Opportunities for combining data of Estonian and Russian monitoring to reflect on water quality in large transboundary Lake Peipsi

Lake Peipsi, one of the world’s largest lakes, is shared between Estonia and Russia. The water quality in different parts of the lake has so far been assessed independently. Here we explore opportunities for combining data of Estonian and Russian monitoring. For that, we 1) analysed the compatibility of data for some water quality variables; 2) estimated the potential effects of the differences in sampling frequency; 3) provided a few regression models to calculate the missing data for months not sampled by the Russian side. Data of the concurrent Estonian and Russian sampling indicated a good compatibility. Estonian data analysis suggested that water quality assessment results are sensitive to sampling frequency. For example, total phosphorus (TP) in the largest basin showed a long-term decreasing trend in three month data that disappeared when data for other months were added. Disregarding some months may lead to under- or overestimation of certain factors with no consistency in the response of different basins. Hence, data of the whole ice-free period are recommended for an adequate water quality assessment. Furthermore, we demonstrated that monthly values of the water quality variables of the same year are autocorrelated. Based on this, we filled the gaps in the long-term data and compiled a dataset for the whole lake that enables its most comprehensive use in water quality assessment and management. Long-term data revealed no water quality improvement of Lake Peipsi. Further reduction of the external nutrient load is needed. Eutrophication is sustained by high internal phosphorus load.     

Presentation attack detection based on two-stream vision transformers with self-attention fusion

Aiming at the performance degradation of the existing presentation attack detection methods due to the illumination variation, a two-stream vision transformers framework (TSViT) based on transfer learning in two complementary spaces is proposed in this paper. The face images of RGB color space and multi-scale retinex with color restoration (MSRCR) space are fed to TSViT to learn the distinguishing features of presentation attack detection. To effectively fuse features from two sources (RGB color space images and MSRCR images), a feature fusion method based on self-attention is built, which can effectively capture the complementarity of two features. Experiments and analysis on Oulu-NPU, CASIA-MFSD, and Replay-Attack databases show that it outperforms most existing methods in intra-database testing and achieves good generalization performance in cross-database testing.     

地磁图数据随机误差建模与补偿

地磁图是影响地磁匹配导航性能的重要因素,其中地磁图的随机误差严重影响匹配定位精度,甚至导致误匹配。 为提 高地磁匹配性能,提出了地磁图数据随机误差建模与补偿方法。 该方法在对地磁图数据随机误差特性分析的基础上,建立数据 的非平稳时间序列模型,并将此模型作为状态方程,以实时数据为量测量,采用 Kalman 滤波方法对地磁图数据进行滤波,补偿 地磁图数据的随机误差。 通过基于滤波前后地磁图数据的导航定位实验,间接证明滤波方法的有效性。 对实际地磁图数据处 理结果表明,应用该方法滤波后的地磁图数据进行导航,其定位精度提高了 54. 7%。     

基于多变量时间序列及向量自回归机器学习模型的水驱油藏产量预测方法

提出了一种基于多变量时间序列(MTS)及向量自回归(VAR)机器学习模型的水驱油藏产量预测方法,并进行了实例应用。该方法在井网分析的基础上通过MTS分析对注采井组数据进行优选,并将井组内不同采出井产油量及注入井注水量作为彼此相关的时间序列,通过建立VAR模型从多个时间序列中提取出相互作用规律,挖掘注采井间流量的依赖关系从而进行产量预测。水驱油藏历史生产数据分析结果表明,与数值模拟历史拟合结果相比,机器学习模型产量预测结果具有更高精度,同时不确定性分析提升了预测结果的安全性。通过脉冲响应分析对注入井的采油贡献量进行评价,可为注水开发方案调整提供理论指导。     

浅渍法发酵豇豆的工艺优化

以具有降解亚硝酸盐功能的植物乳杆菌（Lactobacillus plantarum）SD-7和具有优良抗氧化能力的植物乳杆菌（Lactobacillus plantarum）FM-LP-9为复合发酵剂（1∶1），采用浅渍法发酵豇豆。以硬度和感官评分为考察指标，通过单因素试验及响应面试验研究复合发酵剂接种量、发酵温度和发酵时间对浅渍法发酵豇豆品质的影响。结果表明，最佳发酵工艺条件为发酵温度25 ℃，接种量5%，发酵时间125 h，在此优化条件下，得到的浅渍法发酵豇豆硬度为47.31 N，感官评分为90.98分，香气浓郁、口感脆嫩。     

