# CaGeo: CAnonical Geospatial features
In this repository we want to collect and implement methods to extract
from a set of raw GPS coordinates features that enrich the dataset,
but which, simultaneously also allow dimensionality reduction.
## Features:
### Point Features
- Speed: AVG, STD, MIN, MAX
- Acceleration: AVG, STD, MIN, MAX
- angle/direction: atan2 == Bearing: angle between the magnetic north and an object ??
### Aggregate features
- Turning Angle: AVG, STD, MIN, MAX. π»πΆπ
= |ππ|/π·ππ π‘ππππ Pc is the collection of gps points at which a user changes
his/her heading direction exceeding a certain threshold (Hc), and |ππ | represents the number of elements in Pc
- Traveled Distance: SUM
- Stop Rate: ππ
= |ππ |/π·ππ π‘ππππ Ps is the collection of point with velocity smaller than a certain threshold
- Velocity Change Rate: foreach point π1. ππ
ππ‘π = |π2 β π1|/π1; then ππΆπ
= |ππ£|/π·ππ π‘ππππ where ππ£ ={ππ|ππ β π, ππ . ππ
ππ‘π > ππ }
- FFT?
- duration of movement?
- traveled path?
- displacement?
- Bearing rate: B_rate(i+1) = (Bi+1 β Bi)/βt
- Rate of bearing rate: Br_rate(i+1) = (Brate(i+1) β Brate(i))/βt
### Derivate features
- sinuosity ?
- distance from POI
## References:
- A survey and comparison of trajectory classification methods
- Understanding mobility based on GPS data
- Revealing the physics of movement: comparing the similarity of movement characteristics of different types of moving objects
- Predicting Transportation Modes of GPS Trajectories using Feature Engineering and Noise Removal
- Determination transportation mode on mobile phones
## Note
Per le distanze vedere Intelligent Trajectory Classification for Improved Movement Prediction
In "Identifying Different Transportation Modes from Trajectory Data Using Tree-Based Ensamble Classifier": ci sono varie misure globali
Raw data
{
"_id": null,
"home_page": "https://github.com/USERNAME/project",
"name": "CaGeo",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "keyword1 keyword2 keyword3",
"author": "Cristiano Landi",
"author_email": "cri98li@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/09/06/75fb4bc1f3c547bf04f05ca9892499761b98b0d674a177cda089dbc5d58b/CaGeo-0.1.0.tar.gz",
"platform": null,
"description": "# CaGeo: CAnonical Geospatial features\n\nIn this repository we want to collect and implement methods to extract \nfrom a set of raw GPS coordinates features that enrich the dataset, \nbut which, simultaneously also allow dimensionality reduction.\n\n## Features:\n\n### Point Features\n- Speed: AVG, STD, MIN, MAX\n- Acceleration: AVG, STD, MIN, MAX\n- angle/direction: atan2 == Bearing: angle between the magnetic north and an object ??\n\n### Aggregate features\n- Turning Angle: AVG, STD, MIN, MAX. \ud835\udc3b\ud835\udc36\ud835\udc45 = |\ud835\udc43\ud835\udc50|/\ud835\udc37\ud835\udc56\ud835\udc60\ud835\udc61\ud835\udc4e\ud835\udc5b\ud835\udc50\ud835\udc52 Pc is the collection of gps points at which a user changes \n his/her heading direction exceeding a certain threshold (Hc), and |\ud835\udc43\ud835\udc50 | represents the number of elements in Pc\n- Traveled Distance: SUM\n- Stop Rate: \ud835\udc46\ud835\udc45 = |\ud835\udc43\ud835\udc60|/\ud835\udc37\ud835\udc56\ud835\udc60\ud835\udc61\ud835\udc4e\ud835\udc5b\ud835\udc50\ud835\udc52 Ps is the collection of point with velocity smaller than a certain threshold\n- Velocity Change Rate: foreach point \ud835\udc5d1. \ud835\udc49\ud835\udc45\ud835\udc4e\ud835\udc61\ud835\udc52 = |\ud835\udc492 \u2212 \ud835\udc491|/\ud835\udc491; then \ud835\udc49\ud835\udc36\ud835\udc45 = |\ud835\udc43\ud835\udc63|/\ud835\udc37\ud835\udc56\ud835\udc60\ud835\udc61\ud835\udc4e\ud835\udc5b\ud835\udc50\ud835\udc52 where \ud835\udc43\ud835\udc63 ={\ud835\udc5d\ud835\udc56|\ud835\udc5d\ud835\udc56 \u2208 \ud835\udc43, \ud835\udc5d\ud835\udc56 . \ud835\udc49\ud835\udc45\ud835\udc4e\ud835\udc61\ud835\udc52 > \ud835\udc49\ud835\udc5f }\n- FFT?\n- duration of movement?\n- traveled path?\n- displacement?\n- Bearing rate: B_rate(i+1) = (Bi+1 \u2212 Bi)/\u2206t\n- Rate of bearing rate: Br_rate(i+1) = (Brate(i+1) \u2212 Brate(i))/\u2206t\n\n### Derivate features\n- sinuosity ?\n- distance from POI\n\n## References:\n- A survey and comparison of trajectory classification methods\n- Understanding mobility based on GPS data\n- Revealing the physics of movement: comparing the similarity of movement characteristics of different types of moving objects\n- Predicting Transportation Modes of GPS Trajectories using Feature Engineering and Noise Removal\n- Determination transportation mode on mobile phones \n\n\n\n## Note\nPer le distanze vedere Intelligent Trajectory Classification for Improved Movement Prediction\n\nIn \"Identifying Different Transportation Modes from Trajectory Data Using Tree-Based Ensamble Classifier\": ci sono varie misure globali\n",
"bugtrack_url": null,
"license": "BSD-Clause-2",
"summary": "Package description",
"version": "0.1.0",
"project_urls": {
"Homepage": "https://github.com/USERNAME/project"
},
"split_keywords": [
"keyword1",
"keyword2",
"keyword3"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "090675fb4bc1f3c547bf04f05ca9892499761b98b0d674a177cda089dbc5d58b",
"md5": "5a132673d07968ad73bed5ebcc1bca24",
"sha256": "57bf1c5828ff4c9afdd57fdb2873848a440f8a3daf556472d48508e40738e0f7"
},
"downloads": -1,
"filename": "CaGeo-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "5a132673d07968ad73bed5ebcc1bca24",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 6483,
"upload_time": "2024-07-01T09:15:00",
"upload_time_iso_8601": "2024-07-01T09:15:00.673281Z",
"url": "https://files.pythonhosted.org/packages/09/06/75fb4bc1f3c547bf04f05ca9892499761b98b0d674a177cda089dbc5d58b/CaGeo-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-01 09:15:00",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "USERNAME",
"github_project": "project",
"github_not_found": true,
"lcname": "cageo"
}
JSON
