基于表层剥离原理的传递函数设计

针对体绘制领域目前存在的计算开销、经验提取和复杂人工干预等几个重要的应用问题,提出了传递函数设定的表层剥离算法。表层剥离算法通过单程交越检测和高梯度比例边缘检测,解决了表层起伏现象导致的分类误差较大,需要复杂的人工干预调整的问题;避免引入高阶偏导等复杂的计算,保持了较低的计算开销;而且形成了一种简单且能发挥用户直觉,具有较高自动化成分的传递函数设定方式,取得了较好的效果。据此开发的普及型医学图像分析系统验证了算法的有效性。     

自适应搜索优化算法

自由搜索算法是一种新的群集智能优化算法,已经成功地应用于函数优化问题.针对该算法所存在的对参数敏感等问题,提出自适应搜索算法.通过自适应实时调整搜索半径、搜索步、灵敏度等参数,提高算法对环境的适应性、鲁棒性和在"探索"和"开发"之间的平衡能力.对典型函数的试验结果证明,新算法不仅降低了对参数的依赖性,而且成功率高、收敛速度快,能有效避免陷入局部次优.     

书写文字识别算法研究

介绍模式识别的基本原理和对书写文字字符的识别以及文字识别,阐述模式识别的过程、图像文件的格式,介绍基于住图技术的模式识别理论;讨论分类器设计过程中的特征空间优化设计问题、分类嚣设计准则、基本方法和判别函数的知识,给出模板匹配法识别图像的原理.     

基于小波算法的二阶线性定常分布参数系统的辨识

本文基于正交函数逼近方法,借助于小波变换,并利用其运算矩阵及其运算性质,研究了分布参数系统的辨识问题。将Haar小波正交基应用于分布参数系统的辨识中,经正交小波逼近变换,将原偏微分描述的分布参数系统转化为代数矩阵方程,并且,考虑了初始条件和边界条件,获得了算法简单、计算方便、具有较高精度的辨识算法,简化了分布参数系统辨识的求解过程,应用在分布参数系统辨识中不失为一种有效的分析方法。仿真实例表明了本文所提出的算法的有效性。     

A Multi-scale Attention-based Facial Emotion Recognition Method Based on Deep Learning

Recently, people have been paying more and more attention to mental health, such as depression, autism, and other common mental diseases. In order to achieve a mental disease diagnosis, intelligent methods have been actively studied. However, the existing models suffer the accuracy degradation caused by the clarity and oc-clusion of human faces in practical applications. This paper, thus, proposes a multi-scale feature fusion network that obtains feature information at three scales by locating the sentiment region in the image, and integrates global feature information and local feature information. In addition, a focal cross-entropy loss function is designed to improve the network''s focus on difficult samples during training, enhance the training effect, and increase the model recognition accuracy. Experimental results on the challenging RAF_DB dataset show that the proposed model exhibits better facial expression recognition accuracy than existing techniques.     

运动模糊图像PSF参数估计方法改进及图像复原

运动模糊图像复原的目的是改善运动图像质量,从而为图像处理任务提供高质量的清晰图像以保证算法能够准确获取图像信息,其中运动模糊图像的点扩散函数（PSF）求解是影响复原图像质量的关键步骤。针对现有运动模糊图像PSF参数估计方法中存在的估计误差大、有效估计范围有限等问题,在分析频谱图像特征的基础上,提出一种改进的PSF参数估计方法。通过图像增强处理和形态学变换去除频谱图像中的十字亮线和噪点干扰,获取形态合适的条纹图像以完成Radon变换检测。利用二值频谱图像的条纹特征自适应地控制形态学运算精度,从而保证算法的执行效率和鲁棒性。对条纹进行边缘测定,消除由条纹自身宽度导致的角度估计误差,以提高参数估计结果的精度。实验结果表明,该方法能够提高模糊参数估计的准确率和有效估计范围,由此构建的PSF能复原出更加清晰的重建图像,复原图像总体峰值信噪比不低于25 dB。     

