Predicting fall risk is necessary for rescue and accident prevention in the elderly. In this study, deep learning regression models were used to predict the acceleration sum vector magnitude (SVM) peak value, which represents the risk of a fall. Twenty healthy adults (aged 22.0±1.9 years, height 164.9±5.9 cm, weight 61.4±17.1 kg) provided data for 14 common daily life activities (ADL) and 11 falls using IMU (Inertial Measurement Unit) sensors (Movella Dot, Netherlands) at the S2. The input data includes information from 0.7 to 0.2 seconds before the acceleration SVM peak, encompassing 6-axis IMU data, as well as acceleration SVM and angular velocity SVM, resulting in a total of 8 feature vectors used to model training. Data augmentations were applied to solve data imbalances. The data was split into a 4 : 1 ratio for training and testing. The models were trained using Mean Squared Error (MSE) and Mean Absolute Error (MAE). The deep learning model utilized 1D-CNN and LSTM. The model with data augmentation exhibited lower error values in both MAE (1.19 g) and MSE (2.93g²). Low-height falls showed lower predicted acceleration peak values, while ADLs like jumping and sitting showed higher predicted values, indicating higher risks.

Deaf people use their own national sign or finger languages for communication. They have a lot of inconvenience in both social and financial problems. In this study, a finger language recognition system using an ensemble machine learning algorithm with an armband sensor of 8 channel surface electromyography (sEMG) is introduced. The algorithm consisted of signal acquisition, digital filtering, feature vector extraction, and an ensemble classifier based on artificial neural network (EANN). It was evaluated with Korean finger language (14 consonants, 17 vowels and 7 numbers) in 20 normal subjects. EANN was categorized with the number of classifiers (1 to 10) and the size of training data (50 to 1500). Mean accuracies and standard deviations for each structure were then obtained. Results showed that, as the number of classifiers (1 to 8) and the size of training data (50 to 300) were increased, the average accuracy of the E-ANN classifier was increased while the standard deviation was decreased. Statistical analysis showed that the optimal E-ANN structure was composed with 8 classifiers and 300 training data. This study suggested that E-ANN was more accurate than the general ANN for sign/finger language recognition.

The estimation of muscle force is important to understand the roles of the muscles. The static optimization method can be used to figure out the individual muscle forces. However, muscle forces during the movement including muscle co-contraction cannot be considered by the static optimization. In this study, a hybrid static optimization method was introduced to find the well-matched muscle forces with EMG signals under muscle co-contraction conditions. To validate the developed algorithm, the 3D motion analysis and its corresponding inverse dynamics using the musculoskeletal modeling software (SIMM) were performed on heel-rise movements. Results showed that the developed algorithm could estimate the acceptable muscle forces during heel-rise movement. These results imply that a hybrid numerical approach is very useful to obtain the reasonable muscle forces under muscle co-contraction conditions.

This study investigated biomechanical response through the 3-dimensional virtual skeletal model developed and validated. Ten male subjects in standing posture were exposed to whole body vibrations and measured acceleration on anatomical of interest (head, 7th cervical, 10th thoracic, 4th lumbar, knee joint and bottom of the vibrator). Three dimensional virtual skeletal model and vibration machine were created by using BRG LifeMOD and MSC. ADAMS. The results of forward dynamic analysis were compared with results of experiment. The results showed that the accuracy of developed model was 73.2±19.2% for all conditions.