A CNN Model for Physical Activity Recognition and Energy Expenditure Estimation from an Eyeglass-Mounted Wearable Sensor.

Metabolic syndrome poses a significant health challenge worldwide, prompting the need for comprehensive strategies integrating physical activity monitoring and energy expenditure. Wearable sensor devices have been used both for energy intake and energy expenditure (EE) estimation. Traditionally, sensors are attached to the hip or wrist. The primary aim of this research is to investigate the use of an eyeglass-mounted wearable energy intake sensor (Automatic Ingestion Monitor v2, AIM-2) for simultaneous recognition of physical activity (PAR) and estimation of steady-state EE as compared to a traditional hip-worn device. Study data were collected from six participants performing six structured activities, with the reference EE measured using indirect calorimetry (COSMED K5) and reported as metabolic equivalents of tasks (METs). Next, a novel deep convolutional neural network-based multitasking model (Multitasking-CNN) was developed for PAR and EE estimation. The Multitasking-CNN was trained with a two-step progressive training approach for higher accuracy, where in the first step the model for PAR was trained, and in the second step the model was fine-tuned for EE estimation. Finally, the performance of Multitasking-CNN on AIM-2 attached to eyeglasses was compared to the ActiGraph GT9X (AG) attached to the right hip. On the AIM-2 data, Multitasking-CNN achieved a maximum of 95% testing accuracy of PAR, a minimum of 0.59 METs mean square error (MSE), and 11% mean absolute percentage error (MAPE) in EE estimation. Conversely, on AG data, the Multitasking-CNN model achieved a maximum of 82% testing accuracy in PAR, a minimum of 0.73 METs MSE, and 13% MAPE in EE estimation. These results suggest the feasibility of using an eyeglass-mounted sensor for both PAR and EE estimation.

Wearable sensor device-based detection of decreased heart rate variability in Parkinson's disease.

The evidence that heart rate variability (HRV) decreases during early Parkinson's disease (PD) largely depends on electrocardiogram data. In this study, we examined HRV in PD using wearable sensors and assessed various evaluation methods for detecting disease-related alterations. We evaluated 27 patients with PD and 23 disease controls. The wearable sensors POLAR V800 HR and POLAR H10 were used for the HRV measurements. The participants wore the two sensors for approximately 24 h, and long-term HRV data were acquired. We analyzed the standard deviation of normal R-R intervals (SDNN) and coefficient of variation of R-R intervals (CVRR) for every 100 consecutive beats. Focusing on the fluctuation of SDNN and CVRR, we extracted the minimum, first decile, first quartile, and median values of SDNN and CVRR. The area under the receiver operating characteristic curve (AUC) for each HRV parameter was calculated to differentiate PD from the disease controls. The minimum values of SDNN and CVRR had the highest AUC (SDNN: AUC 0.90, 95% confidence interval [CI] 0.78-0.96; CVRR: AUC 0.90, CI 0.76-0.96) among the evaluation methods tested. The minimum values of SDNN and CVRR were significantly decreased in PD (SDNN: 9.5 ± 4.0 ms vs. 4.4 ± 2.0 ms, p < 0.0001; CVRR: 1.15 ± 0.33% vs. 0.65 ± 0.24%, p < 0.0001). We detected decreased HRV in PD using wearable sensors. Analyzing the minimum values of the HRV parameter in long-term recordings appears to be appropriate for detecting the decrease in HRV in PD.

Test-retest reliability and minimal detectable change for measures of wearable gait analysis system (G-Walk) in children with cerebral palsy.

BACKGROUND: Cerebral Palsy (CP) is the most frequent cause of physical disability in childhood. CP causes primary deficits such as impairments in muscle tone, muscle weakness, problems in selective motor control and secondary deficits such as contractures and deformities. These deficits lead to motor disorders during movement causing limitations in gait. Sixty percent of children with CP can walk independently despite these problems, however, they present with various gait abnormalities. Gait analysis is used in the quantitative assessment of gait disturbances providing functional diagnosis, assessment for treatment, planning, and monitoring of progress. G-Walk is a wearable sensor device which provides quantitative gait analysis via spatiotemporal parameters and pelvic girdle angles. In literature, there is no study investigating the reliability of the G-Walk in children with CP. The purpose of this study was to confirm the test-retest reliability of a commercially available body-worn sensor 'BTS G-WALK sensor system' for spatiotemporal gait parameters in children with CP. METHODS: Fifty-four children with CP (mean age: 9.19 ± 3.49 years), Gross Motor Function Classification System (GMFCS) level I-II completed the test-retest protocol with 5 days between tests. The test-retest reliability was calculated using intra-class correlation coefficients (ICC). Minimal detectable changes were calculated using standard error measurements. RESULTS: According to the analysis, ICC varied from 0.799 to 0.977 in all of the gait parameters. The statistical analysis showed that all G-Walk parameters' measurements were found to have almost perfect test-retest reliability. DISCUSSION: The G-Walk was found to be reliable in gait parameters for children with CP between ages 5 and 15, in GMFCS level I-II. A gait analysis carried out with the G-Walk system is a reliable method to assess gait in children with CP in a clinical setting.

