{"success":true,"data":{"author":"Claas Lendt, Martin Grimmer, Ingo Froböse, Tom Stewart (University of Regensburg, German Sport University Cologne); harmonized by Josef Heidler","bucketAccessType":"public","bucketName":"josefheidler/har_gait_adults_2023-lendt","bucketPrefix":"","category":"Physiology","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:18.400Z","description":"Thigh-worn accelerometry with insole-derived gait events, dataset C of the TWAGA gait pipeline by Claas Lendt and colleagues (University of Regensburg and German Sport University Cologne). Twenty-one healthy adults wore an Axivity AX6 accelerometer on the lateral mid-thigh of the dominant leg (100 Hz) together with a loadsol pro force-sensing insole on the same leg during four 2-minute treadmill walking trials at 2, 3, 4 and 5 km/h and one 5-minute outdoor walk at preferred speed. Every sample carries the insole vertical ground reaction force and initial-contact (heel strike) and final-contact (toe-off) flags, the reference for detecting steps, stride time and cadence from a single thigh sensor. The accelerometer signal was low-pass filtered near 20 Hz upstream. There are about 1.61 million samples and 4.5 labelled hours, plus participants.parquet giving each participant's dominant leg. This Hugging Face copy harmonizes the Zenodo release (DOI 10.5281/zenodo.17629131) into one Parquet file per participant under harmonized/; load with Hugging Face datasets or pandas. The Zenodo record is licensed CC BY 4.0. Cite Lendt, Grimmer, Froböse and Stewart, medRxiv 2025.11.18.25339671 (preprint).","displayTitle":"Thigh-Worn Accelerometry and Gait Event Detection: Axivity AX6 with loadsol Force Insole Ground Truth in 21 Adults (Lendt, Regensburg)","doi":"10.5281/zenodo.17629131","huggingFaceUrl":"https://huggingface.co/datasets/josefheidler/har_gait_adults_2023-lendt","id":"8105089a-5c8b-5516-934f-98ba83ac9081","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/api/records/17629131","objectCountEstimate":24,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1101/2025.11.18.25339671","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"josefheidler/har_gait_adults_2023-lendt\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"josefheidler/har_gait_adults_2023-lendt\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=josefheidler, license:cc-by-4.0, size_categories:1M<n<10M, format:parquet, downloads=223"],"format":"mixed","generatedAt":"2026-11-22T01:10:16.781Z","layout":{"example":"harmonized/alert-aracari.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"harmonized/alert-aracari.parquet","truncatedAt":512}],"sampleObjects":["harmonized/alert-aracari.parquet","harmonized/balmy-bittern.parquet","harmonized/candid-caiman.parquet","harmonized/dainty-dipper.parquet","harmonized/elegant-eagle.parquet"],"sidecars":[{"bytes":"---\npretty_name: \"Lendt 2023 — thigh accelerometry + insole gait events, healthy adults\"\nlicense: cc-by-4.0\nlanguage:\n  - en\ntags:\n  - accelerometry\n  - wearable\n  - human-activity-recognition\n  - time-series-classification\n  - thigh-worn\n  - physical-activity\n  - movement-behaviour\n  - time-series\n  - walking-speed\n  - gait\n  - gait-events\n  - ground-reaction-force\ntask_categories:\n  - tabular-classification\n  - other\nsize_categories:\n  - 1M<n<10M\nconfigs:\n  - config_name: default\n    data_files:\n      - split: train\n        path: \"harmonized/*.parquet\"\n  - config_name: participants\n    data_files:\n      - split: participants\n        path: \"participants.parquet\"\n---\n\n# Lendt 2023 — thigh accelerometry + insole gait events, healthy adults\n\nA thigh-worn Axivity AX6 accelerometer (100 Hz, lateral dominant mid-thigh) recorded\nsimultaneously with a `loadsol pro` force-sensing insole on the same leg, during four\n2-minute treadmill walking trials at 2, 3, 4 and 5 km/h and one 5-minute outdoor walk\nat preferred speed, by 21 healthy adults in Cologne, Germany. Every sample carries the\ninsole vertical ground reaction force and per-sample initial-contact and final-contact\ngait event flags derived from it. Harmonized from the\n[Zenodo release](https://doi.org/10.5281/zenodo.17629130) into per-subject parquet —\none row per sample (100 Hz). 