{"id":27245814,"url":"https://github.com/davidpl1/eit_data_analysis","last_synced_at":"2025-10-08T15:08:44.956Z","repository":{"id":54817940,"uuid":"307425176","full_name":"DavidPL1/eit_data_analysis","owner":"DavidPL1","description":"This repository holds the complementary code for the paper Towards More Robust Hand Gesture Recognition on EIT Data","archived":false,"fork":false,"pushed_at":"2022-05-25T08:02:17.000Z","size":832,"stargazers_count":0,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-10T21:36:12.963Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DavidPL1.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-10-26T15:53:10.000Z","updated_at":"2022-05-25T08:00:26.000Z","dependencies_parsed_at":"2022-08-14T03:40:57.360Z","dependency_job_id":null,"html_url":"https://github.com/DavidPL1/eit_data_analysis","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/DavidPL1/eit_data_analysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DavidPL1%2Feit_data_analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DavidPL1%2Feit_data_analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DavidPL1%2Feit_data_analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DavidPL1%2Feit_data_analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DavidPL1","download_url":"https://codeload.github.com/DavidPL1/eit_data_analysis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DavidPL1%2Feit_data_analysis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278964273,"owners_count":26076638,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-04-10T21:29:23.414Z","updated_at":"2025-10-08T15:08:44.936Z","avatar_url":"https://github.com/DavidPL1.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EIT Data Analysis\n\nThis repository holds the complementary code for the paper `Towards More Robust Hand Gesture Recognition on EIT Data`, David P. Leins, Christian Gibas, Rainer Brück and Robert Haschke.\n\n## Prerequisites\n\n- Python 3.x.x\n- pandas (1.1.2)\n- numpy (1.19.1)\n- matplotlib (3.3.0)\n- seaborn (0.10.1)\n- scikit-learn (0.23.1)\n\n#### For Train and Plot\n\n- tensorflow 2.x\n\nrun `pip install -r requirements_train.txt` to install all needed dependencies.\n\n#### For Interactive Visualization\n\n- plotly (4.12.0)\n- chart-studio (1.1.0)\n- ipywidgets (7.5.1)\n\nrun `pip install -r requirements_interactive.txt` to install all needed dependencies.\n\n## Instructions\n\nDownload the dataset from [https://doi.org/10.4119/unibi/2948441](https://doi.org/10.4119/unibi/2948441) and extract the archive content into the `data` directory.\n\n## Train and Plot\n\nThe [jupyter notebook](train_and_plot.ipynb) can be run to train any TensorFlow model on the raw data and the calibrated variants presented in the paper. The best performing models in the paper are defined in the define_auxiliary_functions script, which is loaded within the notebook.\n\nLoss, optimizer, batch size, epochs, and repetitions can be changed easily by setting the respective variables defined right before the train loop.\nTo reproduce results from the paper, change epochs to 100 and repetitions to 5 or higher (for statistical relevance).\n\nTo train your own models, define a function returning a TensorFlow/Keras Model class and change the `models_to_train` list accordingly.\n\nBelow the training block you'll find a few plot suggestions including our current baseline accuracies.\n\n\u003csub\u003eNote that the code can easily be changed to train PyTorch models.\u003c/sub\u003e\n\n## Interactive Visualization\n\nRun the [jupyter notebook](interactive_calibration_view.ipynb) to get an interactive visualization of global and local calibration on PCA or t-SNE 2D projections powered by plotly and ipywidgets.\nThis visualization can be filtered by session UID, class label and iteration. Below is a preview of the interactive UI.\n\n![preview-image](./resources/preview.png)\n\n\u003csub\u003eNote that the visualization of many data points may be slow, depending on your browser and machine. Also changing colorization or switching between projections requires that all traces are\nreplotted and thus may take a while, too.\u003c/sub\u003e\n\n# Contact\n\nDon't hesitate to open an Issue here or contact me (David Leins) via email under dleins@techfak.de\n\n# Citations\n\n```\n@ARTICLE{10.3389/fnbot.2021.659311,\n  AUTHOR={Leins, David P. and Gibas, Christian and Brück, Rainer and Haschke, Robert},\n  TITLE={Toward More Robust Hand Gesture Recognition on EIT Data},\n  JOURNAL={Frontiers in Neurorobotics},\n  VOLUME={15},\n  YEAR={2021},\n  URL={https://www.frontiersin.org/article/10.3389/fnbot.2021.659311},\n  DOI={10.3389/fnbot.2021.659311},\n  ISSN={1662-5218},\n}\n```\n\n\nIf you use the dataset in your research, please cite it with:\n\n```\n@misc{Leins2020EIT,\n  author          = {D. {Leins} and C. {Gibas} and R. {Brück} and R. {Haschke}},\n  keywords        = {EIT, Gesture Recognition},\n  publisher       = {University of Siegen},\n  title           = {{Hand Gesture Recognition with Electrical Impedance\n                  Tomography (Dataset)}},\n  url             = {https://pub.uni-bielefeld.de/record/2948441},\n  doi             = {10.4119/unibi/2948441},\n  year            = 2020,\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdavidpl1%2Feit_data_analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdavidpl1%2Feit_data_analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdavidpl1%2Feit_data_analysis/lists"}