Framework for fusing traffic information from social and physical transportation data

Zheng, Zhihao; Wang, Chengcheng; Wang, Pu; Xiong, Yusha; Zhang, Fan; Lv, Yisheng

doi:10.1371/journal.pone.0201531

Cited by 24 publications

(9 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In 2018, Zheng et al developed a data fusion framework to identify social media messages reporting non-recurring traffic incidents by connecting the traffic incidents with traffic states inferred from taxi global positioning system (GPS) data [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Duration of Traffic Incidents by Hybrid Deep Learning Based on Multi-Source Incomplete Data

Shang

Xie

2022

IJERPH

View full text Add to dashboard Cite

Traffic accidents causing nonrecurrent congestion and road traffic injuries seriously affect public safety. It is helpful for traffic operation and management to predict the duration of traffic incidents. Most of the previous studies have been in a certain area with a single data source. This paper proposes a hybrid deep learning model based on multi-source incomplete data to predict the duration of countrywide traffic incidents in the U.S. The text data from the natural language description in the model were parsed by the latent Dirichlet allocation (LDA) topic model and input into the bidirectional long short-term memory (Bi-LSTM) and long short-term memory (LSTM) hybrid network together with sensor data for training. Compared with the four benchmark models and three state-of-the-art algorithms, the RMSE and MAE of the proposed method were the lowest. At the same time, the proposed model performed best for durations between 20 and 70 min. Finally, the data acquisition was defined as three phases, and a phased sequential prediction model was proposed under the condition of incomplete data. The results show that the model performance was better with the update of variables.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Duration of Traffic Incidents by Hybrid Deep Learning Based on Multi-Source Incomplete Data

Shang

Xie

2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…A vehicle license plate recognition system can also collect a lot of traffic data over a predefined period of time [11]. Due to the inexperience of the reporters, social media may not be as accurate as other sources of information when it comes to traffic and accidents [12].…”

Section: Figure 1 Accidents That Occurred On Polish Roads Between 199...mentioning

confidence: 99%

Optimization of Methods for Forecasting the Number of Road Accidents

Gorzelańczyk,

Tylicki

2024

AAES

View full text Add to dashboard Cite

Due to the abrupt rise in the number of vehicles on the road, there is an increasing risk of traffic accidents, which can result in fatalities and damage to economic resources. This is due to the rapid growth in the human population and the development in motorization. The biggest issue with anticipating and analyzing data on road accidents is the small quantity of the dataset that may be used for study in this area. Road accidents have a low geographical and temporal density, despite the fact that they cause millions of deaths and injuries annually.The purpose of this article is to suggest a strategy for improving methodologies for determining how frequently traffic accidents occur in Poland. Techniques for multi-criteria optimization were used in this. We can infer from the findings that the suggested method can be utilized to determine the best methods for forecasting the frequency of traffic accidents. The method used can successfully be used to forecast other events not only logistics or transportation.

show abstract

“…Meanwhile, other researchers combined social media with GPS sensors to get better results and more accurate locations. Zheng et al [17] used taxi GPS and Weibo data to analyze traffic anomalies in China and Wang et al [18] collected data from different sources such as social media, GPS, points of interest, and weather data to discover traffic congestion and detect traffic anomalies.…”

Section: A Incident Detectionmentioning

confidence: 99%

Deep Learning Approaches for Multi-Label Incidents Classification from Twitter Textual Information

Anggraeni

Ranggianto

Ghozali

et al. 2022

J. Inf. Syst. Eng. Bus. Intell.

View full text Add to dashboard Cite

Background: Twitter is one of the most used social media, with 310 million active users monthly and 500 million tweets per day. Twitter is not only used to talk about trending topics but also to share information about accidents, fires, traffic jams, etc. People often find these updates useful to minimize the impact. Objective: The current study compares the effectiveness of three deep learning methods (CNN, RCNN, CLSTM) combined with neuroNER in classifying multi-label incidents. Methods: NeuroNER is paired with different deep learning classification methods (CNN, RCNN, CLSTM). Results: CNN paired with NeuroNER yield the best results for multi-label classification compared to CLSTM and RCNN. Conclusion: CNN was proven to be more effective with an average precision value of 88.54% for multi-label incidents classification. This is because the data we used for the classification resulted from NER, which was in the form of entity labels. CNN immediately distinguishes important information, namely the NER labels. CLSTM generates the worst result because it is more suitable for sequential data. Future research will benefit from changing the classification parameters and test scenarios on a different number of labels with more diverse data. Keywords: CLSTM, CNN, Incident Classification, Multi-label Classification, RCNN

show abstract

Framework for fusing traffic information from social and physical transportation data

Cited by 24 publications

References 54 publications

Prediction of Duration of Traffic Incidents by Hybrid Deep Learning Based on Multi-Source Incomplete Data

Prediction of Duration of Traffic Incidents by Hybrid Deep Learning Based on Multi-Source Incomplete Data

Optimization of Methods for Forecasting the Number of Road Accidents

Deep Learning Approaches for Multi-Label Incidents Classification from Twitter Textual Information

Contact Info

Product

Resources

About