Matsui T, Suzuki S, Ujikawa K, Usui T, Gotoh S, Sugamata M, Abe S
Department of Management Systems Engineering, Tokyo Metropolitan University, Hino, Tokyo, Japan.
J Med Eng Technol. 2009;33(6):481-7. doi: 10.1080/03091900902952675.
In order to conduct fast screening of passengers with infections such as severe acute respiratory syndrome (SARS) or pandemic influenza at a quarantine depot, we developed a non-contact screening system with self-produced program to conduct a human screening within five seconds, via a linear discriminant function from non-contact derived variables, i.e. palmer pulse derived from a laser Doppler blood-flow meter, respiration rate determined by a 10-GHz microwave radar, and facial temperature measured by thermography. The system evaluation was conducted on seven healthy male subjects (23 +/- 1 years). In order to achieve a pseudo-infection condition, the subjects maintained an ergometer exercise load (100 W, 10 minutes). Before (normal condition) and after (pseudo-infection condition) exercise, a significant linear discriminant function (p < 0.001) was determined to distinguish pseudo-infection condition from normal condition (Mahalanobis D-square = 20.3, classification error rate <5%). The proposed system appears promising for future application in fast screening of infection at a quarantine depot.
为了在检疫站对严重急性呼吸综合征（SARS）或大流行性流感等感染患者进行快速筛查，我们开发了一种带有自制程序的非接触式筛查系统，通过非接触衍生变量的线性判别函数，即激光多普勒血流仪测得的掌部脉搏、10 GHz微波雷达测定的呼吸频率以及热成像测量的面部温度，在五秒内对人员进行筛查。该系统评估在7名健康男性受试者（23±1岁）身上进行。为了达到模拟感染状态，受试者保持测力计运动负荷（100 W，10分钟）。在运动前（正常状态）和运动后（模拟感染状态），确定了一个显著的线性判别函数（p<0.001），以区分模拟感染状态和正常状态（马氏D平方=20.3，分类错误率<5%）。所提出的系统在未来检疫站感染快速筛查应用中似乎很有前景。
