Changes in kernel properties,in situ gelatinization,and physicochemical properties of waxy rice with inhibition of starch branching enzyme during cooking

The kernel properties, gelatinisation and physicochemical properties of rice were investigated in a waxy rice Guang-ling-xiang-nuo (GLXN) and its transgenic line GLXN-RNAi with inhibition of starch branching enzyme I/IIb. The volume swelling, water content and leached material of cooked kernels increased with increasing cooking time, but they were lower in GLXN-RNAi than in GLXN. The kernels of GLXN-RNAi were more difficultly gelatinised and disrupted than those of GLXN during cooking. The starch in the exterior of GLXN-RNAi endosperm was not completely gelatinised. The C_A-type starch of GLXN-RNAi was more resistant to cooking than A-type starch of GLXN. The cooked kernels of GLXN-RNAi had lower rapidly digestible starch and greater slowly digestible starch than those of GLXN. Brown rice flour had higher peak, hot, final and setback viscosities and lower breakdown viscosity in GLXN than GLXN-RNAi. These results indicated that GLXN-RNAi kernels exhibited great potential in applications as health foods.     

基于改进MobileFaceNet的人脸识别方法北大核心

针对目前大多数人脸识别算法参数多、计算量大,难以部署到移动端和嵌入式设备中的问题,提出了一种基于改进MobileFaceNet的人脸识别方法。通过对MobileFaceNet模型结构的调整,将bottleneck模块优化为sandglass模块,改良深度卷积和逐点卷积的相对位置,适当增大sandglass模块的输出通道数,从而减少特征压缩时的信息丢失,增强人脸空间特征的提取。实验结果表明:改进后的方法在LFW测试数据集上准确率达99.15%,模型大小和计算量分别仅为原算法的61%和45%,验证了所提方法的有效性。     

瓷砖表面非常规尺寸瑕疵的检测

与普通目标检测任务不同, 瓷砖表面瑕疵检测的困难之处在于检测小尺寸和大长宽比等非常规尺寸的目标. 为了解决这两个问题, 本文提出了一种基于改进 Cascade R-CNN 的新型瓷砖表面瑕疵检测算法. 为了提高模型对小瑕疵的检测能力, 本文模型利用侧向连接结构进行上下层语义信息的融合, 使用可切换空洞率的空洞卷积来增加模型的感受野; 为了提高模型对于大长宽比瑕疵的检测能力, 本文模型在标准卷积上引入偏移域以更好提取目标特征信息. 此外, 本文模型调整 Cascade R-CNN 框架中预选锚框的大小和长宽比例. 实验结果表明, 在从瓷砖工厂收集的数据集上, 本文所提出算法的平均精度均值 (mean average precision, mAP) 达到了 73.5%, 比改进前的 Cascade R-CNN 模型提高了9.7%. 本文实验代码可从以下链接获取: https://github.com/mashibin/Ceramic-tile-defect-detection.     

Hybridizing adaptive large neighborhood search with kernel search: a new solution approach for the nurse routing problem with incompatible services and minimum demand

The average age of the population has grown steadily in recent decades along with the number of people suffering from chronic diseases and asking for treatments. Hospital care is expensive and often unsafe, especially for older individuals. This is particularly true during pandemics as the recent SARS-CoV-2. Hospitalization at home has become a valuable alternative to face efficiently a huge increase in treatment requests while guaranteeing a high quality of service and lower risk to fragile patients. This new model of care requires the redefinition of health services organization and the optimization of scarce resources (e.g., available nurses). In this paper, we study a Nurse Routing Problem that tries to find a good balance between hospital costs reduction and the well-being of patients, also considering realistic operational restrictions like maximum working times for the nurses and possible incompatibilities between services jointly provided to the same patient. We first propose a Mixed Integer Linear Programming formulation for the problem and use some valid inequalities to strengthen it. A simple branch-and-cut algorithm is proposed and validated to derive ground benchmarks. In addition, to efficiently solve the problem, we develop an Adaptive Large Neighborhood Search hybridized with a Kernel Search and validate its performance over a large set of different realistic working scenarios. Computational tests show how our matheuristic approach manages to find good solutions in a reasonable amount of time even in the most difficult settings. Finally, some interesting managerial insights are discussed through an economic analysis of the operating context.     

