Objective : detect the start and stop of freezing of gait and types of FOG events: Start Hesitation, Turn, and Walking.
\n\n\n\n- The competition dataset includes time-series data from 3-D accelerometer on subjects lower-back.
\n- The data series include three dataset, collected under distinct circumstances.
\n- The tDCS FOG (tdcsfog) : Collected in the lab. Subjects completed a FOG-provoking protcol.
- The DeFOG (defog) : Collected in the subject's home. Subject completed a FOG-provoking protcol.
- The Daily Living (daily) : Comprising one week of continuous 24/7 recordings from **sixty-five** subjects. Forty-five subjects exhibit FOG symptoms (series in the defog dataset), while the other twenty subjects exhibit no FOG symptoms (no series).
- The tdcsfog and defog dataset include annotation by expert reviewers.
\n- The daily dataset are *unannotated*. This dataset may be useful for modeling unsupervised or semi-supervised learning.
","metadata":{}},{"cell_type":"markdown","source":"# Train data\n\ndefog dataset but lack event-type annotations. The fields present in these series vary by folder.Time An integer timestep. Series from the tdcsfog dataset are recorded at 128Hz (128 timesteps per second), while series from the defog and daily series are recorded at 100Hz (100 timesteps per second).AccV, AccML, and AccAP Acceleration from a lower-back sensor on three axes: V - vertical, ML - mediolateral, AP - anteroposterior. Data is in units of m/s^2 for tdcsfog/ and g for defog/ and notype/.StartHesitation, Turn, Walking Indicator variables for the occurrence of each of the event types.Event Indicator variable for the occurrence of any FOG-type event. Present only in the notype series, which lack type-level annotations.Valid There were cases during the video annotation that were hard for the annotator to decide if there was an Akinetic (i.e., essentially no movement) FoG or the subject stopped voluntarily. Only event annotations where the series is marked true should be considered as unambiguous.Task Series were only annotated where this value is true. Portions marked false should be considered unannotated.tdcsfog_metadata.csv Identifies each series in the tdcsfog dataset by a unique Subject, Visit, Test, Medication condition.
Visit Lab visits consist of a baseline assessment, two post-treatment assessments for different treatment stages, and one follow-up assessment.Test Which of three test types was performed, with 3 the most challenging.Medication Subjects may have been either off or on anti-parkinsonian medication during the recording.defog dataset but lack event-type annotations. The fields present in these series vary by folder.Time An integer timestep. Series from the tdcsfog dataset are recorded at 128Hz (128 timesteps per second), while series from the defog and daily series are recorded at 100Hz (100 timesteps per second).AccV, AccML, and AccAP Acceleration from a lower-back sensor on three axes: V - vertical, ML - mediolateral, AP - anteroposterior. Data is in units of m/s^2 for tdcsfog/ and g for defog/ and notype/.StartHesitation, Turn, Walking Indicator variables for the occurrence of each of the event types.Event Indicator variable for the occurrence of any FOG-type event. Present only in the notype series, which lack type-level annotations.Valid There were cases during the video annotation that were hard for the annotator to decide if there was an Akinetic (i.e., essentially no movement) FoG or the subject stopped voluntarily. Only event annotations where the series is marked true should be considered as unambiguous.Task Series were only annotated where this value is true. Portions marked false should be considered unannotated.defog_metadata.csv Identifies each series in the defog dataset by a unique Subject, Visit, Medication condition.
Visit Lab visits consist of a baseline assessment, two post-treatment assessments for different treatment stages, and one follow-up assessment.Medication Subjects may have been either off or on anti-parkinsonian medication during the recording.subjects.csv Metadata for each Subject in the study, including their Age and Sex as well as:
Visit Only available for subjects in the daily and defog datasets.YearsSinceDx Years since Parkinson's diagnosis.UPDRSIIIOn/UPDRSIIIOff Unified Parkinson's Disease Rating Scale score during on/off medication respectively.NFOGQ Self-report FoG questionnaire score. See: tasks.csv Task metadata for series in the defog dataset. (Not relevant for the series in the fog or daily datasets.)
Id The data series where the task was measured.Begin Time (s) the task began.End Time (s) the task ended.Task One of seven tasks types in the DeFOG protocol, described on this page.events.csv Metadata for each FoG event in all data series. The event times agree with the labels in the data series.
\nId The data series the event occured in.Init Time (s) the event began.Completion Time (s) the event ended.Type Whether StartHesitation, Turn, or Walking.Kinetic Whether the event was kinetic (1) and involved movement, or akinetic (0) and static.