特征回归与检测结合的人数统计方法

针对目前特征回归与检测这2种主流的人流量统计方法的不足,提出一种基于特征回归与检测结合的人数统计方法.对于视频帧的远景区域,采用背景分割的方法提取出前景块,将前景块中的特征通过贝叶斯多核支持向量回归方法估计出人数;对于近景区域提取HOG特征,采用弱标签结构训练出模型,并采用星型结构混合模型级联检测实现行人的准确定位并统计出人数.在视频数据库上的实验结果表明,该方法不仅能够较准确地实现人流量的统计,在一定程度上减少统计时间,还能够准确地定位出一定尺度范围内行人的位置.     

大功率电机控制器和驱动器测试装置的研究

论文介绍了大功率三相无刷电机信号控制器LHB541和无刷电机功率驱动器LHB542测试原理和方法。利用数字电路设计了一种三相方波信号发生装置,考虑到被测器件的功率及测试效率及可靠性而设计制作了相应的测试装置。从而满足了LHB541和LHB542各项参数测试的要求,同时为类似大功率器件测试提供了一种技术参考。     

复杂电磁干扰环境下的C6000 DSP自举方法

对TMS320C620X／670XDSP的存储结构和特点进行分析,采用分两次生成ROM文件的方式实现TMS320C620X／670XDSP自举,并阐述了该自举方法的关键过程。通过该自举方法,程序在片内RAM中执行,预置参数和常量从外部ROM中读取。结合软件三模冗余,该自举方法可以防止复杂电磁干扰环境下单粒子翻转效应。该方法已得到实际应用,行之有效。     

气动激励装置原型机磁共振弹性成像研究

介绍:磁共振弹性成像是一种无创的对生物组织的生物力学特性进行定量分析的新技术。在诸多外部机械激励方法中,气动激励装置因其磁兼容性好而相对被广泛使用。本研究搭建了一台气动装置原型机并测试了该装置在不同频率和振幅条件下的性能。材料和方法:使用超声方法测试气动激励装置原型机在无负载条件和不同频率和振幅情况下的性能,并在磁共振弹性成像环境测试该原型机在有负载条件下的性能。结果:生物组织的弹性值与外部激励的频率和振幅、生物组织的机械力学特性以及传导管的长度和内径有关。结论:稳定可靠的机械波是磁共振弹性成像中准确可靠地重建组织弹性值的保障,气动激励装置的机械激励参数应根据不同生物组织的特性进行优化,以保证弹性值重建的可靠性。     

改进正交试验法在调速器参数优化中的应用

对粤电集团某水电站机组建立仿真模型,采用改进正交试验法对该电站调速器参数进行优化,并对优化后的调节系统进行了频率扰动仿真试验.结果表明:参数优化后的调节过程性能得到明显改善,且用改进正交试验法优化调速器参数是方便、快捷和可行的.     

Production of two-material micro-assemblies by two-component powder injection molding and sinter-joining

In the field of micro-technology the production of metallic and ceramic micro-components by powder injection molding (PIM) has become a more and more established fabrication method. But in order to fulfill the demand for more complex-shaped high-precision micro-components further development work has to be performed. This is especially true if more efficient production routes for multi-component-micro-assemblies consisting of different materials or sub-components are envisaged. To meet these challenges, investigations are performed to realize and to establish two primary shape micro-processes. These are two-component micro-injection molding (2C-MicroPIM) and sinter-joining. The realization of these technologies will lead to a markedly reduction of the efforts for handling, adjustment, and assembling of metallic and ceramic micro-assemblies. Furthermore, an increased integration level and functionality can be yielded. For an effective transfer of scientific results to industrial applications the whole process chain must be considered, from development and construction of the tooling as well as of the components to the quality assurance and determination of the properties of the assemblies after sintering. These primary shape processes shall enable the mutual processing of different materials within the fabrication process, so avoiding separate mounting or assembling steps. Additionally fixed and loose junctions between at least two components shall be realized. The progress in research and development will be demonstrated especially by the implementation of shaft-to-collar connections between micro-gearwheels and corresponding shafts. Regarding two-component micro-injection molding, the tool construction for shaft-to-collar connections will be presented as well as first experimental results on the properties of selected ceramic powders and feedstocks for the special requirements of the 2C-MicroPIM process. With the assembly step being performed outside the injection molding tool before sinter-joining different parts and geometries can be combined quite easily. The presented article gives an overview on the concept and on preliminary testing results for the fabrication of a shaft-to-collar-connection. Additionally, a solution for an automated assembly of a shaft and a toothed wheel outside the injection molding tool is presented.     

