The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index; none of the 9 sources its claims cite is checked for support yet.
A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning
Open accessAbstract
The notion of smart cities is being adapted globally to provide a better quality of living. A smart city's smart mobility component focuses on providing smooth and safe commuting for its residents and promotes eco-friendly and sustainable alternatives such as public transit (bus). Among several smart applications, a system that provides up-to-the-minute information like bus arrival, travel duration, schedule, etc., improves the reliability of public transit services. Still, this application needs live information on traffic flow, accidents, events, and the location of the buses. Most cities lack the infrastructure to provide these data. In this context, a bus arrival prediction model is proposed for forecasting the arrival time using limited data sets. The location data of public transit buses and spatial characteristics are used for the study. One of the routes of Tumakuru city service, Tumakuru, India, is selected and divided into two spatial patterns: sections with intersections and sections without intersections. The machine learning model XGBoost is modeled for both spatial patterns individually. A model to dynamically predict bus arrival time is developed using the preceding trip information and the machine learning model to estimate the arrival time at a downstream bus stop. The performance of models is compared based on the R-squared values of the predictions made, and the proposed model established superior results. It is suggested to predict bus arrival in the study area. The proposed model can also be extended to other similar cities with limited traffic-related infrastructure.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This paper proposes a hybrid bus arrival time estimation model for a Tumakuru, India bus route using only bus location data, combining XGBoost travel-time forecasts with preceding-trip information. The proposed model outperformed XGBoost alone on both spatial patterns, with higher R-squared values for sections with and without intersections.
Key findings
- The proposed model improved R-squared over XGBoost alone: 0.59 vs 0.40 for sections with intersections (SIS) and 0.80 vs 0.71 for normal sections (NS).
- For one sample trip on 11 March 2021 starting at 15:14:00, actual travel time was 1209 seconds; XGBoost predicted 1339 seconds and the proposed model predicted 1261 seconds. XGBoost had a mean section error of 30 seconds, while the proposed model had an average error of 18 seconds.
- Sections without intersections were more predictable by the machine learning model than sections with intersections, with x1 values of 0.71 and 0.40, respectively. Estimated intersection delays were 47, 45, 57, and 20 seconds for sections 2, 3, 5, and 7.
- Preceding trips within 30 minutes showed a positive correlation with current trip travel time. Computed weights were w1 = 0.45 and w2 = 0.55 for SIS, and w1 = 0.56 and w2 = 0.44 for NS.
Methods
- Data: location logs of Tumakuru city service buses from March 2021, including 600 trips on the Tumkur Bus Stand to Kyathasandra route, plus other routes sharing common sections. The route was divided into nine sections and classified into sections with intersections (SIS: 2, 3, 5, 7) and normal sections without intersections (NS: 1, 4, 6, 8, 9). Features included land use pattern, section length, day-of-week, trip start time, and section number.
- XGBoost regression was trained separately for SIS and NS using scikit-learn, with parameters including objective squared error, alpha 1.00, learning_rate 0.05, n_estimators 200, colsample_bytree 0.60, and max_depth 3.00.
- The Bus Arrival Time Estimation Model (BATEM) estimated arrival as current time plus adjusted travel time. Adjusted travel time was a weighted average of XGBoost forecasted travel time and preceding-trip travel time for NS, or dynamic travel time for SIS. Weights were derived from the XGBoost R-squared and the correlation between current and preceding trip travel times; preceding trips within 30 minutes were considered.
Limitations
- The paper states that the study area lacks live traffic flow, congestion, and incident data, and that only bus location data were available. It notes that up-to-the-minute traffic, incident, and delay information could further improve forecasting.
- The paper states that un-signalized intersections were not included in the study. It also notes that sections with intersections showed more variation and less predictability because signalized intersections operate in clearance mode with no bus priority.
