Robot semantic mapping through human activity recognition: A wearable sensing and computing approach

Semantic information can help robots understand unknown environments better. In order to obtain semantic information efficiently and link it to a metric map, we present a new robot semantic mapping approach through human activity recognition in a human–robot coexisting environment. An intelligent mobile robot platform called ASCCbot creates a metric map while wearable motion sensors attached to the human body are used to recognize human activities. Combining pre-learned models of activity–furniture correlation and location–furniture correlation, the robot determines the probability distribution of the furniture types through a Bayesian framework and labels them on the metric map. Computer simulations and real experiments demonstrate that the proposed approach is able to create a semantic map of an indoor environment effectively.     

Lead-free BiFeO3 film on glass fiber fabric: Wearable hybrid piezoelectric-triboelectric nanogenerator

Constructing hybrid nanogenerators (NGs) based on triboelectric effect and piezoelectric effect can combine the merits of the individual type of NG thus have drawn great attention in flexible wearable electronics. Herein, we prepared flexible BiFeO₃ (BFO) film in a simple and cost-effective way, which was used to fabricate a wearable hybrid piezoelectric-triboelectric nanogenerator (H–P/TENG) with silk fiber. By optimizing the experimental conditions, the highest open-circuit voltage of 110 V and short-circuit current density of 3.67 μA/cm² were achieved under 1 Hz contact-separation movement. The device also showed the best output power density of 151.42 μW/cm² with load resistance of 250 MΩ. Stimulating by moving body, the fabricated H–P/TENG successively realized the harvest and conversion of mechanical energy into electric energy, demonstrating great potential to monitor posture and establish a self-powered system. Moreover, the proposed H–P/TENG exhibited great stable output after 1800 contact-separation cycles, indicating the outstanding structure stability and fatigue resistance. This work will provide not only a facile and viable way to realize the application of ferroelectric materials in H–P/TENG but also new opportunities for developing monitor posture and self-powered systems.     

Microfluidic Fabrication of Capsule Sensor Platform with Double‐Shell Structure

Metal nanoparticles are frequently employed for the colorimetric detection of specific target molecules using an aggregation‐induced shift of the localized surface plasmon resonance. However, metal nanoparticles dispersed in bulk solutions are prone to be contaminated by adhesive molecules and the dispersions tend to be diluted by sample fluids, restricting direct application to unpurified pristine samples. Here, a versatile capsule sensor platform is proposed that can encompass a variety of different types of nanoparticle‐based sensors. The capsule sensors are microfluidically prepared to obtain close control over their dimensions and composition. Their aqueous cores that are loaded with sensing materials are surrounded by an ultrathin inner oil shell and an outer hydrogel shell. The hydrogel shell prevents the diffusion of large adhesive molecules into the core, thereby preventing contamination of the sensing materials. The oil shell is selectively permeable such that it further improves the sensor selectivity. Importantly, these shells confine the sensing materials and prevent them from being diluted, securing a consistent optical property. Moreover, the capsule‐based sensors display a higher sensitivity than bulk dispersions because a smaller amount of sensing materials is used. The power of nanoparticle‐loaded capsule sensors is demonstrated using lysine‐coated gold nanoparticles to detect mercury ions.     

一种改进可穿戴设备的血氧测量精度的传感器设计与验证

改进智能穿戴设备上传感器的数据采集方法,以及血氧测量和数据处理的方法,找到在动态测量过程中血氧数据更加精确的测量计算方法.修正现有算法分析模型,提取典型测量数据,设计新的变量标值,分析比较动态变化后的数据相关性,建立原始数据和输出动态血氧数据之间的关系变化模型,通过多人动态变化场景的数据采集实验验证了该方法的有效和精确.结果表明结合硬件设计、反射波长选择,通过血氧饱和度数值的动态变化反应血液中供氧情况,提出一个新的转换关系算法模型,得到精确度达到99％的血氧数据是非常实用和有效可行的方法.改进传统的投射式脉搏波血氧饱和度检测的算法模型到反射式脉搏波血氧饱和度的检测方式,提升其在智能穿戴设备上监测的血氧动态监测精度,该方法得到的数据对判定人体的健康状态和疾病类型非常有帮助.     

