CoChat

Design and Implementation of an ML and IoT Based Adaptive Traffic-Management System for Smart Cities

Open access

The DOI matches its Crossref record; 65 of the 67 references it cites were found in a registry or an index; none of the 7 sources its claims cite is checked for support yet.

Abstract

The rapid growth in the number of vehicles has led to traffic congestion, pollution, and delays in logistic transportation in metropolitan areas. IoT has been an emerging innovation, moving the universe towards automated processes and intelligent management systems. This is a critical contribution to automation and smart civilizations. Effective and reliable congestion management and traffic control help save many precious resources. An IoT-based ITM system set of sensors is embedded in automatic vehicles and intelligent devices to recognize, obtain, and transmit data. Machine learning (ML) is another technique to improve the transport system. The existing transport-management solutions encounter several challenges resulting in traffic congestion, delay, and a high fatality rate. This research work presents the design and implementation of an Adaptive Traffic-management system (ATM) based on ML and IoT. The design of the proposed system is based on three essential entities: vehicle, infrastructure, and events. The design utilizes various scenarios to cover all the possible issues of the transport system. The proposed ATM system also utilizes the machine-learning-based DBSCAN clustering method to detect any accidental anomaly. The proposed ATM model constantly updates traffic signal schedules depending on traffic volume and estimated movements from nearby crossings. It significantly lowers traveling time by gradually moving automobiles across green signals and decreases traffic congestion by generating a better transition. The experiment outcomes reveal that the proposed ATM system significantly outperformed the conventional traffic-management strategy and will be a frontrunner for transportation planning in smart-city-based transport systems. The proposed ATM solution minimizes vehicle waiting times and congestion, reduces road accidents, and improves the overall journey experience.

Overview

CoChat Summary

TL;DR

The paper designs and implements an ML- and IoT-based adaptive traffic-management (ATM) system for smart cities, using vehicle, infrastructure, and event entities, VANET/RSU communication, image processing, and DBSCAN-based accident detection. It reports MATLAB simulations with 100 vehicles on a 5000 m road across three LAV/Non-LAV scenarios, claiming better performance than conventional traffic management.

Key findings

  • The proposed ATM system uses a layered architecture and modules for vehicle location tracking, accident detection via accelerometer/ML, image processing, VANET communication, and ML-based traffic management; DBSCAN clustering is used to detect accidental anomalies.
  • Simulation setup: MATLAB simulator, 100 vehicles, 5000 m road, four moving directions (Channel 1: East to West; Channel 2: North to West; Channel 3: North to East; Channel 4: East to North), random model, inflow probability 0.58%, outflow probability 0.49%, and three scenarios: only LAVs, only Non-LAVs, and mixed LAVs/Non-LAVs.
  • Image-processing signal timing is reported as: if image match = 40%, green light for 90 s; if 40%–70%, green light for 60 s; if 70%–90%, green light for 30 s; if 90%–100%, red light for 90 s.
  • The paper claims the proposed ATM system outperforms conventional traffic management in packet delivery ratio, throughput, and time delay, and reduces vehicle waiting times, congestion, and road accidents, but no numerical values for these outcome comparisons are reported in the provided text.

Methods

  • Design: a four-layer ATM architecture (application, service, network, sensing) with three primary entities (vehicles, infrastructure, events), plus modules for vehicle location tracking, accident detection, vehicle image processing, VANET/RSU communication, and ML in ITM.
  • Data/sample: MATLAB simulation with 100 vehicles on a 5000 m road, four directional channels, random model, inflow probability 0.58%, outflow probability 0.49%, and three traffic scenarios (only LAVs, only Non-LAVs, mixed LAVs/Non-LAVs).
  • Analysis: DBSCAN clustering for accident anomaly detection; image processing using Canny edge detection and pixel-to-pixel matching for adaptive signal timing; a platoon-based mathematical model for traffic flow.

Limitations

  • Stated: future work will integrate energy-efficient systems and security into the proposed ATM system, and the system will be implemented in a real-time environment instead of the simulator with real-time traffic flow.
  • Evident: the evaluation is simulation-only, with assumptions that vehicles are fully equipped with wireless modules and that roadside units are positioned approximately 1.0 km apart; no real-world deployment or validation is reported.
  • Evident: the claimed improvements in packet delivery ratio, throughput, and time delay are not supported by numerical results in the provided text, and several performance claims remain qualitative.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/s22082908

