A conventional motion exercises recognition system only tracks designated motion types, and it enables users cannot use a customized system according to personal needs. The virtual IMU data provides a new opportunity to reduce the cost of training datasets and flexibly design the activity recognition system using online resources. To better design a user-customized motion exercises recognition system using virtual IMU data, this paper proposes a virtual IMU sensor module with a spring-joint model to augment the virtual acceleration signal from the limited online 2D video. The original virtual acceleration signal is extended with data from different acceleration distributions generated by the spring-joint model and used to train a motion exercises recognition system. The proposed method can design a classifier for three motions with limited video resources, showing an average accuracy of 85.5 on the real motion data of seven individuals.

Human activity recognition (HAR) systems combined with machine learning normally serve users based on a fixed sensor position interface. Variations in the installing position will alter the performance of the recognition and will require a new training dataset. Therefore, we need to understand the role of sensor position in HAR system design to optimize its effect. In this paper, we designed an optimization scheme with virtual sensor data for the HAR system. The system is able to generate the optimal sensor position from all possible locations under a given sensor number. Utilizing virtual sensor data, the training dataset can be accessed at low cost. The system can help the decision-making process of sensor position selection with great accuracy using feedback, as well as output the classifier at a lower cost than a conventional training model.

Human activities can introduce variations in various environmental cues, such as light and sound, which can serve as inputs for interfaces. However, one often overlooked aspect is the airflow variation caused by these activities, which presents challenges in detection and utilization due to its intangible nature. In this paper, we have unveiled an approach using mist to capture invisible airflow variations, rendering them detectable by Time-of-Flight (ToF) sensors. We investigate the capability of this sensing technique under different types of mist or smoke, as well as the impact of airflow speed. To illustrate the feasibility of this concept, we created a prototype using a humidifier and demonstrated its capability to recognize motions. On this basis, we introduce potential applications, discuss inherent limitations, and provide design lessons grounded in mist-based airflow sensing.

Guiding users with limb exercise can assist in muscle training or physical recovery. However, traditional vision-based methods often require multiple camera angles to help users understand the motions and require them to be within the range of the screen. Therefore, we propose a non-visual system that can guide users with multiple-directional limb motions utilizing spatial audio, AudioMove , with commercial-off-the-shelf (COTS) devices (i.e., smartphones and earphones). The proposed system addresses the challenge of conveying directional information encompassing multiple planes in real-time. We conduct a mixed-method user study to evaluate the effectiveness of the system with three methods combining motion data with spatial audio perception. Additionally, a user interface is built to collect users' comments. The results conclude that spatial audio guidance could create a natural, pervasive, and non-visual exercise training solution in daily life.

As one of the most natural user behaviors, walking has been widely focused on developing personal identification systems due to its unique biometric authentication features. Popular visual solutions are usually affected by various environmental conditions, and their redundant user information (e.g., body type and appearance) makes it more challenging for users to maintain privacy and security. This paper proposes a distance sensor–based gait identification system that uses only one-dimensional data with a simple system structure. Specifically, a time-of-flight sensor was placed in front of a walking person, and a time series of distances was acquired. We extracted gait features from the data by calculating the velocity and acceleration curves and identifying individuals using a random forest classifier. We evaluated our system on 10 users using leave-one-out cross-validation. The average identification accuracy was 91.05% for 10 users. This study shows that gait recognition is possible using only one-dimensional time-series data with a noncontact sensor. It can be used as a contactless identification, reducing the computational resources required for low-cost and low-power consumption edge computing.

In wearable human activity recognition (HAR), the generation and utilization of virtual IMU data has recently gained attention. The use of virtual data can improve the robustness, effective features, and customized motion types chosen in the HAR system. However, few studies have focused on augmenting virtual IMU data to reduce the dependence on real IMU data during the machine learning model training phase. This work proposes modifying the reconstructed 3D motion by its joint data to generate larger 3D motion based on a given 3D motion sequence, thus augmenting the virtual IMU dataset. The method simulates the intra-difference of the same motion type in the real world. It aims to use fewer 3D motion inputs to generate the larger size of the virtual IMU dataset to recognize the real activity. The experiment demonstrated the feasibility of the proposed method and provided insight into the 3D motion modification-based augmentation method.