TrafficBDE

Traffic Status Prediction

https://github.com/okgreece/trafficbde

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
○
codemeta.json file
○
.zenodo.json file
✓
DOI references
Found 3 DOI reference(s) in README
✓
Academic publication links
Links to: zenodo.org
○
Committers with academic emails
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (16.2%) to scientific vocabulary

Keywords

big-data-europe neural-networks thessaloniki traffic-status-prediction

Last synced: 11 months ago · JSON representation

Repository

Traffic Status Prediction

Basic Info

Host: GitHub
Owner: okgreece
License: gpl-2.0
Language: R
Default Branch: master
Homepage: http://trafficstatusprediction.imet.gr
Size: 730 KB

Statistics

Stars: 1
Watchers: 5
Forks: 4
Open Issues: 2
Releases: 0

Topics

big-data-europe neural-networks thessaloniki traffic-status-prediction

Created about 9 years ago · Last pushed about 4 years ago

Metadata Files

Readme License

TrafficBDE

Aikaterini Chatzopoulou July 27, 2017

$CRAN\_Status\_Badge$

Intoduction

This package was created in order to enable the creation of a neural network model, for the needs of a European project. “TrafficBDE” includes functions for properly formulating the data, training the neural network and predicted the wanted variable. This document introduces you to TrafficBDE’s basic set of tools.

The user should use only the loadData and the kStepsForward functions. The first one to load the historical data and the second for the computation of the predicted value.

Install Package

In order to install TrafficBDE, you should use the following code.

install.packages("devtools")
devtools::install_github("okgreece/TrafficBDE")

Input

The input dataset of the main function could be a link, a csv, an excel file. There are different parameters that a user could specify and interact with the results. The parameters: “path”, “Link_id”, “direction”, “datetime”, “predict” and “steps” should be defined by the user, to form the dataset. Then an automated process formulates the data in order to provide the prediction of the wanted variable for the desired time and road.

| Input | Description | | --------- | ------------------------------------------------------------------------------------------ | | path | The path containing the historical data | | Link_id | The Link_id of the road | | dimension | The dimension of the road | | datetime | The date time for the pediction. The format of the datetime should be ‘%Y-%m-%d %H:%M:%S’ | | predict | The argument to be predicted, appropriate values: “Mean_speed”, “Entries”, “Stdev_speed” | | steps | How many steps forward the prediction will be |

A sort description about the inputs.

Output

The output of this process is a matrix with the predicted and real values and the RMSE. The rows are equal to the steps.

Examples

Simple examples the kStepsForward function are provided, in order for the user to understand the use and how to deal with these function.

The sample of the dataset that is being used is available in TrafficBDE package and represents the traffic fload of the road with Link_id: “163204843”, for January 2017.

