Developing mind-controlled prosthetics that seamlessly integrate with the human nervous system is a significant challenge in the field of bioengineering. This project investigates the use of labelled brainwave patterns to control a bionic arm equipped with a sense of touch. The core objective is to establish a communication channel between the brain and the artificial limb, enabling intuitive and natural control while incorporating sensory feedback.

The project involves:
  • Data Acquisition: Recording brainwave activity using electroencephalography (EEG) while participants perform various hand and arm movement
  • Signal Processing: Labelling and extracting relevant features from the recorded brainwave patterns.
  • Machine Learning: Training a machine learning model to decode the labelled brainwave patterns and translate them into control signals for the bionic arm.
  • Integration: Integrating the trained model with the bionic arm, enabling real-time control based on the user's intent.
  • Sensory Feedback: Incorporating sensory feedback mechanisms into the bionic arm to provide the user with a sense of touch, enhancing control and natural interaction.

The successful completion of this project has the potential to revolutionize the field of prosthetics by offering amputees a more intuitive and natural control over their artificial limbs, ultimately improving their quality of life.


The dataset directory has been divided into 2 different parts

  • EEG Classifier: The preclassifier code to seggregate and labelled regions of EEG as Alpha, Beta, Delta and Theta
  • Mind Control Bionic Arm: This contains the actual dataset. This further has been dived into 2 different parts (folder), MATLAB (it contains the segrrated final output); and the datasets (It contains the raw data into differet folders according to the sources)

Now, if you want to process this on your own then use signal labeller in the MATLAB to classify these data and label it.