Predicting Traffic Flow Propagation Based on Congestion at Neighbouring Roads Using Hidden Markov Model

Priambodo, Bagus; Ahmad, Azlina; Kadir, Rabiah Abdul

doi:10.1109/access.2021.3075911

Cited by 16 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conventional HMM matched all these GPS measurements to the right-side road segment, which is the most probable sequence of states predicted by the Viterbi algorithm. Our method computes the initial probability based on Equation (10). As shown, our proposed method maps GPS measurements to the left-side road segment that the ground truth on.…”

Section: Resultsmentioning

confidence: 99%

“…The main objective of a map-matching algorithm is to map a sequence of observed GPS data to a road segment, providing more accurate and reliable location information for many ITS services such as navigation, map update/inference, object tracking, and traffic prediction [1][2][3][4][5][6][7][8][9][10][11][12]. The HMM is the foundation of map-matching methods as it is capable of handling noisy observations and complex road networks [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Enhanced Hidden Markov Model for Map-Matching in Pedestrian Navigation

Ma,

Wang,

Lee

2024

Electronics

View full text Add to dashboard Cite

Map-matching is a core functionality of pedestrian navigation applications. The localization errors of the global positioning systems (GPSs) in smartphones are one of the most critical factors that limit the large-scale deployment of pedestrian navigation applications, especially in dense urban areas where multiple road segments exist within the range of GPS errors, which can be increased by tall buildings neighboring each other. In this paper, we address two issues of practical importance for map-matching based on the Hidden Markov Model (HMM) in pedestrian navigation systems: large localization error in the initial phase of map-matching and HMM breaks in open field traversals. A heuristic method to determine the probability of initial states of the HMM based on a small number of GPS data received during the short warm-up period is proposed to improve the accuracy of initial map-matching. A simple but highly practical method based on a heuristic evaluation of near-future locations is proposed to prevent the malfunction of the Viterbi algorithm within the area of open fields. The results of field experiments indicate that the enhanced HMM constructed via the proposed methods achieves significantly higher map-matching accuracy compared to that of state of the art.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Enhanced Hidden Markov Model for Map-Matching in Pedestrian Navigation

Ma,

Wang,

Lee

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In another study, the authors overcome the limitations of adaptive K-means clustering and use the pattern by using regression models. In this study, the Markov model was employed to identify traffic patterns to predict the congestion [ 51 , 52 ]. We proposed the Markov approach because it does not require a lot of data, and it can predict the future state by using only the data from the current state.…”

Section: Proposed Modelmentioning

confidence: 99%

A Novel Markov Model-Based Traffic Density Estimation Technique for Intelligent Transportation System

Beenish

Javid

Fahad

et al. 2023

Sensors

View full text Add to dashboard Cite

An intelligent transportation system (ITS) aims to improve traffic efficiency by integrating innovative sensing, control, and communications technologies. The industrial Internet of things (IIoT) and Industrial Revolution 4.0 recently merged to design the industrial Internet of things–intelligent transportation system (IIoT-ITS). IIoT sensing technologies play a significant role in acquiring raw data. The application continuously performs the complex task of managing traffic flows effectively based on several parameters, including the number of vehicles in the system, their location, and time. Traffic density estimation (TDE) is another important derived parameter desirable to keep track of the dynamic state of traffic volume. The expanding number of vehicles based on wireless connectivity provides new potential to predict traffic density more accurately and in real time as previously used methodologies. We explore the topic of assessing traffic density by using only a few simple metrics, such as the number of surrounding vehicles and disseminating beacons to roadside units and vice versa. This research paper investigates TDE techniques and presents a novel Markov model-based TDE technique for ITS. Finally, an OMNET++-based approach with an implementation of a significant modification of a traffic model combined with mathematical modeling of the Markov model is presented. It is intended for the study of real-world traffic traces, the identification of model parameters, and the development of simulated traffic.

show abstract

“…Most scholars have primarily used methods such as complex networks and contagion models to study the mechanisms of traffic congestion risk propagation. However, Priambodo et aldeveloped a method to predict the impact of road congestion on traffic conditions by analyzing spatial and historical data on traffic flows and employing statistical methods to establish relationships between traffic conditions (congestion or smooth flow) and traffic patterns [27]. Chen et alattempted to model the congestion propagation phenomenon using a space-time congestion subgraph [28].…”

Section: Introductionmentioning

confidence: 99%

Propagation and control of congestion risk in scale-free networks based on information entropy

Yan,

Li,

Sun

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

To study the propagation pattern of congestion risk in the traffic network and enhance risk control capabilities, a model has been developed. This model takes into account the probabilities of five threats (the risk occurrence probability; the risk of loss; the unpredictability of risk; the uncontrollability of risk; the transferability of risk) in the traffic network to define the risk entropy and determine the risk capacity, analyze the mechanism of congestion risk propagation, and explore the impact of risk resistance, the average degree of risk capacity at intersections, and the degree of correlation on congestion risk propagation. Further, a control method model for risk propagation is proposed. Numerical simulation results demonstrate that the risk resistance parameter θ can inhibit the propagation of congestion risk during traffic congestion. The highest efficiency in controlling risk propagation is achieved when θ reaches a threshold value θ*. Furthermore, the average degree of intersection risk capacity α shows a positive correlation with θ* and a negative correlation with control efficiency. However, the degree of association ω has a negative effect on risk propagation control, decreasing the degree of association between nodes aids in risk propagation control.

show abstract

Predicting Traffic Flow Propagation Based on Congestion at Neighbouring Roads Using Hidden Markov Model

Cited by 16 publications

References 48 publications

An Enhanced Hidden Markov Model for Map-Matching in Pedestrian Navigation

An Enhanced Hidden Markov Model for Map-Matching in Pedestrian Navigation

A Novel Markov Model-Based Traffic Density Estimation Technique for Intelligent Transportation System

Propagation and control of congestion risk in scale-free networks based on information entropy

Contact Info

Product

Resources

About