基于多颜色分量CLBP提取的浮选泡沫状态识别

针对不同状态的浮选泡沫图像之间纹理结构相似、颜色差异不明显的问题，提出一种基于色调、饱和度和亮度（HSV）颜色空间的完全局部二进制模式（CLBP）纹理提取的浮选泡沫状态识别方法。首先使用双域去噪在保留纹理细节的同时滤除图像噪声，然后转换为HSV图像，在H、S和V颜色分量上分别提取三个尺度的CLBP纹理特征。将提取的纹理特征归一化后线性排列，建立高维度的纹理分类模型。最后通过一对一模式的支持向量机分类器对四类泡沫状态的样本集进行纹理提取后的分类训练与测试。结果表明，该方法对不同浮选泡沫状态的分类正确率较高，优于其他纹理描述方法，适用于浮选泡沫状态的识别。     

智能选厂小型数据中心设计研究与应用

目前,我国各选矿厂均面临关键数据存储和利用问题,采取以往简单的磁盘和服务存储的方法,不仅不能有效保障数据的存储安全,而且无法实现数据的集中管理和应用,这对企业数据业务发展是极大的障碍。设计一套统一化数据中心框架并搭建,实现服务器、防火墙、交换机、共享存储科学搭配,多台服务器虚拟化部署与管理,基于Hadoop集群的高可用数据仓储搭建,对数据进行统一存储、管理与应用。使企业为用户提供优质高效服务、降低企业成本、提高企业经济效益、拓宽企业信息系统的范围,为企业带来更大的竞争力。通过在某金矿选矿厂的智能选厂项目的具体应用,证明系统的可行性与高效性。     

功能追随空间：多尺度层级网络塑造的城市中心

城市商业功能的分布与道路空间结构息息相关。本文以北京内城为例,应用空间句法模型在城市和街区两个尺度上分析了商业功能的聚集和演变规律。其中在城市尺度基于80年跨度中四个时间节点的商业分布数据分析了10个商业中心,在街区尺度上基于2005和2015年的实地调研的商铺数量,分析了前门、东四和西四三个中心区内的各街道段上的商业分布受城市和局域层级网络影响的程度。结论验证了空间句法参数能够有效地在街道精度上分析商铺数量,但各案例街区受两种网络影响程度差异较大。     

One size does not fit all: Rethinking recognition system design for behaviorally heterogeneous online communities

Online knowledge-sharing communities typically acknowledge their top contributors by implementing recognition systems. Extant recognition systems suffer from several limitations such as treatment of the entire community as homogeneous and inflexibility of customization. We propose a framework based on socio-technical design principles for designing a multi-criterion- and multi-segment-based recognition system that exploits multiple user characteristics for differential recognition according to community goals. We apply this framework on data gathered from Yelp.com and show how it can be used to recognize top members of different identified behavioral segments (amateurs, adepts, and enthusiasts) based on their performance on various relevant factors.     

基于动态行为学习的空中目标识别方法

针对空中移动目标识别问题,提出了一种基于动态行为学习的识别方法。首先,从数据源中提取目标要素,经过标注形成目标数据特征集;其次,基于应用场景进行特征组合,形成特征模型要素;然后,基于深度学习算法进行模型训练,得到评估最优的模型参数;最后,利用训练后的模型进行目标识别处理。通过数值仿真验证,该方法能够有效地识别无业务规则的目标身份。     

移动物料信息分布式传输方法及应用

在流程工业生产中,移动物料计量信息的传输普遍采用电台和无线模块。接收电台周围环境严重影响计量信息的传输效果,尤其是钢结构厂房、电磁干扰区内,数据传输过程中的丢包率、误码率相当严重。本文提出一种多节点分布式传输方法,根据各个生产作业区环境条件设置相应的WIFI节点数,实现对作业区的无线信号覆盖。网络覆盖区内无线模块、PDA终端(PDA)、终端查询设备通过节点工作频段和阵列天线自适应调节,实现数据传输最佳化。铜熔炼生产现场测试表明,此种传输方法可以有效消除周围环境的电磁干扰,数据丢包率低于0.1%。     

基于密度聚类与SVM的非法广播信号识别研究

针对非法广播信号的危害,以及传统人工检测效率低的问题,提出一种基于密度聚类与SVM的信号识别模型。首先,采用标准欧式距离对特征信号进行提取;其次,以聚类样本为基础,采用SVM分类器对信号分类;最后,以青海广播电视局中波台整点时刻前后300帧的数据为样本,以静音信号作为评价指标,对信号进行识别。结果表明,在正常信号中加入非法信号后,频谱中有少量的静音信号,且SVM训练时间和识别正确率都要优于传统算法。     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

A star pattern recognition algorithm for cameras with large FOV

In most large field of view (FOV) observations, the distortion problem is inevitably and significantly more serious than in small FOV ones. In the circumstances, many traditional star identification approaches are not able to efficiently identify stars any more. In order to deal with this problem, we put forward a star identification method that is less sensitive to distortion. The method first processes stars in the central area of the image, using traditional identification logic, and then applies the region growing strategy to enlarge the identified regions iteratively until the entire image is covered. The performance of the new scheme is analysed in the presence of both simulated data and real data. The results show that the proposed algorithm has the advantage of speed, and the strategy of regional extension can efficiently identify stars in large FOV images compared with other existing algorithms.