The provably good parallel seeding algorithms for the k-means problem with penalties

As a classic NP-hard problem in machine learning and computational geometry, the k-means problem aims to partition the given points into k sets to minimize the within-cluster sum of squares. The k-means problem with penalties (k-MPWP), as a generalizing problem of the k-means problem, allows a point that can be either clustered or penalized with some positive cost. In this paper, we mainly apply the parallel seeding algorithm to the k-MPWP, and show sufficient analysis to bound the expected solution quality in the case where both the number of iterations and the number of points sampled in each iteration can be given arbitrarily. The approximate guarantee can be obtained as , where is a polynomial function involving the maximal ratio M between the penalties. On one hand, this result can be viewed as a further improvement on the parallel algorithm for k-MPWP given by Li et al., where the number of iterations depends on other factors. On the other hand, our result also generalizes the one solving the k-means problem presented by Bachem et al., because k-MPWP is a variant of the k-means problem. Moreover, we present a numerical experiment to show the effectiveness of the parallel algorithm for k-means with penalties.     

Failure load prediction and optimisation for adhesively bonded joints enabled by deep learning and fruit fly optimisation

Adhesively bonded joints have been extensively employed in the aeronautical and automotive industries to join thin-layer materials for developing lightweight components. To strengthen the structural integrity of joints, it is critical to estimate and improve joint failure loads effectually. To accomplish the aforementioned purpose, this paper presents a novel deep neural network (DNN) model-enabled approach, and a single lap joint (SLJ) design is used to support research development and validation. The approach is innovative in the following aspects: (i) the DNN model is reinforced with a transfer learning (TL) mechanism to realise an adaptive prediction on a new SLJ design, and the requirement to re-create new training samples and re-train the DNN model from scratch for the design can be alleviated; (ii) a fruit fly optimisation (FFO) algorithm featured with the parallel computing capability is incorporated into the approach to efficiently optimise joint parameters based on joint failure load predictions. Case studies were developed to validate the effectiveness of the approach. Experimental results demonstrate that, with this approach, the number of datasets and the computational time required to re-train the DNN model for a new SLJ design were significantly reduced by 92.00% and 99.57% respectively, and the joint failure load was substantially increased by 9.96%.     

大跨径网架屋顶设计与施工实践

某物资仓库拟采用框架结构和40 m跨网架屋顶。首先根据规范确定了屋顶荷载，并根据该建筑物位于台风区的实际，着重研究了风荷载的取值情况。该网架采用螺栓球节点，形式为正放四角锥形，施工采用分段整体吊装和高空散装的安装方式。实际使用情况表明，该物资库采用网架结构可靠耐用，且缩短了施工工期，取得了较好的经济效益。     

一种基于证据推理的视频运动目标融合检测算法

为了解决复杂场景下传统的运动目标检测问题, 利用证据推理—–谨慎有序加权平均方法(COWA-ER), 提出一种综合使用混合高斯、均值滤波和码本的多方法融合的检测方法. 该融合检测算法以上述3 种检测方法为准则建立一个多准则决策框架, 通过双阈值检测法来表征检测过程中的不确定性, 最终利用COWA-ER 方法进行决策级融合, 实现多种方法的优势互补. 实验表明, 所提出的融合检测算法具有更理想的目标检测效果, 能有效应对诸如阴影及光照突变等问题对检测性能的影响.

     

低膦共聚物水质稳定剂的合成工艺研究

以水为溶剂,采用过硫酸铵-次磷酸盐引发体系,用马来酸酐(MA)、2-丙烯酰胺-2-甲基丙磺酸(AMPS)、丙烯酸(AA)为单体合成低膦共聚物水质稳定剂,讨论了合成温度、合成时间、单体配比以及引发剂用量等条件对产物阻垢性能的影响,确定了水质稳定剂的合成工艺。在水相中,膦酸共聚物的最佳合成温度为83~85℃,最佳合成时间为6h,最佳单体配比(MA∶AMPS∶AA)为0.50∶0.05∶0.45,过硫酸铵用量为6%、次磷酸盐相对物质的量含量为0.15时效果最佳。