Assessment of Real-World Fall Detection Solution Developed on Accurate Simulated-Falls

One of the urgent and popular research areas is wearable devices-based fall detection (FD). Over the past 20 years, researchers have conducted many experiments in which falls and activities of daily living were simulated. Researchers inferred that real-world fall data is in demand rather than simulated fall data, but this inference still lacks comparisons. In this study, an assessment of a simulated fall dataset and a real-world fall dataset is proposed. The assessment investigates the efficacy of simulated data for developing an FD solution. Comparisons were conducted between FD methods developed on simulated and real-world data to observe the effectiveness of simulated falls. The experiments showed that the method with real-world data offered similar performances to the method with simulated data. In contrast to existing solutions, the provided comparison revealed that accurate simulated data are beneficial for developing a real-world FD solution.