纳升级生物样品核磁共振微检测高信噪比平面螺旋微线圈的设计

论述了纳升(nL)级生物样品核磁共振微检测技术中,高信噪比平面螺旋微线圈的设计方法及结果,介绍了这种检测技术的优点与缺点,并提出了改进方法。论述了核磁共振平面螺旋微线圈检测方法的理论基础,推导出自由感应衰减信号的信噪比与线圈几何参数的数学关系,利用MATLAB软件对信噪比进行了仿真,得到了最优信噪比条件下的线圈几何参数值,同时计算出相应的品质因数。最后,概括了平面螺旋形微线圈几何参数设计的一般原则。     

主动干扰辅助下的无人机隐蔽通信功率与位置联合优化

利用友好干扰节点发送人工噪声是无线隐蔽通信中一种常见实现方法,可以增加监听者做出判断的不确定性,从而实现隐蔽传输。为此,考虑在无人机隐蔽通信网络中,部署一个空中的友好干扰节点,发射人工噪声干扰地面监听者的检测。对无人机与地面用户之间实现无线隐蔽传输进行了研究,分析了其有效隐蔽性能,联合优化了2架无人机的发送功率和位置部署以最大化隐蔽传输速率,使用粒子群优化算法与功率位置交替迭代算法2种优化方法得到最优的无人机部署位置及功率分配方案。仿真结果表明,联合优化方案相比于固定位置只优化功率的基准方案可以显著地提高系统隐蔽传输性能,且交替迭代算法所得结果要优于粒子群优化算法。     

Recent Development of Jumping Motions Based on Soft Actuators

Drawing inspiration from the jumping motions of living creatures in nature, jumping robots have emerged as a promising research field over the past few decades due to great application potential in interstellar exploration, military reconnaissance, and life rescue missions. Early reviews mainly focused on jumping robots made of lightweight and rigid materials with mechanical components, concentrating on jumping control and stability. Herein, attention is paid to the jumping mechanisms of soft actuators assembled from various soft smarting materials and powered by different stimulus sources. The challenges and prospects of soft jumping actuators are also discussed. It is hoped that this review will contribute to the further development of soft jumping actuators and broaden their practical applications.     

Detection of COVID-19 from chest X-ray images: Boosting the performance with convolutional neural network and transfer learning

Coronavirus disease (COVID-19) is a pandemic that has caused thousands of casualties and impacts all over the world. Most countries are facing a shortage of COVID-19 test kits in hospitals due to the daily increase in the number of cases. Early detection of COVID-19 can protect people from severe infection. Unfortunately, COVID-19 can be misdiagnosed as pneumonia or other illness and can lead to patient death. Therefore, in order to avoid the spread of COVID-19 among the population, it is necessary to implement an automated early diagnostic system as a rapid alternative diagnostic system. Several researchers have done very well in detecting COVID-19; however, most of them have lower accuracy and overfitting issues that make early screening of COVID-19 difficult. Transfer learning is the most successful technique to solve this problem with higher accuracy. In this paper, we studied the feasibility of applying transfer learning and added our own classifier to automatically classify COVID-19 because transfer learning is very suitable for medical imaging due to the limited availability of data. In this work, we proposed a CNN model based on deep transfer learning technique using six different pre-trained architectures, including VGG16, DenseNet201, MobileNetV2, ResNet50, Xception, and EfficientNetB0. A total of 3886 chest X-rays (1200 cases of COVID-19, 1341 healthy and 1345 cases of viral pneumonia) were used to study the effectiveness of the proposed CNN model. A comparative analysis of the proposed CNN models using three classes of chest X-ray datasets was carried out in order to find the most suitable model. Experimental results show that the proposed CNN model based on VGG16 was able to accurately diagnose COVID-19 patients with 97.84% accuracy, 97.90% precision, 97.89% sensitivity, and 97.89% of F1-score. Evaluation of the test data shows that the proposed model produces the highest accuracy among CNNs and seems to be the most suitable choice for COVID-19 classification. We believe that in this pandemic situation, this model will support healthcare professionals in improving patient screening.