一种基于相关向量机的股四头肌收缩力量估计方法研究

针对可穿戴设备及共融机器人中的力/力矩测量需求,提出了一种基于相关向量机的人体股四头肌收缩力量估计方法,该方法具备采集设备安装方便、鲁棒性强且宜人性好等优点。通过采集人体股四头肌主要肌肉的MMG信号,提取平均绝对值MAV、平均功率频率MPF、样本熵SampEn及2个不同通道MMG信号之间的相关系数CC2Cs四个特征,利用基于稀疏贝叶斯理论的相关向量机算法RVM构建了MMG-肌肉收缩力量模型,并验证了所提方法的有效性和准确度。结果表明,同一参与者的模型估计结果的均方根误差RMSE为8.7%MVC（最大肌肉随意收缩力）,决定系数R2为0.817,该方法是一种有效、适宜应用在可穿戴设备的人体股四头肌收缩力量估计方法。     

Automated ergonomic risk monitoring using body-mounted sensors and machine learning

Workers in various industries are often subject to challenging physical motions that may lead to work-related musculoskeletal disorders (WMSDs). To prevent WMSDs, health and safety organizations have established rules and guidelines that regulate duration and frequency of labor-intensive activities. In this paper, a methodology is introduced to unobtrusively evaluate the ergonomic risk levels caused by overexertion. This is achieved by collecting time-stamped motion data from body-mounted smartphones (i.e., accelerometer, linear accelerometer, and gyroscope signals), automatically detecting workers’ activities through a classification framework, and estimating activity duration and frequency information. This study also investigates various data acquisition and processing settings (e.g., smartphone’s position, calibration, window size, and feature types) through a leave-one-subject-out cross-validation framework. Results indicate that signals collected from arm-mounted smartphone device, when calibrated, can yield accuracy up to 90.2% in the considered 3-class classification task. Further post-processing the output of activity classification yields very accurate estimation of the corresponding ergonomic risk levels. This work contributes to the body of knowledge by expanding the current state in workplace health assessment by designing and testing ubiquitous wearable technology to improve the timeliness and quality of ergonomic-related data collection and analysis.     

基于北斗可穿戴式老人心率检测仪

为了实时检测老人在户外的心率健康状况,设计了一种基于北斗的心率检测仪.当老人心率异常时,可以通过穿戴式检测设备及时通知老人的监护人和医护人员,并告知确切的位置,以获得最快的医治.系统由心率信号采集与处理、GSM模块通信、北斗定位、STM32F405组成,实现对心率信号实时采集与处理,远程监护老人心率健康与定位,对北斗民用化在便携式医疗中的应用有一定的参考意义.     

基于Web of Science的可穿戴设备研究文献计量分析

本文通过WOS数据库检索可穿戴设备领域的相关文献为研究对象,利用SATI3.2和VOSviewer计量分析工具对国际上该领域研究成果进行分析.研究结果显示:在国际上可穿戴设备领域的研究也较为热门,同时国内学者对该领域的贡献也较为突出,但暴露出了论文质量不高、引用率较低的缺点,需要国内学者继续努力.国际上关于该领域的研究热点主要集中在新材料、新技术和新元器件的开发及不同领域的应用.     

Review of Recent Advances in Non-invasive, Flexi-ble, Wearable Sweat Monitoring Sensors

Wearable health-monitoring devices are novel and integral developments based on smart-textiles. Conventional wearable technology consists of micro-controllers and a variety of electronic devices embedded on the skin, or in-corporated into the apparels, where they act as signal receptors, analytical devices and transmitters of the signals generated from the human body. Invasive methods are currently more commonly practiced where biofluids are obtained by penetrating the body by incision or injection, while in non-invasive methods no such penetrations take place. A critical review of current non-invasive wearable technology, including colorimetric, enzymatic, pH based, electrochemical and conductivity sensors, is presented in this paper along with the challenges and limitations they pose. Additionally, novel techniques of analysis have been explored concluding that a textile-based medium offers higher compatibility for in-tegration of such sensors in comparison to other existing substrates.     

封严涂层材料及应用

介绍了封严涂层的特点、测试方法、分类以及国内外可磨耗和耐磨封严涂层的应用情况,对部分封严涂层材料的发展过程及涂层的特殊制备工艺进行了阐述。评述了封严涂层的研究现状及在航空工业的发展前景。