Design and Implementation of Adaptive Neuro-fuzzy Exergame Controller

Due to sedentary postures caused by video games many health-related issues have occurred among players. One practical solution for dealing with the aforementioned problem is to come up with game controllers which promote physical exercises. In this paper an adaptive neuro-fuzzy exergame controller was introduced.

During the training stage, the parameters of the fuzzy logic’s member functions were fine-tuned. By calculating a gradient vector and by applying backpropagation, the aforementioned parameters were updated using the measured error. The controller was made of four pads, each containing a resistor and a pushbutton, which were connected to a microcontroller. In order to improve the user experience, an adaptive neuro-fuzzy logic system was used to analyse the gathered data from the controller.

A pure FLS cannot provide an acceptable playing experience for players of different ages and physical characteristics. The proposed controller was made of four pads and a microcontroller for sending commands to the main computer. The received signal from the controller was sent to a fine-tuned FLS. The calculated output of the previously trained FLS is one of the defined classes of “ignore”, “press” and “hold”, which is sent as a command to the main computer.

In the proposed method, the FLS was fine-tuned by gathering data from the user, which improved the performance of the controller due to the fact that the controller was trained to best suit the needs of the user. The gathered data was then used to change the parameters of the FLS to provide an acceptable playing experience for the user.