Research
  Key Laboratories
  Research Divisions
  Research Interests
  Supporting System
  Achievements
  Research Progress
  Research Programs
  Technology Transfer
    Location: Home > Research > Research Progress

Researchers Propose Efficient Fall Detection in Four Directions Based on Smart Insoles and RDAE-LSTM Model

Fall detection is a typical application of both medical expert systems and wearable expert systems. There are four primary types of falls, i.e., left-sided horizontal, right-sided horizontal, supine, and prone, whereas most previous studies and commercial systems focused on distinguishing fall or not.  

Accurate and rapid multi-directional fall detection is of great significance for providing the human body with timely inflatable airbag protection in the fall direction and helping doctors shorten the reaction time to assess the severity of particular joints. 

In a  study published in Expert Systems With Applications, the research group led by Prof. DAI Houde from Fujian Institute of Research on the Structure of Matter of Chinese Academy of Sciences, reported a novel fall detection methodology based on smart insoles and a long short-term memory (LSTM) framework with a trained referencing denoising auto-encoder (RDAE).  

The automatic feature extraction via RDAE, instead of manual offline ex-traction, has the advantage of without subjective labeling and analysis, thereby more likely to select near-optimal features and enhance the detection robustness. 

The researchers employed a pair of wireless in-shoe insoles, each side equipped with 13 plantar pressure sensors and a tri-axial accelerometer, to capture comprehensive spatial-temporal gait parameters. Hence an effective response to a fall, together with the estimation of the corresponding direction, can be accomplished, where the accuracy and response time are two primary concerns.  

The proposed RDAE-LSTM network provides a reliable testing result in classification, with 98.6% accuracy and 8.7 ms response time for determining fall directions, demonstrating a more convincing performance than other algorithms.  

This methodology is an unobtrusive choice for users whose daily life is not affected by the fall detection device. The RDAE-LSTM model was proven to accurately and quickly recognize falls in four directions for the unbalanced fall detection dataset. 

This study has significant application prospects in Internet-of-things applications in the aging society. 

 

Flowchart of the proposed RDAE-LSTM method for fall detectionImage by Prof. DAI’s group 

  

  

Contact:  

Prof. DAI Houde 

Fujian Institute of Research on the Structure of Matter 

Chinese Academy of Sciences 

Email: dhd@fjirsm.ac.cn

 


Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences
Address: 155 Yangqiao Road West,Fuzhou,350002,P.R.China Tel: 0591-83714517 Fax: 0591-83714946 E-mail: fjirsm@fjirsm.ac.cn
Copyright @ 2000-2009 fjirsm. All rights reserved.