脱水过程中无核白葡萄转录组测序及膜脂降解代谢中关键基因的筛选

该研究以吐鲁番地区无核白葡萄为试验材料,在25 ℃常温和30 ℃热风干燥后,取失水25%、50%时褐变和未褐变的样品。利用转录组测序技术筛选出膜脂降解代谢相关的关键基因,并利用实时荧光定量PCR技术对其进行验证,研究结果显示,转录组测序共获得了11.63亿的clean data,当无核白失水50%时未褐变与褐变的相比,在快速脱水组筛选出718个差异表达基因,慢速脱水组2 259个。将上述基因进行GO功能富集和KEGG富集分析后,筛选出43个膜脂代谢相关的差异基因,归类于5种代谢途径。从已获得的差异基因中最终筛选出乙醛脱氢酶7B4（Aldehyde Dehydrogenase7B4,ALDH7B4）、双半乳糖甘油二酯合成酶1（Digalactose Diglycerol Synthetase1,DGD1）、脂氧合酶（Lipoxygenase,LOX）、磷脂磷酸水解酶2（Lipid Phosphate Phosphatase2,LPP2）、二酰基甘油激酶5（Diacylglycerol Kinase5,DGK5）、非特异性磷脂酶C4（Non-specific Phospholipase C4,NPC4）、磷脂酶Dα1（Phospholipase Dα1,PLDα1）7个膜脂代谢相关的关键基因,经qRT-PCR验证,基因表达趋势与转录组测序结果基本一致。结果表明,膜脂降解代谢相关基因表达量变化对无核白脱水褐变有一定影响。     

智能汽车拟人驾驶风险量化方法研究

驾驶风险量化评估对智能汽车拟人驾驶决策至关重要,针对复杂多任务场景下的驾驶风险量化问题,提出了一种基于 人类风险感知机理的智能汽车驾驶风险量化方法。 首先,利用传感器获取驾驶场景周围环境信息与行驶状态信息,并根据人类 驾驶经验对潜在冲突因素赋值代价,生成驾驶场景代价地图;其次,根据车辆运动状态与拟人驾驶的基本原则,利用高斯函数建 立动态风险模型;最后,结合驾驶场景代价图与动态风险模型实时计算拟人驾驶风险量化值。 仿真结果表明,提出的方法能够 基于人类驾驶经验,计算出动态变化的驾驶风险量化值,应用于智能汽车自动驾驶决策,可产生拟人驾驶行为。     

面向同步辐射光源图像的可并行智能压缩方法

在建的高能同步辐射光源预计会产生海量原始数据,其中硬X射线实验线站产生的图像数据占比最高且具有高分辨率和高帧率的特点,亟需有效的无损压缩方法缓解存储和传输压力,然而现有通用无损压缩方法对该类图像压缩效果不佳,基于深度学习的无损压缩方法又耗时较长。结合同步辐射光源图像的特点,提出一种在保证图像压缩比前提下的可并行智能无损图像压缩方法。通过参数自适应的可逆分区量化方法,大幅缩小图像经过时间差分后的像素值分布范围,能够节省20%以上的存储空间。将以CNN为基础架构的时空学习网络C-Zip作为概率预测器,同时以数据集为单位过拟合训练模型进一步优化图像压缩比。针对压缩过程中耗时较长的算术编码过程,利用概率距离量化代替算术编码,结合深度学习进行无损编码,增加编码过程的并行度。实验结果表明,该方法的图像压缩比相比于PNG、FLIF等传统图像无损压缩方法提升了0.23~0.58,对于同步辐射光源图像具有更好的压缩效果。     

Single image shadow detection via uncertainty analysis and GCN-based refinement strategy

Learning-based shadow detection methods have achieved an impressive performance, while these works still struggle on complex scenes, especially ambiguous soft shadows. To tackle this issue, this work proposes an efficient shadow detection network (ESDNet) and then applies uncertainty analysis and graph convolutional networks for detection refinement. Specifically, we first aggregate global information from high-level features and harvest shadow details in low-level features for obtaining an initial prediction. Secondly, we analyze the uncertainty of our ESDNet for an input shadow image and then take its intensity, expectation, and entropy into account to formulate a semi-supervised graph learning problem. Finally, we solve this problem by training a graph convolution network to obtain the refined detection result for every training image. To evaluate our method, we conduct extensive experiments on several benchmark datasets, i.e., SBU, UCF, ISTD, and even on soft shadow scenes. Experimental results demonstrate that our strategy can improve shadow detection performance by suppressing the uncertainties of false positive and false negative regions, achieving state-of-the-art results.     

