Symmetric lifting posture recognition of skilled experts with linear discriminant analysis by center-of-pressure velocity

Abstract

Although it has been well known that novices should train a good lifting posture, there was little way to recognize whether the current posture was good or not based on measured data. The purpose of this paper was to classify the difference between skilled experts working at a freight transport company and unskilled novices without any experience during symmetric lifting by using center-of-pressure (CoP) velocities. All the human subjects performed symmetric lifting experiments with closed eyes; the experiments involved lifting loads (6 and 18 kg) to the upside. Time series data of the CoP position were measured, using a Wii Balance Board, and then, the CoP velocities were calculated. The linear discriminant analysis (LDA) was designed by seven indices which were derived from CoP velocities that reflected the center-of-mass acceleration. The result indicated that the designed LDA discriminated the difference in posture between the two groups with the low error rate (0.100 and 0.017) for classification under 6 and 18 kg. Based on measurement results of CoP trajectories, we inferred that the difference in the CoP velocities between the two groups could be attributed to the difference in the balance ability which means that most skilled experts place their body weight on their rearfeet during symmetric lifting. The LDA classifier designed by CoP velocities was helpful for recognition of the difference between skilled experts and unskilled novices during symmetric lifting. Because the skillful characteristics of experts may be responsible for the lightening of the burden on the waist during lifting, it is considered for the regular check of posture to be helpful for reducing the ratio of occupational low back pain at the workplace.