English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Falls represent a significant cause of injury among the elderly population.Extensive research has been devoted to the utilization of wearable IMU sensorsin conjunction with machine learning techniques for fall detection. To addressthe challenge of acquiring costly training data, this paper presents a novelmethod that generates a substantial volume of synthetic IMU data with minimalreal fall experiments. First, unmarked 3D motion capture technology is employedto reconstruct human movements. Subsequently, utilizing the biomechanicalsimulation platform Opensim and forward kinematic methods, an ample amount oftraining data from various body segments can be custom generated. An LSTM modelis trained, achieving testing accuracies of 91.99% and 86.62% on two distinctdatasets of actual fall-related IMU data, demonstrated the comparableperformance of models trained using genuine IMU data. Building upon thesimulation framework, this paper further optimized the single IMU attachmentposition and multiple IMU combinations on fall detection. The proposed methodsimplifies fall detection data acquisition experiments, provides novel venuefor generating low cost synthetic data in scenario where acquiring data formachine learning is challenging and paves the way for customizing machinelearning configurations.

Synthetic IMU Datasets and Protocols Can Simplify Fall Detection Experiments and Optimize Sensor Configuration