APPCorp: a corpus for Android privacy policy document structure analysis

With the increasing popularity of mobile devices and the wide adoption of mobile Apps, an increasing concern of privacy issues is raised. Privacy policy is identified as a proper medium to indicate the legal terms, such as the general data protection regulation (GDPR), and to bind legal agreement between service providers and users. However, privacy policies are usually long and vague for end users to read and understand. It is thus important to be able to automatically analyze the document structures of privacy policies to assist user understanding. In this work we create a manually labelled corpus containing 231 privacy policies (of more than 566,000 words and 7,748 annotated paragraphs). We benchmark our data corpus with 3 document classification models and achieve more than 82% on F1-score.     

卷积神经网络用于关节角度识别与姿势评估

为了快速准确地输出各种工作姿势风险评估结果，提出采用Kinect v2与卷积神经网络识别人体各关节角度，并输出标准姿势风险的评估得分。首先使用亚像素角点提取的棋盘标定算法标定Kinect两个摄像头，其次使用改进后的双边滤波对深度图像去噪，使用卷积神经网络识别人体关节二维位置，结合深度信息获取实际三维坐标并计算人体关节角度，最后输出姿势风险评估得分。通过两种实验分别验证了提出的Kinect角度识别与姿势评估的准确性，表明该方法关节角度识别与姿势风险评估的准确率均较高，是一种低成本、高可靠性的姿势评价方法，具有一定的科学意义和工程应用价值。     

基于多尺度特征融合双U型皮肤病变分割算法

针对皮肤病分割问题中皮肤病变区域大小不一且形状各异问题,提出一种基于多尺度特征融合的双U型皮肤病分割算法.该算法由粗分U型网络和细分U型网络两部分组成.首先粗分U型网络编码部分采用预训练VGG-19模型对相关特征进行多尺度特征提取;在解码阶段利用改进注意力残差块将底层与高层信息进行有效的映射融合,得到初步的Mask;然后将初步生成的Mask与原图像聚合,并输入多路特征提取编码器中进行二次特征蒸馏;而细分U型网络解码器同时与粗分U型网络编码部分和细分U型网络的编码部分特征映射进行融合,保证网络可以聚合更多的有效特征;最后利用Focal Tversky损失函数进一步提升分割效果.实验表明,所提算法在ISBI2016数据集上实验分割精度为96.11％、敏感度为93.59％、特异性为97.10％、Dice系数为93.14％、Jaccard系数为87.17％,能够有效地分割皮肤病病变区域.     

基于机器视觉的口服液灯检机关键技术研究

设计了一种基于机器视觉的口服液异物检测算法,实现口服液中异物的检测。通过高速工业摄像机获取序列图像,利用二次差分与累积差分法对序列图像进行处理,去除图像中的背景信息,得到只含杂质、少量气泡和部分噪声的灰度图像。通过自适应阈值处理提取运动目标。通过比较异物的大小是否超过医药标准来判断药剂中是否含有异物(比如:毛发、短纤维等),来实现对口服液中可见异物的实时检测。通过实验与现场测试,验证了该检测算法的有效性和可行性。     

Improving MapReduce Performance with Partial Speculative Execution

The MapReduce framework has become the de facto standard for big data processing due to its attractive features and abilities. One is that it automatically parallelizes a job into multiple tasks and transparently handles task execution on a large cluster of commodity machines. The increasing heterogeneity of distributed environments may result in a few straggling tasks, which prolong job completion. Speculative execution is proposed to mitigate stragglers. However, the existing speculative execution mechanism could not work efficiently as many speculative tasks are still slower than their original tasks. In this paper, we explore an approach to increase the efficiency of speculative execution, and further improve MapReduce performance. We propose the Partial Speculative Execution (PSE) strategy to make speculative tasks start from the checkpoint. By leveraging the checkpoint of original tasks, PSE can eliminate the costs of re-reading, re-copying, and re-computing the processed data. We implement PSE in Hadoop, and evaluate its performance in terms of job completion time and the efficiency of speculative execution under several kinds of classical workloads. Experimental results show that, in heterogeneous environments with stragglers, PSE completes jobs 56 % faster than that with no speculation and 12 % faster than that with LATE, an improved speculative execution algorithm. In addition, on average PSE can improve the efficiency of speculative execution by 24 % compared to LATE.     

3D密集全卷积的高光谱地物分类算法研究

针对高光谱遥感图像训练样本较少、光谱维度较高、空间特征与频谱特征存在差异性而导致高光谱地物分类的特征提取不合理、分类精度不稳定和训练时间长等问题,提出了基于3D密集全卷积（3D-DSFCN）的高光谱图像（HSI）分类算法。算法通过密集模块中的3D卷积核分别提取光谱特征和空间特征,采用特征映射模块替换传统网络中的池化层和全连接层,最后通过softmax分类器进行分类。实验结果表明,基于3D-DSFCN的HSI分类方法提高了地物分类的准确率、增强了低频标签的分类稳定性。     

基于树莓派的多串口多总线服务器设计

基于树莓派、USB-hub、USB/串口转换器和Linux操作系统设计一种串口服务器。本文重点介绍了该串口服务器的硬件结构,以及软件架构和3个主要任务的详细设计方法。该串口服务器带有多个串口,具有支持多总线、传输距离远、传输协议多样、低成本及低功耗的特点,已成功应用到工业现场的信号采集和设备监控中,满足长期稳定和实时的性能要求。     

新的数字多签名体制

本文给出了基于Ｓｃｈｎｏｒｒ体制的新的数字多签名体制，包括同时签名和顺序签名的两种类型，文中分别描述了这两个多签名体制的密钥生成，多签名生成和多签名验证过程指出它们对多签名生成的有效性，此外我们还讨论了顺序签名类型的多签名体制的安全性，利用计算复杂度理论证明了它对抗被动攻击用Ｓｃｈｎｏｒｒ体制是同样安全的。     

多星侦察移动目标：一种基于潜在区域的求解策略

针对面向移动目标侦察的多星联合调度,提出了一种新颖的求解策略:将移动目标问题转变为区域目标问题,即在多星联合侦察的框架内利用电子侦察引导信息构建移动目标的潜在区域,基于约束满足问题(CSP)描述方法以最大覆盖率为目标建立了面向潜在区域目标的多星联合调度模型,并提出了相应的禁忌搜索算法。通过基于潜在区域的求解策略,可以优化星载遥感器的侦察方案,指导移动目标侦察任务的执行。     

The melt structures above the liquidus in SiCp/Al composite

The properties and the structures of liquid melt above the liquidus play an important role in determining the resultant properties of the alloy and the composite. In this paper, the melt structures of SiCp/Al composites with two different reinforcement volume fractions were investigated using liquid metal X-ray diffraction and differential scanning calorimetry. The experimental results showed that the melt structures of SiCp/Al composite are different from that of liquid matrix alloy, a Si–Si hump in the pair radial distribution function in SiCp/Al composite melt and the DSC trace indicated that Si is not well distributed above the liquidus, the size change of short-range-order (SRO) in SiCp/Al composite melt indicated the diffusion of Si from chemical reaction between SiC and molten Al is possible only after a given temperature or after some extent concentration fluctuation of Si. The mechanisms for the observed phenomenon are also discussed in this paper.