Accurate prediction of manufacturing carbon emissions is of great significance for subsequent low-carbon optimization.To improve the accuracy of carbon emission prediction with insufficient hobbing data,combining the ...Accurate prediction of manufacturing carbon emissions is of great significance for subsequent low-carbon optimization.To improve the accuracy of carbon emission prediction with insufficient hobbing data,combining the advantages of improved algorithm and supplementary data,a method of carbon emission prediction of hobbing based on cross-process data fusion was proposed.Firstly,we analyzed the similarity of machining process and manufacturing characteristics and selected milling data as the fusion material for hobbing data.Then,the adversarial learning was used to reduce the difference between data from the two processes,so as to realize the data fusion at the characteristic level.After that,based on Meta-Transfer Learning method,the carbon emission prediction model of hobbing was established.The effectiveness and superiority of the proposed method were verified by case analysis and comparison.The prediction accuracy of the proposed method is better than other methods across different data sizes.展开更多
目的系统整合体外受精-胚胎移植(in vitro fertilization and embryo transfer,IVF-ET)治疗夫妻的心理体验与调适,为夫妻二元健康管理提供证据。方法计算机检索Cochrane Library、PubMed、Web of Science、CINAHL、Embase、Scopus、Oiv...目的系统整合体外受精-胚胎移植(in vitro fertilization and embryo transfer,IVF-ET)治疗夫妻的心理体验与调适,为夫妻二元健康管理提供证据。方法计算机检索Cochrane Library、PubMed、Web of Science、CINAHL、Embase、Scopus、Oivd、中国知网、万方和维普数据库中关于IVF-ET治疗夫妻心理体验与调适的质性研究,检索时限为建库至2023年12月31日,按照澳大利亚乔安娜布里格斯研究所(Joanna Briggs Institute,JBI)循证卫生保健中心质性研究质量评价标准进行文献方法学质量评价,采用汇集性整合的方法对结果进行Meta整合。结果纳入15篇文献,提炼出31个结果,归纳为9个类别,形成4个整合结果:获得的积极感受和社会支持、面临的身心压力和社会挑战、夫妻采取多种方式应对治疗压力、夫妻关系经过调适发生变化。结论加强以夫妻二元为中心的IVF-ET治疗全周期健康管理,重视夫妻治疗不同阶段的心理体验,提升夫妻积极应对与调适,完善社会文化和医疗支持体系,进而改善治疗结局和夫妻婚姻质量。展开更多
大量未标注且杂乱的评论是当下情感分类任务面临的难题。文章提出了基于语义的特征迁移策略,对不同领域间的语句进行语义相关度和语义相似度度量,并量化排序,从而将源领域特征项的类别指示作用迁移至目标领域。此外,还提出了语句情感空...大量未标注且杂乱的评论是当下情感分类任务面临的难题。文章提出了基于语义的特征迁移策略,对不同领域间的语句进行语义相关度和语义相似度度量,并量化排序,从而将源领域特征项的类别指示作用迁移至目标领域。此外,还提出了语句情感空间向量元模型(Sentence Emotion Space Vector Meta Model,SESVMM),实验表明该方法具有可行性和优越性。展开更多
睡眠障碍受到越来越多的关注,且自动化睡眠分期的准确性、泛化性受到了越来越多的挑战。然而,公开的睡眠数据十分有限,睡眠分期任务实际上更近似于一种小样本场景;同时由于睡眠特征的个体差异普遍存在,现有的机器学习模型很难保证准确...睡眠障碍受到越来越多的关注,且自动化睡眠分期的准确性、泛化性受到了越来越多的挑战。然而,公开的睡眠数据十分有限,睡眠分期任务实际上更近似于一种小样本场景;同时由于睡眠特征的个体差异普遍存在,现有的机器学习模型很难保证准确判读未参与训练的新受试者的数据。为了实现对新受试者睡眠数据的精准分期,现有研究通常需要额外采集、标注新受试者的大量数据,并对模型进行个性化微调。基于此,借鉴迁移学习中基于缩放-偏移的权重迁移思想,提出一种元迁移睡眠分期模型MTSL(Meta Transfer Sleep Learner),设计了一种新的元迁移学习框架:训练阶段包括预训练与元迁移训练两步,其中元迁移训练时使用大量的元任务进行训练;而在测试阶段仅使用极少的新受试者数据进行微调,模型就能轻松适应新受试者的特征分布,大幅减少对新受试者进行准确睡眠分期的成本。在两个公开的睡眠数据集上的实验结果表明,MTSL模型在单数据集、跨数据集两种条件下都能取得更高的准确率和F1分数,这表明MTSL更适合小样本场景下的睡眠分期任务。展开更多
基金Supported by National Natural Science Foundation of China(Grant No.52005062)Chongqing Municipal Natural Science Foundation of China(Grant No.CSTB2023NSCQ-MSX0390)。
文摘Accurate prediction of manufacturing carbon emissions is of great significance for subsequent low-carbon optimization.To improve the accuracy of carbon emission prediction with insufficient hobbing data,combining the advantages of improved algorithm and supplementary data,a method of carbon emission prediction of hobbing based on cross-process data fusion was proposed.Firstly,we analyzed the similarity of machining process and manufacturing characteristics and selected milling data as the fusion material for hobbing data.Then,the adversarial learning was used to reduce the difference between data from the two processes,so as to realize the data fusion at the characteristic level.After that,based on Meta-Transfer Learning method,the carbon emission prediction model of hobbing was established.The effectiveness and superiority of the proposed method were verified by case analysis and comparison.The prediction accuracy of the proposed method is better than other methods across different data sizes.
文摘大量未标注且杂乱的评论是当下情感分类任务面临的难题。文章提出了基于语义的特征迁移策略,对不同领域间的语句进行语义相关度和语义相似度度量,并量化排序,从而将源领域特征项的类别指示作用迁移至目标领域。此外,还提出了语句情感空间向量元模型(Sentence Emotion Space Vector Meta Model,SESVMM),实验表明该方法具有可行性和优越性。
文摘睡眠障碍受到越来越多的关注,且自动化睡眠分期的准确性、泛化性受到了越来越多的挑战。然而,公开的睡眠数据十分有限,睡眠分期任务实际上更近似于一种小样本场景;同时由于睡眠特征的个体差异普遍存在,现有的机器学习模型很难保证准确判读未参与训练的新受试者的数据。为了实现对新受试者睡眠数据的精准分期,现有研究通常需要额外采集、标注新受试者的大量数据,并对模型进行个性化微调。基于此,借鉴迁移学习中基于缩放-偏移的权重迁移思想,提出一种元迁移睡眠分期模型MTSL(Meta Transfer Sleep Learner),设计了一种新的元迁移学习框架:训练阶段包括预训练与元迁移训练两步,其中元迁移训练时使用大量的元任务进行训练;而在测试阶段仅使用极少的新受试者数据进行微调,模型就能轻松适应新受试者的特征分布,大幅减少对新受试者进行准确睡眠分期的成本。在两个公开的睡眠数据集上的实验结果表明,MTSL模型在单数据集、跨数据集两种条件下都能取得更高的准确率和F1分数,这表明MTSL更适合小样本场景下的睡眠分期任务。
