基于阈值和极端随机树的实时跌倒检测方法

针对基于可穿戴设备的跌倒检测存在的实时性与准确性无法兼得的问题,提出一种阈值和极端随机树融合的实时跌倒检测方法。在该方法中,可穿戴设备只需计算阈值量,无需确保跌倒检测的准确率,从而减少了计算量;同时,上位机利用极端随机树算法确保了跌倒检测的准确率。可穿戴设备通过阈值的方法过滤了大部分日常动作,因此减少了上位机检测的动作数据量。这样一来所提方法既满足了跌倒检测的高准确率,又满足了实时性。另外,为了降低跌倒检测的假阳性率,可穿戴设备融合了姿态角度传感器和压力传感器,上位机中加入了反馈机制。当检测结果出现假阳性时,通过上位机将检测错误的样本加入非跌倒数据集中进行再训练,模型经过这样的不断学习会生成适合个人的报警模型,且这种反馈机制为降低跌倒检测的假阳性率提供了新思路。实验结果表明,在1 259个测试样本中,所提方法具有平均99.7%的准确率,最低0.08%的假阳性率。     

Hand shape classification in various pronation angles using a wearable wrist contour sensor

Hand gestures are potentially useful for communications between humans and between a human and a machine. However, existing methods entail several problems for practical use. We have proposed an approach to hand shape recognition based on wrist contour measurement. Especially in this paper, two assignments are addressed. First is the development of a new sensing device in which all elements are installed in a wrist-watch-type device. Second is the development of a new hand shape classifier that can accommodate pronation angle changes. The developed sensing device enables wrist contour data collection under conditions in which the pronation angle varies. The classifier recognizes the hand shape based on statistics produced through data forming and statistics conversion processes. The most important result is that no large difference exists between classification rates that include or those that exclude the independent (preliminary) pronation estimation process using inertia measurement units. This result shows two possible insights: (1) the wrist contour has some features that depend on the hand shape but which do not depend on the pronation angle, or (2) the wrist contour potentially includes pronation angle variation information. These insights indicate the possibility that hand shape can be recognized solely from the wrist contour, even while changing the pronation angle.     

一种战场士兵多生命体征监测头带设计

针对战场环境,从便携式角度出发,采用可穿戴技术,设计了一种集成心电、脑电、脉搏波、体温以及人体姿态测量的战场士兵多生命体征监测头带。其中,以超低功耗的MSP430单片机为主控芯片,以低功耗的ADS1292R作为双电极心电和脑电采集芯片,以反射式光频转换器采集人体光电容积脉搏波,以医疗专用负温度系数（ NTC）热敏电阻器作为体温传感器,以MMA7660数字三轴加速度计作为姿态测量传感器。通过蓝牙将所采集信息传送至单兵PDA,实现了多生命体征的监测,具备体积小、重量轻、功耗低、成本低、便携舒适等特点。     

Skin-like Omnidirectional Stretchable Platform with Negative Poisson's Ratio for Wearable Strain–Pressure Simultaneous Sensor

Conventional elastomeric polymers used as substrates for wearable platforms have large positive Poisson's ratios (≈0.5) that cause a deformation mismatch with human skin that is multidirectionally elongated under bending of joints. This causes practical problems in elastomer-based wearable devices, such as delamination and detachment, leading to poorly reliable functionality. To overcome this issue, auxetic-structured mechanical reinforcement with glass fibers is applied to the elastomeric film, resulting in a negative Poisson's ratio (NPR), which is a skin-like stretchable substrate (SLSS). Several parameters for determining the materials and geometrical dimensions of the auxetic-structured reinforcing fillers are considered to maximize the NPR. Based on numerical simulation and digital image correlation analysis, the deformation tendencies and strain distribution of the SLSS are investigated and compared with those of the pristine elastomeric substrate. Owing to the strain-localization characteristics, an independent strain-pressure sensing system is fabricated using SLSS with a Ag-based elastomeric ink and a carbon nanotube-based force-sensitive resistor. Finally, it is demonstrated that the SLSS-based sensor platform can be applied as a wearable device to monitor the physical burden on the wrist in real time.     

Wearable Organic Electrochemical Transistor Array for Skin-Surface Electrocardiogram Mapping Above a Human Heart

Electrocardiogram (ECG) mapping can provide vital information in sports training and cardiac disease diagnosis. However, most electronic devices for monitoring ECG signals need to use multiple long wires, which limit their wearability and conformability in practical applications, while wearable ECG mapping based on integrated sensor arrays has been rarely reported. Herein, ultra-flexible organic electrochemical transistor (OECT) arrays used for wearable ECG mapping on the skin surface above a human heart are presented. QRS complexes of ECG signals at different recording distances and directions relative to the heart are obtained. Furthermore, the ECG signals are successfully analyzed by the devices before and after exercise, indicating potential applications in some sports training and fitness scenarios. The OECT arrays that can conveniently monitor spacial ECG signals in the heart region may find niche applications in wearable electronics and healthcare products in the future.     

A Sensing and Stretchable Polymer-Dispersed Liquid Crystal Device Based on Spiderweb-Inspired Silver Nanowires-Micromesh Transparent Electrode

Polymer-dispersed liquid crystal (PDLC) devices are truly promising optical modulators for information display, smart window as well as intelligent photoelectronic applications due to their fast switching, large optical modulation as well as cost-effectiveness. However, realizing highly soft PDLC devices with sensing function remains a grand challenge because of the intrinsic brittleness of traditional transparent conductive electrodes. Here, inspired by spiderweb configuration, a novel type of silver nanowires (AgNWs) micromesh-based stretchable transparent conductive electrodes (STCEs) is developed to support the realization of soft PDLC device. Benefiting from the embedding design of AgNWs micromesh in polydimethylsiloxane (PDMS), the STCEs can maintain excellent electrical conductivity and transparency even in various extreme conditions such as bending, folding, twisting, stretching as well as multiple chemical corrosion. Further, STCEs with the embedded AgNWs micromesh endow the assembled PDLC device with excellent photoelectrical properties including rapid switching speed (<1 s), large optical modulation (69% at 600 nm), as well as robust mechanical stability (bending over 1000 cycles and stretching to 40%). Moreover, the device displays the pressure sensing function with high sensitivity in response to pressure stimulus. It is conceivable that AgNWs micromesh transparent electrodes will shape the next generation of related soft smart electronics.     

Flexible Nanowire Cluster as a Wearable Colorimetric Humidity Sensor

Wearable plasmonic devices combine the advantages of high flexibility, ultrathinness, light weight, and excellent integration with the optical benefits mediated by plasmon‐enhanced electric fields. However, two obstacles severely hinder further developments and applications of a wearable plasmonic device. One is the lack of efficient approach to obtaining devices with robust antimotion‐interference property, i.e., the devices can work independently on the morphology changes of their working structures caused by arbitrary wearing conditions. The other issue is to seek a facile and high‐throughput fabrication method to satisfy the financial requirement of industrialization. In order to overcome these two challenges, a functional flexible film of nanowire cluster is developed, which can be easily fabricated by taking the advantages of both conventional electrochemical and sputtering methods. Such flexible plasmonic films can be made into wearable devices that work independently on shape changes induced by various wearing conditions (such as bending, twisting and stretching). Furthermore, due to plasmonic advantages of color controlling and high sensitivity to environment changes, the flexible film of nanowire cluster can be used to fabricate wearable items (such as bracelet, clothes, bag, or even commercial markers), with the ability of wireless visualization for humidity sensing.