Achieving robust design through statistical effect screening

This work proposes a method for statistical effect screening to identify design parameters of a numerical simulation that are influential to performance while simultaneously being robust to epistemic uncertainty introduced by calibration variables. Design parameters are controlled by the analyst, but the optimal design is often uncertain, while calibration variables are introduced by modeling choices. We argue that uncertainty introduced by design parameters and calibration variables should be treated differently, despite potential interactions between the two sets. Herein, a robustness criterion is embedded in our effect screening to guarantee the influence of design parameters, irrespective of values used for calibration variables. The Morris screening method is utilized to explore the design space, while robustness to uncertainty is quantified in the context of info‐gap decision theory. The proposed method is applied to the National Aeronautics and Space Administration Multidisciplinary Uncertainty Quantification Challenge Problem, which is a black‐box code for aeronautic flight guidance that requires 35 input parameters. The application demonstrates that a large number of variables can be handled without formulating simplifying assumptions about the potential coupling between calibration variables and design parameters. Because of the computational efficiency of the Morris screening method, we conclude that the analysis can be applied to even larger‐dimensional problems. (Approved for unlimited, public release on October 9, 2013, LA‐UR‐13‐27839, Unclassified.) Copyright © 2015 John Wiley & Sons, Ltd.     

Vibration data-driven machine learning architecture for structural health monitoring of steel frame structures

A vibration data-based machine learning architecture is designed for structural health monitoring (SHM) of a steel plane frame structure. This architecture uses a Bag-of-Features algorithm that extracts the speeded-up robust features (SURF) from the time-frequency scalogram images of the registered vibration data. The discriminative image features are then quantised to a visual vocabulary using K-means clustering. Finally, a support vector machine (SVM) is trained to distinguish the undamaged and multiple damage cases of the frame structure based on the discriminative features. The potential of the machine learning architecture is tested for an unseen dataset that was not used in training as well as with some datasets from entirely new damages close to existing (i.e., trained) damage classes. The results are then compared with those obtained using three other combinations of features and learning algorithms—(i) histogram of oriented gradients (HOG) feature with SVM, (ii) SURF feature with k-nearest neighbours (KNN) and (iii) HOG feature with KNN. In order to examine the robustness of the approach, the study is further extended by considering environmental variabilities along with the localisation and quantification of damage. The experimental results show that the machine learning architecture can effectively classify the undamaged and different joint damage classes with high testing accuracy that indicates its SHM potential for such frame structures.     

Application of the Strain Index in multiple task jobs

Six different methods to calculate the Strain Index (SI) scores for jobs with multiple forces/tasks were developed. Exposure data of 733 subjects from 12 different worksites were used to calculate these SI scores. Results show that using different SI computation methods could result in different SI scores, hence different risk level classifications. However, some simpler methods generated SI scores were comparable to the more complicated composite SI method. Despite differences in the scores between the six different SI computation methods, Spearman rank-order correlation coefficients of 0.61-0.97 were found between the methods. With some confidence, ergonomic practitioners may use simpler methods, depending on their specificity requirement in job evaluations and available resources. Some SI computation methods may tend to over-estimate job risk levels, while others may tend to under-estimate job risk levels, due to different ways used in obtaining the various SI parameters and computations.     

Robust Cardiac Function Assessment in 4D PC‐MRI Data of the Aorta and Pulmonary Artery

Four‐dimensional phase‐contrast magnetic resonance imaging (4D PC‐MRI) allows the non‐invasive acquisition of time‐resolved, 3D blood flow information. Stroke volumes (SVs) and regurgitation fractions (RFs) are two of the main measures to assess the cardiac function and severity of valvular pathologies. The flow rates in forward and backward direction through a plane above the aortic or pulmonary valve are required for their quantification. Unfortunately, the calculations are highly sensitive towards the plane's angulation since orthogonally passing flow is considered. This often leads to physiologically implausible results. In this work, a robust quantification method is introduced to overcome this problem. Collaborating radiologists and cardiologists were carefully observed while estimating SVs and RFs in various healthy volunteer and patient 4D PC‐MRI data sets with conventional quantification methods, that is, using a single plane above the valve that is freely movable along the centerline. By default it is aligned perpendicular to the vessel's centerline, but free angulation (rotation) is possible. This facilitated the automation of their approach which, in turn, allows to derive statistical information about the plane angulation sensitivity. Moreover, the experts expect a continuous decrease of the blood flow volume along the vessel course. Conventional methods are often unable to produce this behaviour. Thus, we present a procedure to fit a monotonous function that ensures such physiologically plausible results. In addition, this technique was adapted for the usage in branching vessels such as the pulmonary artery. The performed informal evaluation shows the capability of our method to support diagnosis; a parameter evaluation confirms the robustness. Vortex flow was identified as one of the main causes for quantification uncertainties.