机器翻译译文质量估计综述

机器翻译译文质量估计(Quality Estimation,QE)是指在不需要人工参考译文的条件下,估计机器翻译系统产生的译文的质量,对机器翻译研究和应用具有很重要的价值。机器翻译译文质量估计经过最近几年的发展,取得了丰富的研究成果。该文首先介绍了机器翻译译文质量估计的背景与意义;然后详细介绍了句子级QE、单词级QE、文档级QE的具体任务目标、评价指标等内容,进一步概括了QE方法发展的三个阶段: 基于特征工程和机器学习的QE方法阶段,基于深度学习的QE方法阶段,融入预训练模型的QE方法阶段,并介绍了每一阶段中的代表性研究工作;最后分析了目前的研究现状及不足,并对未来QE方法的研究及发展方向进行了展望。     

多感官设计的可视化分析:研究进展、热点与趋势

目的 对国内多感官设计的相关文献进行总结分析，探寻该领域的研究现状、热点与发展趋势，为今后多感官设计理论及实践研究提供参考。方法 基于文献计量分析法，以2005-2021年知网、万方、维普、超星及华艺数据库收录的741篇多感官设计文献为分析对象，采用CiteSpace、NoteExperss等软件对该领域文献的发表时间、载文期刊、高被引文献、作者、机构、     

A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

基于卷积神经网络的食品图像识别

目的 探究一种基于Inception_V3-CNN模型的食品图像识别和分类方法。方法 选取包含20类食品和19609张的食品图像建立数据集Food-101, 通过卷积神经网络(convolutional neural networks, CNN)提取图像候选区域的视觉特征, 并自动进行分类, 使其具有较高的识别率; 此外, 采集来自kaggle库中已标注的食品图像集做预测对比实验, 以保证Inception_V3-CNN模型检测的准确度。结果 该方法能够去除背景噪音, 且仅需部分提取视觉特征, 可以有效解决网络食品图像的分类问题, 与多视图支持向量机(support vector machine, SVM)+方向梯度直方图(histogram of oriented gradients, HOG)和传统CNN方法相比, 在测试时间相近、设备计算能力相同的条件下, 该方法识别率更高, 迭代次数为15000次时, Loss值降至4.92, 准确率可达93.89%。结论 此方法可以快速识别食品图像, 在实际网络图片中能有较好的可移植性。将算法移植到移动设备中实现APP的模块化操作也将成为后续工作探索的重点方向。     

Discrete choice experiments in the analysis of consumers’ preferences for finfish products: A systematic literature review

Discrete choice experiments (DCEs) have become an important tool for assessing the preferences of consumers for finfish seafood products. This investigation presents a systematic literature review of studies performed in the last 20 years (2000–2019) that use DCEs to analyse consumers’ preferences for finfish products, with the purpose to identify the main insights of consumer behaviour towards these products, the most used attributes for this type of experiments and to discuss and compare some willingness to pay estimations. We found that origin was the most used attribute for this kind of experiments, while other important factors were the harvest method, a specific certification label and the species or products considered. The WTP estimates evidenced that consumers are willing to pay premiums for domestic products, while similarly, wild products were preferred over farmed products. Also, there were higher WTP estimates for certified products, in which specific certification labels were better options rather than just claiming that the product was certified or not. All claims and labels related to sustainability, nutritional, health and safety information provided premiums that consumers were willing to pay, however, the importance differed depending on the type of label or claim, the country and species. Future research should consider the influence of being or not the main purchaser in the household, as it might affect the WTP values. Also, given the importance, future research extensions using DCEs are needed on the Chinese and Asian finfish market.     

In-situ deflectometic measurement of transparent optics in precision robotic polishing

In the ultra-precision manufacturing of large optics, industrial robots have the potential to become an intelligent and economical choice of surface polishing. However, the transport of the workpieces between the polishing platform and the measurement instrument seriously limits the manufacturing efficiency. Therefore, an in-situ measurement system based on the monoscopic deflectometry is developed to determine the form quality of the optical lenses during rough polishing. Stray light reflected from the lower surface of transparent lenses may degrade the measuring quality, thus an effective absolute phase retrieval algorithm is developed to decouple the superposed fringes associated with the upper and lower surfaces. Then, the form of the upper surface under polishing can be reconstructed to guide the subsequent polishing. Experimental results demonstrate that the accuracy of the method is comparable to that of the coordinate measuring machine, consequently the manufacturing efficiency and reliability of large optical workpieces can be greatly improved.     

The roles of conceptual modelling in improving construction simulation studies: A comprehensive review

The conceptual modelling phase of simulation studies has proven to be effective in enhancing the impact of simulation modelling in different domains. However, this simulation phase did not receive much attention in the construction simulation domain. The objective of this paper is to identify the roles that conceptual modelling can play in advancing the engagement, accuracy, and adoption (among other things) of discrete-event simulation studies in construction. In this paper, a Systematic Literature Review (SLR) is conducted, which involves a comprehensive search of databases and researchers’ profiles to identify journal papers, conference articles, books, and theses that have reported the benefits of conceptual modelling for discrete-event simulation studies. The review resulted in 82 documents that were published from 2000 to 2020. Results indicate that the benefits of conceptual modelling include facilitating communications between stakeholders, capturing sufficient information for the simulation model, improving the quality of simulation models, guiding other simulation modelling activities, and facilitating verification and validation of simulation models. By linking these benefits to the current research agenda in construction simulation, this paper shows the significance and potential of the conceptual modelling phase to enhance the impact of discrete-event simulation studies in construction.