多维关联在汽车销售中的应用

为挖掘隐藏在大量汽车销售数据背后的知识,给出了一种基于数据立方体的多维关联挖掘算法.在Visual C 7.0中实现了该算法并将其集成到SQL Server的分析服务中,用该算法对汽车销售数据立方体进行了关联分析,结果显示其正确和可行的.     

SQI优化思路

在GSM无线网络中,对无线质量的评估是通过RXQUAL来实现的。但是无线网络的语音是经过话音编码及信道编码两个过程的,RXQUAL只能反映出网络在空中接口上的传输质量,并不能反映终端用户对无线网络语音保真度的最终感受。为此爱立信提出了一个能够表达终端用户对无线网络质量直接感受的指标—SQI。     

采用半速率技术解决话务突发

针对当前一些地区无线网络资源紧张,话务量波动较大的情况.本报告通过理论分析与实际测试,分析了半速率技术对增加系统容量,缓解拥塞的效果.同时结合实际测试结果,分析半速率技术对话音质量、无线网络各性能参数的影响,最后给出重要参数的设置原则与使用该技术的建议.     

基于眼部自商图—梯度图共生矩阵的疲劳驾驶检测

目的 疲劳驾驶是引发车辆交通事故的主要原因之一,针对现有方法在驾驶员面部遮挡情况下对眼睛状态识别效果不佳的问题,提出了一种基于自商图—梯度图共生矩阵的驾驶员眼部疲劳检测方法。方法 利用以残差网络（residual network,ResNet）为前置网络的SSD（single shot multibox detector）人脸检测器来获取视频中的有效人脸区域,并通过人脸关键点检测算法分割出眼睛局部区域图像;建立驾驶员眼部的自商图与梯度图共生矩阵模型,分析共生矩阵的数字统计特征,选取效果较好的特征用以判定人眼的开闭状态;结合眼睛闭合时间百分比（percentage of eyelid closure,PERCLOS）与最长闭眼持续时间（maximum closing duration,MCD）两个疲劳指标来判别驾驶员的疲劳状态。结果 在六自由度汽车性能虚拟仿真实验平台上模拟汽车驾驶,采集并分析驾驶员面部视频,本文方法能够有效识别驾驶员面部遮挡时眼睛的开闭状态,准确率高达99.12%,面部未遮挡时的识别精度为98.73%,算法处理视频的速度约为32帧/s。对比方法1采用方向梯度直方图特征与支持向量机分类器相结合的人脸检测算法,并以眼睛纵横比判定开闭眼状态,在面部遮挡时识别较弱;以卷积神经网络（convolutional neural network,CNN）判别眼睛状态的对比方法2虽然在面部遮挡情况下的准确率高达98.02%,但眨眼检测准确率效果不佳。结论 基于自商图—梯度图共生矩阵的疲劳检测方法能够有效识别面部遮挡时眼睛的开闭情况和驾驶员的疲劳状态,具有较快的检测速度与较高的准确率。     

An integrated analysis of urbanization-triggered cropland loss trajectory and implications for sustainable land management

This paper demonstrates an integrated method for studying cropland loss dynamics and the resultant impacts on sustainable development spanning the past 10 years (1996-2006) in response to rampant urban growth. This study deploys remote sensing to obtain accurate measures of cropland change information and applies GIS to examine the spatio-temporal trajectory of cropland loss. Coupled with landscape metrics and soil quality assessment approach, this paper also explores the impacts on fragmentation of cropland landscape and soil resource in detail. The case study concludes that cropland has undergone considerable loss from 1996 to 2006 and exhibited distinct variation of change dynamics between 1996-2000, 2000-2003 and 2003-2006. In the meantime, cropland loss was spatially concentrated in Jianggan, Xihu and Binjiang districts. However, these changes have caused an increasingly fragmented composition and dispersed distribution of cropland landscape over the time. Moreover, the study further documented a severe competition between urban development and good quality soil concomitant with the rapid urbanization process. In addition, some distinct soil types, with their unique physical structure and history of formation, may be in the verge of disappearance. The permanent loss of valuable cropland and increasing fragmented landscape patterns along with continued urban sprawl may also impose potential threat on the sustainable development and food security of the region.     

基于双串行RAM的超长LED显示屏实时控制系统

利用ARM处理器SPI和DMA的工作特点,设计辅助电路对两组RAM进行逻辑控制,使得修改超长LED显示屏数据时不影响显示效果。控制系统设计2组串行RAM,通过控制2组串行RAM的逻辑和时序,可以实现同步刷新、异步修改和DMA方式高速输出等多种功能。在显示输出时采用SPI接口的DMA输出方式,实现了超长LED显示屏的控制。同时,阐述了该控制系统的设计理念、电路原理图及编程方法,并给出实测实验结果。实验结果表明,此设计具有很高的实用价值。     

Fast self-quotient image method for lighting normalization based on modified Gaussian filter kernel

ABSTRACT

The Self-Quotient Image (SQI) Method [Wang H, Li SZ, Wang Y, et al. Self quotient image for face recognition. International Conference on Image Processing (ICIP’04); 2004;Vol. 2. p. 1397–1400; Wang H, Li SZ, Wang Y. Generalized quotient image. IEEE CVPR; 2004; Vol. 2. p. 498–505] is a simple method for lighting normalization based on the Quotient Image method [Shashua A, Riklin-Raviv T. The quotient image: class-based re-rendering and recognition with varying illuminations. T Pattern Anal Mach Intel. 2001;23(2):129–139; Riklin-Raviv T, Shashua A. The quotient image: class based recognition and synthesis under varying illumination. Proceedings of the 1999 Conference on Computer Vision and Pattern Recognition; 1999; Fort Collins (CO). p. 566–571]. The main advantage of the SQI is the use of only one image for lighting normalization. Nevertheless, the SQI still has few disadvantages which make hard to use it in some face recognition systems. In this paper, we introduce the modified version of the SQI method based on globally modified Gaussian filter kernel. In this modification, we tried to solve the disadvantages of the original SQI method, simplify the computational process, and increase the quality of illumination normalization. We have investigated two modification of the original SQI method and shown how they normalize different shadow regions.     

爱立信3算法应用探讨

话音质量是日常的网络优化中备受关注的重要指标,保障良好的话音质量是提升网络指标和客户满意度的双重需求,本文介绍了一种利用合理设置爱立信3算法的切换参数,从减少切换角度来改善SQI从而提升话音质量的方法应用。     

改进的自商图算法

针对人脸识别中的光照变化问题,提出一种改进的自商图算法。对光照图像进行伽玛变换,使用非下采样轮廓波变换对图像进行多尺度多方向分析,对各方向子带进行Wiener滤波,利用自商图模型提取人脸图像的光照不变特性。Yale B与CMU PIE人脸库上的实验结果表明,与传统算法相比,该算法的平均识别率更高。     

SQI优化思路

在GSM无线网络中,对无线质量的评估是通过RXQUAL来实现的。但是无线网络的语音是经过话音编码及信道编码两个过程的,RXQUAL只能反映出网络在空中接口上的传输质量,并不能反映终端用户对无线网络语音保真度的最终感受。为此爱立信提出了一个能够表达终端用户对无线网络质量直接感受的指标—SQI。