Transfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfalls

Manibardo, Eric L.; Laña, Ibai; Ser, Javier Del

doi:10.1109/itsc45102.2020.9294557

Cited by 11 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph based, image based, together with some time series based model works, represent more than half of revised publications dealing with network-wide coverage solutions. While these studies usually concentrate on performing simultaneous predictions for multiple traffic network points, publications classified as point often put their effort on other specific issues like traffic signal processing [111], [132], the exploration of new data sources [59], [118], the improvement of performance under particular situations [103], [165] or missing data [47], [160].…”

Section: B Understanding Deep Learning Based Short-term Traffic Forec...mentioning

confidence: 99%

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Manibardo¹,

Laña²,

Ser³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems (ITS), in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular ITS research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field.

show abstract

Section: B Understanding Deep Learning Based Short-term Traffic Forec...mentioning

confidence: 99%

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Manibardo¹,

Laña²,

Ser³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In many occasions this issue has been addressed by deploying temporal sensors that provide measurements for certain locations of interest during a limited period of time. However, a proper characterization of the traffic behavior under a variety of circumstances (e.g., events or holidays) requires real traffic measurements over more dilated periods [2]. Thus, real traffic data are not available for every road link, nor are they collected for the time needed for a thorough characterization.…”

Section: Introductionmentioning

confidence: 99%

On the Design of Graph Embeddings for the Sensorless Estimation of Road Traffic Profiles

Manibardo¹,

Laña²,

Villar³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Traffic forecasting models rely on data that needs to be sensed, processed, and stored. This requires the deployment and maintenance of traffic sensing infrastructure, often leading to unaffordable monetary costs. The lack of sensed locations can be complemented with synthetic data simulations that further lower the economical investment needed for traffic monitoring. One of the most common data generative approaches consists of producing real-like traffic patterns, according to data distributions from analogous roads. The process of detecting roads with similar traffic is the key point of these systems. However, without collecting data at the target location no flow metrics can be employed for this similarity-based search. We present a method to discover locations among those with available traffic data by inspecting topological features of road segments. Relevant topological features are extracted as numerical representations (embeddings) to compare different locations and eventually find the most similar roads based on the similarity between their embeddings. The performance of this novel selection system is examined and compared to simpler traffic estimation approaches. After finding a similar source of data, a generative method is used to synthesize traffic profiles. Depending on the resemblance of the traffic behavior at the sensed road, the generation method can be fed with data from one road only. Several generation approaches are analyzed in terms of the precision of the synthesized samples. Above all, this work intends to stimulate further research efforts towards enhancing the quality of synthetic traffic samples and thereby, reducing the need for sensing infrastructure.

show abstract

“…However, there are approaches within the field of Transfer Learning (TL) that have been developed to solve new but comparable problems by utilizing prior knowledge. Integrating existing knowledge when training such DL models allows a reduction in the amount of required training data and leads to better learning rates [76]. Examples of such methods can be found in [77,78], where the outputs of physics-based models were utilized as soft constraints to penalize or regulate data-driven implementations, and in [79], where a fusion of prior knowledge network was developed using self-similarity properties of network traffic data.…”

mentioning

confidence: 99%

Urban Traffic Congestion Prediction: A Multi-Step Approach Utilizing Sensor Data and Weather Information

Tsalikidis,

Mystakidis,

Koukaras

et al. 2024

Smart Cities

View full text Add to dashboard Cite

The continuous growth of urban populations has led to the persistent problem of traffic congestion, which imposes adverse effects on quality of life, such as commute times, road safety, and the local air quality. Advancements in Internet of Things (IoT) sensor technology have contributed to a plethora of new data streams regarding traffic conditions. Therefore, the recognition and prediction of traffic congestion patterns utilizing such data have become crucial. To that end, the integration of Machine Learning (ML) algorithms can further enhance Intelligent Transportation Systems (ITS), contributing to the smart management of transportation systems and effectively tackling traffic congestion in cities. This study seeks to assess a wide range of models as potential solutions for an ML-based multi-step forecasting approach intended to improve traffic congestion prediction, particularly in areas with limited historical data. Various interpretable predictive algorithms, suitable for handling the complexity and spatiotemporal characteristics of urban traffic flow, were tested and eventually shortlisted based on their predictive performance. The forecasting approach selects the optimal model in each step to maximize the accuracy. The findings demonstrate that, in a 24 h step prediction, variating Ensemble Tree-Based (ETB) regressors like the Light Gradient Boosting Machine (LGBM) exhibit superior performances compared to traditional Deep Learning (DL) methods. Our work provides a valuable contribution to short-term traffic congestion predictions and can enable more efficient scheduling of daily urban transportation.

show abstract

Transfer Learning and Online Learning for Traffic Forecasting under Different Data Availability Conditions: Alternatives and Pitfalls

Cited by 11 publications

References 17 publications

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

On the Design of Graph Embeddings for the Sensorless Estimation of Road Traffic Profiles

Urban Traffic Congestion Prediction: A Multi-Step Approach Utilizing Sensor Data and Weather Information

Contact Info

Product

Resources

About