Cognition and affect in measures of driving style

The study of the dispositions of drivers to drive in particular styles provides important clues to the likelihood of unsafe actions occurring in their driving. In this paper, data of occurrences and non-occurrences of certain actions during test drives, collected by S. W. Quenault, are analysed in a two-dimensional framework of cognitive and affective styles. Some other driver performance studies are then reviewed in this light, and some new data are reported arising from the use of Quenault's reported technique on male and female groups of drivers matched for age and experience.     

基于CAN数据的安全驾驶评价的建模与分析

研究中自主搭建车辆CAN数据采集平台,提出以行车安全性为主,辅以乘车舒适度和机动车油耗量共3个指标评价驾驶人的综合素质,其很大程度上反应了驾驶安全,涉及到方向盘转角熵值、方向盘转角速率、机动车速度熵值等7个因素。模型中先用层次分析法建立单因素权重向量,然后建立隶属度函数确定单因素模糊判断矩阵,最后结合最大隶属度原则对模型求解评定驾驶人的综合素质。实践表明,此模型为驾驶安全的评价提供了一个简单有效的数据分析方法。     

基于Lotos的面向宏的规范风格

Lotos范风格在系统规范描述中可以体现系统模型的结构性。在已存在的4种Lotos范风格中,引入了宏的思想,构思了一种新的Lotos描述风格,即面向宏的规范风格,并分析了基于此风格的规范进程设计方法,以及将此进程应用于系统实现的方法。该风格适合于描述分层的、内部模型具有相似结构的分布式系统。     

轮腿式爬楼轮椅后腿机构模糊PID控制系统

为实现爬楼轮椅后腿机构的动作要求,需要一套实时控制策略。采用TMS320F2812作为核心控制芯片,设计了一种复合式模糊比例—积分—微分(PID)后腿位姿调节控制系统。首先,根据爬楼轮椅的功能需求,给出了后腿机构的动作要求,并确定出合理的传感器安装位置;然后,搭建了控制系统的硬件结构,建立了模糊PID控制系统模型,制定出控制规则,并进行了软件开发。最后,构建了基于VC++6. 0的上位机监控界面,并对该控制系统进行了测试和结果分析。实验结果表明:该系统在一定程度上降低了调节过程中的超调现象和稳态误差,提高了系统响应速度。     

Investigations into the skills of modern and traditional train driving

Rail operations are housed inside a complex and extremely dynamic system where work is distributed in time and space. The train driver has traditionally relied on their own decisions, plans, and actions to navigate the rail environment, but the use of modern driver systems that force how these activities are regulated has altered this dynamic. This paper reports the findings of a study that set out to investigate the skills of modern (enhanced display-based) and traditional (real world) train driving. Data were collected from a variety of UK domain experts (n = 45) using an innovative methodology that converged multiple techniques for knowledge elicitation and analysis. The findings are represented in a model of dynamic train control and discussed according to the specific features and nature of tracking skill in the rail domain. The utility of the model is demonstrated through work of its application to the design of a train simulator and research tool for systematic study of rail human factor issues.     

基于GMR传感器校正的智能轮椅控制系统设计

为解决头部姿态智能轮椅控制精度问题,设计了一种基于巨磁阻(GMR)传感器校正与融合的头部姿态控制系统.系统以STM32F103为硬件平台,采用四元素法描述姿态信息,通过三轴陀螺仪输出角度解算姿态.由于陀螺仪漂移误差随时间积累,利用梯度下降法动态计算最优收敛步长,逐次迭代修正陀螺漂移误差.实验结果表明:传感器校准过程正确有效、校正后漂移误差减小,控制系统能精准控制智能轮椅运动.     

基于多传感器的爬楼轮椅底盘机构控制策略研究

为了使底盘机构能够准确地辅助轮椅实现爬楼动作,为其安装检测楼梯环境信息的传感器系统,包括检测踏面与踢面距离的超声波模块和红外线模块,以及检测底盘角度的传感器模块.给出了各传感器模块在底盘机构的位置布局,并通过各传感器模块检测获取底盘机构周围环境的楼梯信息;将采集的模拟数据信息,送入主控板数字信号处理器(DSP)进行融合处理,并采用多机串行通信模式将数据通过串行通信接口(SCI)模块传送至上位机,上位机经分析处理后向电机传送命令使其带动执行机构部件完成相应调节动作,实现对轮椅底盘机构的控制;将传感器的采集结果在VC++6.0界面上实时显示.     

