一种完整的汉字识别系统设计

数字图像处理是计算机视觉技术的在交通管理领域的一个重要课题.它是指将图像信号转换成数字信号并利用计算机对其进行处理的过程.字符及汉字识别技术的成功运用,节省了大量的人力,而不影响正常的车辆行驶,并且可以快速的记录车辆的违章情况,它是交通管理自动化中的一项有效手段.本文将介绍一种完整的汉字识别系统设计,实现对36号宋体汉字的辨识.     

A novel fault-tolerant execution model by using of mobile agents

The exponential expansion of the Internet and the widespread popularity of the World Wide Web give a challenge to experts on reliable and secure system design, e.g., e-economy applications. New paradigms are on demand and mobile agent technology is one of the features. In this paper, we propose a fault-tolerance execution model by using of mobile agents, for the purpose of consistent and correct performance with a required function under stated conditions for a specified period of time. Failures are classified into two classes based on their intrinsic different effects on mobile agents. For each kind of failure, a specified handling method is adopted. The introduction of exceptional handling method allows performance improvements during mobile agents’ execution. The behaviors of mobile agents are statistically analyzed through several key parameters, including the migration time from node to node, the life expectancy of mobile agents, and the population distribution of mobile agents, to evaluate the performance of our model. The analytical results give new theoretical insights to the fault-tolerant execution of mobile agents and show that our model outperforms the existing fault-tolerant models. Our model provides an effective way to improve the reliability of computer systems.     

Minimizing Energy Barrier in Intermediate Connection Layer for Monolithic Tandem WPeLEDs with Wide Color Gamut

Perovskite light-emitting diodes (PeLEDs) show promising prospects in the wide color gamut display owing to their ultra-narrow full width at half maximum (FWHM). However, up to now, all perovskite white LEDs integrated by standard red, green, and blue perovskite emitters, namely, monolithic white PeLEDs (WPeLEDs), have been rarely reported, owing to facing some issues, e.g., solvent incompatibility in solution technique, ion exchange, and energy transfer between different emission centers. Herein, centered on these issues, an optimal intermediate connection layer (ICL) of Po-T2T/LiF/Ag/HAT-CN/MoO₃ is adopted to successfully develop monolithic tandem multicolor PeLEDs and WPeLEDs for the first time. The multicolor PeLEDs can achieve the best external quantum efficiency of 1.8% and the highest luminance of 4844 cd m⁻². Besides, the red/green/blue (R/G/B) monolithic tandem WPeLED shows a standard white International Commission on Illumination coordinate of (0.33, 0.33) and achieves an extremely wide color gamut reaching  National Television Standards Committee of 130%. This study is the first to realize the standard R/G/B co-electroluminescence in a monolithic perovskite device and offers a feasible strategy for developing wide-color gamut perovskite displays.     

Blood cell counting based on U-Net++ and YOLOv5

Clinical information about a variety of disorders is available through blood cell counting, which is usually done by manual methods. However, manual methods are complex, time-consuming and susceptible to the subjective experience of inspectors. Although many efforts have been made to develop automated blood cell counting algorithms, the complexity of blood cell distribution and the highly overlapping nature of some red blood cells (RBCs) remain significant challenges that limit the improvement of analytical accuracy. Here, we proposed an end-to-end method for blood cell counting based on deep learning. Firstly, U-Net++ was used to segment the whole blood cell image into several regions of interest (ROI), and each ROI contains only one single cell or multiple overlapping cells. Subsequently, YOLOv5 was used to detect blood cells in each ROI. Specifically, we proposed several strategies, including fine classification of RBCs, adaptive adjustment for non-maximal suppression (NMS) threshold and blood cell morphology constraints to improve the accuracy of detection. Finally, the detection outcomes for each ROI were combined and superimposed. The results show that our method can effectively address the issue of high overlap and precisely segment and detect blood cells, with a 98.18% accuracy rate for blood cell counting.     

Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper.     

基于SSH架构的高职院校成绩管理系统的分析和设计

本文介绍了当前基于Struts2、Spring、Hibernate框架的高职院校成绩管理系统的分析和设计。     

Consensus of multiple Euler-Lagrange systems using one Euler-Lagrange System’s velocity measurements

International Journal of Control, Automation and Systems - This brief paper studies the stationary consensus of multiple Euler-Lagrange systems with nonlinear protocols. Two consensus protocols are...