“…In contrast, these hurdles can be alleviated and accurate action recognition can be achieved by the usage of wearable sensors 13–16 . Wearable sensor‐based techniques acquire data from sensors attached to the human body, such as accelerometers, gyroscopes, magnetometers and so forth.…”
SUMMARY
With the advancement of mobile computing, understanding, and interpretation of human activities has become increasingly popular as an innovative human computer interaction application over the past few decades. This article presents a new scheme for action recognition based on sparse representation theory using a novel dictionary learning algorithm. This system employs two types of inertial signals from smartphones namely, accelerometer and gyroscope sensory data. Attainment of higher values of classification accuracy depends on the creation of effective dictionaries that completely retain the important features of every action while maintaining the least correlation with the features of other actions. Accordingly, in this research, we propose a new algorithm for learning dictionaries with two levels of dictionary training that aims at learning a compact, representative, and discriminative dictionary for each class. Unlike typical dictionary learning algorithms that aim at the creation of dictionaries that best represents the features of each class, our proposed algorithm incorporates a discriminative criterion that eventually produces better classification results. To validate the proposed framework, all the experiments were performed using three publicly available datasets.
“…In contrast, these hurdles can be alleviated and accurate action recognition can be achieved by the usage of wearable sensors 13–16 . Wearable sensor‐based techniques acquire data from sensors attached to the human body, such as accelerometers, gyroscopes, magnetometers and so forth.…”
SUMMARY
With the advancement of mobile computing, understanding, and interpretation of human activities has become increasingly popular as an innovative human computer interaction application over the past few decades. This article presents a new scheme for action recognition based on sparse representation theory using a novel dictionary learning algorithm. This system employs two types of inertial signals from smartphones namely, accelerometer and gyroscope sensory data. Attainment of higher values of classification accuracy depends on the creation of effective dictionaries that completely retain the important features of every action while maintaining the least correlation with the features of other actions. Accordingly, in this research, we propose a new algorithm for learning dictionaries with two levels of dictionary training that aims at learning a compact, representative, and discriminative dictionary for each class. Unlike typical dictionary learning algorithms that aim at the creation of dictionaries that best represents the features of each class, our proposed algorithm incorporates a discriminative criterion that eventually produces better classification results. To validate the proposed framework, all the experiments were performed using three publicly available datasets.
“…On the other hand, Everon and Empatica have developed wearable multimodal temperature sensors that are worn on the wrist. [22] Also, the Max3010 series from Maxim Integrated is commonly used as pulse oximeter sensors, [23][24][25] which are usually made from rigid materials and are placed on the fingertip. Despite these advances, most of these sensors are made of rigid materials that not only are uncomfortable to wear but also lack conformal contact with our bodies' curved surfaces and fine topology, making real-time diagnosis difficult to achieve.…”
Wearable sensors are emerging as a new technology to detect physiological and biochemical markers for remote health monitoring. By measuring vital signs such as respiratory rate, body temperature, and blood oxygen level, wearable sensors offer tremendous potential for the noninvasive and early diagnosis of numerous diseases such as Covid‐19. Over the past decade, significant progress has been made to develop wearable sensors with high sensitivity, accuracy, flexibility, and stretchability, bringing to reality a new paradigm of remote health monitoring. In this review paper, the latest advances in wearable sensor systems that can measure vital signs at an accuracy level matching those of point‐of‐care tests are presented. In particular, the focus of this review is placed on wearable sensors for measuring respiratory behavior, body temperature, and blood oxygen level, which are identified as the critical signals for diagnosing and monitoring Covid‐19. Various designs based on different materials and working mechanisms are summarized. This review is concluded by identifying the remaining challenges and future opportunities for this emerging field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.