Intelligent Sitting Posture Classifier for Wheelchair Users

Abstract

In recent years, there has been growing interest in postural monitoring while seated, thus preventing the appearance of ulcers and musculoskeletal problems in the long term. To date, postural control has been carried out by means of subjective questionnaires that do not provide continuous and quantitative information. For this reason, it is necessary to carry out a monitoring that allows to determine not only the postural status of wheelchair users, but also to infer the evolution or anomalies associated with a specific disease. Therefore, this paper proposes an intelligent classifier based on a multilayer neural network for the classification of sitting postures of wheelchair users. The posture database was generated based on data collected by a novel monitoring device composed of force resistive sensors. A training and hyperparameter selection methodology has been used based on the idea of using a stratified K-Fold in weight groups strategy. This allows the neural network to acquire a greater capacity for generalization, thus allowing, unlike other proposed models, to achieve higher success rates not only in familiar subjects but also in subjects with physical complexions outside the standard. In this way, the system can be used to support wheelchair users and healthcare professionals, helping them to automatically monitor their posture, regardless physical complexions.

Intelligent systems for sitting posture monitoring and anomaly detection: an overview

“…Although several studies have been done using this type of sensors, the proper location of the sensors has not yet been defined, with each researcher placing the sensors in a different position. The most common is to locate the sensors both in the seat and in the backrest, thus monitoring a greater number of postures [ 25 , 68 , 69 ]. Similarly, and depending on the chair used, especially in the case of office chairs, it is common to locate the sensors only on the seat [ 59 , 70 ], at the cost of reducing the number of postures to be monitored.…”

“…On the left, example of sensor implementation under the seat cushion [ 62 ]. Right, example of implementation of FSR sensors inside the seat cushion [ 68 ] …”

“…There are several typologies of neural networks, which are classified according to the structure of the layers or the interneuronal connections, among other aspects. One of the most widely used neural network models are the Multilayer FeedFordward or Multilayer Perceptron (MLP) networks [ 66 , 68 , 80 – 82 ]. This type of networks are characterized by having an input layer and an output layer, together with an undetermined number of hidden layers.…”

Optimization of Spatial and Temporal Configuration of a Pressure Sensing Array to Predict Posture and Mobility in Lying

“…Literature reports several studies [ 12 , 13 ] assessing the optimal sensors’ distribution to accurately predict seated postures. However, these analytical methods have been limited to assess the optimal spatial resolution and predict postures from pressure data acquired on one type of cushion, e.g., foam.…”