Workers at construction sites are prone to fall-from-height (FFH) accidents. The severity of injury can be represented by the acceleration peak value. In the study, a risk prediction against FFH was made using IMU sensor data for accident prevention at construction sites. Fifteen general working movements (NF: non-fall), five low-hazard-fall movements, (LF), and five high-hazard-FFH movements (HF) were performed by twenty male subjects and a dummy. An IMU sensor was attached to the T7 position of the subject to measure the three-axis acceleration and angular velocity. The peak acceleration value, calculated from the IMU data, was 4 g or less in general work movements and 9 g or more in FFHs. Regression analysis was performed by applying various deep learning models, including 1D-CNN, 2D-CNN, LSTM, and Conv-LSTM, to the risk prediction, and then comparing them in terms of their mean absolute error (MAE) and mean squared error (MSE). The FFH risk level was estimated based on the predicted peak acceleration. The Conv-LSTM model trained by MAE showed the smallest error (MAE: 1.36 g), and the classification with the predicted peak acceleration showed the best accuracy (97.6%). This study successfully predicted the FFH risk levels and could be helpful to reduce fatal injuries at construction sites.

Falls represent a significant health concern for the elderly. While studies on deep learning-based preimpact fall detection have been conducted to mitigate fall-related injuries, additional efforts are needed for embedding in microcomputer units (MCUs). In this study, ConvLSTM, the state-of-the-art model, was benchmarked, and we attempted to lightweight it by leveraging features from image-classification models VGGNet and ResNet while maintaining performance for wearable airbags. The models were developed and evaluated using data from young subjects in the KFall public dataset based on an inertial measurement unit (IMU), leading to the proposal of TinyFallNet based on ResNet. Despite exhibiting higher accuracy (97.37% < 98.00%) than the benchmarked ConvLSTM, the proposed model requires lower memory (1.58 MB > 0.70 MB). Additionally, data on the elderly from the fall data of the FARSEEING dataset and activities of daily living (ADLs) data of the KFall dataset were analyzed for algorithm validation. This study demonstrated the applicability of image-classification models to preimpact fall detection using IMU and showed that additional tuning for lightweighting is possible due to the different data types. This research is expected to contribute to the lightweighting of deep learning models based on IMU and the development of applications based on IMU data.

Quantification of pain or discomfort induced by pressure is essential for understanding human responses to physical stimuli and improving user interfaces. Pain research has been conducted to investigate physiological signals associated with discomfort and pain perception. This study analyzed changes in electrodermal activity (EDA), tissue oxygen saturation (StO₂), heart rate variability (HRV), and Visual Analog Scale (VAS) under pressures of 10, 20, and 30 kPa applied for 3 min to the thigh, knee, and calf in a seated position. Twenty participants were tested, and relationships between biosignals, pressure intensity, and pain levels were evaluated using Friedman tests and post-hoc analyses. Multiple linear regression models were used to predict VAS and pressure, and five machine learning models (SVM, Logistic Regression, Random Forest, MLP, KNN) were applied to classify pain levels (no pain: VAS 0, low: VAS 1–3, moderate: VAS 4–6, high: VAS 7–10) and pressure intensity. The results showed that higher pressure intensity and pain levels affected sympathetic nervous system responses and tissue oxygen saturation. Most EDA features and StO₂ significantly changed according to pressure intensity and pain levels, while NN interval and HF among HRV features showed significant differences based on pressure intensity or pain level. Regression analysis combining biosignal features achieved a maximum R² of 0.668 in predicting VAS and pressure intensity. The four-level classification model reached an accuracy of 88.2% for pain levels and 81.3% for pressure intensity. These results demonstrated the potential of EDA, StO₂, HRV signals, and combinations of biosignal features for pain quantification and prediction.

This study proposes a hybrid approach combining threshold-based algorithm and deep learning to detect four major gait events—initial contact (IC), toe-off (TO), opposite initial contact (OIC), and opposite toe-off (OTO)—using only a smartphone’s built-in inertial sensor placed in the user’s pocket. The algorithm enables estimation of spatiotemporal gait parameters such as cadence, stride length, loading response (LR), pre-swing (PSw), single limb support (SLS), double limb support (DLS), and swing phase and symmetry. Gait data were collected from 20 healthy individuals and 13 hemiparetic stroke patients. To reduce sensitivity to sensor orientation and suppress noise, sum vector magnitude (SVM) features were extracted and filtered using a second-order Butterworth low-pass filter at 3 Hz. A deep learning model was further compressed using knowledge distillation, reducing model size by 96% while preserving accuracy. The proposed method achieved error rates in event detection below 2% of the gait cycle for healthy gait and a maximum of 4.4% for patient gait in event detection, with corresponding parameter estimation errors also within 4%. These results demonstrated the feasibility of accurate and real-time gait monitoring using a smartphone. In addition, statistical analysis of gait parameters such as symmetry and DLS revealed significant differences between the normal and patient groups. While this study is not intended to provide or guide rehabilitation treatment, it offers a practical means to regularly monitor patients’ gait status and observe gait recovery trends over time.

Gait event detection is essential for controlling an orthosis and assessing the patient’s gait. In this study, patients wearing an electromechanical (EM) knee–ankle–foot orthosis (KAFO) with a single IMU embedded in the thigh were subjected to gait event detection. The algorithm detected four essential gait events (initial contact (IC), toe off (TO), opposite initial contact (OIC), and opposite toe off (OTO)) and determined important temporal gait parameters such as stance/swing time, symmetry, and single/double limb support. These gait events were evaluated through gait experiments using four force plates on healthy adults and a hemiplegic patient who wore a one-way clutch KAFO and a pneumatic cylinder KAFO. Results showed that the smallest error in gait event detection was found at IC, and the largest error rate was observed at opposite toe off (OTO) with an error rate of −2.8 ± 1.5% in the patient group. Errors in OTO detection resulted in the largest error in determining the single limb support of the patient with an error of 5.0 ± 1.5%. The present study would be beneficial for the real-time continuous monitoring of gait events and temporal gait parameters for persons with an EM KAFO.

The quantification of comfort in binding parts, essential human–machine interfaces (HMI) for the functioning of rehabilitation robots, is necessary to reduce physical strain on the user despite great achievements in their structure and control. This study aims to investigate the physiological impacts of binding parts by measuring electrodermal activity (EDA) and tissue oxygen saturation (StO₂). In Experiment 1, EDA was measured from 13 healthy subjects under three different pressure conditions (10, 20, and 30 kPa) for 1 min using a pneumatic cuff on the right thigh. In Experiment 2, EDA and StO₂ were measured from 10 healthy subjects for 5 min. To analyze the correlation between EDA parameters and the decrease in StO₂, a survey using the visual analog scale (VAS) was conducted to assess the level of discomfort at each pressure. The EDA signal was decomposed into phasic and tonic components, and the EDA parameters were extracted from these two components. RM ANOVA and a post hoc paired t-test were used to determine significant differences in parameters as the pressure increased. The results showed that EDA parameters and the decrease in StO₂ significantly increased with the pressure increase. Among the extracted parameters, the decrease in StO₂ and the mean SCL proved to be effective indicators. Such analysis outcomes would be highly beneficial for studies focusing on the comfort assessment of the binding parts of rehabilitation robots.