A Trust-Aware Modeling Framework for Jakarta Smart Transportation Open Data

Abstract

Smart transportation open data can support urban data-quality assessment and operational-risk screening, but it does not contain verified cybersecurity labels. This study develops a preliminary trust-aware modeling dataset for Jakarta Smart Transportation Open Data using nine Satu Data Jakarta sources covering TransJakarta operations and stops, road-speed observations, ATCS and CCTV locations, busway ITS corridors, traffic violations, congestion-risk points, and modal share. The sources are harmonized into a record-level schema comprising node_id, data_type, period, location, value, trust, output, source_dataset, and raw_label. Researcher-defined, source-specific rules assign trust scores from recency, completeness, active status, speed, violation intensity, and congestion-risk status. The resulting dataset contains 2,790 records: 2,508 trusted/non-malicious and 282 anomalous/untrusted proxy records. A separate baseline-repository ANN replication is reported only as a trust-threshold pipeline-consistency check, not as Jakarta model performance. The heuristic labels require expert review, sensor and incident logs, and controlled attack simulation before cybersecurity use. The contribution is therefore dataset construction and an exploratory trust-risk modeling framework rather than validated attack detection.

SIGMA: Symmetry-aware, Intelligent, Geometric, Multi-faced Adaptive Traffic Control for Reliable Intelligent Transportation Systems
Pratham Payra, Jagadish, Tanmay Sen +1
arXiv13 Oct 2026PreprintarXiv licenceFull textStatisticsarXiv
TriTrust: Risk-Aware Three-Factor Trust Fusion for Secure UAV Handover Admission
Mustafa Ghaleb, Zaafir Riaz, Radhwan A. Saleh +5
Mathematics20 Oct 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Machine learning and spatial regression approaches to estimating willingness to pay for ecosystem services in Jakarta and Taoyuan
Shafira Wuryandani, Yu-Pin Lin, Pei-Chen Lin +2
Ecosystem Services2 Oct 2026Peer-reviewedPublisher termsFull text3 citedEcology Environmental science & pollutionHAL
STREGO: A Scalable Implementation of a Trust-Region Framework for Noisy Bayesian Optimization
Youssef Diouane, Issmail El Hallaoui, Meisseme Kadri +1
arXiv9 Oct 2026PreprintCC BY-NC-SA 4.0Full textOptimisation & controlarXiv
PENGARUH METODE PEMBELAJARAN DAN KEMAMPUAN AWAL TERHADAP HASIL BELAJAR MATEMATIKA (Studi Eksperimen di MAN 3 Jakarta )
Farida Hanun
Widyariset27 Aug 2026Peer-reviewedCC BY-SAFull text5 citedGeneral mathematicsOpenAlex

Cite

BibTeX RIS

BibTeX

@article{widyarto2026trustaware,
  title = {{A Trust-Aware Modeling Framework for Jakarta Smart Transportation Open Data}},
  author = {Setyawan Widyarto and Riki and Sulaiman Said Omar Al-Hinai and Dur Soomro},
  journal = {Journal of Information Systems and Informatics},
  year = {2026},
  month = oct,
  doi = {10.63158/journalisi.v8i5.1785},
  url = {https://doi.org/10.63158/journalisi.v8i5.1785},
  note = {CC BY},
}

RIS

TY  - JOUR
TI  - A Trust-Aware Modeling Framework for Jakarta Smart Transportation Open Data
AU  - Setyawan Widyarto
AU  - Riki
AU  - Sulaiman Said Omar Al-Hinai
AU  - Dur Soomro
PY  - 2026
DA  - 2026/10/24
JO  - Journal of Information Systems and Informatics
DO  - 10.63158/journalisi.v8i5.1785
UR  - https://doi.org/10.63158/journalisi.v8i5.1785
AB  - Smart transportation open data can support urban data-quality assessment and operational-risk screening, but it does not contain verified cybersecurity labels. This study develops a preliminary trust-aware modeling dataset for Jakarta Smart Transportation Open Data using nine Satu Data Jakarta sources covering TransJakarta operations and stops, road-speed observations, ATCS and CCTV locations, busway ITS corridors, traffic violations, congestion-risk points, and modal share. The sources are harmonized into a record-level schema comprising node_id, data_type, period, location, value, trust, output, source_dataset, and raw_label. Researcher-defined, source-specific rules assign trust scores from recency, completeness, active status, speed, violation intensity, and congestion-risk status. The resulting dataset contains 2,790 records: 2,508 trusted/non-malicious and 282 anomalous/untrusted proxy records. A separate baseline-repository ANN replication is reported only as a trust-threshold pipeline-consistency check, not as Jakarta model performance. The heuristic labels require expert review, sensor and incident logs, and controlled attack simulation before cybersecurity use. The contribution is therefore dataset construction and an exploratory trust-risk modeling framework rather than validated attack detection.
SN  - 2656-5935
SN  - 2656-4882
ER  -

Abstract

Related

Cite