ANALYZING DECELERATION TIME LEAD TO CONGESTION BASED ON BEHAVIOR PATTERNS

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

ABDI A.; SALEHI KALAM A.; AMINRAD A.

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Modares Civil Engineering journal Year:2016 | Volume:16 | Issue:5 (SUPPLEMENT) Page(s): 91-102

Download Full-Text

Persian Verion

View:

700

Download:

Cites:

Information Journal Paper

Title

ANALYZING DECELERATION TIME LEAD TO CONGESTION BASED ON BEHAVIOR PATTERNS

Author(s)

ABDI A. | SALEHI KALAM A. | AMINRAD A. | Issue Writer Certificate

Keywords

DECELERATION PHASE TIME LEADING TO CONGESTIONQ2

STOP AND GO TRAFFICQ2

NGSIM DATA TRAJECTORYQ1

BEHAVIOR PATTERNSQ1

NEURAL NETWORKSQ2

Abstract

Stop-and-go traffic is frequently observed in congested freeways and is usually developed by a large traffic volume in commuting time by a lane block coming from incidents or road works, lane change maneuvers, sudden speed drop, and rubbernecking behavior. Traffic oscillation results in negative effects such as increasing fuel consumption and safety hazards. Speed drop of leader vehicle results in STOP AND GO TRAFFIC in platoon from downstream to upstream. Follower vehicle drivers of platoon make different reactions to the receiving wave based on their BEHAVIOR PATTERNS. In this paper, behavioral patterns of follower driver are classified based on asymmetric microscopic driving behavior theory and traffic hysteresis in NGSIM trajectories. Vehicle trajectory data from Next Generation Simulation (NGSIM) program was also employed. Platoons of vehicles identified through a traffic disturbance were classified into deceleration and acceleration phases based on drivers’ behaviors and hysteresis in traffic oscillation. Drivers’ behaviors in the deceleration phase led to the classification of congestion into four behavioral patterns, based on the maneuvering errors of the follower driver, namely under reaction, under constant reaction, over reaction, and over constant reaction. Moreover, in the acceleration phase, traffic hysteresis was classified into two different categories: aggressive and timid behaviors. The two parameters of last deceleration wave which led to congestion i.e., d t, are calculated based on Newell’s car following model. The time of the two phases, stop and congestion phases, are identified based on follower vehicle trajectory. In order to calculate the time of the two mentioned phases, two points are identified in this paper: point of receiving the stop wave leading to congestion and point of entering congestion. As there are many parameters and errors of raw trajectory data, it is not important to illustrate target function, which is the main reason for developing the behavioral patterns. Effective parameters of behavior diversion in stop-and-go traffic are identified and analyzed at the microscopic level based on artificial NEURAL NETWORKS (ANNS). Artificial neural network is a computational model, consisted of a large parameter space and an adaptable structure, which is inspired by the structure and functional aspects of biological NEURAL NETWORKS. Artificial neural network is constructed based on learning various functions with actual and discontinuous vector values. It is created based on connecting several processors which relate input groups to the output by artificial neurons. A neural network consists of an interconnected groups of artificial neurons with activation functions, and processes information using a connectionist approach to computation. Neurons relate input and output groups to each other. Multi-layer perceptron (MLP) - used in this paper - belongs to the feed-forward artificial NEURAL NETWORKS which are usually trained via the error back-propagation learning rule. Neural network models are developed to analyze the relationship between the microscopic parameters and the duration of the two phases. In this research, Crystal Ball software is used, as it can define the sensitivity analysis of behavioral diversion based on independent variables at the microscopic level. The software is linked to artificial NEURAL NETWORKS in MATLAB using Excel software, so that, sensitivity analysis of the dependent variables to the independent variables can be performed by uniform probability. Based on three BEHAVIOR PATTERNS, the analyses results show that the two most effective parameters are the deceleration wave leading to congestion and the stop phase duration. Increasing the deceleration wave results in reducing the time between the two phases based on “over reaction-timid”, and its increase based on “under reaction-timid” and “pattern and over constant up reaction – timid”. In addition, results of stop phase leading to congestion, based on three BEHAVIOR PATTERNS, show that increasing the stop phase duration results in an increase in the time between the two phases.

Cites

No record.

References

No record.

Cite

APA: Copy

ABDI, A., SALEHI KALAM, A., & AMINRAD, A.. (2016). ANALYZING DECELERATION TIME LEAD TO CONGESTION BASED ON BEHAVIOR PATTERNS. MODARES CIVIL ENGINEERING JOURNAL, 16(5 (SUPPLEMENT)), 91-102. SID. https://sid.ir/paper/256696/en

Vancouver: Copy

ABDI A., SALEHI KALAM A., AMINRAD A.. ANALYZING DECELERATION TIME LEAD TO CONGESTION BASED ON BEHAVIOR PATTERNS. MODARES CIVIL ENGINEERING JOURNAL[Internet]. 2016;16(5 (SUPPLEMENT)):91-102. Available from: https://sid.ir/paper/256696/en

IEEE: Copy

A. ABDI, A. SALEHI KALAM, and A. AMINRAD, “ANALYZING DECELERATION TIME LEAD TO CONGESTION BASED ON BEHAVIOR PATTERNS,” MODARES CIVIL ENGINEERING JOURNAL, vol. 16, no. 5 (SUPPLEMENT), pp. 91–102, 2016, [Online]. Available: https://sid.ir/paper/256696/en

Related Journal Papers