Learning keyword phrases from query logs of USPTO patent examiners for automatic query scope limitation in patent searching

Professional search in patent repositories poses several unique challenges. One key requirement is to search the entire affected space of concepts, following well-defined procedures to ensure traceability of results obtained. Several techniques have been introduced to enhance query generation, preferably via automated query term expansion, to improve retrieval effectiveness. Currently, these approaches are mostly limited to computing additional query terms from patent documents based on statistical measures. For conceptual search to solve the limitation of traditional keyword search standard dictionaries are used to provide synonyms and keyword phrases for query refinement. Studies show that these are insufficient in such highly specialized domains. In this paper, we present an approach to extract keyword phrases from query logs created during the validation procedure of the patent applications. This creates valuable domain-specific lexical databases for several specific patent classes that can be used to both expand as well as limit the scope of a patent search. This provides a more powerful means to guide a professional searcher through the search process. We evaluate the lexical databases based on real query sessions of patent examiners.     

Creating formative feedback spaces in large lectures

Large lectures are the predominant way of teaching first-year students at universities in Norway. However, this forum for education is seldom discussed as a context for a formative feedback practice. The purpose of this sequential mixed methods study was to address whether and how a student-response system can open for a formative feedback practice in lectures and thereby support students' ability to monitor their own learning, as well as supply insight into how students engage with the feedback in their course work. The context for the study was large lectures (150–200 students) in a qualitative method course for first-year psychology students. Findings from the survey (n = 149) showed a positive correlation between the extent to which students report that they use clickers to monitor their own learning, and the extent to which they report that they used the feedback in their own course work. However, findings indicate that students valued the process of monitoring their own learning during the lectures to a greater extent than they actually used the feedback in their course work. Findings from interviews (n = 6) illustrated various ways students applied feedback in their course work.     

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.     

基于深度学习的人体姿态估计方法综述

基于深度学习的人体姿态估计方法旨在通过构建合适的神经网络，直接从二维的图像特征中回归出人体姿态信息。主要按照2D人体姿态估计到3D人体姿态估计的顺序，并从单人检测与多人检测、稀疏的关节点检测与密集的模型构建等方面，对近年来基于深度学习的人体姿态估计方法进行系统介绍，从而初步了解如何通过深度学习的方法得到人体姿态的各个要素，包括肢体部件的相对朝向和比例尺度、骨骼关节点的位置坐标和连接关系，甚至更为复杂的人体蒙皮模型信息。最后,对当前研究面临的挑战以及未来的热点动向进行概述，清晰地呈现出该领域的发展脉络。     

Distributed learning consensus control based on neural networks for heterogeneous nonlinear multiagent systems

This paper considers a novel distributed iterative learning consensus control algorithm based on neural networks for the control of heterogeneous nonlinear multiagent systems. The system's unknown nonlinear function is approximated by suitable neural networks; the approximation error is countered by a robust term in the control. Two types of control algorithms, both of which utilize distributed learning laws, are provided to achieve consensus. In the provided control algorithms, the desired reference is considered to be an unknown factor and then estimated using the associated learning laws. The consensus convergence is proven by the composite energy function method. A numerical simulation is ultimately presented to demonstrate the efficacy of the proposed control schemes.     

深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

基于射流冲击作用的舰机适配性数值分析与优化

准确分析和控制射流冲击对航母甲板环境的影响是新型喷气偏流板设计和布局的关键所在。为了确定射流冲击影响最小的偏流板布局，运用有限体积法，采用分区混合网格方案，结合雷诺时均纳维斯托克斯（RANS）方程和SST k-ω湍流模型对喷气偏流板在不同布局下的射流冲击效应进行三维数值模拟。选取舰载机双发动机全加力状态时喷气偏流板与发动机距离不同、喷气偏流板倾角不同共12种布局组合进行射流冲击效应的对比计算,计算结果显示了喷气偏流板各布局下的流场参数、传热特性、尾喷口温升、冲击力和力矩等分布规律。定性和定量分析了燃气射流冲击下温度场和速度场的危险区域，结果表明，偏流板与发动机距离5 m、偏流板倾角45°时的布局更有利于将燃气射流向上引导。在此基础上，基于倾角最小化原则及二次导流原理优化设计了一种导流隔热性能好、工作稳定性高的被动隔热式喷气偏流板装置。     

Graph-based video fingerprinting using double optimal projection

A double optimal projection method that involves projections for intra-cluster and inter-cluster dimensionality reduction are proposed for video fingerprinting. The video is initially set as a graph with frames as its vertices in a high-dimensional space. A similarity measure that can compute the weights of the edges is then proposed. Subsequently, the video frames are partitioned into different clusters based on the graph model. Double optimal projection is used to explore the optimal mapping points in a low-dimensional space to reduce the video dimensions. The statistics and geometrical fingerprints are generated to determine whether a query video is copied from one of the videos in the database. During matching, the video can be roughly matched by utilizing the statistics fingerprint. Further matching is thereafter performed in the corresponding group using geometrical fingerprints. Experimental results show the good performance of the proposed video fingerprinting method in robustness and discrimination.     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。