Improved Self-Organizing Map-Based Unsupervised Learning Algorithm for Sitting Posture Recognition System

Abstract

As the intensity of work increases, many of us sit for long hours while working in the office. It is not easy to sit properly at work all the time and sitting for a long time with wrong postures may cause a series of health problems as time goes by. In addition, monitoring the sitting posture of patients with spinal disease would be beneficial for their recovery. Accordingly, this paper designs and implements a sitting posture recognition system from a flexible array pressure sensor, which is used to acquire pressure distribution map of sitting hips in a real-time manner. Moreover, an improved self-organizing map-based classification algorithm for six kinds of sitting posture recognition is proposed to identify whether the current sitting posture is appropriate. The extensive experimental results verify that the performance of ISOM-based sitting posture recognition algorithm (ISOM-SPR) in short outperforms that of four kinds of traditional algorithms including decision tree-based (DT), K-means-based (KM), back propagation neural network-based (BP), self-organizing map-based (SOM) sitting posture recognition algorithms. Finally, it is proven that the proposed system based on ISOM-SPR algorithm has good robustness and high accuracy.

Smart Sensing Chairs for Sitting Posture Detection, Classification, and Monitoring: A Comprehensive Review

“…Kim et al [41] achieved 95.30% accuracy using an 8 × 8 pressure array and a CNN classifier to classify five sitting postures among children. Similarly, Cai et al [43] utilized a flexible pressure sensor array (400 mm × 400 mm) placed on a bottom seat cushion to recognize six different sitting postures, as shown in Figure 6a. Ran et al [30] installed an 11 × 13 Pressure Sensor Array (IMM00014, I-MOTION) that communicated with a Raspberry PI computer, achieving 96.22% classification accuracy using a five-layer ANN classifier, seen in Figure 6b.…”

“…Only 36% ( 14) of all the studies incorporated a feedback platform to encourage users to maintain a correct posture. The implementation of mobile applications was seen as the most used platform for alerting a user whenever an improper sitting posture was detected [27,36,43,54]. Another common method was the use of a desktop application, which was observed in some studies [40,45,48,53].…”

“…Statistical models analyze data by identifying correlations between variables and making predictions based on statistical hypotheses derived from a dataset [80]. Various statistical models have been used to classify sitting postures, including K-Nearest Neighbors (KNNs) [23,35,57,60], Decision Tree [38,46,50], Support Vector Machines (SVMs) [29,31,40], Random Forests (RFs) [33,39,55], Light Gradient-Boosting Machine (LightGBM) [24,58], Simple Logistic Regression (SLR) [37], and Self-Organizing Maps (SOMs) [43]. In the context of smart sensing chairs, statistical models offer a balance between complexity and performance, making them integral tools for posture classification.…”

Smart-Sensing Chairs for Sitting Posture Detection, Classification and Monitoring: A Comprehensive Review

“…Kim et al [47] achieved a 95.30% accuracy using 8 x 8 pressure array and a CNN classifier to classify 5 sitting postures among children. Similarly, Cai et al [48] utilized a flexible pressure sensor array (400mm x 400mm) placed on the bottom seat cushion to recognize 6 different sitting postures as shown in Figure 6a. Ran et al [49] installed a 11 × 13 Pressure Sensor Array (IMM00014, I-MOTION) which communicated with a Raspberry PI computer which achieve a 96.22% classification accuracy using a 5-layer ANN classifier seen in Figure 6b.…”

Detecting Phase-Synchrony Connectivity Anomalies in EEG Signals. Application to Dyslexia Diagnosis

“…Betti et al [50] designed a fault prediction system in large power plants based on SOM. An improved SOM algorithm was used in the work of Cai et al [51]. They employed SOM to classify different sitting postures.…”