一种无监督数据驱动的学习算法

用代表点替代类均值代表类、用加权距离替代欧氏距离作为样本与类之间的相似性度量,由此建立一种新的无监督数据聚类算法.提取指标对分类所作贡献大小的量化值,以此为启发性知识定义加权距离,建立了用质心修正当前代表点的迭代算法.与均值聚类等序贯算法不同,基于质心的迭代算法的批处理性可消除输入产生的随机性干扰.采用IRIS数据和Breast Cancer数据验证了该算法的有效性.     

Attention and driving skills in aging and Alzheimer's disease.

The number of older drivers with dementia is rising with the aging of the adult population. A public health issue is growing because of concerns about the motor vehicle accident risk posed by drivers with dementia of the Alzheimer's type (DAT) and other progressive, degenerative dementias. However, little is known about the specific perceptual/cognitive deficits contributing to impaired driving in DAT. The present paper proposes, on both theoretical and empirical grounds, that attentional skills in relation to driving should be examined in older adults with and without DAT. Such investigations should focus on normal older adults and those in the mild, early stages of dementia because the latter are the most likely among the dementia population to be still driving. Evidence is presented indicating (1) that motor vehicle accident rates are related to performance on information-processing measures of different components of attention; (2) that this relationship is greatest for measures of the switching of selective attention and less for that of divided and sustained attention (vigilance); and (3) that many of these same attentional functions, and particularly the switching of visual selective attention, are impaired in the early stages of DAT and thus may contribute to increased accident risk. Further studies of cognitive and driving performance in older drivers are necessary to establish that the attentional impairments found in mild DAT contribute to increased accident risk. Implications of these findings for driver assessment, education, and training are discussed.     

基于图像的流体型风格画仿真研究

为了模拟艺术家的流体型风格绘画,提出了一种新的流体型风格化图像绘制算法。提取图像中的流体信息,通过随机扰动生成纹理参考图,再运用小波技术的融合方法,使得输出图像具有流体效果,最后采用色彩转换的方法,将颜色参考图中的色彩特征转换到绘制图像上。实验结果表明,该算法自动化程度高,复杂度低,渲染效果更接近于流体型风格绘画。     

User-adapted plan recognition and user-adapted shared control: A Bayesian approach to semi-autonomous wheelchair driving

Many elderly and physically impaired people experience difficulties when maneuvering a powered wheelchair. In order to ease maneuvering, powered wheelchairs have been equipped with sensors, additional computing power and intelligence by various research groups. This paper presents a Bayesian approach to maneuvering assistance for wheelchair driving, which can be adapted to a specific user. The proposed framework is able to model and estimate even complex user intents, i.e. wheelchair maneuvers that the driver has in mind. Furthermore, it explicitly takes the uncertainty on the user’s intent into account. Besides during intent estimation, user-specific properties and uncertainty on the user’s intent are incorporated when taking assistive actions, such that assistance is tailored to the user’s driving skills. This decision making is modeled as a greedy Partially Observable Markov Decision Process (POMDP). Benefits of this approach are shown using experimental results in simulation and on our wheelchair platform Sharioto.

Style synthesis and analysis of car designs for style quantification based on product appearance similarities

Understanding how similar design appears is a key element to understanding companies’ design strategies. However, it is difficult to evaluate companies’ design strategies with conventional style measurement methods since they only taxonomically measure whether a specific characteristic is included in a specific style. This study numerically measured car design similarities to synthesize and analyze car brand styles, thereupon discovering the design trends among car brands for strategic design positioning. This paper aims to find methods for quantifying style differences and identifying unique design elements of car designs among 23 automobile manufacturers based on design similarities of a large quantity of car designs (N = 119). To achieve this goal, a hybrid style quantification methodology – a mixture of Fourier decomposition, eye tracker, and shape grammar – was created to evaluate similarities, visual significance, and combinations of 19 car design elements. Fourier decomposition was incorporated to find the quantifiable values of design similarities of car design elements. Visual significance analysis was also conducted for each car design element through eye tracker to measure the importance of certain design elements for weighting factors. Then, each combination of design elements was compared with car design elements of other cars for similarity calculations. Finally, car design alternatives were synthesized, and transitions of design positioning were analyzed based on the similarity values weighed by the visual significance results. Using the suggested methods, alternate designs can be synthesized while preserving brands’ design styles, and design trends can be analyzed for strategic evaluation.     