Effect of Drying Temperature on Mechanical Properties of Dried Corn

The effect of drying air temperature on the mechanical properties of corn kernels was investigated. Corn was dried at drying temperatures of 40, 50, 60 and 70°C and air flow rate of 1.8 kg/min in a convective dryer. The kernels were then loaded uniaxially in a material testing machine at a loading rate of 3 mm/min, up to the rupture point. An increase in drying temperature from 40 to 70°C increased kernel deformation at the rupture point by an average of 12%. Moreover, values of force, stress, toughness, and modulus of elasticity of corn decreased on average by 21, 26, 36, and 38%, respectively.     

A multi-model approach for soft sensor development based on feature extraction using weighted kernel fisher criterion简

Multi-model approach can significantly improve the prediction performance of soft sensors in the proc- ess with multiple operational conditions. However, traditional clustering algorithms may result in overlapping phe- nomenon in subclasses, so that edge classes and outliers cannot be effectively dealt with and the modeling result is not satisfactory. In order to solve these problems, a new feature extraction method based on weighted kernel Fisher criterion is presented to improve the clustering accuracy, in which feature mapping is adopted to bring the edge classes and outliers closer to other normal subclasses. Furthermore, the classified data are used to develop a multiple model based on support vector machine. The proposed method is applied to a bisphenol A production process for prediction of the quality index. The simulation results demonstrate its ability in improving the data classification and the prediction performance of the soft sensor.     

P-反演半群上的部分核正规系

设S(P)为P-反演半群.首先介绍了S(P)上的正则P-同余和部分核正规系的概念.然后借助于部分核正规系给出了S(P)上正则P-同余的一个抽象刻画,给出了互不相交的S(P)的子集B={Bi∶i∈I}是以P∩Bi为C-集的S(P)的部分核正规系的充分必要条件.由此推出了P-正则半群上的每个P-同余完全是由其包含幂等元的部分核正规系所决定的.     

多尺度相似性迭代查找的可靠双目视差估计

目的 双目视差估计可以实现稠密的深度估计,因而具有重要研究价值。而视差估计和光流估计两个任务之间具有相似性,在两种任务之间可以互相借鉴并启迪新算法。受光流估计高效算法RAFT （recurrent all-pairs field transforms）的启发,本文提出采用单、双边多尺度相似性迭代查找的方法实现高精度的双目视差估计。针对方法在不同区域估计精度和置信度不一致的问题,提出了左右图像视差估计一致性检测提取可靠估计区域的方法。方法 采用金字塔池化模块、跳层连接和残差结构的特征网络提取具有强表征能力的表示向量,采用向量内积表示像素间的相似性,通过平均池化得到多尺度的相似量,第0次迭代集成初始视差量,根据初始视差单方向向左查找多尺度的相似性得到的大视野相似量和上下文3种信息,而其他次迭代集成更新的视差估计量,根据估计视差双向查找多尺度的相似性得到的大视野相似量和上下文3种信息,集成信息通过第0次更新的卷积循环神经网络和其他次更新共享的卷积循环神经网络迭代输出视差的更新量,多次迭代得到最终的视差估计值。之后,通过对输入左、右图像反序和左右翻转估计右图视差,对比左、右图匹配点视差差值的绝对值和给定阈值之差判断视差估计置信度,从而实现可靠区域提取。结果 本文方法在Sceneflow数据集上得到了与先进方法相当的精度,平均误差只有0.84像素,并且推理时间有相对优势,可以和精度之间通过控制迭代次数灵活平衡。可靠区域提取后,Sceneflow数据集上误差进一步减小到了历史最佳值0.21像素,在KITTI （Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago）双目测试数据集上,估计区域评估指标最优。结论 本文方法对于双目视差估计具有优越性能,可靠区域提取方法能高效提取高精度估计区域,极大地提升了估计区域的可靠性。     

