基于音频特征的工程车辆工况识别研究

高效率地使用工程车辆是工程项目管理中节约成本的有效方法，无人监管环境下工程车辆的工况识别，是实现工程车辆高效率使用的有效手段。目前以GPS等技术为核心的车辆智能管理系统未对工程车辆进行工况识别，提出一种基于GRU循环神经网络的工程车辆工况识别方法，通过对工程车辆在不同工况下产生的音频信号进行分析，从中提取Mel倒谱系数作为主要特征，构建GRU循环神经网络模型进行训练和识别。实验结果表明，该方法可以实现对工程车辆工况的有效识别。     

Understanding the asymmetric perceptions of smartphone security from security feature perspective: A comparative study

Smartphones are being used and relied on by people more than ever before. The open connectivity brings with it great convenience and leads to a variety of risks that cannot be overlooked. Smartphone vendors, security policy designers, and security application providers have put a variety of practical efforts to secure smartphones, and researchers have conducted extensive research on threat sources, security techniques, and user security behaviors. Regrettably, smartphone users do not pay enough attention to mobile security, making many efforts futile. This study identifies this gap between technology affordance and user requirements, and attempts to investigate the asymmetric perceptions toward security features between developers and users, between users and users, as well as between different security features. These asymmetric perceptions include perceptions of quality, perceptions of importance, and perceptions of satisfaction. After scoping the range of smartphone security features, this study conducts an improved Kano-based method and exhaustively analyzes the 245 collected samples using correspondence analysis and importance satisfaction analysis. The 14 security features of the smartphone are divided into four Kano quality types and the perceived quality differences between developers and users are compared. Correspondence analysis is utilized to capture the relationship between the perceived importance of security features across different groups of respondents, and results of importance-satisfaction analysis provide the basis for the developmental path and resource reallocation strategy of security features. This article offers new insights for researchers as well as practitioners of smartphone security.     

Synthesis of Hollow Three-Dimensional Channels LiNi_(0.5)Mn_(1.5)O_4 Microsphere by PEO Soft Template Assisted with Solvothermal Method

A appropriate size with three-dimension(3 D) channels for lithium diffusion plays an important role in constructing highperforming LiNi_(0.5)Mn_(1.5)O_4(LNMO) cathode materials, as it can not only reduce the transport path of lithium ions and electrons, but also reduce the side effects and withstand the structural strain in the process of repetitive Li~+ intercalation/deintercalation. In this work, an e fficient method for designing the hollow LNMO microsphere with 3 D channels structure by using polyethylene oxide(PEO) as soft template agent assisted solvothermal method is proposed. Experimental results indicate that PEO can make the reagents mingle evenly and nucleate slowly in the solvothermal process, thus obtaining a homogeneous distribution of carbonate precursors. In the final LNMO products, the hollow 3 D channels structure obtained by the decomposition of PEO and carbonate precursor in the calcination can provide abundant electroactive zones and electron/ion transport paths during the charge/discharge process, which benefits to improve the cycling performance and rate capability. The LNMO prepared by adding 1 g PEO possesses the most outstanding electrochemical performance, which presented an excellent discharge capacity of 143.1 mAh g~(-1) at 0.1 C and with a capacity retention of 92.2% after 100 cycles at 1 C. The superior performance attributed to the 3 D channels structure of hollow microspheres, which provide uninterrupted conductive systems and therefore achieve the stable transfer for electron/ion.     

Multilayer Si@SiOx@void@C anode materials synthesized via simultaneously carbonization and redox for Li-ion batteries

In the development of high-performance lithium-ion batteries (LIBs), the composition and structure of electrode materials are of critical importance. Silicon has a theoretical specific capacity 10 times that of graphite, nonetheless, its application as an anode material confronts challenge as it undergoes huge volume change and pulverization amidst the alloying and dealloying processes. Herein, a novel method to prepare a multilayer Si-based anode was proposed. Three layers, SiO₂, nickel and triethylene glycol (TEG), were coated successively on Si nanoparticles, which served respectively as the sources of SiO_x, sacrificial templates and carbon. Nickel can not only serve as a hollow template, but also play a catalytic role, which makes carbonization and redox reactions occur synchronously under a mild condition. Amid the carbonization process of TEG at 450 °C, several-nm-thick SiO₂ layer can react with the as-derived carbon to form a silicon suboxides (SiO_x (0 < x < 2)) intermedium layer. After removing the nickel template, a micro-nano scaled Si@SiO_x@void@C with conformal multilayer-structure can be obtained. The BET specific surface area and pore volume of powders were increased dramatically because of the derivation of abundant voids, which can not only buffer the swelling effect of silicon, but also provide richer ionic conductivity. The as-assembled half-cell with Si@SiOx@void@C as the anode material possesses high capacity (～1000 mAh g^?1 at 3 A g^?1), long cycle life (300 cycles with 77% capacity retention) and good rate performance (558 mAh g^?1 at 5 A g^?1).     

