融合引导滤波和小波变换的水下图像增强算法

针对水下环境对比度低和极其模糊的视觉效果问题,提出了一种融合引导滤波和小波变换的水下图像增强算法。利用引导滤波将图像分为基础部分和细节部分,将小波变换应用于基础部分,对产生的低频图像进行限制对比度直方图均衡,高频部分分别使用改进的对数函数增强,然后将处理后的高低频部分进行小波逆变换。细节部分进行增益计算;最后将处理后的基础部分和细节部分进行加权融合,再对融合图像进行限制对比度直方图均衡,得到目标图像。仿真实验表明,该方法在保留图像细节的同时很好地克服了光照不均匀对图像的影响.     

基于时序特征和集成算法的用户购买预测

大数据时代,电商平台积累了大量用户在平台上的行为数据,比如浏览、点击、下单和加入购物车等等.如何使用机器学习算法去探索大数据背后的用户消费喜好和习惯成为了一个新的研究热点.本文主要在特征工程和模型搭建两个方面对用户购买预测的效果做出提高.通过深入理解电商业务知识,利用统计学知识,分别从用户、商品和评论数据等多个方面的数据构建了115个特征;在模型搭建方面,主要设计了一个两层融合模型,第一层采用了XGBoost、CatBoost和逻辑回归作为基分类器,从不同的角度考虑用户购买预测,第二层采用加权平均的方法对基类模型的预测结果进行融合,其权重由线性分类器学习生成.实验结果表明该融合模型的F1评分要高于个体分类器,并且多次实验证明,融合模型的稳定性也要比个体分类器好.     

基于多尺度特征融合的行人重识别方法

针对行人重识别任务在特征提取时缺乏对行人特征尺度变化的考虑,导致其易受环境影响而具有低行人重识别准确率的问题,提出了一种基于多尺度特征融合的行人重识别方法。首先,在网络浅层通过混合池化操作来提取多尺度的行人特征,从而帮助网络提升特征提取能力;然后,在残差块内添加条形池化操作以分别提取水平和竖直方向的远程上下文信息,从而避免无关区域的干扰;最后,在残差网络之后利用不同尺度的空洞卷积进一步保留多尺度的特征,从而帮助模型灵活有效地解析场景结构。实验结果表明,在Market-1501数据集上,所提方法的Rank1达到95.9%,平均精度均值（mAP）为88.5%;在DukeMTMC-reID数据集上,该方法的Rank1达到90.1%,mAP为80.3%。可见所提方法能够较好地保留行人特征信息,从而提高行人重识别任务准确率。     

Probabilistic observation model correction using non-Gaussian belief fusion

This paper presents a framework for state estimation which tolerates uncertainty in observation model parameters by (1) incorporating this uncertainty in state observation, and (2) correcting model parameters to improve future state observations. The first objective is met by an uncertainty propagation approach, while the second is achieved by gradient-descent optimization. The novel framework allows state estimates to be represented by non-Gaussian probability distribution functions. By correcting observation model parameters, estimation performance is enhanced since the accuracy of observations is increased. Monte Carlo simulation experiments validate the efficacy of the proposed approach in comparison with conventional estimation techniques, showing that as model parameters converge to ground-truth over time, state estimation correspondingly improves when compared to a static model estimate. Because observation models cannot be known with perfect accuracy and existing approaches do not address parametric uncertainties in non-Gaussian estimation, this work has both novelty and usefulness in most state estimation contexts.     

Differentially private data fusion and deep learning Framework for Cyber–Physical–Social Systems: State-of-the-art and perspectives

The modern technological advancement influences the growth of the cyber–physical system and cyber–social system to a more advanced computing system cyber–physical–social system (CPSS). Therefore, CPSS leads the data science revolution by promoting tri-space information resource from a single space. The establishment of CPSSs increases the related privacy concerns. To provide privacy on CPSSs data, various privacy-preserving schemes have been introduced in the recent past. However, technological advancement in CPSSs requires the modifications of previous techniques to suit its dynamics. Meanwhile, differential privacy has emerged as an effective method to safeguard CPSSs data privacy. To completely comprehend the state-of-the-art developments and learn the field’s research directions, this article provides a comprehensive review of differentially private data fusion and deep learning in CPSSs. Additionally, we present a novel differentially private data fusion and deep learning Framework for Cyber–Physical–Social Systems , and various future research directions for CPSSs.     

基于改进特征融合的微表情识别方法

微表情的变化是非常微小的,这使得微表情的研究非常困难。微表情是不能伪造和压制的,因此也成为判断人们主观情感的重要依据。本文提出了以卷积神经网络及改进长短时记忆网络特征融合为依托的微表情识别方法,先介绍了相关的背景知识,再介绍了实验的预处理过程、特征提取以及相应的特征融合的过程,将所得的结果用于实验模型的预测分类。实验结果表明,新模型具有更好的识别率。     

Multi-Dimensional Pedestrian System on the New Campus of University of Macau

The Multi-dimensional Pedestrian System( MPS) is an integral part of the new campus of University of Macau. It observes the principle of "pedestrian first " and features a pedestrian-vehicle dividing system.Based on a comprehensive analysis of the location,climate,ecology and other factors of the project site,the conception of the idea of MPS and the related researches are illustrated. The transportation features of the MPS,as summarized,include multi-dimensions,short-distance and weather-resistance. Its features for the sake of livability include integration of nature, respect for the environment and sharing of landscape. Upon the completion of the project, the effects on its users were tested. Finally, some constructive rules for the construction of similar campus pedestrian systems were proposed.     

立体图像对亮度差异对立体视融合的影响研究

针对具有亮度差异的立体图像对如何影响立体融合,提出了对不同亮度差异的立体图像对识别融合的影响范围。通过8名被试对亮度差异分别为0,10,20,30,40,50,60,70,80,90的立体图像对融合识别的反应时和正确率进行分析,给出了亮度差异对立体视融合的定量影响范围。结果表明:反应时随着亮度差异的增大逐渐增加,但识别正确率逐渐降低。亮度差异为20以下,立体识别可达到较好的识别效果,反应时较短并且正确率很高。当亮度差异介于20~60之间,反应时急剧增加,正确率稍有降低。但当亮度差异达到60以上,不仅反应时急剧增加,而且正确率急剧降低,达到很难识别的程度。     

基于智能家居的一致性模型融合技术研究

在智能家居的自适应软件设计中,往往采用传统的模块构建技术。但由于其适应逻辑存在着低复用性、高复杂度等问题,很难验证模块组合后的正确性及有效性。为了满足开发过程中用户的增量性需求,针对适应逻辑的组合难题,提出把部分行为模型的形式化方法引入到适应行为的描述中。通过三值逻辑KMTS模型描述语言,提出一致性模型的判断方法以及融合算法,以提供明确的适应模型在线融合支持。最后通过智能家居中的一个模型实例来分析并验证融合后的适应逻辑。     

基于扫描枪的字符二维条码识读算法研究

不同于传统的图像二维条码,字符二维条码由字符组成条码矩阵.字符二维条码可通过扫描枪获取后,因其结构不同于传统图像二维条码,需对字符二维条码进行定位、分割以及字符识别.在扫描枪有限的内存空间和运行速度限制下,开发了字符二维条码的识读算法.提出了基于圆定位符的字符二维条码定位算法,对条码字符进行投影分割后,采用基于特征融合的识别方法实现了字符识别.实验表明:种字符二维条码识读算法能够很好地运行在扫描枪上,快速、准确地实现字符二维条码的识读.