This algorithm is able to distinguish between falls (forward, backward and fall into a sitting position) and the normal daily activity, such as walking, mastering stairs, sitting in a chair, lying ... Walking is also detected by the sensors. However, these impacts are not isolated, and after them there is no significant change in orientation between the two sensors. Vectors are in the area that we call common zone. If an isolated stroke which causes a change in orientation of the body is detected, or the orientation of certain body parts in relation to the situation before the stroke, then with some certainty it can be said that the fall had occurred.
Figure 5 presents the vector of gravity in certain areas such as common zone and lying zone. Its combination obtained from the sensor and the measured vector defines the state of sitting in a chair, lying in bed, walking on stairs and other everyday activities. The change in orientation is when the patient moves from one zone to another. If the time span in within such orientation change occurred also has a large amplitude of the measured acceleration, or shock, it can be said that it is an unnatural body position change.
Orientations in the standing position are shown on Fig. 6.
Both sensors are worn on the body. After the fall it is possible that only one changes orientation, as shown in Fig. 7. And that is the case in backward fall or fall in to the chair.
Figure 7 shows the orientation of the body after the fall. It can be seen that the sensor 1 remained in its normal position, although there has been an impact. In the case with only one sensor on the body, this situation would be characterized as a jump.