bonndata catalog
Thumbnail for Implementation of the paper "SCANNER+: Neighborhood-based self-enrichment approach for traffic speed prediction"

Implementation of the paper "SCANNER+: Neighborhood-based self-enrichment approach for traffic speed prediction"

Open this dataset in the live repository

Important usage condition: Use and redistribution are governed by MIT. Review and comply with the license before using the data.
Persistent identifier
doi:10.60507/FK2/DRYP80
Published version
2.0
Publication date
2026-01-08
License
MIT

Description

In this repository, you can find the code to train and evaluate SCANNER+, a novel neighborhood-based self-enrichment approach for traffic speed prediction. SCANNER+ learns effective node representations in dynamic road traffic settings. This work extends SCANNER, which utilizes correlation-based pattern detection and a self-enrichment mechanism.

Creators

Keywords

Traffic speed prediction, Spatio-temporal enrichment

Files

Before downloading: Use and redistribution are governed by MIT. Review and comply with the license before using the data.
FileTypeBytesChecksum
stnorm.pytext/x-python2130MD5 504e2317ef971d65b290ab33cb6607dc
LICENSEtext/plain; charset=US-ASCII1063MD5 9166a54d6b45565ba0e1420c2de7fdf0
loader.pytext/x-python9823MD5 0bc47c5210de4b0479c71c968b9aadb9
config.pytext/x-python4979MD5 0389a89900e28058294d79ee957393cf
models.pytext/x-python11955MD5 c9ea92936a88e78c8e37215c261226da
.gitignoretext/plain3443MD5 be85f81e6cc8066629a0464226450c3c
main.pytext/x-python2900MD5 1d18549aaaf4c8b13ae9e2a6855f1099
metrics.pytext/x-python3706MD5 821a8b8c9d075a387d5c5901b31c4b84
trainer.pytext/x-python9761MD5 8527d7647042d0aa37a228828ca31c4c
requirements.txttext/plain324MD5 b8e3464bca1e99800beec8e671e19f91
correlations.pytext/x-python4196MD5 3dafcd83c5833accf319e6363b0521c4
README.mdtext/markdown4213MD5 e0d58f8633a84bea05fec828fc1e5f07
util.pytext/x-python366MD5 38ea4a944cc63023dbc079d1a8f428c6

Citation

Gounoue, Steve, 2026-01-08, Implementation of the paper "SCANNER+: Neighborhood-based self-enrichment approach for traffic speed prediction", doi:10.60507/FK2/DRYP80, V2.0

Additional Dataverse fields

Id573
Dataset Typedataset
Internal Version Number8
Latest Version Publishing StateDRAFT
Release Time2026-01-26T15:28:35Z
Create Time2026-01-26T08:35:09Z
Citation Date2026-01-08
File Access RequestTrue

Export metadata

Static metadata exports available for this published dataset version:

Complete Dataverse metadata

Citation Metadata

Title title
Implementation of the paper "SCANNER+: Neighborhood-based self-enrichment approach for traffic speed prediction"
Alternative URL alternativeURL
https://github.com/D-Stiv/SCANNER_plus/releases/tag/v1.0.0
Author author
  1. Author Name
    Gounoue, Steve
    Author Affiliation
    Data Science and Intelligent Systems Group (DSIS), University of Bonn
    Author Identifier Scheme
    ORCID
    Author Identifier
    Type Name
    authorIdentifier
    Multiple
    False
    Type Class
    primitive
    Value
    https://orcid.org/0009-0003-4580-3173
    Expandedvalue
    Person Name
    GOUNOUE GUIFFO, Steve Ludovic
    @id
    https://orcid.org/0009-0003-4580-3173
    Scheme
    ORCID
    @type
    https://schema.org/Person
Dataset Contact datasetContact
  1. Dataset Contact Name
    Gounoue, Steve
    Dataset Contact Affiliation
    Data Science and Intelligent Systems Group (DSIS), University of Bonn
    Dataset Contact Email
    steve.gounoue@cs.uni-bonn.de
Ds Description dsDescription
  1. Ds Description Value
    In this repository, you can find the code to train and evaluate SCANNER+, a novel neighborhood-based self-enrichment approach for traffic speed prediction. SCANNER+ learns effective node representations in dynamic road traffic settings. This work extends SCANNER, which utilizes correlation-based pattern detection and a self-enrichment mechanism.
Subject subject
  1. Computer and Information Science
  2. Engineering
Free Keyword freeKeyword
  1. Free Keyword Value
    Traffic speed prediction
  2. Free Keyword Value
    Spatio-temporal enrichment
Publication publication
  1. Publication Relation Type
    IsSupplementTo
    Publication Citation
    Steve Gounoue, Ran Yu, and Elena Demidova. 2026. SCANNER+: Neighborhood-based self-enrichment approach for traffic speed prediction. ACM Transactions on Spatial Algorithms and Systems
  2. Publication Relation Type
    References
    Publication Citation
    Steve Gounoue, Ran Yu, and Elena Demidova. 2023. SCANNER: A Spatio-temporal Correlation and Neighborhood-based Feature Enrichment for Traffic Prediction. In Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL '23). Association for Computing Machinery, New York, NY, USA, Article 103, 1–4.
    Publication IDType
    doi
    Publication IDNumber
    10.1145/3589132.3625653
    Publication URL
    https://doi.org/10.1145/3589132.3625653
Depositor depositor
Gounoue Guiffo, Steve
Date Of Deposit dateOfDeposit
2026-01-06
Related Material relatedMaterial
  1. SCANNER: A Spatio-temporal Correlation and Neighborhood-based Feature Enrichment for Traffic Prediction: https://github.com/D-Stiv/SCANNER

Software Metadata (CodeMeta v2.0)

Code Version codeVersion
v1.0.0
Development Status developmentStatus
Inactive
Code Repository codeRepository
  1. https://github.com/D-Stiv/SCANNER_plus
Programming Language programmingLanguage
  1. Python
Runtime Platform runtimePlatform
  1. Python 3.8.30
Operating System operatingSystem
  1. Any 64-bit OS supporting Python and PyTorch (e.g., Linux, macOS, Windows)
Software Requirements Item softwareRequirementsItem
  1. Software Requirements
    PyTorch 1.9.0+cu111
  2. Software Requirements
    NumPy 1.23.5
  3. Software Requirements
    Pandas 2.2.3
  4. Software Requirements
    Scikit-learn 1.6.1
  5. Software Requirements
    Scipy 1.13.1
Readme readme
https://github.com/D-Stiv/SCANNER_plus/blob/master/README.md

Expected crawler behaviour

Use a stable, truthful User-Agent with product/version and a working contact URL. Across all IP addresses and HTTP connections used by one crawler identity, allow no more than 5 requests in flight and wait at least 20 seconds between request starts. Crawl URLs listed in the catalog sitemap, including file pages and download URLs when they are published, use conditional requests, honor Retry-After, and apply exponential backoff after errors.

The welcome page may link to the interactive repository for human navigation. Automated clients must not treat that human link as a catalog crawl target.

Read the live machine-readable crawler policy before and during a crawl. Stop crawling when it reports CPU or memory utilization at or above 80% and 80% respectively.