基于CNN的人体姿态识别

姿态识别是人机交互中重要的研究课题之一，随着机器学习与神经网络的发展，研究的方式和成果趋于多样化，姿态识别的应用价值也日趋广泛。本文通过构建卷积神经网络模型，该模型共有11层，在对采样的数据集中5种人体姿态进行卷积与池化操作，最后进入全连接层进行分类，从而完成对数据集的训练和识别。结果显示，相较于机器学习方法，该模型的识别性能更加优秀，且免去了复杂的特征提取方式设计，让网络自身提取特征进行识别分类，效果更好。     

纳米零价铁材料对放射性核素的 去除及机理研究进展

随着人类社会的发展，放射性铀矿的开采和使用越来越多，环境面临着越来越严重的放射性污染问题。从生物和环境的角度来看，有效地清除环境中的放射性核素是核能利用过程中最重要的问题之一。纳米零价铁（nanoscale zero valent iron, nZVI）具有较大的比表面积和较高的活性位点，能显著提高放射性污染物的修复效率。本综述的目的是展示nZVI基材料对放射性核素的高效去除能力和环境修复作用。简介了常用的nZVI基材料（表面改性或多孔材料支撑的nZVI材料）及其对放射性核素的去除效果和相互作用机制（如吸附和氧化还原）。最后，对nZVI材料的应用和挑战给出个人见解。本综述有助于为高效去除放射性核素的nZVI材料的设计指明方向，为放射性核素的高效处理处置提供新材料。     

Nonlinear modal analysis via non‐parametric machine learning tools

Modal analysis is an important tool in the structural dynamics community; it is widely utilised to understand and investigate the dynamical characteristics of linear structures. Many methods have been proposed in recent years regarding the extension to nonlinear analysis, such as nonlinear normal modes or the method of normal forms, with the main objective being to formulate a mathematical model of a nonlinear dynamical structure based on observations of input/output data from the dynamical system. In fact, for the majority of structures where the effect of nonlinearity becomes significant, nonlinear modal analysis is a necessity. The objective of the current paper is to demonstrate a machine learning approach to output‐only nonlinear modal decomposition using kernel independent component analysis and locally linear‐embedding analysis. The key element is to demonstrate a pattern recognition approach which exploits the idea of independence of principal components from the linear theory by learning the nonlinear manifold between the variables. In this work, the importance of output‐only modal analysis via “blind source” separation tools is highlighted as the excitation input/force is not needed and the method can be implemented directly via experimental data signals without worrying about the presence or not of specific nonlinearities in the structure.     

Simplification and applicability studies of a hydrogen-air detailed reaction mechanism

The research of hydrogen fuel internal combustion engine (HICE) had great significance facing the challenges of energy and environmental problems. Based on the detailed hydrogen-air reaction mechanism, the pre-mix model of CHEMKIN-Pro software was selected to simplify the detailed mechanism GRI-3.0. The most important elements and reactions was chose to construct framework mechanism firstly based on the sensitivity coefficient for H₂O and NO formation, and additional elements and reactions were added to framework mechanism for complementing the oxidation path of N2 and H₂. A simplified mechanism including 24-step elementary reaction was obtained and the laminar burning velocity calculated by this simplified mechanism matches well with the detailed mechanism in a wide range. This simplified mechanism was also applied in a CFD model which predicted the cylinder instantaneous pressure and NOx emission accurately within a large range of fuel air equivalent ratio. Showing that this mechanism has good applicability.     

基于结构光的星箭对接环相对位姿测量方法

空间非合作目标位姿测量是空间在轨维护的前提。面向空间机械手对空间载体自动抓捕的应用需求，提出了基于结构光的空间非合作目标视觉测量方法。该方法以双套双线结构光测量装置作为测量传感器，以空间载体上普遍存在的星箭对接环作为抓捕目标。根据对接环的共同特点，选择直线特征和点特征相结合作为相对位姿的求解特征；基于直线特征求解圆环平面法向量，基于点特征求解圆环圆心坐标，进而得到机械手工具坐标系与对接环坐标系间的相对位姿关系；基于多重几何约束实现了不同光照条件下图像上目标直线的鲁棒识别。建立了演示验证实验系统，在大量演示实验的基础上，进行了实验结果分析。     

Antenna selection for MIMO system based on pattern recognition

This paper proposes a novel Multiple-Input Multiple-Output (MIMO) transmission scheme based on Pattern Recognition (PR), which is termed as the PR aided Transmission Antenna Selection MIMO (PR-TAS aided MIMO). As the conventional TAS algorithms need to search all possible legitimate antenna subsets, they may impose some redundant calculations. In order to avoid this problem, we employ some pattern recognition methods to carry out the TAS algorithm in this paper. To be specific, two PR algorithms, namely the K-Nearest Neighbor (KNN) algorithm and the Support Vector Machine (SVM) algorithm, are introduced and redesigned to obtain a TAS with lower complexity but higher efficiency. Moreover, in order to improve the performance of the SVM, we propose a new feature extraction of channel matrix for the TAS. Our simulation results show that the proposed KNN and SVM based PR-TAS algorithms are capable of striking a flexible tradeoff between the complexity and the Bit Error Rate (BER), and the new feature can effectively improve the BER performance compared with the conventional feature extraction method.     

Location Privacy in Device-Dependent Location-Based Services: Challenges and Solution

With the evolution of location-based services (LBS), a new type of LBS has already gain a lot of attention and implementation, we name this kind of LBS as the Device-Dependent LBS (DLBS). In DLBS, the service provider (SP) will not only send the information according to the user’s location, more significant, he also provides a service device which will be carried by the user. DLBS has been successfully practised in some of the large cities around the world, for example, the shared bicycle in Beijing and London. In this paper, we, for the first time, blow the whistle of the new location privacy challenges caused by DLBS, since the service device is enabled to perform the localization without the permission of the user. To conquer these threats, we design a service architecture along with a credit system between DLBS provider and the user. The credit system tie together the DLBS device usability with the curious behaviour upon user’s location privacy, DLBS provider has to sacrifice their revenue in order to gain extra location information of their device. We make the simulation of our proposed scheme and the result convince its effectiveness.     

Tibetan Multi-Dialect Speech and Dialect Identity Recognition

Tibetan language has very limited resource for conventional automatic speech recognition so far. It lacks of enough data, sub-word unit, lexicons and word inventories for some dialects. And speech content recognition and dialect classification have been treated as two independent tasks and modeled respectively in most prior works. But the two tasks are highly correlated. In this paper, we present a multi-task WaveNet model to perform simultaneous Tibetan multi-dialect speech recognition and dialect identification. It avoids processing the pronunciation dictionary and word segmentation for new dialects, while, in the meantime, allows training speech recognition and dialect identification in a single model. The experimental results show our method can simultaneously recognize speech content for different Tibetan dialects and identify the dialect with high accuracy using a unified model. The dialect information used in output for training can improve multi-dialect speech recognition accuracy, and the low-resource dialects got higher speech content recognition rate and dialect classification accuracy by multi-dialect and multi-task recognition model than task-specific models.