- Evident from the text: the model was developed and evaluated on a single route in Tumakuru using 600 trips from March 2021, so generalizability to other routes or cities is suggested but not empirically tested in this paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 of 9 cited sources checked · 0 supported · 0 flagged
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The R-squared (x1) value indicates that the sections without intersections are more predictable by the machine learning model than those with intersections.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The preceding trip within 30 minutes to that of the current demonstrated a positive correlation, illustrating its usefulness in forecasting travel times.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 6. Conclusion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The length of sections with intersections is less than 800 meters.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The proposed model estimated the bus arrival time based on both machine learning model results and the preceding trip travel time and demonstrated better accuracy than the XGBoost model for both spatial patterns.”
- Also stated in: § 6. Conclusion · plain
“The proposed model exhibited better accuracy based on the R-squared values.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 6. Conclusion
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 6. Conclusion · plain
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“The intersections in Tumakuru city operate in clearance mode with no bus priority [32] [33].”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
What the sources say
- Not matchedcites [32]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [33]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Not matched
In the paper
“According to the previous study [24], the non-linear models are best suited for BTT prediction in the current study area.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 4.2. Extreme Gradient Boosting (XGBoost)
What the sources say
- Not matchedcites [24]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Not matched
- It may state two separate claims as one. 7
- The quote only partly states this claim. 1
- Probably not a substantial claim. 8
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is evident from the plot that the proposed model can recognize the dynamic changes in the traffic flow and estimate the travel time better as compared to the XGBoost model.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The actual travel time of the trip is 1209 seconds, the total duration predicted by XGBoost is 1339 seconds, and the proposed model is 1261.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The XGBoost predicted individual sections' travel time with a mean error of 30 seconds, whereas the proposed models' average error was 18 seconds.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The R-squared of the XGBoost model is 0.4 and 0.71.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In contrast, the R-squared of the proposed model is 0.59 and 0.80 for sections with and without intersections, respectively, demonstrating significant improvement in the predictions.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“The precision of the predictions mainly depends on the data sources available [13];”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 1. Introduction
What the sources say
- Not matchedcites [13]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“The average intersection delay for each intersection is estimated in [34].”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 5. Results and Discussion
What the sources say
- Not matchedcites [34]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“It is a widely used model to predict BTT [26][27] [28].”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 4.2. Extreme Gradient Boosting (XGBoost)
What the sources say
- Not matchedcites [26]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [27]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [28]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“Variability analysis of the travel times in the selected route (up and downstream) is presented in [25].The same procedure is followed to pre-process the data in the current article.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 4.1 Preprocessing
What the sources say
- Not matchedcites [25]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The raw location data are pre-processed to remove missing and erroneous entries and are transformed into aggregates at the bus stop level for further study.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 4.1 Preprocessing
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall, with the available limited datasets, the proposed model is a promising option for forecasting the bus arrival time.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 6. Conclusion
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Overall, it is concluded from the existing literature that there are no generic models for accurate BTAT prediction, and most of the solutions are location specific.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > 2. Literature review
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The proposed model can also be extended to other similar cities with limited traffic-related infrastructure.”
- Also stated in: § Actual XGBoost Proposed Model · plain
“And there are several similar cities with limited traffic infrastructure for which the proposed model can be extended.”
§ A Dynamic Model for Bus Arrival Time Estimation based on Spatial Patterns using Machine Learning > Abstract
Strength:plain· not yet calibratedTests✓ Asserted: passes✗ Checkable: fails✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- Also stated in: § Actual XGBoost Proposed Model · plain
The paper relies on this without support.
Most cities lack the infrastructure to provide live traffic flow, accident, event and bus location data.
“Most cities lack the infrastructure to provide these data.”
“Several cities lack the infrastructure to capture live traffic flow information across the entire network.”
The paper relies on this without support.
Installing the required traffic-monitoring infrastructure is economically not viable.
“Installing the required infrastructure is mammoth and economically not viable”
The paper relies on this without support.
The travel time between bus stops depends on factors such as land use patterns, signalized intersections, un-signalized intersections and section length.
“The travel time between bus stops depends on factors such as Land Use patterns (LUP), signalized intersections, un-signalized intersections, section length, etc.”
The paper relies on this without support.
The presence of signalized intersections has a major influence on travel time.
“The presence of signalized intersections has a major influence on travel time; hence the trip aggregates are split as sections (bus stop to bus stop) with and without intersections.”
