ID 原文 译文
57898 提出了一种基于机器学习的多变量制造过程中的关键变量检测算法. A key variable detection algorithm based on machine learning in multivariate manufacturing process was proposed.
57899 该算法利用机器学习分类器对多变量制造过程进行数学建模，以随机打乱过程变量后分类器的性能变化作为评价指标，检测导致产品质量相对异常的关键变量. It uses the machine learning classifier to mathematically model the multivariate manufacturing process. And the performance change of the classifier after the process variable shuffled randomly is used as an evaluation index to detect the key variables that lead to relatively abnormal product quality.
57900 设计并生成了多变量制造过程的仿真数据集，在仿真数据集和基于中国某工厂的 2 个实际生产案例数据集上对算法的检测性能进行了性能验证，2 次验证结果均表明算法检测性能良好. Simulation data of the multivariate manufacturing process is designed and generated. The per- formance of the algorithm was verified by simulation data set and two actual production case data sets based on a factory in China. Both verifications show that the algorithm has good detection performance.
57901 Scratch 是一种适合少年儿童使用的可视化编程语言，并在全球的编程教育领域中受到广泛地关注.由于目前各大教育编程平台都开始使用 Scratch3.0 版本，而已有的特征提取和检测系统并不支持新版本，为此，提出了一种基于链表数据结构和一种语言识别工具( ANTLＲ) 的面向 Scratch3.0 的特征提取和检测系统. As a visual programming language for children，Scratch has received wide attention in the pro- gramming education. Considering that Scratch has evolved to the latest version 3. 0 and its storage struc- ture changes significantly from the previous version，the existing methods cannot be directly applied to project analysis. A new feature extraction and detection system based on linked list data structure and an- other tool for language recognition ( ANTLＲ) was presented to solve the problem.
57902 实验结果表明，该系统可以有效地从项目中提取编程特征，并为学生和教师提供反馈，其检测性能和检测稳定性比 Scratch2.0 均有所提升. Experimental results show that the system can effectively extract programming features from the projects and provide feedback to students and teachers. Moreover，its detection performance and stability perform better than the origi- nal methods in Scratch2. 0.
57903 针对现有骨质疏松评估中诊断依据单一、准确率低的问题，综合考虑骨骼图像数据和问卷数据，首先提出一种基于深度神经网络的多模态特征融合骨质疏松评估方法; Aiming at the problems that the problems of single diagnosis and low accuracy in the existing osteoporosis assessment，considering the bone image data and questionnaire data，a multi-modal feature fusion osteoporosis evaluation method based on deep neural network was proposed.
57904 然后，针对骨骼图像特征较浅、结构固定的特点，使用Unet 进行图像分割预处理，去除冗余信息以提升分类准确性; And，for the charac- teristics of shallow image and fixed structure of bone image，Unet is used to perform image segmentation preprocessing to remove redundant information.
57905 最后，针对普通卷积操作在把握全局信息方面的不足，提出采用基于 non-local 模块的卷积神经网络来进一步丰富特征信息. In view of the shortcomings of ordinary convolution opera- tions in grasping the global information，a new convolutional neural network based on non-local module was proposed to further enrich the feature information.
57906 交叉验证结果表明，提出的多模态特征融合方法与仅单独使用图像数据或问卷数据的机器学习方法相比具有明显的优势，分类准确率分别提升了 3.2% 和 22.3% . Cross-validation shows that the proposed multimo- dal feature fusion method has obvious advantages compared with the machine learning method using only image data or questionnaire data alone，and the classification accuracy rate is increased by 3. 2% and 22. 3% .
57907 传统的流量工程策略的研究大多集中在构建和求解数学模型方面，其计算复杂度过高，为此，提出了一种经验驱动的基于多智能体强化学习的流量分配算法. Most of the researches on traditional traffic engineering strategies focus on constructing and sol- ving mathematical models. To reduce computational complexity，an experience-driven traffic allocation al- gorithm based on multi-agent reinforcement learning was proposed.