## Background The brain controls movement by sending electrical signals through the nervous system to the muscles, causing them to contract. This contraction is the fundamental mechanism that generates movement in the body. When a muscle contracts, it pulls on the bone it is attached to, creating motion at the joint. This intricate process allows for a wide range of movements, from simple actions like lifting a cup to complex activities like playing a musical instrument. By measuring muscle activity, known as electromyography (EMG), we can gain insight into which muscles are contracting and thus infer the pose or position of a person's limbs.
Courtesy of Scidraw.io, Smith Breault, Macauley.
This principle becomes particularly useful in the context of prosthetics for amputees. For an individual with an upper limb amputation, the remaining muscles in the residual limb still produce EMG signals when the person attempts to move their missing limb. By measuring these signals with dedicated sensors, we can predict what the pose of the hand "should" be, based on the muscle activity that is recorded. For instance, if the muscles that used to control the hand and wrist are still active, their EMG signals can indicate intended movements, such as grasping or pointing. By applying advanced AI models to interpret these EMG signals, we can map the muscle activity onto specific hand poses. These AI models are crucial because they must accurately decode the complex patterns of muscle activity into precise movements. Once the intended pose is determined, this information can be used to send commands to a prosthetic hand, instructing it to take on the desired position. This process allows for natural and effective control of the prosthesis, enabling the user to perform a wide range of movements with their artificial limb. The development of robust AI models is essential in this context. These models need to handle the variability in EMG signals and provide consistent, accurate mappings to ensure the prosthetic hand responds correctly to the user's intentions. With continued advancements in AI and sensor technology, we can enhance the functionality of prosthetic devices, offering amputees a more intuitive and seamless way to control their artificial limbs, thus improving their quality of life. One of ALVI Labs' goals is to develop the next generation of AI models for this task. In this challenge, you get to have a go at it too! ## This challenge We've prepare some [example code](https://github.com/BCI-I/BCI_ALVI_challenge) to help illustrate how to load the data and train the baseline model. ### The dataset ALVI Labs generously shared some of the data they have acquired during their research. This data was acquired using the [Myo Armbdand](https://www.researchgate.net/figure/The-Myo-Armband-Thalmic-Labs_fig2_346959518) from Thalmic labs to measure the activity of several forearm muscles while subjects performed several hand movements. The data includes muscle activity and reconstructed hand position in both healthy and amputee subjects. The **goal** is to predict hand pose (expressed as the angle of multiple joints) from the measured muscle activation. Note that you will only be asked to make predictions for a single subject: data from the additional subjects is included in case it would help you engineer more effective models. Head over to the `Data` tab for more information about how the data is structured. ### The Baseline Model ALVI Labs prepare a model that can be used as baseline to assess the performance of your own! You can see how exactly the model works [here](https://github.com/BCI-I/BCI_ALVI_challenge/blob/main/utils/hvatnet.py). Briefly, their model is based on the idea of a Convolutional Neural Network with a few additional modification. You can use the baseline model as an inspiration for how to effectively tackle this challenge, but don't forget to explore other options too! ### Prizes The prizes offered as part of this competition are aligned to the BCI Initiative's goal to help promote research and education in this field. Winning teams will have a unique opportunity to have 1-on-1 meeting with some of the members of ALVI Labs' team to learn more about their experience launching this startup and what ALVI Labs' hopes to achieve in the future. In addition, outstanding teams will be offered the opportunity to work with the ALVI Labs' team to prepare an online blog post describing their approach to solving the challenge and, potentially, to work together on a conference paper submission. ## Preparing for the competition As the start date approaches, we will host additional material on this page, including example code and baseline models. We will also plan an online workshop, so stay tuned for more details! ## Participating in person While this challenge is held asynchronously and online, we will endeavor to organize in-person periodic meetups prior to and while the challenge is running for those that want to meet with other participants. Stay tuned!