The authors state this as an assumption.
The travel time of the preceding buses reflects the delays in the link.
“Hence, the preceding buses are considered probe vehicles, and the travel time of the preceding buses is assumed to reflect the delays in the link.”
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Scikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
A gradient boosting method to improve travel time prediction
Zhang, Y., & Haghani, A. E. (2015) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2015.02.019 · Cited by 874
Developing Smart Cities: An Integrated Framework
Joshi, S., Saxena, S., Godbole, T., & Shreya (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.07.258 · Cited by 319
Usefulness of Correlation AnalysisPreprint
Senthilnathan, S. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3416918 · Cited by 291
Smart mobility and public transport: Opportunities and challenges in rural and urban areas
Porru, S., Misso, F. E., Pani, F. E., & Repetto, C. (2019) · Journal of Traffic and Transportation Engineering (English Edition) · doi:10.1016/j.jtte.2019.10.002 · Cited by 260
IoT Based Intelligent Transportation System (IoT-ITS) for Global Perspective: A Case Study
Muthuramalingam, S., Bharathi, A., kumar, S. R., Gayathri, N., Sathiyaraj, R., & Balusamy, B. (2018) · Intelligent systems reference library · doi:10.1007/978-3-030-04203-5_13 · Cited by 167
Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes
Bai, C., Peng, Z., Lu, Q.-C., & Sun, J. (2015) · Computational Intelligence and Neuroscience · doi:10.1155/2015/432389 · Cited by 102
Dynamic Travel Time Prediction Models for Buses Using Only GPS Data
Fan, W. D., & Gurmu, Z. (2015) · International Journal of Transportation Science and Technology · doi:10.1016/s2046-0430(16)30168-x · Cited by 94
Intelligent Transportation System (ITS) for Smart-Cities using Mamdani Fuzzy Inference System
Iqbal, K., Khan, M. A., Abbas, S., Hasan, M. Z., & Fatima, A. (2018) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2018.090215 · Cited by 91
Flagged first, then by citations
Cited by
Sorted by citations
Spatio-Temporal Forecasting: A Survey of Data-Driven Models Using Exogenous Data
Berkani, S., Guermah, B., Zakroum, M., & Ghogho, M. (2023) · IEEE Access · doi:10.1109/access.2023.3282545 · Cited by 27
Berkani, S., Bahaj, A., Guermah, B., & Ghogho, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110161 · Cited by 4
Munadi, R., Ramadan, D. N., Sussi, Fitriyanti, N., & Nuha, H. H. (2026) · IoT · doi:10.3390/iot7010022 · Cited by 3
Public Transit Bus Travel Time Variability Analysis Using Limited Datasets: A Case Study
Prakash, A. B., Sumathi, R., & Sudhira, H. S. (2024) · Current Applied Science and Technology · doi:10.55003/cast.2024.257174 · Cited by 2
Comparison of Models for the Prediction of Travel Time for Public Transport Prioritization
Xie, W., Hepner, E., Duensing, J., & Hoyer, R. (2024) · IEEE Forum on Integrated and Sustainable Transportation Systems (FISTS) · doi:10.1109/fists60717.2024.10485531
Metadata
- Authors
- B P, A., R, S., & H S, S.
- Venue
- International Journal of Engineering Trends and Technology
- Published
- 2022-09-22
- Volume
- 70
- Issue
- 9
- Pages
- 185-193
- ISSN
- 2231-5381 (ISSN-L)
- OpenAlex
- W4297143847
- Semantic Scholar
- 0d8ce5cd50125d4ff3540b7aeccbb7b93a13a71d
- Cited by
- 7
- References
- 32
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 2 · 2023: 1
- FWCI
- 0.52
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Journal of Engineering Trends and Technology (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Social Sciences › Transportation › Transportation Planning and Optimization
- Physical Sciences › Engineering › Civil and Structural Engineering › Urban Transport Systems Analysis
- Keywords
- bus arrival time prediction, public transport, smart mobility, spatial patterns, intersections, XGBoost, smart cities
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 2026-11-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-05 (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
