A 6-DOF humanoid wall-climbing robot with flexible adsorption feet based on negative pressure suction

A wide range of dangerous and special tasks have witnessed the applications of wall-climbing robots, but they still cannot adapt well torough or sloping walls. This paper proposes a 6-DOF (degree of freedom) humanoid wall-climbing robot (HWCR) based on the principle of negative pressure suction. HWCR has the advantages of flexible adsorption feet, strong adaptability, strong anti-subversion performance, and high friction to the wall. We deduce mechanics formulas and carry out a parametric design of the foot structure so that it can meet the requirement of robot wall climbing. We use Fluent to analyze the flow field of the adsorption foot and determine the motor speed that can provide a reliable adsorption force. Using the D-H matrix to plan gait, we also design a compound cycloid-based foot trajectory to reduce the impact between the HWCR and the wall. Experiments on the uneven wall and sloping wall show that the vehicle can walk with an ideal gait, and the resistance value of the servo on each joint is much lower than the critical value, which ensures the smooth movement of the HWCR.     

SOINN-Based Abnormal Trajectory Detection for Efficient Video Condensation

With the evolution of video surveillance systems, the requirement of video storage grows rapidly; in addition, safe guards and forensic officers spend a great deal of time observing surveillance videos to find abnormal events. As most of the scene in the surveillance video are redundant and contains no information needs attention, we propose a video condensation method to summarize the abnormal events in the video by rearranging the moving trajectory and sort them by the degree of anomaly. Our goal is to improve the condensation rate to reduce more storage size, and increase the accuracy in abnormal detection. As the trajectory feature is the key to both goals, in this paper, a new method for feature extraction of moving object trajectory is proposed, and we use the SOINN (Self-Organizing Incremental Neural Network) method to accomplish a high accuracy abnormal detection. In the results, our method is able to shirk the video size to 10% storage size of the original video, and achieves 95% accuracy of abnormal event detection, which shows our method is useful and applicable to the surveillance industry.     

基于卷积神经网络的单目深度估计

针对利用深度学习方法对街道图像进行深度估计，提出采用语义分割的方法解决深度图出现边界模糊等问题；估计深度通过左右视角图生成视差图进行无监督的训练。在网络模型中添加语义分割层，采取多个空洞卷积并行的结构增加感受野，同时减少了图像下采样的次数，降低了由于下采样带来的信息损失，使得的结果更加准确。这也是在深度估计中首次与空洞卷积相结合增加准确率。通过对KITTI街道数据集进行训练，与现有结果相比，除了增加检测准确性，降低错误率之外，使得效果图中的物体更加清晰，并且在效果图中还保留了一些原模型中被忽视掉的细节信息，将原始图像更加完整的表现出来。     

面向连续查询的敏感语义位置隐私保护方案

针对连续查询位置服务中构造匿名区域未考虑语义位置信息导致敏感隐私泄露问题，通过设计[(K,θ)]-隐私模型，提出一种路网环境下面向连续查询的敏感语义位置隐私保护方案。该方案利用Voronoi图将城市路网预先划分为独立的Voronoi单元，依据用户的移动路径和移动速度，选择具有相似特性的其他[K-1]个用户，构建匿名用户集；利用匿名用户集用户设定的敏感语义位置类型和语义安全阈值，以及用户所处语义位置的Voronoi单元，构建满足[(K,θ)]-隐私模型的语义安全匿名区域，可以同时防止连续查询追踪攻击和语义推断攻击。实验结果表明，与SCPA算法相比，该方案在隐私保护程度上提升约15%，系统开销上降低约20%。     

R2D2: A scalable deep learning toolkit for medical imaging segmentation

Deep learning has gained a significant popularity in recent years thanks to its tremendous success across a wide range of relevant fields of applications, including medical image analysis domain in particular. Although convolutional neural networks (CNNs) based medical applications have been providing powerful solutions and revolutionizing medicine, efficiently training of CNNs models is a tedious and challenging task. It is a computationally intensive process taking long time and rare system resources, which represents a significant hindrance to scientific research progress. In order to address this challenge, we propose in this article, R2D2, a scalable intuitive deep learning toolkit for medical imaging semantic segmentation. To the best of our knowledge, the present work is the first that aims to tackle this issue by offering a novel distributed versions of two well-known and widely used CNN segmentation architectures [ie, fully convolutional network (FCN) and U-Net]. We introduce the design and the core building blocks of R2D2. We further present and analyze its experimental evaluation results on two different concrete medical imaging segmentation use cases. R2D2 achieves up to 17.5× and 10.4× speedup than single-node based training of U-Net and FCN, respectively, with a negligible, though still unexpected segmentation accuracy loss. R2D2 offers not only an empirical evidence and investigates in-depth the latest published works but also it facilitates and significantly reduces the effort required by researchers to quickly prototype and easily discover cutting-edge CNN configurations and architectures.     

