Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 8

年份

2023 2

2021 2

2020 1

2019 2

关键词

人群计数；密度估计；分割先验图；均匀函数 1

去雾；暗通道先验；雾图像模型；双边滤波 1

大规模多入多出；毫米波；信道估计；车辆通信；时变 1

用户界面（UI）生成代码；UI设计规范；UI碎片图层合并；目标检测 1

血管滤波器；邻域；血管分割；外围值 1

展开︾

检索范围：

排序：展示方式：

The prior rules of designing Ti

Yingying Jian, Danyao Qu, Lihao Guo, Yujin Zhu, Chen Su, Huanran Feng, Guangjian Zhang, Jia Zhang, Weiwei Wu, Ming-Shui Yao

《化学科学与工程前沿（英文）》 2021年第15卷第3期页码 505-517 doi: 10.1007/s11705-020-2013-y

摘要： Working temperature, sensitivity, and selectivity are some of the characteristics of the applied gas sensors. How to design and fabricate an ideal gas sensor working at room temperature is still challenging and attracting lots of interest. Two-dimensional (2D) materials with ultra-thin structure have been demonstrated as a family of ideal candidates to achieve this goal. Among them, Ti C T MXene, a kind of layered sheet synthesized by selectively etching MAX phases materials, shows remarkable potential to be the sensitive materials solely or in a composite. However, their designing rules are still lacking critical thinking from the viewpoint of the intrinsic property of Ti C T MXene based materials. In this article, two critical features, i.e., the thickness of the sensitive materials, and the scope of the analytes, are elaborated towards Ti C T MXene based gas sensors after characterizing the performance of sensing reducing gases (NH and CO) and oxidizing gas (NO ). First, the thinner the Ti C T MXene sensitive layer, the better the sensitivity. Second, the Ti C T MXene based gas sensor is not suitable for strong and moderate oxidation gas due to its ease of oxidation. These two rules are demonstrated, and could be considered with priority both in the future researches and practical applications.

关键词： MXene based sensor prior reducing gases oxidizing gases

HTML PDF 收藏

Host protection against Omicron BA.2.2 sublineages by prior vaccination in spring 2022 COVID-19 outbreak

《医学前沿（英文）》 2023年第17卷第3期页码 562-575 doi: 10.1007/s11684-022-0977-3

摘要： The Omicron family of SARS-CoV-2 variants are currently driving the COVID-19 pandemic. Here we analyzed the clinical laboratory test results of 9911 Omicron BA.2.2 sublineages-infected symptomatic patients without earlier infection histories during a SARS-CoV-2 outbreak in Shanghai in spring 2022. Compared to an earlier patient cohort infected by SARS-CoV-2 prototype strains in 2020, BA.2.2 infection led to distinct fluctuations of pathophysiological markers in the peripheral blood. In particular, severe/critical cases of COVID-19 post BA.2.2 infection were associated with less pro-inflammatory macrophage activation and stronger interferon alpha response in the bronchoalveolar microenvironment. Importantly, the abnormal biomarkers were significantly subdued in individuals who had been immunized by 2 or 3 doses of SARS-CoV-2 prototype-inactivated vaccines, supporting the estimation of an overall 96.02% of protection rate against severe/critical disease in the 4854 cases in our BA.2.2 patient cohort with traceable vaccination records. Furthermore, even though age was a critical risk factor of the severity of COVID-19 post BA.2.2 infection, vaccination-elicited protection against severe/critical COVID-19 reached 90.15% in patients aged ≥ 60 years old. Together, our study delineates the pathophysiological features of Omicron BA.2.2 sublineages and demonstrates significant protection conferred by prior prototype-based inactivated vaccines.