Cites

65 of 65 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 The layered architecture of IoT.
Figure 1 The layered architecture of IoT.CC BY · PubMed Central
Figure 2 IoT application in ITM.
Figure 2 IoT application in ITM.CC BY · PubMed Central
Figure 3 Layered architecture of the proposed ATM model.
Figure 3 Layered architecture of the proposed ATM model.CC BY · PubMed Central
Figure 4 Vehicle Location Tracking in ITM.
Figure 4 Vehicle Location Tracking in ITM.CC BY · PubMed Central
Figure 5 Vehicle location tracking process in ITM (using DBSCAN Clustering method).
Figure 5 Vehicle location tracking process in ITM (using DBSCAN Clustering method).CC BY · PubMed Central
Figure 6 Traffic flow space vs. time (incoming and outgoing vehicles).
Figure 6 Traffic flow space vs. time (incoming and outgoing vehicles).CC BY · PubMed Central
Figure 7 System Design of proposed ITM.
Figure 7 System Design of proposed ITM.CC BY · PubMed Central
Figure 8 Vehicles moving on the freeway where fuel less fuel consumption, and average less travel time is generated by the travel report.
Figure 8 Vehicles moving on the freeway where fuel less fuel consumption, and average less travel time is generated by the travel report.CC BY · PubMed Central
Figure 9 Vehicle moving on the freeway (multilane), connected/linked and automated vehicle, and signals in 3 categories (red, green, and yellow).
Figure 9 Vehicle moving on the freeway (multilane), connected/linked and automated vehicle, and signals in 3 categories (red, green, and yellow).CC BY · PubMed Central
Figure 10 Vehicle moving on forward and backward over multiple lanes (traffic congestion).
Figure 10 Vehicle moving on forward and backward over multiple lanes (traffic congestion).CC BY · PubMed Central
Figure 11 Vehicle movement based on signals received from RSUs.
Figure 11 Vehicle movement based on signals received from RSUs.CC BY · PubMed Central
Figure 12 Simulation results for scenario 1 only with LAVs (From Figure 12a–h). (a) Traffic congestion; (b) space utilization; (c) traffic jam ratio; (d) time mean speed; (e) harmonic mean; (f) time means speed vs. space means speed; (g) scenario 1 results for average speed vs. traffic flow. (h) Scenario 1 results for average speed vs. traffic density.
Figure 12 Simulation results for scenario 1 only with LAVs (From Figure 12a–h). (a) Traffic congestion; (b) space utilization; (c) traffic jam ratio; (d) time mean speed; (e) harmonic mean; (f) time means speed vs. space means speed; (g) scenario 1 results for average speed vs. traffic flow. (h) Scenario 1 results for average speed vs. traffic density.CC BY · PubMed Central
Figure 13 Simulations results for scenario 2, no-LAVs vehicles (from Figure 13a–h). (a) Traffic congestion; (b) space utilization; (c) traffic jam ratio; (d) time mean speed; (e) harmonic mean; (f) simulation results for TMS vs. SMS during the whole time; (g) simulation results for scenario 2 average speed vs. traffic density; (h) simulation results for scenario 2 average speed vs. traffic flow.
Figure 13 Simulations results for scenario 2, no-LAVs vehicles (from Figure 13a–h). (a) Traffic congestion; (b) space utilization; (c) traffic jam ratio; (d) time mean speed; (e) harmonic mean; (f) simulation results for TMS vs. SMS during the whole time; (g) simulation results for scenario 2 average speed vs. traffic density; (h) simulation results for scenario 2 average speed vs. traffic flow.CC BY · PubMed Central
Figure 14 Scenario 3: Hybrid simulation (LAVs and no-LAVs) vehicles results. (a) Traffic congestion; (b) space utilization; (c) traffic jam ratio; (d) average speed vs. traffic flow results; (e) average speed vs. traffic density results.
Figure 14 Scenario 3: Hybrid simulation (LAVs and no-LAVs) vehicles results. (a) Traffic congestion; (b) space utilization; (c) traffic jam ratio; (d) average speed vs. traffic flow results; (e) average speed vs. traffic density results.CC BY · PubMed Central

Verification

Claims the paper makes

0 Valid · 3 Not valid · 7 Not checked · 24 Own results and interpretations

9 more claims

Create a free account to see all 34 claims and to verify the 1 reference still open.

See all claims — free account
  • Probably not a substantial claim. 18
  • It may state two separate claims as one. 6

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Self-check results appear here once an independent check has confirmed them.

Cited works that were retracted

Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.

1 of 1

Citations

Cites

1 retracted

Cited by

See all 206

Metadata

Authors
Lilhore, U. K., Imoize, A. L., Li, C.-T., Simaiya, S., Pani, S. K., Goyal, N., Kumar, A., & Lee, C.-C.
Affiliations
  • KIET Group of Institutions, NCR, Ghaziabad 201206, UP, India
  • University of Lagos (NG)
  • Tainan University of Technology (TW)
  • Chitkara University (IN)
  • Biju Patnaik University of Technology (IN)
  • Shri Vishwakarma Skill University (IN)
  • Panipat Institute of Engineering and Technology, Panipat 132102, Haryana, India
  • Fu Jen Catholic University (TW)
Corresponding author
  • Li, Chun-Ta
  • Lee, Cheng-Chi
Venue
Sensors
Publisher
MDPI AG
Published
2022-04-10
Volume
22
Issue
8
Pages
2908
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4223505602
Cited by
206
References
67
Citations by year
2026: 31 · 2025: 62 · 2024: 60 · 2023: 45 · 2022: 8
FWCI
17.62
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Deutscher Akademischer Austauschdienst (57473408)
  • Ministry of Science and Technology, Taiwan (MOST 110-2410-H-165-001-MY2)
  • Petroleum Technology Development Fund (57473408)
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
  • Social Sciences › Transportation › Traffic Prediction and Management Techniques
  • Physical Sciences › Engineering › Civil and Structural Engineering › Road Transport and Highway Systems
Keywords
adaptive traffic management, smart cities, Internet of Things, machine learning, DBSCAN, traffic signal control, traffic congestion, anomaly detection, vehicle waiting time, traffic volume estimation, intelligent transportation systems
MeSH terms
Accidents, Machine Learning, Automobiles, Cities, Transportation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.