基于近似测地线的分层次自动铺带轨迹规划方法

自动铺带技术是一种增量制造技术，适用于制造翼面、壁板等大尺寸、小曲率复合材料构件，具有加工成本低、效率高等特点。轨迹规划是自动铺带技术的关键环节，它直接关系到复合材料构件的成型精度与质量。现有的自动铺带轨迹规划方法难以便捷兼顾调控铺放间隙与防止铺放褶皱，保证铺带产品的最终质量。有鉴于此，提出了一种基于近似测地线的分层次铺放轨迹规划方法。主要目标是合理利用预浸带允许变形能力，在防止铺放褶皱产生的前提下，保证相邻带料不产生覆盖，且间隙不超过2.5 mm。首先，研究了铺放间隙的产生与演化规律，给出了几种典型曲面上初始铺放间隙的优化方法。接下来，提出了近似测地线的数学模型与求解格式。然后，基于铺放褶皱的产生机制与铺放间隙的演化规律，确定了近似测地线的测地曲率大小与符号。最后，在双曲面模具以及自由曲面模具上验证了所提出方法的有效性。     

伪标签置信选择的半监督集成学习视频语义检测

在视频语义检测中，有标记样本不足会严重影响检测的性能，而且伪标签样本中的噪声也会导致集成学习基分类器性能提升不足。为此，提出一种伪标签置信选择的半监督集成学习算法。首先，在三个不同的特征空间上训练出三个基分类器，得到基分类器的标签矢量；然后，引入加权融合样本所属某个类别的最大概率与次大概率的误差和样本所属某个类别的最大概率与样本所属其他各类别的平均概率的误差，作为基分类器的标签置信度，并融合标签矢量和标签置信度得到样本的伪标签和集成置信度；接着，选择集成置信度高的样本加入到有标签的样本集，迭代训练基分类器；最后，采用训练好的基分类器集成协作检测视频语义概念。该算法在实验数据集UCF11上的平均准确率到达了83.48%，与Co-KNN-SVM算法相比，平均准确率提高了3.48个百分点。该算法选择的伪标签能体现样本所属类别与其他类别的总体差异性，又能体现所属类别的唯一性，可减少利用伪标签样本的风险，有效提高视频语义概念检测的准确率。     

Title加TextRank抽取关键句的情感分类研究

考虑到不同句子对判断文档情感倾向的重要程度不同，因而区分文档的关键句和细节句将有助于提高情感分类的性能。同时，考虑到Title和上下文信息，提出了一种基于Title和加权TextRank抽取关键句的情感分析方法SKTT，实现了高效的情感分析。根据文档Title的情感权重计算Title贡献度，考虑到标点和语义规则对情感倾向的影响；根据加权TextRank算法思想，在文档正文中构建了一个情感句有向图来提取关键句；计算所有关键句的情感倾向进行情感分类。在4个领域上进行实验，实验结果表明，该SKTT方法性能明显优于Baseline，具有高效性。     

物联网环境下基于情境的语义Web服务选择

当前Web服务海量增加，物联网应用技术快速发展、不断普及，而现有的Web服务选择算法低效、用户匹配度低。针对该问题提出一种物联网环境下基于情境的语义Web服务选择方法。该方法应用QoS参数的无量纲化与语义Web服务动态选择方式，将物联网环境下服务与语义Web服务相结合，并根据用户需求针对QoS选择最优的服务集。实验表明，该方法能有效地提高用户服务动态选择的成功率。     

水平井筒气水流动规律及影响因素

由于流动方向变化及壁面流体的不断径向入流，水平井筒的气水流动规律与常规直井存在较大差异。在总结前人研究结果的基础上，优选水平井筒气液两相预测模型，并在验证模型可靠的情况下，考虑管壁入流和气液流型变化，改变气量、水量、管径、倾角、轨迹波动、气水入流位置等多个影响因素，对水平段流型、压力分布规律及影响因素进行综合预测分析，为水平气井的生产管理及后期措施优化提供依据。研究结果表明，一般生产条件下水平井筒存在分层流、间歇流和环雾流3种流型，管径和倾角对水平井筒的气、水流型影响最为明显，管壁入流对入流就地井筒流态的影响较小。水平井筒压力损失与气量、水量、轨迹上倾角及轨迹波动起伏程度呈正相关性，而与管径和下倾角呈负相关性。预测范围内，气量、轨迹上倾和管径对水平井筒压力损失的影响最为明显，是水平井筒压降的关键影响因素。随着轨迹上倾角增加，水平井筒压降随气量的变化规律发生明显反转，低气量条件下水平井筒压降随气量的减小而增加，高气量下压降随气量增加而增加。