# Goal of the Competition:
Develop a machine learning model to decoding the gait phase by using electroencephalogram (EEG) data collected from a person with spinal cord injury using the Lokomat system. As a reference, the signal from a inertial unit motion (IMU) sensor is used.

# Motivation
Wearable devices, such as robotic exoskeletons, have been used to assist spinal cord injury (SCI) individuals in regaining some of their lost mobility. These devices can be further enhanced by incorporating the individual's intended movement via motor imagery (MI) detected through EEG. To promote the development of more accurate and efficient machine learning models for decoding joint values from EEG data, we propose here a competition that utilizes data collected from SCI individuals who walked on a treadmill with the Lokomat's assistance.

# Methodology:
To record EEG signals, 16 wet electrodes were placed on the scalp according to the international 10-20 system (FP1, FP2, F3, F4, FC1, FC2, C4, C3, Cz, CP2, CP1, P4, Pz, P3, O2, and O1). The Fpz and Fz electrodes were used as ground and reference, respectively. The electrode's impedance was kept below 10 kΩ. Signals were acquired with the V-Amp 16 system at 512 Hz sampling rate. An in-house inertial sensor, termed  JAMA, was placed between the calf and ankle braces to acquire the gait phases by using sampling rate at 20 Hz. Both raw EEG and IMU signal were synchronized for analysis. The participant was positioned on Lokomat, and received 100% assistance walking at 1 km/h with body weight support. 

The Lokomat robotic system is designed to assist and control lower-limb movements during gait rehabilitation. It is equipped with a sophisticated software system that allows the therapist to program various walking patterns and levels of assistance, which can be tailored to the individual needs of each patient. The Lokomat also provides body weight support and an adjustable speed control.

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10622352%2F4d7955623ff1e61153cbce9403e9a029%2FLogos%20assinatura.png?generation=1681933899167807&alt=media)