EMD-HIST-DF handgesture recognition
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Pubblicazione: |
Zenodo
2026
|
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901993486811136 |
|---|---|
| author | Li, Hui-bin |
| author_facet | Li, Hui-bin |
| contents | <p>This repository contains the datasets and source code used in the above study.</p> <h3>Data</h3> <ul> <li> <p><strong>Raw sEMG signals</strong>: 8 subjects (S1–S8), 6 channels, 2000 Hz sampling rate, each CSV file includes 6 channel columns + gesture label (0–15).</p> </li> <li> <p><strong>Processed features</strong>: Feature sets extracted after Empirical Mode Decomposition (EMD) and/or histogram‑based methods. Each CSV file contains a feature matrix with the last column as the gesture label. Available feature combinations include:</p> <ul> <li> <p><code>HIST</code> (126 dimensions, without EMD)</p> </li> <li> <p><code>EMD_HIST</code> (504 dimensions)</p> </li> <li> <p><code>HIST_mDWT_TD</code> (720)</p> </li> <li> <p><code>HIST_mDWT</code> (600)</p> </li> <li> <p><code>HIST_TD</code> (624)</p> </li> <li> <p><code>mDWT_TD</code> (216)</p> </li> <li> <p><code>mDWT</code> (96)</p> </li> <li> <p><code>TD</code> (120)</p> </li> <li> <p><code>MAV</code> (24)</p> </li> </ul> </li> </ul> <p>All feature matrices are provided for each subject separately. The data are fully anonymized and comply with ethical requirements.</p> <h3>Code</h3> <ul> <li> <p><code>GCForest.py</code>: Implementation of the Deep Forest classifier.</p> </li> <li> <p><code>K_val_main.py</code>: Main script for nested 8‑fold cross‑validation, training, and evaluation.</p> </li> <li> <p>Additional scripts for parameter sensitivity and histogram analysis.</p> </li> <li> <p><code>requirements.txt</code>: List of Python dependencies.</p> </li> </ul> <p>For details on the methodology and experimental setup, please refer to the associated manuscript.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19248598 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | EMD-HIST-DF handgesture recognition Li, Hui-bin <p>This repository contains the datasets and source code used in the above study.</p> <h3>Data</h3> <ul> <li> <p><strong>Raw sEMG signals</strong>: 8 subjects (S1–S8), 6 channels, 2000 Hz sampling rate, each CSV file includes 6 channel columns + gesture label (0–15).</p> </li> <li> <p><strong>Processed features</strong>: Feature sets extracted after Empirical Mode Decomposition (EMD) and/or histogram‑based methods. Each CSV file contains a feature matrix with the last column as the gesture label. Available feature combinations include:</p> <ul> <li> <p><code>HIST</code> (126 dimensions, without EMD)</p> </li> <li> <p><code>EMD_HIST</code> (504 dimensions)</p> </li> <li> <p><code>HIST_mDWT_TD</code> (720)</p> </li> <li> <p><code>HIST_mDWT</code> (600)</p> </li> <li> <p><code>HIST_TD</code> (624)</p> </li> <li> <p><code>mDWT_TD</code> (216)</p> </li> <li> <p><code>mDWT</code> (96)</p> </li> <li> <p><code>TD</code> (120)</p> </li> <li> <p><code>MAV</code> (24)</p> </li> </ul> </li> </ul> <p>All feature matrices are provided for each subject separately. The data are fully anonymized and comply with ethical requirements.</p> <h3>Code</h3> <ul> <li> <p><code>GCForest.py</code>: Implementation of the Deep Forest classifier.</p> </li> <li> <p><code>K_val_main.py</code>: Main script for nested 8‑fold cross‑validation, training, and evaluation.</p> </li> <li> <p>Additional scripts for parameter sensitivity and histogram analysis.</p> </li> <li> <p><code>requirements.txt</code>: List of Python dependencies.</p> </li> </ul> <p>For details on the methodology and experimental setup, please refer to the associated manuscript.</p> |
| title | EMD-HIST-DF handgesture recognition |
| url | https://doi.org/10.5281/zenodo.19248598 |