一种基于FCOS神经网络的小建筑物目标检测方法北大核心

提出了一种基于FCOS神经网络的小建筑物目标检测算法,针对FCOS模型在特征提取阶段提取到的小建筑物目标特征较少问题,引入多尺度检测和可变形卷积方式,加强网络对小建筑物目标的特征提取能力,并通过改进后的SGE注意力机制降低特征图中的干扰噪声权重。改进后的网络可以提取到更多的小建筑物目标特征,对环境干扰噪声的鲁棒性更强。在自己搭建的数据集上进行了实验测试,结果表明,在相同环境下网络改进后建筑物的整体检测准确率提升了1.7%,其中对小建筑物目标提升了3.6%,减少了小建筑物目标漏检、误检的问题。     

一种基于抽取LMS的距离旁瓣抑制方法

在噪声雷达中，传统相关处理方法的距离旁瓣受到时宽带宽积的限制，在有限相关处理时间内得到的距离旁瓣较高，会造成微弱目标被强目标、杂波旁瓣淹没的现象。提出一种基于抽取最小均方（Least Mean Square,LMS）滤波的噪声雷达旁瓣抑制方法，将LMS滤波器的系数作为距离压缩结果，从而获取较低的距离旁瓣。对该方法的性能进行了理论分析，并通过数字仿真验证了算法的有效性和理论分析的正确性。     

Farmers' preferences for adopting on-farm concentration of raw milk: Results from a discrete choice experiment in Germany

Milk concentrates are used in the manufacturing of dairy products such as yogurt and cheese or are processed into milk powder. Processes for the nonthermal separation of water and valuable milk ingredients are becoming increasingly widespread at farm level. The technical barriers to using farm-manufactured milk concentrate in dairies are minimal, hence the suspicion that the practice of on-farm raw milk concentration is still fairly uncommon for economic reasons. This study, therefore, set out to investigate farmers' potential willingness to adopt a raw milk concentration plant. The empirical analysis was based on discrete choice experiments with 75 German dairy farmers to identify preferences and the possible adoption of on-farm raw milk concentration. The results showed that, in particular, farmers who deemed the current milk price to be insufficient viewed on-farm concentration using membrane technology as an option for diversifying their milk sales. We found no indication that adoption would be impeded by a lack of trustworthy information on milk processing technologies or capital.     

铅基卤素钙钛矿阻变式存储器研究进展

随着数字通信在大数据以及物联网等领域的应用,推动了下一代存储设备的发展。阻变式存储器因其功耗低、尺寸可调、操作速度快等优点被认为是最有前景的信息存储器件之一。近年来,兼具成本低、带隙可调、载流子扩散长度长、离子迁移速率快、载流子迁移率高等优点的铅基卤素钙钛矿,在阻变式存储器领域引起了广泛关注。主要对铅基卤素钙钛矿阻变式存储器最新研究进展进行了概述,就铅基卤素钙钛矿阻变式存储器结构、阻变性能、阻变机理等方面进行了综述。最后,对铅基卤素钙钛矿阻变式存储器当前面临的挑战进行了讨论,并对其未来的发展前景进行了展望。     

Probabilistic learning on manifolds (PLoM) with partition

The probabilistic learning on manifolds (PLoM) introduced in 2016 has solved difficult supervised problems for the “small data” limit where the number N of points in the training set is small. Many extensions have since been proposed, making it possible to deal with increasingly complex cases. However, the performance limit has been observed and explained for applications for which N is very small and for which the dimension of the diffusion-map basis is close to N. For these cases, we propose a novel extension based on the introduction of a partition in independent random vectors. We take advantage of this development to present improvements of the PLoM such as a simplified algorithm for constructing the diffusion-map basis and a new mathematical result for quantifying the concentration of the probability measure in terms of a probability upper bound. The analysis of the efficiency of this extension is presented through two applications.     

Coupling effects of water content,temperature, oxygen density,and polytetrafluoroethylene loading on oxygen transport through ionomer thin film on platinum surface in catalyst layer of proton exchange membrane fuel cell

In this work, coupling effects of water content, temperature, oxygen density, and polytetrafluoroethylene (PTFE) loading on oxygen transport through an ionomer thin film on a platinum surface in a catalyst layer of a proton exchange membrane (PEM) fuel cell are investigated using molecular dynamics approach. Taguchi orthogonal algorithm is employed to comprehensively analyze the coupling effects in a limited number of cases. It is found that the effect of operation temperature is the weakest among the four factors, which has the smallest effect index 14.4. Coupling effects including the PTFE loadings on the oxygen transfer through the ionomer thin film is uncovered. Less PTFE loadings should be beneficial for the oxygen transfer. The chemical potential gradient is considered as the major driven force for the oxygen transport through the ionomer thin film, and oxygen density is the dominating factor, significantly affecting the chemical potential in the thin film.     

Prediction of pullout interaction coefficient of geogrids by extreme gradient boosting model

Geogrids embedded in fill materials are checked against pullout failure through standard pullout testing methodology. The test determines the pullout interaction coefficient which is critical in fixing the embedment length of geogrids in mechanically stabilized earth walls. This paper proposes prediction of pullout interaction coefficient using data driven machine learning regression algorithms. The study primarily focusses on using extreme gradient boosting (XGBoost) method for prediction. A data set containing 220 test results from the literature has been used for training and testing. Predicted results of XGBoost have been compared with the results of random forest (RF) ensemble learning based algorithm. The predictions of XGBoost model indicates 85% accuracy and that of RF model shows 77% accuracy, indicating significantly superior and robust prediction through XGBoost above RF model. The importance analysis indicates that normal stress is the most significant factor that influences the pullout interaction coefficients. Subsequently pullout tests have been performed on geogrid embedded in four different fill materials at three normal stresses. The proposed XGBoost model gives 90% accuracy in prediction of pullout interaction coefficient compared to laboratory test results. Finally, an open-source graphical user interface based on the XGBoost model has been created for preliminary estimation of the pullout interaction coefficient of geogrid at different test conditions.     

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.     

草原石林：东北亚早白垩世花岗岩伸展穹隆和岩浆成矿爆发的地质遗迹及其形成过程

东北亚地区至少发育9个大型草原石林,属花岗岩石林的一种,是东北亚早白垩世巨量伸展和第四系冰川、风化作用的共同产物,主要特点是发育密集的近水平节理。本文通过整理岩浆岩专题填图和构造研究发现,这些石林的主体是早白垩世东北亚地区巨量伸展过程中形成众多的不对称花岗岩穹隆或同减薄岩体,岩体边部发育韧性剪切带,核部发布近水平岩浆流动面理,伸展和岩浆多期侵位导致与成矿密切相关的岩浆热液大量上涌,岩体抬升至地表,沿岩浆面理发育密集的近水平节理和部分垂直节理,后期沿这些构造面理发生的物理风化和化学作用(包括风蚀、冰川以及盐风化等)造就了千奇百怪的形态。草原石林是花岗岩地貌中的“另类”,不仅具有指示东北亚地区花岗岩形成时代(早白垩世)的特点,也是寻找晚中生代中国北方大规模成矿的良好标志体,而且风化形成的千姿百态的景色极具观赏价值,可以作为整个蒙古草原地区和大兴安岭南段地区特色的地学科普和生态旅游资源。