Search

Electrocardiogram (ECG), usually measured by Ag/AgCl electrode with conductive gels, is one of the most frequently used tools for the diagnosis of cardiovascular diseases (CVDs) symptoms, but it may encounter the gels drying issue and the risk of skin allergic reaction for long-term ECG monitoring. Recently, the technique of noncontact electrode has developed to access biopotentials without contacting the skin directly to improve the above issue and the convenience and comfort of use, but its signal quality may be affected by the fabric material and the skin-electrode interface condition that still cannot be monitored by current wearable devices. In this study, a novel automatic adjustment noncontact sensing smart clothing was proposed. The designed smart clothing could access biopotentials without contacting the skin directly. Moreover, the function of real-time skin-electrode interface capacitance monitoring was also built to monitor the interface condition simultaneously. The attenuation compensation mechanism was also designed to automatically compensate the attenuation of ECG signal according to the fabric material and the change of interface condition. Finally, the system performance was validated, and the influence of fabric conditions and motion artifact on the change of interface capacitance and ECG signal quality was also investigated. From the experimental results, its ECG signal quality was similar to that of the conventional Ag/AgCl electrodes (correlation >95%) and was stable for long-term monitoring, and the cotton fabric material, thinner fabric thickness, and sweating condition would also improve the ECG signal quality.

Energy expenditure (EE) is often used to quantify physical activity. Currently, EE is estimated with data collected by inertial measurement units or depth cameras and verified by oxygen consumption data. Due to the different data collection time spans in this system, raw data were split into minute-by-minute windows, and summary statistics for each window were computed. However, using summary statistics to aggregate data might be influenced by redundant noise or result in the loss of valuable information. This article presents a modeling method using functional analysis to characterize the trajectory of the collected skeletal data, thus enabling the effective use of the complete data. Next, the fitted values of the skeletal data can be aligned to the overall EE data and used to predict the overall EE as well as the task-based EE. The study results revealed for metabolic equivalent of task prediction that the root-mean-square error (RMSE) derived for the proposed method was $< $0.5 and that the mean absolute error (MAE) was approximately 0.3. Models for estimating task-based EE, including EE related to standing and walking task, also exhibited low RMSE and MAE values. Accordingly, the proposed modeling approach is superior to summary statistics for estimating EE in depth camera systems.

Long-term poor sitting posture leads to physical injuries such as muscle soreness and waist and neck alignment problems. In this study, we proposed an intelligent sitting posture detection system that uses depth cameras fixed on a chair to capture depth images of the user's sitting posture, and then applies a trained artificial intelligence (AI) model on an embedded Raspberry Pi board to recognize the user's sitting posture from the image data. Finally, through Bluetooth on the Raspberry Pi, the results are sent to the user's smartphone application for display and recording to achieve rapid detection of sitting posture and warning of poor sitting posture. The contribution of this study is its use of two depth cameras mounted on a chair, thereby eliminating the problem of cumbersome sensors that compromise user comfort or are prone to damage. The detection of the user's entire sitting posture was completed on an edge computing platform, which leads to power savings and offers privacy protection. Furthermore, because of the low battery power usage, the system is portable. To perform quick AI calculations, we developed a lightweight EfficientNet model and programmed it for the Raspberry Pi. The system achieved an accuracy of 99.71% and an execution speed of almost one posture result per second.

Unbalanced walking is increasingly common among older adults; therefore, routinely assessing the balance of older adults is crucial. The traditional method of assessing balance uses scales, requires the supervision of a physical therapist (PT), and is time-consuming. The present study, therefore, proposes a deep learning (DL) model architecture that combines a convolutional neural network (CNN) and a long short-term memory (LSTM) network model to predict the scores of three scales, namely the Berg balance scale (BBS), timed up and go (TUG), and single-leg stance (SLS). The gait data of 15 m of walking were collected from seven inertial measurement units (IMUs) and input into the CNN-LSTM model for evaluation. The BBS and TUG only require the participants to wear two IMUs on the left and right thighs, respectively, for accurate predictions. The mean absolute errors (MAEs) of predicting the scores of the BBS and TUG are 1.2562 and 1.4016 s, respectively; however, the MAE of score predictions of SLS is higher than that of the BBS and TUG, indicating that gait data cannot be used for assessing SLS; moreover, participants only wear one IMU on the right calf for BBS and TUG evaluations, which yield MAEs of 1.4334 and 1.5229 s, respectively. The proposed system can quickly and accurately predict the scores of the BBS and TUG. The proposed model can assist PTs with making clinical decisions.