化提取方法。以亚马逊电商平台的8680条运动鞋用户评论为研究对象,采用GLM-4-9B-Chat模型自动生成感性词汇对,经数据清理后获得7619条有效数据;通过TF-IDF向量化处理后,设计k=10、15、20、25四组K-means聚类实验,对冗余维度进行合并优化,最终收敛得到6个核心感性因子。该方法通过整合LLM自动化提取、多聚类去冗余与PCA分析,为运动鞋感性工学的自动分析提供了一条技术路径,也为纺织服装领域的感性因子自动化提取研究提供了有益参考。展开更多
湖泊生态系统中溶解性有机物(dissolved organic matter,DOM)来源复杂,不同污染源输入差异显著,并深刻影响着湖泊物质循环与生态功能。以洞庭湖为研究对象,利用傅里叶变换离子回旋共振质谱(Fourier transform ion cyclotron resonance m...湖泊生态系统中溶解性有机物(dissolved organic matter,DOM)来源复杂,不同污染源输入差异显著,并深刻影响着湖泊物质循环与生态功能。以洞庭湖为研究对象,利用傅里叶变换离子回旋共振质谱(Fourier transform ion cyclotron resonance mass spectrometry,FT-ICR MS)分子表征技术,结合主成分分析(principal component analysis,PCA)-绝对主成分分数(absolute principal component scores,APCS)-多元线性回归(multiple linear regression,MLR)受体模型,定量解析湖区外源DOM的分子特征及贡献。结果表明:湖水DOM以CHO化合物为主,枯水期富含含硫化合物,丰水期含氮化合物比例较高;2个季节的DOM均以高度不饱和类化合物为主,且丰水期DOM的芳香性和稳定性更强;污染源DOM整体不饱和度和芳香性较高,难以降解;受体模型定量结果显示,外源对DOM的贡献顺序为农田水(37.7%)>污水(26.7%)>鱼塘水(18.3%)>未知来源(17.3%)。研究揭示了农业面源污染和生活污水是洞庭湖DOM的主要输入来源,可为湖泊DOM迁移转化机制解析和流域污染治理提供科学依据。展开更多
Active Shape Model （ASM） is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis （PCA） to statistically model the variabil...Active Shape Model （ASM） is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis （PCA） to statistically model the variability in the training set of example shapes. Independent Component Analysis （ICA） has been proven to be more efficient to extract face features than PCA. In this paper, we combine the PCA and ICA by the consecutive strategy to form a novel ASM. Firstly, an initial model, which shows the global shape variability in the training set, is generated by the PCA-based ASM. And then, the final shape model, which contains more local characters, is established by the ICA-based ASM. Experimental results verify that the accuracy of facial feature extraction is statistically significantly improved by applying the ICA modes after the PCA modes.展开更多
文摘针对传统方法在运动鞋用户评论的感性因子提取中存在的效率低下、维度冗余问题,提出一种结合大语言模型(large language model,LLM)与主成分分析(principal component analysis,PCA)的自动化提取方法。以亚马逊电商平台的8680条运动鞋用户评论为研究对象,采用GLM-4-9B-Chat模型自动生成感性词汇对,经数据清理后获得7619条有效数据;通过TF-IDF向量化处理后,设计k=10、15、20、25四组K-means聚类实验,对冗余维度进行合并优化,最终收敛得到6个核心感性因子。该方法通过整合LLM自动化提取、多聚类去冗余与PCA分析,为运动鞋感性工学的自动分析提供了一条技术路径,也为纺织服装领域的感性因子自动化提取研究提供了有益参考。
文摘湖泊生态系统中溶解性有机物(dissolved organic matter,DOM)来源复杂,不同污染源输入差异显著,并深刻影响着湖泊物质循环与生态功能。以洞庭湖为研究对象,利用傅里叶变换离子回旋共振质谱(Fourier transform ion cyclotron resonance mass spectrometry,FT-ICR MS)分子表征技术,结合主成分分析(principal component analysis,PCA)-绝对主成分分数(absolute principal component scores,APCS)-多元线性回归(multiple linear regression,MLR)受体模型,定量解析湖区外源DOM的分子特征及贡献。结果表明:湖水DOM以CHO化合物为主,枯水期富含含硫化合物,丰水期含氮化合物比例较高;2个季节的DOM均以高度不饱和类化合物为主,且丰水期DOM的芳香性和稳定性更强;污染源DOM整体不饱和度和芳香性较高,难以降解;受体模型定量结果显示,外源对DOM的贡献顺序为农田水(37.7%)>污水(26.7%)>鱼塘水(18.3%)>未知来源(17.3%)。研究揭示了农业面源污染和生活污水是洞庭湖DOM的主要输入来源,可为湖泊DOM迁移转化机制解析和流域污染治理提供科学依据。
文摘Active Shape Model （ASM） is a powerful statistical tool to extract the facial features of a face image under frontal view. It mainly relies on Principle Component Analysis （PCA） to statistically model the variability in the training set of example shapes. Independent Component Analysis （ICA） has been proven to be more efficient to extract face features than PCA. In this paper, we combine the PCA and ICA by the consecutive strategy to form a novel ASM. Firstly, an initial model, which shows the global shape variability in the training set, is generated by the PCA-based ASM. And then, the final shape model, which contains more local characters, is established by the ICA-based ASM. Experimental results verify that the accuracy of facial feature extraction is statistically significantly improved by applying the ICA modes after the PCA modes.
