Sleep is characterized by episodes of immobility interrupted by periods of voluntary and involuntary movement. Increased mobility in bed can be a sign of disrupted sleep that may reduce sleep quality. This paper describes a method for classification of the type of movement in bed using load cells installed at the corners of a bed. The approach is based on Gaussian Mixture Models using a time-domain feature representation. The movement classification system is evaluated on data collected in the laboratory, and it classified correctly 84.6% of movements. The unobtrusive aspect of this approach is particularly valuable for longer-term home monitoring against a standard clinical setting.