两类非线性密码组件可重构研究与电路设计

为解决对称密码中s盒和非线性布尔函数（NBF）在实现密码专用处理器时采用异构化设计导致的资源浪费问题,提出一种类AESs盒和NBF的可重构电路结构方法。分析s盒问题中的原有非线性布尔函数模块（NBFM）,4-4、6-4的s盒电路能够提供更好的适配性,但不能很好地支持8-8的s盒电路。基于塔域分解理论,论证不同的类AESs盒电路差异在于输入前后的转换矩阵。采用混合基的方法将类AESs盒电路分解成GF （16）上的各个运算模块,并推导出模块比特级别表达式,在具体适配运算模块时采取门级实现、NBFM适配实现或对NBFM进行改进3种方案,实现类AESs盒和NBF的可重构电路。实验结果表明,该方法在不影响原有NBF功能的基础上,利用4个NBFM与22.7%的s盒电路面积即可实现一个完整的类AESs盒电路。     

基于CvM算法的Nakagami衰落信道统计特性检验

Nakagami信道通过不同的衰落因子m可以仿真不同的信道衰落环境,仿真数据与实际测量值吻合度较高,在信道仿真领域得到广泛应用。然而,目前针对Nakagami信道模型的可信性研究较少,缺少科学的比对验证方法。根据典型Nakagami信道的一阶包络序列服从Nakagami分布这一信道统计特性,提出一种基于Cramer-von Mises （CvM）算法的拟合优度检验方法。使用“高斯+瑞利+直流”组合法建立Nakagami衰落信道模型,得到信道输出序列并从中提取包络序列。在此基础上,利用双样本CvM检验算法对包络序列的理论分布和实际分布进行拟合优度检验,实现对Nakagami信道模型的可信性评估。半实物仿真结果表明,与K-S检验、卡方检验和Z检验+卡方检验融合检验算法相比,CvM针对不同m下的Nakagami衰落信道均具有较好的识别性能,同时在可靠性和复杂度方面也具有优势,其对虚警概率为0.01以下的Nakagami衰落信道识别准确率达到92.6%,对样本长度为300 000以上的Nakagami衰落信道平均识别准确率达到96.4%,而当待检验信道为其他信道时,不存在误识别的情况。     

Augmented body surveillance: Human microchip implantations and the omnipresent threat of function creep

Implanted microchips can store users' medical, financial, and other personal information, and provide users with easy and quick access to various locations and items. While adopted for their convenience outside of the healthcare sector, these invasive, semi-permanent implantable devices create augmented bodies that can be subject to ubiquitous surveillance. Situating human microchip implantations within surveillance literature, we draw from neoliberal perspectives of surveillance to examine augmented bodies, particularly as sources for market activity and as subjects of social control and sorting when these bodies are used as access control mechanisms, payment methods, and tracking means in employment, residential, commercial, and transportation sectors. History has demonstrated time and time again how unfettered technology applications and uses have led to real and/or perceived misuse by private and public sectors. Through the lens of function creep, we identify a pattern of expansion of applications and uses of technology beyond those originally intended across new technologies, such as DNA genetic genealogy databases, IoT wearables, and COVID-19 contact tracing apps, and provide illustrative examples of function creep, particularly the use of these technologies in criminal investigations and prosecutions despite not being intended or marketed for such use. By demonstrating the lack of clearly defined boundaries in the applications and uses of various new technologies and their associated data, and the ways they were misused, we demonstrate how human microchip implantations are headed on a similar path. The current and potential future uses of this technology raise concerns about the absence of regulation, law, and policy barring or limiting its application and use in specific sectors, and the impact of this technology on users’ security, data protection, and privacy. Undeniably, the present and potential future functions, applications, uses, and extensions of human microchip implantations in various sectors warrant a proactive examination of their security, privacy, and data protection consequences and the implementation of proactive policies to regulate new and currently unregulated uses of this technology and its associated data within these sectors.     

Some approximation properties of adaptive fuzzy systems with variable universe of discourse

In the last 20 years, while most research on fuzzy approximation theory has focused on nonadaptive fuzzy systems, little work has been done on adaptive fuzzy systems. This paper introduces an algorithm for adaptive fuzzy systems with Variable Universe of Discourse (VUD). By means of contraction-expansion factors, universe of discourse can be modified online, and fuzzy rules can reproduce automatically to adapt to the modified universe of discourse. Thus, dependence on the size of initial rule base is greatly reduced. Using Stone-Weierstrass theorem, VUD adaptive fuzzy systems are proved to be universal approximators with two-order approximation accuracy. In addition, the convergence properties of approximation error are discussed, and a sufficient condition is presented to partition universe of discourse and to calculate the size of rule base. An example is also given to illustrate the approximation power of VUD adaptive fuzzy systems.