Inferring Traffic Incident Start Time with Loop Sensor Data

Yue, Mingxuan; Fan, Liyue; Shahabi, Cyrus

doi:10.1145/2983323.2983339

Cited by 11 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) Analyze features of noise in raw traffic data and apply denoising algorithms to remove intense fluctuation and highlight its variation patterns. In this part, methods mainly focus on how to apply the Wavelet Decomposition (WD) [13], Butterworth Filter (BF) [14] and Moving Smoothing (MS) algorithm [15] to eliminate noise before implementing various prediction models, such as, Kalman filter [16], a combined method with ARIMA and Support Vector Machine (SVM) [17], neuro network with wavelet [18], [19], and fuzzy-neural network [20]. Overall, all these previous works demonstrated that the denoising method used in traffic flow data is an effective approach to enhance prediction performance.…”

Section: Introductionmentioning

confidence: 99%

A Denoising Scheme-Based Traffic Flow Prediction Model: Combination of Ensemble Empirical Mode Decomposition and Fuzzy C-Means Neural Network

et al. 2020

View full text Add to dashboard Cite

In the Intelligent Transportation Systems (ITS), highly accurate traffic flow prediction is considered as key technology to evaluate traffic state of the urban road network. However, due to disturbing from environment, the original traffic flow data may be influenced by noise and finally cause the decline of prediction accuracy. This study design a hybrid prediction model combining Ensemble Empirical Mode Decomposition (EEMD) denoising schemes and classifying learning algorithm based on Fuzzy C-means Neural Network (FCMNN) to improve prediction accuracy. In the model training process, several key parameters in EEMD and FCMNN are determined according to prediction errors based on traffic volume detected from highway network in the Minneapolis city. In the model validation, three widely used indicators for error evaluation are applied to estimate the prediction accuracy of four candidate models under single and multi step, including Artificial Neural Network (ANN), EEMD+ANN, FCMNN and EEMD+FCMNN. The results shown in the case study indicate that the prediction models combined with denoising methods are superior to the models without adopting denoising algorithm. Furthermore, the model using classifying learning method FCMNN can produce higher prediction accuracy than traditional ANN model. In addition, the long-term prediction performance of FCMNN is also much better than that of ANN because that sub-NN system is trained according to each classifying patterns to obtain better optimization effect. Results summarized in this study could be helpful for administration to design managing and controlling strategies according to high prediction accuracy. INDEX TERMS Traffic flow prediction, ensemble empirical mode decomposition, artificial neural network, fuzzy c-means, de-noising algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

A Denoising Scheme-Based Traffic Flow Prediction Model: Combination of Ensemble Empirical Mode Decomposition and Fuzzy C-Means Neural Network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This requires complete knowledge of the traffic incident data during both training, testing, and implementation; however, it is often difficult to get accurate reports of incidents (Ren et al, 2012). In particular, it is hard to obtain accurate estimates for start time, duration, and impacted regions due to traffic incidents (Yue et al, 2016). To alleviate this issue, we propose to use alternate robust summary statistics (learned from the time series tensor itself) for the location and scale parameters so that the affect of the presence of anomalies can be minimized.…”

Section: Univariate Threshold Computationmentioning

confidence: 99%

Data-driven parallelizable traffic incident detection using spatio-temporally denoised robust thresholds

Chakraborty

Hegde

Sharma

2019

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Automatic incident detection (AID) is crucial for reducing non-recurrent congestion caused by traffic incidents. In this paper, we propose a data-driven AID framework that can leverage large-scale historical traffic data along with the inherent topology of the traffic networks to obtain robust traffic patterns. Such traffic patterns can be compared with the real-time traffic data to detect traffic incidents in the road network. Our AID framework consists of two basic steps for traffic pattern estimation. First, we estimate a robust univariate speed threshold using historical traffic information from individual sensors. This step can be parallelized using MapReduce framework thereby making it feasible to implement the framework over large networks. Our study shows that such robust thresholds can improve incident detection performance significantly compared to traditional threshold determination. Second, we leverage the knowledge of the topology of the road network to construct threshold heatmaps and perform image denoising to obtain spatio-temporally denoised thresholds. We used two image denoising techniques, bilateral filtering and total variation for this purpose. Our study shows that overall AID performance can be improved significantly using bilateral filter denoising compared to the noisy thresholds or thresholds obtained using total variation denoising. AbstractAutomatic incident detection (AID) is crucial for reducing non-recurrent congestion caused by traffic incidents. In this paper we propose a data-driven AID framework that can leverage large-scale historical traffic data along with the inherent topology of the traffic networks to obtain robust traffic patterns. Such traffic patterns can be compared with the real-time traffic data to detect traffic incidents in the road network. Our AID framework consists of two basic steps for traffic pattern estimation. First, we estimate robust univariate speed threshold using historical traffic information from individual sensors. This step can be parallelized using MapReduce framework thereby making it feasible to implement the framework over large networks. Our study shows that such robust thresholds can improve incident detection performance significantly compared to traditional threshold determination. Second, we leverage the knowledge of the topology of the road network to construct threshold heatmaps and perform image denoising to obtain spatio-temporally denoised thresholds. We used two image denoising techniques, bilateral filtering and total variation for this purpose. Our study shows that overall AID performance can be improved significantly using bilateral filter denoising compared to the noisy thresholds or thresholds obtained using total variation denoising.

show abstract

“…Cities also accumulate data generated by government entities, citizens and systems. [Zheng et al 2014] classify urban data into five categories: (i) urban mobility data such as traffic data [Yue et al 2016], displacement, and mobile telephony; (ii) geographic data such as information about the transport network, road network, and areas of interest; (iii) social media data such as text, photos, and videos; (iv) environmental data such as those from weather and energy consumption; and (v) data from other sources not necessarily related to the urban context such as public service, Health [Klemm et al 2016], and Economy.…”

Section: Introductionmentioning

confidence: 99%

A Scalable Data Integration Architecture for Smart Cities: Implementation and Evaluation

Ribeiro

Braghetto

2022

jidm

View full text Add to dashboard Cite

The collection, processing, and analysis of data generated by varied sources can help us better understand the functioning and demands of the cities. However, developing efficient solutions to explore urban data is challenging due to the large volume, heterogeneity, and lack of accessibility and integration of this kind of data. In this work, we identify the main requirements of a data integration system to support decision-making in cities, focusing on its challenges. We analyze some existing data integration solutions, to uncover their features and limitations. Based on these results, we propose a new microservice architecture to support the development of software platforms for integrating smart cities’ heterogeneous data and a guideline to assess their performance. We also present details of a proof-of-concept implementation of the proposed architecture and its performance evaluation. The results demonstrate that the platform can scale horizontally to handle the highly dynamic demands of a smart city while maintaining low response times.

show abstract

Inferring Traffic Incident Start Time with Loop Sensor Data

Cited by 11 publications

References 5 publications

A Denoising Scheme-Based Traffic Flow Prediction Model: Combination of Ensemble Empirical Mode Decomposition and Fuzzy C-Means Neural Network

A Denoising Scheme-Based Traffic Flow Prediction Model: Combination of Ensemble Empirical Mode Decomposition and Fuzzy C-Means Neural Network

Data-driven parallelizable traffic incident detection using spatio-temporally denoised robust thresholds

A Scalable Data Integration Architecture for Smart Cities: Implementation and Evaluation

Contact Info

Product

Resources

About