Face tracking with automatic model construction

This paper describes an active model with a robust texture model built on-line. The model uses one camera and it is able to operate without active illumination. The texture model is defined by a series of clusters, which are built in a video sequence using previously encountered samples. This model is used to search for the corresponding element in the following frames. An on-line clustering method, named leaderP is described and evaluated on an application of face tracking. A 20-point shape model is used. This model is built offline, and a robust fitting function is used to restrict the position of the points. Our proposal is to serve as one of the stages in a driver monitoring system. To test it, a new set of sequences of drivers recorded outdoors and in a realistic simulator has been compiled. Experimental results for typical outdoor driving scenarios, with frequent head movement, turns and occlusions are presented. Our approach is tested and compared with the Simultaneous Modeling and Tracking (SMAT) [1], and the recently presented Stacked Trimmed Active Shape Model (STASM) [2], and shows better results than SMAT and similar fitting error levels to STASM, with much faster execution times and improved robustness.     

InTouch在热风炉控制系统中的应用

介绍了InTouch在吉林建龙钢铁公司热风炉工程中的应用,论述了热风炉系统结构和信息通讯方式.应用表明设计合理,达到了实时监控的目的.     

基于ZigBee技术的远端通信站监控系统及其实现

提出了一种基于ZigBee技术的远端通信站环境监控系统设计方案。包括系统结构、Zigbee通信接口、单片微处理器、温度采集等模块的软硬件设计。此方案设计的监测系统已在某远端无人小型频谱监测站使用。     

利用RDS实现浏览器环境下的批量数据修改

ＲＤＳ的工作原理及利用ＲＤＳ实现基于浏览器的批量数据修改的具体实现方法。     

Identification of statistical patterns in complex systems via symbolic time series analysis

Identification of statistical patterns from observed time series of spatially distributed sensor data is critical for performance monitoring and decision making in human-engineered complex systems, such as electric power generation, petrochemical, and networked transportation. This paper presents an information-theoretic approach to identification of statistical patterns in such systems, where the main objective is to enhance structural integrity and operation reliability. The core concept of pattern identification is built upon the principles of Symbolic Dynamics, Automata Theory, and Information Theory. To this end, a symbolic time series analysis method has been formulated and experimentally validated on a special-purpose test apparatus that is designed for data acquisition and real-time analysis of fatigue damage in polycrystalline alloys.     

Emotion understanding and performance during computer-supported collaboration

Individuals collaborating around and through computers benefit from receiving information that helps them understand one another, which is often termed awareness. This article explores what collaborators understand about each other’s emotions and the potential benefits for performance that might come from raising this understanding. In Experiment 1 co-located collaborators judged each other’s emotions after playing a game that required cooperative data collection and analysis. Their judgements were largely inaccurate and based on their own emotions, suggesting limited emotion understanding. Experiment 2 explored if this could be overcome by making collaborators aware of each other’s emotions. Co-located and remote collaborators played a cooperative puzzle-solving game under conditions of awareness or no awareness. Awareness was manipulated by making collaborators share their self-reported emotions during key moments of their game play. Both remote and co-located collaborators improved their performance after sharing their emotions. However, unlike co-located collaborators, remote collaborators also improved their understanding of each other’s emotions and experienced more positive affect. We conclude by discussing the content of collaborators’ emotion understanding and the probable mechanisms underlying the observed effects of being made aware of a partner’s emotions.     

Estimation of energy expenditure in a work environment: Comparison of accelerometry and oxygen consumption/heart rate regression

The aim of this study was to compare estimation of energy expenditure (EE) in working environments, either from accelerometry or from an individual oxygen consumption/heart rate ([Vdot]O₂/HR) regression curve. The study participants were 46 volunteer workers aged 27±6 years old. A significant correlation between EE predicted by the [Vdot]O₂/HR curve and the accelerometer was observed (r=0.78, p <0.01). However, more disparities were observed between the two methods when the mean job intensity was not within 16% and 23% higher than resting HR. The accelerometer overestimated by a mean of 34.4% the prediction by [Vdot]O₂/HR regression if the intensity of the task was lower than a total of 1000 kcal/shift and underestimated the prediction by a mean of –24.9% if EE estimation of the work shift was higher than a total of 1500 kcal/shift. Despite a high correlation between both methods in the whole group, EE evaluated by accelerometry does not correspond to EE predicted by the [Vdot]O₂/HR regression curves when evaluated individually.     

一种有创血压模拟器的设计

针对有创血压测量设备研发阶段、校准测试或在教学实验中难以采用人体或动物来做试验的缺点,提出一种新型有创血压模拟器设计方法。该模拟器通过微控制器产生正弦波和各种人体血压波形,输送到扬声器产生振动,利用传动模块和压力传感器将压力变化值传送到上位机作显示分析。实验表明该模拟器具有精度高、波形显示速度快的特点。     

GM（1,1）在航道驳岸沉降监测中的应用

在施工建设中,实时准确地观测、分析和预报建筑物的沉降变形对最后施工的成功与否有着很大的影响。在变形监测中经常遇到数据信息不完备的情况,而灰色系统理论则是用来解决此问题的有效方法。建立了灰色预测模型,并将其应用于苏南运河整治工程中新建驳岸的沉降监测分析和预测中,预测效果较好。     

ZigBee在动态血压监测中的应用研究

我国已成为世界上高血压危害最严重的国家之一,在全国范围大力开展高血压病的防治,积极治疗高血压病患者,已经刻不容缓.通过研究ZigBee技术,提出了以ZigBee无线传感器网络为核心,以以太网为骨干网,采用CC2430芯片为血压传感器控制核心的动态血压测量方案,系统测量的收缩压、舒张压误差范围均小于5mmHg.试验证明,系统能够实时监测患者的血压变化,工作稳定可靠,具有较高的实用性和市场价值.