TCN-attention-HAR: human activity recognition based on attention mechanism time convolutional network.

Wearable sensors are widely used in medical applications and human-computer interaction because of their portability and powerful privacy. Human activity identification based on sensor data plays a vital role in these fields. Therefore, it is important to improve the recognition performance of different types of actions. Aiming at the problems of insufficient time-varying feature extraction and gradient explosion caused by too many network layers, a time convolution network recognition model with attention mechanism (TCN-Attention-HAR) was proposed. The model effectively recognizes and emphasizes the key feature information. The ability of extracting temporal features from TCN (temporal convolution network) is improved by using the appropriate size of the receiver domain. In addition, attention mechanisms are used to assign higher weights to important information, enabling models to learn and identify human activities more effectively. The performance of the Open Data Set (WISDM, PAMAP2 and USC-HAD) is improved by 1.13%, 1.83% and 0.51%, respectively, compared with other advanced models, these results clearly show that the network model presented in this paper has excellent recognition performance. In the knowledge distillation experiment, the parameters of student model are only about 0.1% of those of teacher model, and the accuracy of the model has been greatly improved, and in the WISDM data set, compared with the teacher's model, the accuracy is 0.14% higher.

Wearable sensor devices can automatically identify the ON-OFF status of patients with Parkinson's disease through an interpretable machine learning model.

Introduction: Accurately and objectively quantifying the clinical features of Parkinson's disease (PD) is crucial for assisting in diagnosis and guiding the formulation of treatment plans. Therefore, based on the data on multi-site motor features, this study aimed to develop an interpretable machine learning (ML) model for classifying the "OFF" and "ON" status of patients with PD, as well as to explore the motor features that are most associated with changes in clinical symptoms. Methods: We employed a support vector machine with a recursive feature elimination (SVM-RFE) algorithm to select promising motion features. Subsequently, 12 ML models were constructed based on these features, and we identified the model with the best classification performance. Then, we used the SHapley Additive exPlanations (SHAP) and the Local Interpretable Model agnostic Explanations (LIME) methods to explain the model and rank the importance of those motor features. Results: A total of 96 patients were finally included in this study. The naive Bayes (NB) model had the highest classification performance (AUC = 0.956; sensitivity = 0.8947, 95% CI 0.6686-0.9870; accuracy = 0.8421, 95% CI 0.6875-0.9398). Based on the NB model, we analyzed the importance of eight motor features toward the classification results using the SHAP algorithm. The Gait: range of motion (RoM) Shank left (L) (degrees) [Mean] might be the most important motor feature for all classification horizons. Conclusion: The symptoms of PD could be objectively quantified. By utilizing suitable motor features to construct ML models, it became possible to intelligently identify whether patients with PD were in the "ON" or "OFF" status. The variations in these motor features were significantly correlated with improvement rates in patients' quality of life. In the future, they might act as objective digital biomarkers to elucidate the changes in symptoms observed in patients with PD and might be used to assist in the diagnosis and treatment of patients with PD.

Gaussian mixture modeling of acceleration-derived signal for monitoring external physical load of tennis player.

Introduction: With the widespread use of wearable sensors, various methods to evaluate external physical loads using acceleration signals measured by inertial sensors in sporting activities have been proposed. Acceleration-derived external physical loads have been evaluated as a simple indicator, such as the mean or cumulative values of the target interval. However, such a conventional simplified indicator may not adequately represent the features of the external physical load in sporting activities involving various movement intensities. Therefore, we propose a method to evaluate the external physical load of tennis player based on the histogram of acceleration-derived signal obtained from wearable inertial sensors. Methods: Twenty-eight matches of 14 male collegiate players and 55 matches of 55 male middle-aged players wore sportswear-type wearable sensors during official tennis matches. The norm of the three-dimensional acceleration signal measured using the wearable sensor was smoothed, and the rest period (less than 0.3 G of at least 5 s) was excluded. Because the histogram of the processed acceleration signal showed a bimodal distribution, for example, high- and low-intensity peaks, a Gaussian mixture model was fitted to the histogram, and the model parameters were obtained to characterize the bimodal distribution of the acceleration signal for each player. Results: Among the obtained Gaussian mixture model parameters, the linear discrimination analysis revealed that the mean and standard deviation of the high-intensity side acceleration value accurately classified collegiate and middle-aged players with 93% accuracy; however, the conventional method (only the overall mean) showed less accurate classification results (63%). Conclusion: The mean and standard deviation of the high-intensity side extracted by the Gaussian mixture modeling is found to be the effective parameter representing the external physical load of tennis players. The histogram-based feature extraction of the acceleration-derived signal that exhibit multimodal distribution may provide a novel insight into monitoring external physical load in other sporting activities.