The first example provides, in one step, the prediction of the Mean speed at 14.00 on 27 Jan. 2017

``` r library(TrafficBDE) Data <- X163204843_1

kStepsForward(Data = Data, Linkid = "163204843", direction = "1", datetime = "2017-01-27 14:00:00", predict = "Meanspeed", steps = 1) ```

## Training...

## Loading required package: lattice

## Loading required package: ggplot2

## + Fold01: layer1=4, layer2=3, layer3=4 
## - Fold01: layer1=4, layer2=3, layer3=4 
## + Fold01: layer1=5, layer2=3, layer3=4 
## - Fold01: layer1=5, layer2=3, layer3=4 
## + Fold01: layer1=4, layer2=4, layer3=4 
## - Fold01: layer1=4, layer2=4, layer3=4 
## + Fold01: layer1=5, layer2=4, layer3=4 
## - Fold01: layer1=5, layer2=4, layer3=4 
## + Fold02: layer1=4, layer2=3, layer3=4 
## - Fold02: layer1=4, layer2=3, layer3=4 
## + Fold02: layer1=5, layer2=3, layer3=4 
## - Fold02: layer1=5, layer2=3, layer3=4 
## + Fold02: layer1=4, layer2=4, layer3=4 
## - Fold02: layer1=4, layer2=4, layer3=4 
## + Fold02: layer1=5, layer2=4, layer3=4 
## - Fold02: layer1=5, layer2=4, layer3=4 
## + Fold03: layer1=4, layer2=3, layer3=4 
## - Fold03: layer1=4, layer2=3, layer3=4 
## + Fold03: layer1=5, layer2=3, layer3=4 
## - Fold03: layer1=5, layer2=3, layer3=4 
## + Fold03: layer1=4, layer2=4, layer3=4 
## - Fold03: layer1=4, layer2=4, layer3=4 
## + Fold03: layer1=5, layer2=4, layer3=4 
## - Fold03: layer1=5, layer2=4, layer3=4 
## + Fold04: layer1=4, layer2=3, layer3=4 
## - Fold04: layer1=4, layer2=3, layer3=4 
## + Fold04: layer1=5, layer2=3, layer3=4 
## - Fold04: layer1=5, layer2=3, layer3=4 
## + Fold04: layer1=4, layer2=4, layer3=4 
## - Fold04: layer1=4, layer2=4, layer3=4 
## + Fold04: layer1=5, layer2=4, layer3=4 
## - Fold04: layer1=5, layer2=4, layer3=4 
## + Fold05: layer1=4, layer2=3, layer3=4 
## - Fold05: layer1=4, layer2=3, layer3=4 
## + Fold05: layer1=5, layer2=3, layer3=4 
## - Fold05: layer1=5, layer2=3, layer3=4 
## + Fold05: layer1=4, layer2=4, layer3=4 
## - Fold05: layer1=4, layer2=4, layer3=4 
## + Fold05: layer1=5, layer2=4, layer3=4 
## - Fold05: layer1=5, layer2=4, layer3=4 
## + Fold06: layer1=4, layer2=3, layer3=4 
## - Fold06: layer1=4, layer2=3, layer3=4 
## + Fold06: layer1=5, layer2=3, layer3=4 
## - Fold06: layer1=5, layer2=3, layer3=4 
## + Fold06: layer1=4, layer2=4, layer3=4 
## - Fold06: layer1=4, layer2=4, layer3=4 
## + Fold06: layer1=5, layer2=4, layer3=4 
## - Fold06: layer1=5, layer2=4, layer3=4 
## + Fold07: layer1=4, layer2=3, layer3=4 
## - Fold07: layer1=4, layer2=3, layer3=4 
## + Fold07: layer1=5, layer2=3, layer3=4 
## - Fold07: layer1=5, layer2=3, layer3=4 
## + Fold07: layer1=4, layer2=4, layer3=4 
## - Fold07: layer1=4, layer2=4, layer3=4 
## + Fold07: layer1=5, layer2=4, layer3=4 
## - Fold07: layer1=5, layer2=4, layer3=4 
## + Fold08: layer1=4, layer2=3, layer3=4 
## - Fold08: layer1=4, layer2=3, layer3=4 
## + Fold08: layer1=5, layer2=3, layer3=4 
## - Fold08: layer1=5, layer2=3, layer3=4 
## + Fold08: layer1=4, layer2=4, layer3=4 
## - Fold08: layer1=4, layer2=4, layer3=4 
## + Fold08: layer1=5, layer2=4, layer3=4 
## - Fold08: layer1=5, layer2=4, layer3=4 
## + Fold09: layer1=4, layer2=3, layer3=4 
## - Fold09: layer1=4, layer2=3, layer3=4 
## + Fold09: layer1=5, layer2=3, layer3=4 
## - Fold09: layer1=5, layer2=3, layer3=4 
## + Fold09: layer1=4, layer2=4, layer3=4 
## - Fold09: layer1=4, layer2=4, layer3=4 
## + Fold09: layer1=5, layer2=4, layer3=4 
## - Fold09: layer1=5, layer2=4, layer3=4 
## + Fold10: layer1=4, layer2=3, layer3=4 
## - Fold10: layer1=4, layer2=3, layer3=4 
## + Fold10: layer1=5, layer2=3, layer3=4 
## - Fold10: layer1=5, layer2=3, layer3=4 
## + Fold10: layer1=4, layer2=4, layer3=4 
## - Fold10: layer1=4, layer2=4, layer3=4 
## + Fold10: layer1=5, layer2=4, layer3=4 
## - Fold10: layer1=5, layer2=4, layer3=4 
## Aggregating results
## Selecting tuning parameters
## Fitting layer1 = 4, layer2 = 4, layer3 = 4 on full training set
## Training Completed.
