基于SOM神经网络聚类的车牌号码倾斜校正算法

经过摄像机摄入的图像会发生倾斜,给车牌的准确识别带来了困难.针对此问题,利用SOM神经网络良好的聚类性能,在水平倾斜校正时,把车牌号码图像中的像素坐标聚成两类,拟合成一条直线,计算出该直线倾斜角,完成水平校正;按照以上同样方法进行垂直倾斜校正.实验结果表明,该方法能准确获取车牌号码的倾斜角,算法结构简单,抗干扰能力较强,符合汽车牌照图像的特点,具有较好的处理效果.     

人工气候室监控系统的环境控制器研究

根据集散型控制系统(DCS)的技术特点,结合集散型人工气候室监控系统的需求,研究并实现了一种基于STC89C54RD+单片机的人工气候室环境控制器;为了充分利用STC89C54RD+单片机的片上资源,该控制器在无需外部扩展I/O的情况下实现了12路控制输出、8路开关量检测输入、5路A/D采集通道和1个RS-485通讯接口;为了增强系统的抗干扰能力,该控制器采用V/F转换作为A/D转换的主要手段并在各个前、后向通道上采取了三极管和光电耦合器相结合的双重隔离措施;为了提高控制器的灵活性和降低系统的整体开发成本,该控制器还提供了一种同时兼容热电阻、湿敏电阻等传感器和电流、电压型集成传感器的解决方案。     

网络资源的多层监测方法与实现

设计了针对网络资源不同层次进行监测的实现方法,这些层次包括：网络传输层对象（网络服务器性能、TCP、UDP实现过程）、应用层对象（主要是业务数据库）、表示层对象（页面及相关的脚本行为）、用户（浏览器）以及Web服务（HTTP协议实现过程）。对于不同层次的数据,采用了不同的采集方法,并实现了对不同监测资源的重新组合分析。在分层获取、分析、存储数据基础上进行了统一身份认证、统一展示标准和指标集成展示,从而实现了分布式监测系统的集成。     

基于光纤环网的隧道火灾监控系统研究

文章对基于光纤环网的隧道群火灾报警系统进行研究,分析了其优缺点,提出了解决办法,并完成改造,应用于实际.     

A novel approach of data race detection based on CNN-BiLSTM hybrid neural network

Neural Computing and Applications - Existing data race detection approaches based on deep learning are suffering from the problems of unique feature extraction and low accuracy. To this end, this...     

Ultrafast measurement of transient electroosmotic flow in microfluidics

We present a non-intrusive molecular dye based method, i.e., laser-induced fluorescence photobleaching anemometer (LIFPA), to significantly increase temporal resolution (TR) for velocity measurement of fast transient electrokinetic flows. To our knowledge, the TR has been for the first time achieved to 5–10 μs, about 100 times better than that published from state-of-the-art micro particle image velocimetry (μPIV), which is currently the most widely used velocimetry in the microfluidics community. The new method provides us with new opportunities to study experimentally the fundamental phenomena of unsteady electrokinetics (EK) and to validate relevant theoretical models. One application of the new method is demonstrated by measuring the rise time of DC electroosmotic flows (EOFs) in a microcapillary of 10 μm in diameter.     

Surface tension calculation of the Ni3S2---FeS---Cu2S mattes

The surface tension of the Ni₃S₂-FeS-Cu₂S ternary mattes have been calculated from those of the Ni₃S₂-FeS·FeS-Cu₂S and Cu₂S-Ni₃S₂ pseudo-binary boundary systems by using geometric models (Kohler and Toop model) and a general solution model (Chou model). Taking account of the experimental accuracy of ±2.5%, the respective calculated results are in agreement with the experimental data. At the same time, surface tensions of molten Ni₃S₂-FeS-Cu₂S mattes and their pseudo-binary boundary systems are predicted based on Butler's original treatment with great attention to the model parameter β. The predicted results also agree with the experimental data. Therefore, the resulting iso-surface tension curves in molten Ni₃S₂-FeS-Cu₂S mattes at 1473K, especially calculated by using Kohler, Toop and Chou models, are generally acceptable.     

A MEMS Thermal Biosensor for Metabolic Monitoring Applications

This paper presents a microelectromechanical systems (MEMS) differential thermal biosensor integrated with microfluidics for metabolite measurements in either flow-injection or flow-through mode. The MEMS device consists of two identical freestanding polymer diaphragms, resistive heaters, and a thermopile between the diaphragms. Integrated with polymer-based microfluidic measurement chambers, the device allows sensitive measurement of small volumes of liquid samples. Enzymes specific to a metabolic analyte system are immobilized on microbeads packed in the chambers. When a sample solution containing the analyte is introduced to the device, the heat released from the enzymatic reactions of the analyte is detected by the thermopile. The device has been tested with glucose solutions at physiologically relevant concentrations. In flow-injection mode, the device demonstrates a sensitivity of approximately 2.1 muV/mM and a resolution of about 0.025 mM. In flow-through mode with a perfusion flow rate of 0.5 mL/h, the sensitivity and resolution of the device are determined to be approximately 0.24 muV/mM and 0.4 mM, respectively. These results illustrate that the device, when integrated with subcutaneous sampling methods, can potentially allow for continuous monitoring of glucose and other metabolites.