Keyframe-based recognition and localization during video-rate parallel tracking and mapping

Generating situational awareness by augmenting live imagery with collocated scene information has applications from game-playing to military command and control. We propose a method of object recognition, reconstruction, and localization using triangulation of SIFT features from keyframe camera poses in a 3D map. The map and keyframe poses themselves are recovered at video-rate by bundle adjustment of FAST image features in the parallel tracking and mapping algorithm. Detected objects are automatically labeled on the user's display using predefined annotations. Experimental results are given for laboratory scenes, and in more realistic applications.     

Hybrid electronic tongue for the characterization and quantification of grape variety in red wines

A multisensor system combined with multivariate analysis was applied to the characterization of red wines and to the quantification of the grape variety percentage. The proposed system, known as hybrid electronic tongue, consists of a colorimetric optofluidic system and an array of electrochemical sensors. Three monovarietal red wines were studied: Pinot Noir, Merlot and Cabernet Sauvignon. Homemade mixtures were elaborated from these wines according to a Simplex experimental design with 60 samples. The data obtained were treated using advanced chemometric tools like Principal Component Analysis (PCA) and Soft Independent Modeling Class Analogy (SIMCA) for the classification of the wine mixtures and Partial Least Squares (PLS) regression for the quantification of the grape variety composition. The results have shown a good classification of the grape varieties and the identification of the mixtures with Pinot Noir up to 75%. Besides, using the PLS regression, the system has demonstrated a high potential for quantifying the percentage of each grape variety.     

Magic Touch: A Simple Object Location Tracking System Enabling the Development of Physical-Virtual Artefacts in Office Environments

A novel method for tracking physical activities is presented. The method is based on the assumption that all changes to the physical environment are done by users themselves, and that these actions can be tracked using wearable computer technology placed on human hands. Various limitations of the proposed method are discussed. Acknowledging these limitations, a range of possible applications are presented, e.g. a set of Physical-Virtual Artefacts intended to decrease the gap between the physical and virtual environments within offices. Also, some aspects of the modelling of user actions in office environments are discussed.     

基于函数型数据时间序列建模的单传感器日常行为识别

在基于惯性传感器的人体行为识别中,传统算法常忽略行为的周期性与时序性,对提取特征的滑动窗口大小也有相应要求.文中基于单个腰部传感器分析人体日常行为,提出面向周期行为的函数型数据分析方法和隐马尔可夫模型结合的行为识别算法.首先,使用函数型数据分析方法,拟合周期性日常行为的动作捕捉数据,提取拟合后的单个周期数据.然后基于此周期时间序列数据建立描述各个日常行为过程的隐马尔可夫模型.最后,使用最大似然估计判别行为,得到识别结果.该算法通过单个腰部传感器即可快速有效地识别8种日常行为,在基于用户依赖策略和用户独立策略时识别率较高.     

Shape and Size Matter for Smartwatches: Effects of Screen Shape,Screen Size,and Presentation Mode in Wearable Communication

This study investigates how variations in the screen shape (round vs. square) and screen size (large vs. small) of smartwatches affect their hedonic and pragmatic qualities and the evaluation of transmitted information. Results from a between‐subjects experiment (N = 160) indicate that large screens positively influence information quality by simultaneously increasing both the hedonic and pragmatic qualities of smartwatches. However, the effects of round screens on information quality are mediated only by the hedonic quality, suggesting that square screens are more closely associated with the pragmatic, rather than hedonic, quality of the medium. The results also reveal that the effects of screen shape and screen size are moderated by the presentation mode (text + image vs. text only) of information.     

A wearable H-shirt for exercise ECG monitoring and individual lactate threshold computing

Millions of people worldwide are involved in daily physical exercise and fitness, which implies the growing demand for wearable devices and gadgets monitoring these activities. To ensure the comfort of exercise, wearable health monitoring devices are the most lucrative for real-time and continuous electrocardiogram (ECG) monitoring, which is essential for making individualized fitness plans and avoiding the occurrence of cardiac arrest. Moreover, the ECG monitoring data obtained are instrumental in the computation of the individual lactate threshold heart rate, which is the inflection point of the heart rate-time curve and indicates the exercise intensity level, at which the blood concentration of lactate and lactic acid begins to exponentially increase and will result in overstraining, unless the exercise efforts (running speed or muscle intensity) are temporarily reduced. The respective monitoring and overstrain-warning devices have a large potential for the individual assessment of the endurance performance, as well as for prescribing intensities in the endurance training. However, the common drawbacks of commercial wearable devices used in healthcare and medical fields for continuous monitoring of ECG, electroencephalogram, respiration, temperature, SpO_2, and human activity, such as smart helmets, wearable patches, and activity-tracking bands, are motion artifacts and unstable skin-electrode contact, which jeopardize the accurate measurements during exercise. Given this, the Health shirt (H-shirt) integrated with conductive fabric ECG electrodes enabling the accurate ECG monitoring during physical exercise has been introduced and validated by the authors. In this paper, the modified design of the sports H-shirt with the lactate threshold heart rate computing is proposed and implemented. High elasticity of the H-shirt not only ensures a stable skin-electrode contact but also avoids the discomfort caused by the measurement. A highly integrated printed circuit board is used to filter, amplify, digitalize, and transmit the ECG signal sampled from the electrodes, while a high input impedance amplifier circuit is designed to improve its signal-to-noise ratio. The Bluetooth low energy (BLE) is used as the data transmission protocol between the H-shirt and the mobile phone. A mobile phone-based ECG analysis and exercise evaluation platform have been developed, which allow one to detect six types of abnormal ECG (tachycardia, bradycardia, a dropped beat, premature beat, bigeminy, and trigeminy) and individual lactate threshold, as well as to provide real-time health warning and exercise optimization hints through mobile phone voice messages. Being powered by a 150 mAh 3.7 V lithium battery, the H-shirt operated for at least 24 h and was tested on four volunteers of both genders and age from 14 to 32 years, whose ECG and the lactate threshold heart rate values were accurately measured during their test exercise on a treadmill with running speed up to 16 km/h and used as a reference for the users to adjust their exercise intensity. The available options of adding sensors for measurement of more physiological parameters by the proposed sports H-shirt make it quite lucrative for the rehabilitation exercise monitoring.     