## 
## Time taken for training:  2.574222
## Predicting Mean_speed for the Next Quarter...

##                     Predicted Real Value     RMSE
## 2017-01-27 14:00:00  39.36151         29 10.36151

The second example provides, in one step, the prediction of the Entries at 20.00 on 15 Jan. 2017

## Training...
## + Fold01: layer1=4, layer2=3, layer3=4 
## - Fold01: layer1=4, layer2=3, layer3=4 
## + Fold01: layer1=5, layer2=3, layer3=4 
## - Fold01: layer1=5, layer2=3, layer3=4 
## + Fold01: layer1=4, layer2=4, layer3=4 
## - Fold01: layer1=4, layer2=4, layer3=4 
## + Fold01: layer1=5, layer2=4, layer3=4 
## - Fold01: layer1=5, layer2=4, layer3=4 
## + Fold02: layer1=4, layer2=3, layer3=4 
## - Fold02: layer1=4, layer2=3, layer3=4 
## + Fold02: layer1=5, layer2=3, layer3=4 
## - Fold02: layer1=5, layer2=3, layer3=4 
## + Fold02: layer1=4, layer2=4, layer3=4 
## - Fold02: layer1=4, layer2=4, layer3=4 
## + Fold02: layer1=5, layer2=4, layer3=4 
## - Fold02: layer1=5, layer2=4, layer3=4 
## + Fold03: layer1=4, layer2=3, layer3=4 
## - Fold03: layer1=4, layer2=3, layer3=4 
## + Fold03: layer1=5, layer2=3, layer3=4 
## - Fold03: layer1=5, layer2=3, layer3=4 
## + Fold03: layer1=4, layer2=4, layer3=4 
## - Fold03: layer1=4, layer2=4, layer3=4 
## + Fold03: layer1=5, layer2=4, layer3=4 
## - Fold03: layer1=5, layer2=4, layer3=4 
## + Fold04: layer1=4, layer2=3, layer3=4 
## - Fold04: layer1=4, layer2=3, layer3=4 
## + Fold04: layer1=5, layer2=3, layer3=4 
## - Fold04: layer1=5, layer2=3, layer3=4 
## + Fold04: layer1=4, layer2=4, layer3=4 
## - Fold04: layer1=4, layer2=4, layer3=4 
## + Fold04: layer1=5, layer2=4, layer3=4 
## - Fold04: layer1=5, layer2=4, layer3=4 
## + Fold05: layer1=4, layer2=3, layer3=4 
## - Fold05: layer1=4, layer2=3, layer3=4 
## + Fold05: layer1=5, layer2=3, layer3=4 
## - Fold05: layer1=5, layer2=3, layer3=4 
## + Fold05: layer1=4, layer2=4, layer3=4 
## - Fold05: layer1=4, layer2=4, layer3=4 
## + Fold05: layer1=5, layer2=4, layer3=4 
## - Fold05: layer1=5, layer2=4, layer3=4 
## + Fold06: layer1=4, layer2=3, layer3=4 
## - Fold06: layer1=4, layer2=3, layer3=4 
## + Fold06: layer1=5, layer2=3, layer3=4 
## - Fold06: layer1=5, layer2=3, layer3=4 
## + Fold06: layer1=4, layer2=4, layer3=4 
## - Fold06: layer1=4, layer2=4, layer3=4 
## + Fold06: layer1=5, layer2=4, layer3=4 
## - Fold06: layer1=5, layer2=4, layer3=4 
## + Fold07: layer1=4, layer2=3, layer3=4 
## - Fold07: layer1=4, layer2=3, layer3=4 
## + Fold07: layer1=5, layer2=3, layer3=4 
## - Fold07: layer1=5, layer2=3, layer3=4 
## + Fold07: layer1=4, layer2=4, layer3=4 
## - Fold07: layer1=4, layer2=4, layer3=4 
## + Fold07: layer1=5, layer2=4, layer3=4 
## - Fold07: layer1=5, layer2=4, layer3=4 
## + Fold08: layer1=4, layer2=3, layer3=4 
## - Fold08: layer1=4, layer2=3, layer3=4 
## + Fold08: layer1=5, layer2=3, layer3=4 
## - Fold08: layer1=5, layer2=3, layer3=4 
## + Fold08: layer1=4, layer2=4, layer3=4 
## - Fold08: layer1=4, layer2=4, layer3=4 
## + Fold08: layer1=5, layer2=4, layer3=4 
## - Fold08: layer1=5, layer2=4, layer3=4 
