Search

Purpose Gait analysis is an important method to evaluate the function of the human body, such as mobility, flexibility, stability, and functional strength. Most previous studies used the 3D motion capture system to calculate gait parameters in the gait laboratory. The 3D motion capture system is very accurate to determine the gait parameters and useful to apply to the various experimental protocols synchronizing with the other devices. However, it had spatial-disadvantages and is expensive to be used for the elderly and the patient[1], [2]. In this study, gait parameters were calculated using the multi-sensor, and were compared with those of the 3D motion capture system. Method Ten healthy adults were asked to perform level walking. Inertial measurement units (IMUs; Xsens DOT; 60Hz) and force plates (KISTLER & AMTI; 1000Hz) were used to determine gait parameters: knee joint angle and ankle joint moment. Four IMUs were attached on the lateral side of both thighs and shanks (left& right). 3D motion capture system (Vicon Motion System Ltd, Oxford, UK; 200Hz) was used as the reference data with the plug-in-lower-body marker set. Knee joint angle was calculated by the difference between the Euler angles of two IMUs (thigh and shank) using the quaternion algorithm. The ground reaction force and the center of pressure with the coordinate data of the ankle joint were used to calculate the ankle joint moment. Knee joint angles of the multi-sensor and 3D motion capture system were normalized to be 0° at the initial contact. The normalization of the ankle joint moment was carried out using each subject's weight. Gait parameters of the multi-sensor were compared with those of 3D motion capture system in each gait event (Initial contact (IC), Foot flat (FF), Heel off (HO), Toe off (TO)). The correlation coefficient was calculated to analyze the similarity between the multi-sensor and 3D motion capture system. Results and Discussion In knee joint angle, the differences between the multi-sensor and 3D motion capture system were 2.71°±1.80 (FF), 2.72°±1.06 (HO), and 6.04°±2.93 (TO) respectively (Figure 1). The correlation coefficient of the knee joint angle was 0.9644. The difference of ankle joint moment between the multi-sensor and the 3D motion capture system were 0.010±0.003Nm/kg (IC), 0.043±0.024Nm/kg (FF), 0.051±0.030Nm/kg (HO), and 0.039±0.012m/kg (TO) respectively (Figure 2). Ankle joint moments determined by the two systems showed a strong correlation of 0.9963, which supported that the multi-sensor system could be used to replace the 3D motion capture system to determine gait parameters. [ABSTRACT FROM AUTHOR]

Purpose Fall is one of the major health risks for older people. Hip fractures are considered the most dangerous among various injuries, as they can reduce mobility and lead to many complications, and even death (Hagen, G et al., 2020). Some researchers tried to protect the user using a wearable airbag based on the threshold-based algorithm (Jung, H et al., 2021). The more accurate algorithm was developed using the deep learning methods, but it was heavy and needed GPU or PC (Yu, X et al., 2021). This study was focused on developing the lightweight deep learning algorithm to detect pre-impact falls for targeting edge devices. Method The KFall public dataset was used in this study. The experimental protocol consisted of 15 fall movements and 21 activities of daily living (ADLs). The 9-axis IMU sensor data with 100 Hz sampling frequency were acquired from the waists of 32 young male subjects. Data of 26 subjects were used to train the deep learning models and those of remained 6 subjects were used to test the models. We developed the fall detection algorithm based on ResNet method. It consisted of 2 convolution layers, 4 convolution blocks, 3 identity blocks, 1 average pooling layer, and 1 SoftMax layer. We removed one by one except for the factors that affect the output size. ResNet14 model was transformed to a flat buffer type and two quantization techniques were applied using TensorFlow Lite. Results and Discussion Table 1 showed the performance of ResNet algorithms. When continuously reducing the layers, demanded memory decreased, but there was no dramatic change in accuracy. It suggested that our model was sufficiently deep and additional identity blocks were not needed. Table 2 showed the performance of ResNet14 models according to quantization. The integer quantization showed the smallest size of memory but the worst accuracy. The float16 quantization showed the bigger size of memory than the integer quantization, but the accuracy was maintained. As a result, the float16 quantization showed 98% of accuracy with 539 ±278 ms of sufficient lead time and 0.104 MB of memory size. [ABSTRACT FROM AUTHOR]

Purpose sEMG-based recognition system provides the intuitive and accurate classification of various gestures and useful for human-computer interaction. Especially, recognition of hand postures is often suggested as the interaction protocol of rehabilitation systems or robotic orthosis for the elderly and disabled [1]. However, the variability of the sEMG signal was caused by the individual differences and the change of the force or proficiency. In this study, the hand posture recognition algorithm was developed using sEMG sensors, and the visual-feedback training was performed to improve the classification performance. Method Four healthy adults and a forearm amputee participated in this study to perform twelve hand postures (Rest, Hook, Spread, Scissor-sign, Finger pointing, V-sign, O.K.-sign, Cylindrical grasp, Spherical grasp, Lateral pinch, Palmar pinch, and Tip pinch) [2]. Commercial sEMG sensors (Delsys Trigno; 1926 Hz) were placed on the nine forearm muscles of the healthy adults (FDS, ED, EDM, EP, FCR, FCU, ECR, ECU, BRD) and the eight forearm muscles of an amputee (based on 3D reconstruction data from MRI; BRD, FCR, ECR, ED, ECU, FDP, FDS, FCU) (Figure 1). A LabVIEW-based radar plot was used for hand posture training (1 day for the healthy adults and 5 days for the amputee) to minimize the variability of the sEMG signal. In the session for recording the sEMG signal, all participants repeated the hand postures 10 times with 20% MVC [3]. The 10-fold cross validation was performed on the ANN classifiers with the feature vector of MAV or the Hudgins' set (MAV, WL, ZC, and SSC) [4] on MATLAB. Results and Discussion The classification accuracy was improved by increasing the number of training data in both trained and untrained sessions (Table 1). ANN classifiers of the healthy adults with MAV showed the classification accuracies of 84.3% and 85.8% in untrained session and trained session respectively. The classification performance was improved as 88.4%(untrained) and 91.6%(trained) by the Hudgins' set. In untrained session of the forearm amputee, poor classification accuracies appeared in both MAV(31.7%) and the Hudgins' set(33.0%). After the 5 days training, MAV and the Hudgins' set showed the classification accuracy of 76.3% and 84.7% respectively. In this study, the Hudgins' set and the posture training were useful to improve the classification accuracy. Furthermore, the great improvement of the classification performance appeared in the forearm amputee with an appropriate posture training (day 5). These results supported that the posture training with visual feedback had an effect to minimize the variability of sEMG signals. [ABSTRACT FROM AUTHOR]

The aim of this study was to evaluate nutritional care and outcomes in a medical intensive care unit (ICU) following multidisciplinary nutritional team (MNT) involvement. The authors retrospectively reviewed the data of all patients admitted to a medical ICU from April to October 2013 (pre-MNT period) and from April to October 2014 (post-MNT period). In total, 140 patients were included and allocated to the pre-MNT group (n=70) or the post-MNT group (n=70). The post-MNT group was more likely to use enteral nutrition (61.4 vs 37.1%, P=0.002). In terms of total calories and protein provided, the number of nutritional goal-achieved days during stays in ICU was significantly greater in the post-MNT group than in the pre-MNT group (63.7% vs 47.6%, P<0.05 and 44.3% vs 29.9%, respectively, P<0.05). The MNT activities resulted in significant improvements in terms of nutritional provision and adequacy in a medical ICU. [ABSTRACT FROM AUTHOR]