Skip to main content

Table 1 The data

From: Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems

Data

Participants

Signals

In-group fall data

Collected from 5 healthy volunteers, 2 females and 3 males. Volunteers aged between 19 and 28 years.

293 fall signals were collected. Of these, 153 signals were used for training, and 140 signals used for testing (in-group performance)

Out-group fall data

Collected from 3 different healthy male volunteers whose data was not included in the training data. Volunteers aged between 19 and 28 years.

This set included 85 signals, all used to test "out-group" performance. The term "out-group" is used to indicated that these people's data was not used as training data.

The Activities of Daily Living (ADL) training data

Collected from 3 people. A total of 8 hours of ADL data was collected in a home environment. An additional hour of exercise data was recorded from 2 people in a gym environment. Volunteers aged between 19 and 28 years.

1831 ADL signals were collected. 1000 randomly selected ADL signals were used for the training set while 831 were used for testing. Of the 1000 randomly selected signals used for training, 750 related to ADL routine, and 250 related to ADL exercise. Of the 831 signals used for testing, 400 related to ADL routine and 381 related to ADL gym exercise.

Validation set

 

Taken randomly from the training set with the ratio of training versus validation = 4:1.