基于模糊神经网络算法的智能轮椅沿墙走行为研究

为了解决移动机器人在户外自主导航移动过程中的局部路径规划问题,提出了一种更为实用的模糊神经网络算法来进行局部路径规划。利用多个声纳和一个摄像头来采集外部环境信息,使智能轮椅在移动过程中可以得到较全面的外部环境信息,使用模糊神经网络算法来对得到的环境信息进行融合,应用的神经网络模型为Takagi-Sugeno(T-S)型,通过融合的结果来控制轮椅的沿墙走行为。通过计算机仿真和实验,验证了该方法的可行性和有效性,轮椅沿墙行走的路径得到了优化。     

基于级联宽度学习的疲劳驾驶检测

为减少因疲劳驾驶引发的交通事故,提出融合多参数的驾驶员疲劳检测算法。用渐进校准网络(PCN)检测人脸图像,通过基于CNN的回归模型定位人脸关键点;根据关键点坐标和面部器官的分布规律提取眼睛和嘴部图像,用宽度学习系统(BLS)分别识别眼睛与嘴巴的状态;将眼睛、嘴巴和头部状态的时序序列送入二级宽度网络对司机的状态进行判别。实验结果表明,该算法的疲劳检测准确率为94.9%,单帧检测时间52.43ms。     

基于Open Inventor的虚拟驾驶仿真系统

基于虚拟现实技术,以3ds MAX为建模软件,Open Inventor为开发平台,通过面向对象的编程方法设计了虚拟驾驶仿真系统,介绍了三维模型的导入、层次细节技术、碰撞检测、运动相机的控制与渲染等关键技术.通过实验表明,本系统真实地模拟了汽车在驾驶过程中起步、换挡、加减速、转向、制动等行驶工况,并实时地通过碰撞检测算法来判断虚拟车辆模型与虚拟场景之间的碰撞.     

基于挖掘技术的音乐风格识别系统

目前使用计算机来识别音乐的风格的实践活动是相对比较少的。利用音乐的旋律特征可以帮助计算机识别音乐的风格，数据挖掘技术是开展这项工作的一条途径。这方面的工作涉及了音乐旋律的表达、旋律特征的抽取以及分类技术等许多内容。介绍了一个音乐风格识别系统MSC，系统以MIDI乐曲为数据源提取出乐曲的旋律，对不同风格乐曲的旋律进行了频繁模式的挖掘和对测试乐曲的风格识别。     

Attachment style,social skills,and Facebook use amongst adults

Research suggests that online communication may benefit those high in social anxiety. The current study examined Facebook use from the perspective of adult attachment theory, exploring relationships between attachment anxiety and avoidance and Facebook use. Social skills have been found to be related to attachment style and internet use thus we also examined the role of these skills. A diverse sample of adult participants (N = 617; 50.1% female) completed a self report questionnaire measuring attachment dimensions, social skills, and Facebook use and experience. In line with predictions grounded in attachment theory, we found that individuals with high attachment anxiety used Facebook more frequently, were more likely to use it when feeling negative emotions and were more concerned about how others perceived them on Facebook. High attachment avoidance was related to less Facebook use, less openness and less positive attitudes towards Facebook. These relationships remained when social skills were controlled. These results suggest that Facebook may serve attachment functions and provide a basis for understanding how online communication may be related to attachment styles.     

基于REST风格的轻量级注册中心设计

为解决远程过程调用技术(RPC)中应用简单对象映射协议(SOAP)导致的传输带宽过大问题,设计一种轻量级注册中心系统.基于表述性状态传递(REST)风格接口实现跨语言访问功能,提出基于线程化的服务管理方式,设计并实现一种注册中心集群的搭建方式和基于RAFT理论的数据一致性解决办法.通过对系统功能和性能测试可知,与SOA...     

A robotic intelligent wheelchair system based on obstacle avoidance and navigation functions

Abstract. David Chalmers argues that a materialist theory of mind is in principle unattainable because consciousness does not logically supervene on the physical. In order to demonstrate this, he needs to make a convincing case for the conceptual possibility of zombies. His position, however, is rather tenuous due to the paradoxical nature of phenomenal judgments (among other things). That is, the fact that zombies would have to talk about consciousness and conscious experience may render them inconceivable. It is argued that this paradox is indeed fatal to his position, because zombies will never make meaningful phenomenal judgments.     

基于FPGA的电泳式电子纸驱动芯片设计

为了克服专用驱动芯片成本居高不下及软件驱动方式占用大量处理器资源的缺点,在分析主流的电泳式电子纸驱动设计方法的基础上,针对电泳式电子纸的显示特性及接口规范,提出了基于FPGA及IP软核整合的通用驱动解决方案,开发出可以适应多种主控接口及多种电泳式电子纸接口的驱动芯片,并利用VerilogHDL编程以硬逻辑部署方式实现了波形表的设计。仿真及实验结果验证了设计的正确性,驱动芯片性能优异,成本低,兼容性好。