Identifying Elderly Patients at Risk of Falling using Time-Domain and Cyclostationarity Related Features


  • Reem Brome Univ Lyon
  • Jad Nasreddine Rafik Hariri University
  • Frédéric Bonnardot Univ Lyon
  • Mohamad O. Diab Rafik Hariri University
  • Mohamed El Badaoui Univ Lyon


Classification models, cyclostationarity, degree of cyclostationarity, elderly people, fallers, machine learning, walk pressure signals


Falls are a prevalent and severe health problem in the elderly community, leading to unfortunate and devastating consequences. Some falls can be prevented through interventions, proper management, and extra care. Therefore, studying and identifying elderly people with risk of falls is essential to minimize the falling risk and to minimize the severity of injuries that can occur from these falls. Besides, identifying at-risk patients can profoundly affect public health in a positive way. In this paper, we use classification techniques to identify at-risk patients using pressure signals of the innersoles of 520 elderly people. These people reported whether they had experienced previous falls or not. Two different types of feature sets were used as inputs to the classification models and were compared: The first feature set includes time-domain, physiological, and cyclostationary features, whereas the second includes a subset of those features chosen by Relief-F as the most important features. Our study showed that the use of features from different walking conditions and using Relief-F as a feature selection method significantly improved the model prediction accuracy, i.e. by 5.24% from the best previously existing model. The results also point out that the mean and standard deviation of the stride time, gender, the degree of cyclostationarity were the most important features to include in classification models for the identification of elderly people at risk of falling.


Download data is not yet available.




How to Cite

Brome, R., Nasreddine, J. ., Bonnardot, F., Diab, M. O., & El Badaoui, M. (2021). Identifying Elderly Patients at Risk of Falling using Time-Domain and Cyclostationarity Related Features . International Journal of Integrated Engineering, 13(5), 57–66. Retrieved from