The aim was to classify lifting activities into low and high risk categories (according to The Danish Working Environment Authority guidelines) based on surface electromyography (sEMG) and trunk inclination (tri-axial accelerometer) measurements. Lifting tasks with different weights, horizontal distance and technique were performed. The lifting tasks were characterised by a feature vector composed of either the 90th, 95th or 99th percentile of sEMG activity level and trunk inclinations during

more »

... e task. Linear Discriminant Analysis and a subject-specific threshold scheme were applied and lifting tasks were classified with an accuracy of 65.1-65.5%. When lifts were classified based on the subject-specific threshold scheme from low and upper back accelerometers, the accuracy reached 52.1-58.1% and 72.7-78.1%, respectively. In conclusion, the use of subject-specific thresholds from sEMG from upper trapezius and erector spinae as well as inclination of the upper trunk enabled us to identify low and high risk lifts with an acceptable accuracy.