System for Posture Evaluation and Correction - Development of a Second Prototype for an Intelligent Chair

Abstract

The sitting position has become one of the most common postures in developed countries. However, assuming a poor sitting posture leads to several health problems, namely back, shoulder and neck pain. In a previous work, an intelligent chair was developed and was shown to classify and correct the seating position. This work describes improvements on this intelligent chair prototype culminating with the development of a new prototype. The improvements of this new prototype are presented, resulting in new studies for posture identification. Pressure maps for 12 sitting postures were gathered in order to automatically detect user's posture through a neural network algorithm, obtaining an overall posture classification of around 81%.

Optimization of sitting posture classification based on user identification

“…For this reason we used the default values from the fitctree function but changing the splitting criterion (Gini and Twoing), as shown in Table III. TABLE III. RESULTS FROM THE AUTOMATIC SEPRATION BASED ON CLASSIFICATION TREES This would mean that for an automatic optimization we would get a 87.1% overall classification (0.890*0.9790 = 0.871), which is still a 6.2% improvement over the previously reported result of 80.9% score for 12 standard sitting postures [28]. When the user is identified with the Android application, we have an 8.1% classification optimization.…”

“…The data of the participants in the experiment, namely, Sex, Age, Weight and Height is presented in Table 1. In that protocol [28], we showed the postures P1 to P12 (as seen in figure 2), each for a duration of 20 seconds, asking the subject to mimic each posture, as in a previous protocol [27], which were based on the most familiar postures observed in office environments [1]- [4], [6], [30]. We used a sampling rate of 8 Hz and took 100 time-points (corresponding to 12.5 seconds out of 20 for each posture), and divided them in maps of 20 pressure acquisitions.…”

“…In this second prototype we introduced new features, like a vacuum pump (to have a better control of the air inside the bladder for the posture correction), industrialized air bladders (the first ones were manually manufactured), and a more independent control system (we used a Raspberry Pi to control the chair's instrumentation through an I 2 C connection, but still with Bluetooth for alternative smartphone communication) [28]. This prototype was able to classify 12 different sitting postures with an overall classification of 80.9% [28]. In order to compile the information about the posture habits of the user, an android application was developed to inform the user about their sitting behavior statistics.…”

“…After the development of the first prototype, a second one was built in order to solve the limitations of the first prototype [28]. In this second prototype we introduced new features, like a vacuum pump (to have a better control of the air inside the bladder for the posture correction), industrialized air bladders (the first ones were manually manufactured), and a more independent control system (we used a Raspberry Pi to control the chair's instrumentation through an I 2 C connection, but still with Bluetooth for alternative smartphone communication) [28]. This prototype was able to classify 12 different sitting postures with an overall classification of 80.9% [28].…”

Optimization of Sitting Posture Classification based on Anthropometric Data

“…The second prototype was built in order to overcome the gaps identified in the first prototype, mainly the introduction of a vacuum pump to control efficiently the air inside the bladders, the design of industrially constructed air bladders and the reorganization of the communication protocols (Pereira et al, 2015). We then revised our classification and correction algorithms and introduced Fuzzy Logic to the existing ANN algorithms, which was able to integrate time spent in each posture (recognized by the ANN) and was able to identify intermediate postures, other than the 12 standard ones and correct them based on fuzzy logic actuators .…”