Many stroke patients are prescribed canes or other mobility assistive devices. Once taken home, these mobility assistive devices are often abandoned or misused. A means for assessing the use of the cane in the home and community settings is required to assist clinicians in the prescription of these devices. In this study, we propose the use of wearable sensors to identify tasks performed by stroke patients with a mobility assistive device. Subjects performed ten tasks with a three-axis accelerometer attached to their ankle and a neural network was trained to identify the task being performed. Results from 15 stroke patients indicated that these motor tasks can be reliably identified with a median sensitivity of 90 % at a median specificity of 95%. These results indicate that it is possible to use a single module with a three-axis accelerometer attached to the ankle to reliably identify motor tasks associated with the use of a cane. Therefore, we envision that the methodology presented in this paper could be used to evaluate the use of a cane in the context of the task being performed.