TY  - JOUR
PY  - 2023//
TI  - Comparison of machine learning approaches for near-fall-detection with motion sensors
JO  - Frontiers in digital health
A1  - Hellmers, Sandra
A1  - Krey, Elias
A1  - Gashi, Arber
A1  - Koschate, Jessica
A1  - Schmidt, Laura
A1  - Stuckenschneider, Tim
A1  - Hein, Andreas
A1  - Zieschang, Tania
SP  - e1223845
EP  - e1223845
VL  - 5
IS  - 
N2  - INTRODUCTION: Falls are one of the most common causes of emergency hospital visits in older people. Early recognition of an increased fall risk, which can be indicated by the occurrence of near-falls, is important to initiate interventions. <br><br>METHODS: In a study with 87 subjects we simulated near-fall events on a perturbation treadmill and recorded them with inertial measurement units (IMU) at seven different positions. We investigated different machine learning models for the near-fall detection including support vector machines, AdaBoost, convolutional neural networks, and bidirectional long short-term memory networks. Additionally, we analyzed the influence of the sensor position on the classification results. <br><br>RESULTS: The best results showed a DeepConvLSTM with an F1 score of 0.954 (precision 0.969, recall 0.942) at the sensor position "left wrist." DISCUSSION: Since these results were obtained in the laboratory, the next step is to evaluate the suitability of the classifiers in the field.<p />  <p>Language: en</p>
LA  - en
SN  - 2673-253X
UR  - http://dx.doi.org/10.3389/fdgth.2023.1223845
ID  - ref1
ER  -