Modeling of preprogrammed scenario data of a gesture-based, access control system
A method of training a gesture-based access control system includes repetitiously performing an intentional gesture indicative of an intentional gesture type by a user of a mobile device. The intentional gesture is representative of an intent of the user to gain access. The application then forms a model of the selected intentional gesture type from the repetitious performances of the intentional gesture. The model is configured to be applied by the software-based application to confirm future performances of the intentional gesture.
1. A method of training a gesture-based access control system comprising:
using a software-based application of the gesture-based access control system to provide training instructions to a user;
wherein a first set of the training instructions instruct the user to perform a motion with a mobile device;
storing a first set of scenario data that results from the user performing the motion with the mobile device;
wherein a second set of the training instructions instruct the user to perform the motion with the mobile phone while performing a user-chosen event intended to cause an access assembly to unlock;
storing a second set of the scenario data that results from the user performing the motion with the mobile device while performing the user-chosen event intended to cause the access assembly to unlock; and
using the first set of the scenario data and the second set of the scenario data to perform an initial training of a machine learning algorithm to perform a set of tasks;
wherein a first one of the set of tasks comprises, based on receiving post-initial-training instances of the scenario data, and based on a first characteristic of the user-chosen event, initiating a process to cause the access assembly to unlock; and
wherein a second one of the set of tasks comprises authenticating the user based on receiving the post-initial-training instances of the scenario data, and based on a second characteristic of the user-chosen event.
2. The method set forth in claim 1 , wherein:
the first characteristic of the user-chosen event comprises a pattern; and
the second characteristic of the user-chosen event comprises an intensity.
3. The method set forth in claim 1 , wherein the scenario data is collected from at least one detection system of the mobile device.
4. The method set forth in claim 2 , wherein the scenario data includes motion data detected by an inertial measurement unit (IMU) sensing system of the at least one detection system.
5. The method set forth in claim 4 , wherein the scenario data includes audible data detected by a microphone of the mobile device.
6. The method set forth in claim 2 , wherein the user-chosen event comprises tapping by the user upon the mobile device.
7. The method set forth in claim 1 , wherein the software-based application provides the training instructions to the user via a human interface device (HID) of the mobile device.
8. The method set forth in claim 1 further comprising performing a continued training on the machine learning algorithm based at least in part on the post-initial-training instances of the scenario data.