21 participants, 1.61 M samples, 100% labelled, 4.5 h labeled.\n\n> **The accelerometer signal is not raw** — it carries a low-pass filter near 20 Hz applied\n> upstream. Do not filter it again, and do not compare its spectra against raw-data sets.\n\n## Source\n\n- **Paper**: Lendt, C., Grimmer, M., Froböse, I., & Stewart, T. (2025). Gait Analysis for\n  Thigh-Worn Accelerometry — A Data Processing Pipeline using Data-Driven Approaches.\n  *medRxiv* 2025.11.18.25339671. https://doi.org/10.1101/2025.11.18.25339671\n  — **a preprint, not peer reviewed** (posted 2025-11-19).\n- **Raw data**: https://doi.org/10.5281/zenodo.17629130 (concept DOI; v1.0.0 is\n  https://doi.org/10.5281/zenodo.17629131), *Thigh-Worn Accelerometry and Gait Event\n  Detection*, Claas Lendt, University of Regensburg.\n- **Pipeline code**: https://github.com/claaslendt/twaga\n- **Scope**: the paper covers six datasets, A to F. This record is **dataset C only**,\n  described on one page of Supplementary File 1. What the paper says about the other five\n  does not apply here.\n- **Ethics**: German Sport University Cologne ethics committee, ref. 107/2023.\n- **License**: CC-BY-4.0\n\n## Protocol\n\n- **Participants**: 21 healthy adults (9 female, 43%), mean age 26.7 ± 4 years, mean BMI\n  23.4 ± 1.6 kg/m².\n- **Sensor**: Axivity AX6 triaxial accelerometer at 100 Hz, placed on the lateral side of\n  the dominant leg, midway between hip and knee, attached directly to the skin with medical\n  adhesive tape. The dynamic range is not stated anywhere upstream.\n- **Reference signal**: `loadsol pro` force-sensing insole (novel GmbH, Germany), vertical\n  ground reaction force at 100 Hz, in the shoe of the **same leg** as the accelerometer.\n- **Protocol**: Four two-minute treadmill walking trials at 2, 3, 4 and 5 km/h on the level,\n  plus one five-minute outdoor walk on level ground at each participant's preferred speed.\n  The four treadmill trials run **back to back as one continuous eight-minute recording** —\n  the speed was stepped up without a pause. See [Coverage](#coverage).\n\n### Ground-truth provenance\n\n**Activity labels** are fully scripted: each source file holds exactly one trial at one known\ncondition, so `label`, `variant`, `condition` and `speed_kph` come from the protocol rather\nthan from annotation. Treadmill speeds are the **set** speeds; no measured speed exists, and\nthe outdoor preferred speed was never recorded.\n\n**Gait events** are reference truth measured by the insole, not model output. Initial contacts\n(IC) and final contacts (FC) were identified from the ground reaction force with an adaptive\nthreshold of 25 N plus the 10th percentile of the GRF\n([Pijnappels et al. 2001](https://doi.org/10.1016/S0966-6362(01)00110-2)), then ","encoding":"utf8","key":"README.md","name":"README.md","size":16879,"truncated":true}],"sourceObjectKey":"harmonized/alert-aracari.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"josefheidler/har_gait_adults_2023-lendt\")\nprint(ds)","starterSamplePath":"harmonized/alert-aracari.parquet","totalObjects":24},"summary":"Thigh-worn accelerometry with insole-derived gait events, dataset C of the TWAGA gait pipeline by Claas Lendt and colleagues (University of Regensburg and German Sport University…","title":"Thigh-Worn Accelerometry and Gait Event Detection: Axivity AX6 with loadsol Force Insole Ground Truth in 21 Adults (Lendt, Regensburg)","updatedAt":"2026-11-22T04:03:16.942Z","visibility":"public","websiteUrl":"https://doi.org/10.5281/zenodo.17629131"}}