Fall risk assessment of construction workers based on biomechanical gait stability parameters using wearable insole pressure system

Falls on the same level are a leading cause of non-fatal injuries in the construction industry, and loss of balance events are the primarily contributory risk factors associated with workers’ fall injuries. Previous studies have indicated that changes in biomechanical gait stability parameters provide substantial safety gait metrics for assessing workers’ fall risks. However, scant research has been conducted on changes in biomechanical gait stability parameters based on foot plantar pressure patterns to assess workers’ fall risks. This research examined the changes in spatial foot regions and loss of balance events associated with biomechanical gait stability parameters based on foot plantar pressure patterns measured by wearable insole pressure system. To test the hypotheses of this study, ten asymptomatic participants conducted laboratory simulated loss of balance events which are often initiated by extrinsic fall risk factors. Our results found: (1) statistically significant differences in biomechanical gait stability parameters between spatial foot regions, especially with the peak pressure parameter; and (2) statistically significant differences in biomechanical gait stability parameters between loss of balance events when compared to normal gait (baseline), especially with the pressure-time integral parameter. Overall, the findings of this study not only provide useful safety gait metrics for early detection of specific spatial foot regions but also allow safety managers to understand the mechanism of loss of balance events in order to implement proactive fall-prevention strategies.     

可穿戴医疗设备的安全方法研究

针对可穿戴医疗设备应用中所存在的隐私保护和安全问题,在分析了已有生物密钥和量子密钥的优缺点的基础上,给出了将两者结合并用于可穿戴医疗设备安全保护中的思路;针对可穿戴医疗设备组成的异构网络的数据安全传输问题,在分析已有的密钥预分配方案的基础上,提出将其应用于可穿戴医疗设备构成的动态、异构网络中,为解决可穿戴医疗设备数据安全传输提供理论和技术基础。     

Flexible humidity sensor in a sandwich configuration with a hydrophilic porous membrane

We constructed a wearable and flexible humidity sensor (thickness: 80 μm) in a sandwich configuration, with a hydrophilic poly-tetrafluoroethylene membrane placed between two gold deposited layers, using soft-MEMS techniques. The device was used to measure humidity level, via its electrical conductivity, using a multi-frequency LCR-meter at frequencies ranging from 100 Hz to 100 kHz. The device was calibrated at 100 Hz against moist air over the range of 30–85% RH, which includes normal humidity levels in the atmosphere and physiological air such as breath and evaporating sweat. The response sensitivity of the humidity device was extremely high, even for recovery to dry air; for example response time was less than 1 s for a conductivity shift between humid air of 80% RH and dry air of −60 °C dew point. The sensor performance was reproducible over multiple measurements, with a coefficient of variation of 1.77% (n = 5). The sensor was appropriate for physiological applications, and was successfully used in two non-invasive approaches: to monitor breath air at the mouth, and to measure sweat moisture from the nostrils.     

Research on data load balancing technology of massive storage systems for wearable devices

Because of the limited memory of the increasing amount of information in current wearable devices, the processing capacity of the servers in the storage system can not keep up with the speed of information growth, resulting in low load balancing, long load balancing time and data processing delay. Therefore, a data load balancing technology is applied to the massive storage systems of wearable devices in this paper. We first analyze the object-oriented load balancing method, and formally describe the dynamic load balancing issues, taking the load balancing as a mapping problem. Then, the task of assigning each data node and the request of the corresponding data node’s actual processing capacity are completed. Different data is allocated to the corresponding data storage node to complete the calculation of the comprehensive weight of the data storage node. According to the load information of each data storage node collected by the scheduler in the storage system, the load weight of the current data storage node is calculated and distributed. The data load balancing of the massive storage system for wearable devices is realized. The experimental results show that the average time of load balancing using this method is 1.75 ?h, which is much lower than the traditional methods. The results show the data load balancing technology of the massive storage system of wearable devices has the advantages of short data load balancing time, high load balancing, strong data processing capability, short processing time and obvious application.