FUTURE, blocked by #223: Combine eye tracking, EDA and EEG streams with flight data
Los mantenedores suelen responder en 3 días
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 5/5
- Tiempo estimado
- Más de una semana
- Aptitud para principiantes
- 1/100
- Tipo de issue
- Nueva funcionalidad
- Claridad
- Necesita aclaración
- Estado de actividad
- Activo
- Stack tecnológico
- rust
- Área
- data-engineering
Línea de trabajo
Do not start this work: the issue explicitly records future work blocked by #223 and says not to build or design it yet. Read docs/client_meeting_notes.md for the client context; the open decisions include aligning sensor streams, choosing a join key, and deciding how physiological features may be used. Work can begin only after the stated blocker is resolved and the client questions are answered.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
FUTURE WORK. DO NOT START. This is blocked until a good working real-time model exists (#223, which needs the batch model from #216, targets from #213 and the data from #228 and #229). Nothing here should be built, designed in detail or used to change the telemetry format before then. It exists only to record what the client said so it is not lost.
Blocked by: #223
Is your feature request related to a problem? Please describe.
The client wants flight data, physiological data and (eventually) demographics combined before clustering is automated. Today inference/ only knows the flight telemetry. The client records three physiological sensors in iMotions: eye tracking, electrodermal activity (EDA) and EEG. They are stored separately from the flight data and the demographics.
Describe the solution you'd like
Nothing to build yet. This issue records the future work and what blocks it, so the telemetry design does not rule it out.
- Decide how streams recorded at different rates are aligned. As transcribed, the sample rates are: simulator about 90 Hz, EEG 256 Hz, EDA 128 Hz, eye tracking 51 Hz. These are unconfirmed, and the Prepar3D export we have is 1 Hz. iMotions synchronizes the timestamps; the client is not sure a common rate exists for clustering.
- Decide the join key, probably the timestamp plus
pilot_idandflight_id(#211). - Keep physiological features out of the first clustering (flight data alone is the starting point, per the client), and decide later whether they form groups or only interpret them (compare ADR 0001 for pilot metadata).
Describe alternatives you've considered
Run the clustering on the iMotions computer (#223), where all streams are already synchronized, and read the physiological data from there.
Additional context
Open questions for the client:
- Will we ever see the physiological data? The client said raw data is large and sampled at separate rates, so it is hard to share. For now the answer is "for starting the work, no".
- Can instruction timestamps (the standardized in-flight instructions logged in iMotions) be exported on their own? They would give targets (#213) and leg boundaries (#229) without the physiological data. That, and later a model that detects the instruction automatically, is the most valuable piece.
Notes in docs/client_meeting_notes.md.
- Lenguaje dominante
- Python
- Estrellas
- 4
- Forks
- 8
- Merge medio
- 3 d 6 h
- PR fusionados (30 d)
- 12
Preparar el entorno
- Sin Dockerfile ni archivo de Docker Compose
- Tiene una plantilla de pull request
- Leer la guía de contribución
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de oss-slu/PilotDataSynchronization
-
Connect TCP with an invalid address is silent in the event logPosiblemente ocupada @PRINCEKK122 la tomó hace 9 días. Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 77/100
oss-slu/PilotDataSynchronization#241 ·
Los mantenedores suelen responder en 3 días
-
cluster_pilots.py shows a traceback for a bad --k and leaves outputs when --truth is invalidAbiertoarea:ml bug python
Dificultad 2/5 1-3 horas Aptitud para principiantes 83/100
oss-slu/PilotDataSynchronization#232 ·
Los mantenedores suelen responder en 3 días
-
area:docs area:xplane-plugin documentation ready-for-human
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
oss-slu/PilotDataSynchronization#194 · 1 comentario ·
Los mantenedores suelen responder en 3 días
-
Live performance groups: relay → Mirror → Python sidecarPosiblemente ocupada @Phlabry la tomó hace 8 días. Abiertoarea:ml area:relay
oss-slu/PilotDataSynchronization#245 · 1 comentario · 2 asignados ·
Los mantenedores suelen responder en 3 días
-
Relay rejects host names, so a changing iMotions IP can't be entered as a namePosiblemente ocupada Un pull request vinculado a esta issue está abierto o ya se fusionó. Abiertoarea:relay enhancement needs-triage rust
Dificultad 3/5 1-2 días Aptitud para principiantes 48/100
oss-slu/PilotDataSynchronization#240 ·
Los mantenedores suelen responder en 3 días
Todos los issues de oss-slu/PilotDataSynchronization
Issues similares
-
difficulty:2 enhancement good first issue
Dificultad 2/5 1-3 horas Aptitud para principiantes 85/100
MakazhanAlpamys/Soup#2309 ·
Los mantenedores suelen responder en 1 día
-
TAPVid-3D: per_trajectory and local_neighborhood scaling always score 0 in evaluate_model.pyAbierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 85/100
google-deepmind/tapnet#173 ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 70/100
-
change-description-authoring: jdk-33173-audit check 4 grades the hunk translation by its verbAbierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 65/100
Netcracker/qubership-ai-packages#203 ·
Los mantenedores suelen responder en 1 día
-
PAC Wording
Dificultad 1/5 Menos de una hora Aptitud para principiantes 72/100
Los mantenedores suelen responder en 1 día