关键词： SARS-CoV-2 COVID-19 host response bronchoalveolar lavage fluid (BALF)

HTML PDF 收藏

Entity and relation extraction with rule-guided dictionary as domain knowledge

《工程管理前沿（英文）》页码 610-622 doi: 10.1007/s42524-022-0226-0

摘要： Entity and relation extraction is an indispensable part of domain knowledge graph construction, which can serve relevant knowledge needs in a specific domain, such as providing support for product research, sales, risk control, and domain hotspot analysis. The existing entity and relation extraction methods that depend on pretrained models have shown promising performance on open datasets. However, the performance of these methods degrades when they face domain-specific datasets. Entity extraction models treat characters as basic semantic units while ignoring known character dependency in specific domains. Relation extraction is based on the hypothesis that the relations hidden in sentences are unified, thereby neglecting that relations may be diverse in different entity tuples. To address the problems above, this paper first introduced prior knowledge composed of domain dictionaries to enhance characters’ dependence. Second, domain rules were built to eliminate noise in entity relations and promote potential entity relation extraction. Finally, experiments were designed to verify the effectiveness of our proposed methods. Experimental results on two domains, including laser industry and unmanned ship, showed the superiority of our methods. The F1 value on laser industry entity, unmanned ship entity, laser industry relation, and unmanned ship relation datasets is improved by +1%, +6%, +2%, and +1%, respectively. In addition, the extraction accuracy of entity relation triplet reaches 83% and 76% on laser industry entity pair and unmanned ship entity pair datasets, respectively.

关键词： entity extraction relation extraction prior knowledge domain rule

HTML PDF 收藏

基于先验形状和局部统计的血管影像图像分割方法 Research Articles

Yun TIAN, Zi-feng LIU, Shi-feng ZHAO

《信息与电子工程前沿（英文）》 2019年第20卷第8期页码 1099-1108 doi: 10.1631/FITEE.1800129

摘要：快速准确地从医学图像中提取血管结构是许多临床医疗的基础。然而，大多数血管分割方法忽略了分割结果中孤立点和冗余点的存在。本文提出一种基于先验形状和局部统计的血管分割方法，能有效消除异常值并精确分割粗细血管。首先，定义了一种改进的血管滤波器，用于量化每个体素属于管状结构的可能性；其次，执行匹配和连接操作以获得血管掩模；最后，在血管掩模基础上实现基于局部统计的区域生长方法，得到较为完整的无外围值的血管树。与Frangi方法以及Yang方法在实际血管造影图像上的实验和比较，证明该方法在保持血管分支连通的同时，可以有效去除异常值。

关键词：血管滤波器；邻域；血管分割；外围值

HTML PDF 收藏

基于暗通道先验的单幅图像快速去雾算法 Research Articles

Bo-xuan YUE, Kang-ling LIU, Zi-yang WANG, Jun LIANG

《信息与电子工程前沿（英文）》 2019年第20卷第8期页码 1109-1118 doi: 10.1631/FITEE.1700148

摘要：在雾气中，可见光的散射降低了图像可见度。目前，去雾仍是图像处理应用的一个挑战。为实现去雾，提出一种基于单个像素的去雾加速算法。不同于基于区块的方法，所提方法分别估计每个区域的变换矩阵和大气光参数，其中加速的关键在于所有参数能在一次遍历中获得。然后，对传输映射进行双边过滤，恢复像素之间的关系。通过线性模糊模型恢复后，对恢复的图像进行调整，以提高对比度、光照强度和饱和度，尤其是补偿由相应波长引起的不同通道的光强误差。实验结果表明，该方法在处理速率方面优于已有的最先进去雾算法。与其他去雾方法比较和引入定量准则（峰信噪比、可检测边际速率、信息熵差）验证该方法有效。

关键词：去雾；暗通道先验；雾图像模型；双边滤波

HTML PDF 收藏

一种新的基于卷积神经网络的人群计数方法 Research Articles

黄杰浩,遆晓光,吴俊德,陈瑷玥

《信息与电子工程前沿（英文）》 2020年第21卷第8期页码 1119-1266 doi: 10.1631/FITEE.1900282

摘要：人群密度估计是一项具有挑战性的任务，因为人群中人头大小存在大范围变化。现有方法均采用多列式结构卷积神经网络去适应这种变化，但会导致密度图上不同密度区域产生平均效应并引入额外噪声。为解决该问题，提出一种新的基于分割先验图的神经网络方法，在分割图基础上生成一个高质量且没有噪声的密度图。该网络主要包括两个部分，即头部的人群前景分割神经网络和尾部的人群回归神经网络。在数据集只提供单点人头标记的情况下，采用均匀函数生成人群头部的掩膜真值图。基于该真值图，前景分割网络输出人群分割图，可有效减少密度图中无人区域噪声。将人群分割图输入人群回归网络，后者能生成高质量人群密度图并提供准确的人数估计。在4个公开数据集（即ShanghaiTech、UCF-CC-50、WorldExpo’10和UCSD）上验证了所提方法有效性；其中，在ShanghaiTech part B和UCF-CC-50两个数据集上该方法取得了当前最好结果。