## + Fold09: layer1=4, layer2=3, layer3=4 
## - Fold09: layer1=4, layer2=3, layer3=4 
## + Fold09: layer1=5, layer2=3, layer3=4 
## - Fold09: layer1=5, layer2=3, layer3=4 
## + Fold09: layer1=4, layer2=4, layer3=4 
## - Fold09: layer1=4, layer2=4, layer3=4 
## + Fold09: layer1=5, layer2=4, layer3=4 
## - Fold09: layer1=5, layer2=4, layer3=4 
## + Fold10: layer1=4, layer2=3, layer3=4 
## - Fold10: layer1=4, layer2=3, layer3=4 
## + Fold10: layer1=5, layer2=3, layer3=4 
## - Fold10: layer1=5, layer2=3, layer3=4 
## + Fold10: layer1=4, layer2=4, layer3=4 
## - Fold10: layer1=4, layer2=4, layer3=4 
## + Fold10: layer1=5, layer2=4, layer3=4 
## - Fold10: layer1=5, layer2=4, layer3=4 
## Aggregating results
## Selecting tuning parameters
## Fitting layer1 = 4, layer2 = 3, layer3 = 4 on full training set
## Training Completed.
## 
## Time taken for training:  2.062091
## Predicting Entries for the Next Quarter...

##                     Predicted Real Value       RMSE
## 2017-01-15 20:00:00  1.012089          1 0.01208873

Github:

https://github.com/okgreece/TrafficBDE

Owner

Name: Open Knowledge Greece
Login: okgreece
Kind: organization
Email: info@okfn.gr
Location: Greece

Website: http://okfn.gr/
Repositories: 44
Profile: https://github.com/okgreece

GitHub Events

Total

Fork event: 1

Last Year

Fork event: 1

Committers

Last synced: over 3 years ago

All Time

Total Commits: 74
Total Committers: 3
Avg Commits per committer: 24.667
Development Distribution Score (DDS): 0.446

Top Committers

Name	Email	Commits
katerinachat	k**t@y**m	41
Kleanthis Koupidis	k**r@g**m	32
Kleanthis	k**0@u**m	1

Issues and Pull Requests

Last synced: 11 months ago

All Time

Total issues: 1
Total pull requests: 1
Average time to close issues: N/A
Average time to close pull requests: N/A
Total issue authors: 1
Total pull request authors: 1
Average comments per issue: 0.0
Average comments per pull request: 1.0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 0
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

kleanthisk10 (1)

Pull Request Authors

ptzenos (1)

Top Labels

Issue Labels

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- cran 256 last-month

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 3
Total maintainers: 1

cran.r-project.org: TrafficBDE

Traffic Predictions Using Neural Networks

Homepage: https://github.com/okgreece/TrafficBDE
Documentation: http://cran.r-project.org/web/packages/TrafficBDE/TrafficBDE.pdf
License: GPL-2 | file LICENSE
Latest release: 0.1.2
published over 3 years ago

Versions: 3
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 256 Last month

Rankings

Forks count: 14.9%

Dependent packages count: 29.8%

Stargazers count: 31.7%

Dependent repos count: 35.5%

Average: 39.7%

Downloads: 86.5%

Maintainers (1)

koupidis.okfgr@gmail.com

Last synced: 11 months ago

Dependencies

DESCRIPTION cran

DescriptiveStats.OBeu * imports
RCurl * imports
caret * imports
data.table * imports
dplyr * imports
lubridate * imports
stats * imports
zoo * imports
devtools * suggests
knitr * suggests
neuralnet * suggests
rmarkdown * suggests

TrafficBDE

Science Score: 23.0%

Keywords

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

TrafficBDE

Intoduction

Install Package

Input

Output

Examples

Github:

Owner

GitHub Events

Total

Last Year

Committers

All Time

Top Committers

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

cran.r-project.org: TrafficBDE

Rankings

Maintainers (1)

Dependencies