Extrinsic parameter's adjustment and potential implications in Plasmodium falciparum malaria diagnosis

Malaria is a major public health concern, affecting over 3.2 billion people in 91 countries. The advent of digital microscopy and Machine learning with the aim of automating Plasmodium falciparum diagnosis extensively depends on the extracted image features. The color of the cells, plasma, and stained artifacts influence the topological, geometrical, and statistical parameters being used to extract image features. During microscopic image acquisition, custom adjustments to the condenser and color temperature controls often have an influence on the extracted statistical features. But, our human visual system sub-consciously adjusts the color and retains the originality in a different lighting environment. Despite the use of appropriate image preprocessing, findings from the literature indicate that statistical feature variations exist, allowing the risk of P. falciparum misinterpretation. In order to eliminate this pervasive variation, the current work focuses on preprocessing the extracted statistical features rather than the prepossessing of the source image. It begins with the augmentation of series images for a microscopic field by inducing illumination variations during the microscopic image acquisition stage. A set of such image series is analyzed using a Nonlinear Regression Model to generalize the relationship between microscopic images acquired with variable ambient brightness and a specific feature. The projection point of the centroid feature onto the brightness parameter is identified in the model and it is denoted as the optimum brightness factor (OBF). Using the model, the feature correction factor (CF) is calculated from the rate of change of feature values over the interval OBF, and the brightness of the test image is processed. The present work has investigated OBF for selected image textural features, namely Contrast, Homogeneity, Entropy, Energy, and Correlation individually from its co-occurrence matrices. For performance analysis, the best state-of-the-art method uses selected texture as a subset feature to evaluate the effectiveness of P. falciparum malaria classification. Then, the impact of proposed feature processing is evaluated on 274 blood smear images with and without Feature Correction (FC). As a result, the “p” value is less than .05, which leads to the result that it is highly significant and the classification accuracy and F-score of P. falciparum malaria are increased.     

改进RetinaFace的自然场景口罩佩戴检测算法

新型冠状病毒可以通过空气中的飞沫、气溶胶等载体进行传播，在公共场所下正确佩戴口罩可以有效地防止病毒的传播。提出了一种自然场景下人脸口罩佩戴检测方法，对RetinaFace算法进行了改进，增加了人脸口罩佩戴检测任务，优化了损失函数。在特征金字塔网络中引入了一种改进的自注意力机制，增强了特征图的表达能力。建立了包含3 000张图片的数据集，并进行手工标注，用于网络训练。实验结果表明该算法可以有效进行口罩佩戴检测，在自然场景视频中也取得了不错的检测效果。     

基于语言特征自动获取的反问句识别方法

反问句是以疑问的形式表达强烈情感的修辞方式,对其有效识别可为自然语言处理中的情感分析任务提供技术支持。该文提出了一种基于语言特征自动获取的反问句识别方法。首先,利用标签注意机制,建立了一个数据驱动的特征抽取模型,用于获取与任务相关的词汇、句法结构、符号标记和话题等语言特征。其次,利用Bi-LSTM模型分别对句子和语言特征进行表示,两者的交互注意被用于获取句子的各个词和符号的注意力权重向量。该权重向量作用于句子的表示,用于构建一个强化语言特征的反问句识别模型。在中文微博数据集上的实验结果表明,提出的方法与之前的工作相比,反问句识别性能有显著提升。     

机翼极限环颤振的CFD/CSD全隐式紧耦合方法

针对轴承振动实时状态监控的需要，从符号动力学角度提出了符号聚合近似与Lempel-ziv复杂度（SAX-LZC）融合的振动监控参数。首先，以Logistic映射和Duffing方程为对象，从理论角度验证了SAX-LZC对动力学结构表征的准确性，并验证了该指标的抗噪能力和计算效率；其次，将SAX-LZC指标与信息熵、样本熵、多分段Lempel-ziv复杂度等动力学参数性能进行了综合对比；最后，从实验角度对轴承早期微弱异常进行了监测，并对轴承典型故障进行了特征提取。理论研究结果表明，SAX-LZC具有动力学结构表征准确、抗噪能力好、计算高效简洁等优点，克服了常规动力学参数工程应用能力弱的问题。实验研究结果表明，SAX-LZC对早期微弱异常有准确的监测，对不同种类故障具有较好的区分度，弥补了时域和频域对轴承微弱故障表征能力不足的缺陷，是一种轴承振动实时状态监控与故障特征提取的有效参数。     

小尺度交通信号灯的检测与状态识别

交通信号灯识别包括检测和状态识别，在智能交通系统中发挥重要作用。基于YOLOv3算法提出了一种交通信号灯检测与状态识别模型。针对交通信号灯相较于交通场景中其他目标具有尺度小的特性进行了算法的设计：降低骨干网络的下采样倍率以增加小尺度目标的特征描述能力；通过增大特征图的尺度来改进多尺度特征融合；引入广义交并比作为检测任务的损失函数来改进目标边界框的回归效果。同时，根据交通信号灯本身的特性，使用颜色和形状约束的方法对信号灯进行状态识别和类别验证。最后在公开的Bosch交通信号灯数据集上和实际的城区道路进行了实验验证。实验结果表明，所提出的算法能够提升交通信号灯识别的精度和召回率，识别准确率可以达到90%左右。     

Human action recognition toward massive-scale sport sceneries based on deep multi-model feature fusion

In sport sceneries, automatically recognizing human actions is a useful technique that can be popularly applied in may domains, such as human body tracking and athlete behavior analysis Most state-of-the-art deep architectures have achieved competitive performance in recognizing human action. However, it is still a challenging task due to the unavoidable occlusion, camera angle changes, and varied human posture. In this paper, we propose a novel deep multimodal feature fusion algorithm for human action recognition. The key technique is a multi-model feature fusion scheme. More specifically, we fuse visual feature, skeleton posture, probability maps and audio signal into a hybrid feature, which is utilized to represent human action. Then these feature channels are optimally combined using a deep model, wherein the weights of multiple feature channels can be predicted intelligently. Finally, the optimally fused feature are fed into a multi-class SVM for conducting human action recognition. Extensive comparative results and parameter analysis have shown the effectiveness of our proposed method.