关键词：人群计数；密度估计；分割先验图；均匀函数

HTML PDF 收藏

基于先验信息的5G及后5G毫米波大规模多入多出车载通信信道估计 Research Articles

易钊1,邹卫霞1,2,孙学斌1

《信息与电子工程前沿（英文）》 2021年第22卷第6期页码 777-789 doi: 10.1631/FITEE.2000515

摘要：毫米波（mmWave）被认为是5G及后5G高带宽车载通信的可行解决方案。为实现在未来车辆通信中的应用，鲁棒的毫米波车载网络非常重要。然而，一个挑战是，毫米波应在车辆或车辆到基础设施（V2I）之间提供高速和超高速数据交换。此外，由于车辆的高速移动引起毫米波信道快速变化，传统的实时信道估计方案难以实现。针对这些问题，提出一种毫米波V2I车辆通信信道估计方法。首先考虑快速运动的车辆场景，建立相应的快速时变信道数学模型。然后，利用基站与每个移动用户之间的时间变化规律和确定的到达方向，预测时变信道先验信息（PI）。最后，利用PI和信道特性对时变信道进行估计。仿真结果表明，在毫米波时变车载通信系统中，该方案在归一化均方误差和和率性能上均优于传统方案。

关键词：大规模多入多出；毫米波；信道估计；车辆通信；时变

HTML PDF 收藏

UI图层合并器：基于计算机视觉与边界先验的UI图层合并方法 Research Article

陈云农1,5,甄焱鲲4,施楚宁2,李佳智2,陈柳青2,3,5,李泽健1,3,5,孙凌云2,3,5,周婷婷4,常艳芳4

《信息与电子工程前沿（英文）》 2023年第24卷第3期页码 373-387 doi: 10.1631/FITEE.2200099

摘要：随着互联网行业图形用户界面（GUI）开发工作量的快速增长，国内外学者试图从GUI图片生成可维护的前端代码。该任务更适合从包含有用户界面元数据的UI设计稿来实现代码生成。然而，碎片图层不可避免地会出现在UI设计稿中，这大大降低了生成代码的质量。目前尚未有自动化GUI技术来检测并合并碎片图层以提高生成代码的可维护性。本文提出UI图层合并器（UILM），一种基于计算机视觉的方法，可以自动检测并合并碎片图层为完整的UI组件。本文提出的UILM包含合并区域检测器和碎片图层合并算法。合并区域检测器结合边界先验知识来准确地检测出UI组件的边界。基于此，碎片图层合并算法可以搜索出边界内的相关碎片层并将其合并为整体。此外，我们提出一种动态数据增强算法来提高合并区域检测器的性能。我们还构建了用于训练合并区域检测器和测试UILM的大规模UI数据集。实验结果表明，本文提出的方法在合并区域检测方面优于最佳基线，并达到了有效的图层合并准确率。最后，对真实应用程序的用户研究也证实了本文方法的有效性。

关键词：用户界面（UI）生成代码；UI设计规范；UI碎片图层合并；目标检测

HTML PDF 收藏

标题作者时间类型操作

The prior rules of designing Ti

Yingying Jian, Danyao Qu, Lihao Guo, Yujin Zhu, Chen Su, Huanran Feng, Guangjian Zhang, Jia Zhang, Weiwei Wu, Ming-Shui Yao

期刊论文

Host protection against Omicron BA.2.2 sublineages by prior vaccination in spring 2022 COVID-19 outbreak

期刊论文

Entity and relation extraction with rule-guided dictionary as domain knowledge

期刊论文

基于先验形状和局部统计的血管影像图像分割方法

Yun TIAN, Zi-feng LIU, Shi-feng ZHAO