检测小篡改区域的U型网络

目的 图像篡改区域检测是图像取证领域的一个挑战性任务,其目的是找出图像的篡改区域。传统方法仅针对某种特定的篡改方式进行设计,难以检测其他篡改方式的图像。基于卷积神经网络的方法能够自适应地提取特征,同时检测包含多种篡改方式的图像。但是其中多数方法都选择增强图像的噪声特征,这种机制无法较好处理篡改区域与原图像来源相同、噪声相似的情况。多数方法还忽略了篡改区域过小而产生的样本不平衡问题,导致检测效果不佳。方法 提出了一个基于区域损失的用于检测小篡改区域的U型网络,该网络构建了一个异常区域特征增强机制,放大与图像背景差异较大的异常区域的特征。此外,还利用区域损失增强对篡改区域框内像素的判别能力,可以解决因篡改区域过小而产生的样本不平衡问题。结果 消融实验说明了异常区域特征增强机制和区域损失机制的有效性;对JPEG压缩和高斯模糊的对抗性测试证明了模型的鲁棒性;在CASIA2.0（CASI-A image tampering detection evaluation database）、NIST2016（NIST nimble 2016 datasets）、COLUMBIA （Columbia uncompressed image splicing detection evaluation dataset）和COVERAGE （a novel database forcopy-move forgery detection）数据集上与最新方法进行比较时,本文方法取得了最优性能,其F1 score分别为0.979 5、0.982 2、0.995 3和0.987 0。结论 本文的异常区域特征增强机制和区域损失机制能有效提高模型性能,同时缓解篡改区域过小导致的样本不平衡问题,大量实验也表明了本文提出的小篡改区域检测方法的优越性。     

基于半监督对抗学习的图像语义分割

目的 将半监督对抗学习应用于图像语义分割,可以有效减少训练过程中人工生成标记的数量。作为生成器的分割网络的卷积算子只具有局部感受域,因此对于图像不同区域之间的远程依赖关系只能通过多个卷积层或增加卷积核的大小进行建模,但这种做法也同时失去了使用局部卷积结构获得的计算效率。此外,生成对抗网络（generative adversarial network,GAN）中的另一个挑战是判别器的性能控制。在高维空间中,由判别器进行的密度比估计通常是不准确且不稳定的。为此,本文提出面向图像语义分割的半监督对抗学习方法。方法 在生成对抗网络的分割网络中附加两层自注意模块,在空间维度上对语义依赖关系进行建模。自注意模块通过对所有位置的特征进行加权求和,有选择地在每个位置聚合特征。因而能够在像素级正确标记值数据的基础上有效处理输入图像中广泛分离的空间区域之间的关系。同时,为解决提出的半监督对抗学习方法的稳定性问题,在训练过程中将谱归一化应用到对抗网络的判别器中,这种加权归一化方法不仅可以稳定判别器网络的训练,并且不需要对唯一的超参数进行密集调整即可获得满意性能,且实现简单,计算量少,即使在缺乏互补的正则化技术的情况下,谱归一化也可以比权重归一化和梯度损失更好地改善生成图像的质量。结果 实验在Cityscapes数据集及PASCAL VOC 2012（pattern analysis,statistical modeling and computational learning visual object classes）数据集上与9种方法进行比较。在Cityscapes数据集中,相比基线模型,性能提高了2.3%~3.2%。在PASCAL VOC 2012数据集中,性能比基线模型提高了1.4%~2.5%。同时,在PASCAL VOC 2012数据集上进行消融实验,可以看出本文方法的有效性。结论 本文提出的半监督对抗学习的语义分割方法,通过引入的自注意力机制捕获特征图上各像素之间的依赖关系,应用谱归一化增强对抗生成网络的稳定性,表现出了较好的鲁棒性和有效性。