We propose a novel use of the conventional energy storage component, i.e., capacitor, in kinetic-powered wearable IoTs as a sensor to detect human activities. Since different activities accumulate energies in the capacitor at different rates, these activities can be detected directly by observing the charging rate of the capacitor. The key advantage of the proposed capacitor based activity sensing mechanism, called CapSense, is that it obviates the need for sampling the motion signal during the activity detection period thus significantly saving power consumption of the wearable device. A challenge we face is that capacitors are inherently non-linear energy accumulators, which, even for the same activity, leads to significant variations in charging rates at different times depending on the current charge level of the capacitor. We solve this problem by jointly configuring the parameters of the capacitor and the associated energy harvesting circuits, which allows us to operate on charging cycles that are approximately linear. We design and implement a kinetic-powered shoe sole and conduct experiments with 10 subjects. Our results show that CapSense can classify five different daily activities with 95% accuracy while consuming 73% less system power compared to conventional motion signal based activity detection.
Localization based on visible light is gaining significant attention. But most existing studies rely on a key requirement: the object of interest needs to carry an optical receiver (camera or photodiode). We remove this requirement and investigate the possibility of achieving accurate localization in a passive manner, that is, without requiring objects to carry any optical receiver. To achieve this goal, we exploit the reflective surfaces of objects and the unique propagation properties of LED luminaires. We present geometric models, a testbed implementation, and empirical evaluations to showcase the opportunities and challenges posed by this new type of localization. Overall, we show that our method can track with high accuracy (few centimeters) a subset of an object's trajectory and it can also identify passively the object's ID.
This paper describes an approach to detect and classify goalkeeper training exercises using a wearable motion sensor attached to a goalkeeper glove. We collected data from 14 goalkeeper trainees while performing a series of training exercises (e.g., dives, catches, throws). Our approach first detects the exercises using an event detection algorithm based on a high-pass filter, a peak detector, and Dynamic Time Warping to detect specific motion instances. Then, it extracts a set of statistical and heuristic features to describe the different exercises and train a machine learning classifier. Our exercise detection approach retrieves 93.8% of the relevant exercises with 90.6% precision and classifies the detected exercises with an accuracy of 96.5%. Our approach can be used to keep track of the training and give personalised feedback to goalkeepers who do not have access to or cannot afford a personal coach.
Sensing technology and the emerging Internet of Things (IoT) have the potential to solve major societal challenges associated with healthcare provision. Yet, to fully meet this potential, Health IoT applications must be supported by dependable data collection infrastructures. In this context, low-power wireless protocols for residential Health IoT applications are characterized by high reliability requirements, the need for an energy-efficient operation, and the need to operate robustly in diverse environments and in presence of external interference. To address these challenges, we enhance the Time-Slotted Channel Hopping (TSCH) protocol from the IEEE 802.15.4 standard with a new schedule and an adaptive channel selection mechanism to increase its performance in this domain. Our evaluation in a test house shows that for our e-Health application, the enhanced system shows better results than both the standard TSCH and state-of-the-art options such as the SmartMesh IP stack, the Orchestra scheduler, and the 6top distributed scheduling mechanism. Results from 29 long-term residential deployments confirm the suitability for the application. The results show 99.96 % average reliability in the uncontrolled environments for networks that generate 7.5 packets per second on the average.