There are two major sensory modules that help with the training of dance postures and actions, namely, audio and visual feedback. This method of training has been in use for a few centuries now, to compare one's reflection and the perceived ideal picture of the performance of a given step or expression. The negative aspects of having a mirror for dance training as a mirror might lead a dancer to pay too much attention on their body’s reflection and this self-consciousness may overpower their own internalized sense of their body as it moves through space leading to imperfections in postures and rhythm. To top it off, there is no signifier associated with this kind of setup that could alert a person if they are practicing something properly or not unless it’s a dance trainer observing and guiding them at all times.
“Positron” is a visual coding and machine learning based audio-visual project that generates audio-visual output using the data received from a real-time data stream from the IMU and EMG sensors present inside the Myo armband. The idea behind the project is basically an attempt to make an interface that could help beginner / learning dance artists to speed up the learning process of dance actions and gestures involved in tutting dance form.
This project aims at working with three major aspects; 1) visual memory: to provide a visual interface that could help perfect the posture of the user; 2) muscle memory: to provide a physical feedback to embed a sense of rhythm into the muscle memory of the user ; 3) musical interaction: to enable the dancers explore gesture-based musical interactions that will help the user strengthen their visual and muscle memory by providing it a third sensory module in the form of audio feedback.