# BCI Initiative & ALVI labs - HCI Challenge — Data 来源：https://www.kaggle.com/competitions/bci-initiative-alvi-hci-challenge/data 本地 Meta Kaggle 快照；不是本次实时页面。 # Dataset Description The dataset includes EMG forelimb muscle activity recordings and associated target hand pose (joint angles) from several healthy and amputee subjects. The data was acquired as subjects performed a cued hand movement task: a visual input showed the subject which movement to execute (e.g. flex index finger) and participants performed that movement with both hands. Movements varied in complexity, from single finger movement to more complicated gestures. Amputees attempted the imagined movement with the missing limb in parallel to the movement of the intact one. The pose of the hand opposite the arm wearing the EMG armband was reconstructed in 3D and is represented by 20 joint angle values. Your task is to train a model that can predict hand pose from the EMG data. ### Dataset structure When you download the data (~5GB), you'll need to un-zip it. Within it, you'll find several folders for `health`y and `amputant` subjects and organized by the arm on which the EMG armband was worn (left/right). Within each subject's folder, you'll find a folder called `preproc_angles` with the pre-processed data for the challenge. Each subject's data is further separated into `train` and `test` subsets (not all subjects have `test` data) for your convenience: you can use the `test` data to evaluate your model's performance on unseen data. Each `train/test` folder contains a series of `.npz` files, each storing data from a single movement (approximately 10 seconds). Each `.npz` file includes the EMG data and the joint angles data (see below). Although you can use any of the data provided to train your model, there's a specific subset of the data that is used to evaluate all models. This session belongs to one of the two amputant subjects, `fedya`, and is stored within a distinct subfolder called `submit`. Refer back to our [example code](https://github.com/BCI-I/BCI_ALVI_challenge/tree/main) to see how to load the data for your machine learning model and how to prepare your submissions! ### Inputs The inputs to your machine learning models are 8-dimensional time-series data, corresponding to the signals picked up by the 8 sensors in the Myo armband. The input data is already pre-processed to eliminate some noise and make the analysis simpler for you. Note that since subjects used the armband on either arm, the electrode position relative to the arm's muscles will be different. We provided some code for correcting for this difference while loading the data to simplify model training. ### Targets The output of your model should be a 20-dimensional time-series with the predicted angle for each hand joint at each time stamp. #### Columns Each `.npz` file in the dataset includes the following entries: - **myo_X**: with `X` a number in `[0,6]`. Time series data from each EMG sensor - the inputs to your model. - **ang_X**: with `X` a number in `[0, 19]`. Time series data with the ground truth values for each joint angle - what your model should predict. ### The submission data As described in the `Overview` tab, you'll use data from one of the two amputant subjects to prepare submissions to evaluate your model. This is the data in the `fedya_tropin_standart_elbow_left/submit` folder. The `npz` files in this folder **only include myo data** - the joint angles data is not provided such that models cannot be trained using this information. You'll have to use these data and **only these data** to prepare your submission. We shared some code to show how to prepare your submissions. ## A note on sampling The data, both EMG and hand pose, is sampled at 200Hz. However, each model's predictions should be down sampled to 25Hz. When preparing your submissions, make sure that your model's predictions are down sampled accordingly. We share some code to illustrate this in detail.