Published on Sat Aug 21 2021

Deep Representation of Imbalanced Spatio-temporal Traffic Flow Data for Traffic Accident Detection

Pouya Mehrannia, Shayan Shirahmad Gale Bagi, Behzad Moshiri, Otman Adam Al-Basir

Automatic detection of traffic accidents has a crucial effect on improving transportation, public safety, and path planning. The LSTM-based framework increases class separability in the encoded feature space while reducing the dimension of data.

1
0
0
Abstract

Automatic detection of traffic accidents has a crucial effect on improving transportation, public safety, and path planning. Many lives can be saved by the consequent decrease in the time between when the accidents occur and when rescue teams are dispatched, and much travelling time can be saved by notifying drivers to select alternative routes. This problem is challenging mainly because of the rareness of accidents and spatial heterogeneity of the environment. This paper studies deep representation of loop detector data using Long-Short Term Memory (LSTM) network for automatic detection of freeway accidents. The LSTM-based framework increases class separability in the encoded feature space while reducing the dimension of data. Our experiments on real accident and loop detector data collected from the Twin Cities Metro freeways of Minnesota demonstrate that deep representation of traffic flow data using LSTM network has the potential to detect freeway accidents in less than 18 minutes with a true positive rate of 0.71 and a false positive rate of 0.25 which outperforms other competing methods in the same arrangement.

Sun Dec 15 2019
Machine Learning
Applying Deep Learning to Detect Traffic Accidents in Real Time Using Spatiotemporal Sequential Data
Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) are used to detect traffic accidents in Chicago. The full dataset consists of 241 accident and 6,038 non-accident cases selected from Chicago expressway.
0
0
0
Thu Sep 19 2019
Machine Learning
Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights
Reducing traffic accidents is an important public safety challenge. Accident analysis and prediction has been a topic of much research over the past few decades. Using small-scale datasets with limited coverage, and being dependent on extensive set of data are the important shortcomings of the existing studies.
0
0
0
Sun Oct 01 2017
Machine Learning
DeepTFP: Mobile Time Series Data Analytics based Traffic Flow Prediction
Traffic flow prediction is an important research issue to avoid traffic congestion in transportation systems. This study proposes a deep learning based prediction algorithm, DeepTFP, to collectively predict the traffic flow on each and every traffic road of a city.
0
0
0
Mon Jul 15 2019
Machine Learning
Motorway Traffic Flow Prediction using Advanced Deep Learning
Congestion prediction represents a major priority for traffic management. This paper proposes an advanced deep learning framework for simultaneously predicting the traffic flow on a highly circulated motorway in Sydney, Australia.
0
0
0
Tue Feb 18 2020
Neural Networks
Short-Term Traffic Flow Prediction Using Variational LSTM Networks
Traffic flow characteristics are one of the most critical decision-making and policing factors in a region. VLSTM-E can provide more reliable short-term traffic flow by considering the distribution and missing values.
0
0
0
Thu Sep 06 2018
Machine Learning
Travel Speed Prediction with a Hierarchical Convolutional Neural Network and Long Short-Term Memory Model Framework
Deep learning has become increasingly popular in recent years. However, there are few examples exploiting this emerging technology to develop applications for traffic prediction. This is largely due to the difficulty in capturing random, seasonal, non-linear, and correlated nature of traffic data.
0
0
0
Thu Jun 09 2011
Artificial Intelligence
SMOTE: Synthetic Minority Over-sampling Technique
An approach to the construction of classifiers from imbalanced datasets is described. A dataset is imbalanced if the classification categories are not approximately equally represented. Under-sampling of the majority (normal) class has been proposed as a good means of increasing the sensitivity of a classifier to the minority class.
2
0
10
Mon Dec 22 2014
Machine Learning
Adam: A Method for Stochastic Optimization
Adam is an algorithm for first-order gradient-based optimization of stochastic objective functions. The method is straightforward to implement and has little memory requirements. It is well suited for problems that are large in terms of data and parameters.
3
0
2
Tue Dec 26 2017
Artificial Intelligence
A Real-Time Autonomous Highway Accident Detection Model Based on Big Data Processing and Computational Intelligence
Traffic congestion is becoming a major problem of the 21st century. Early detection of an accident can save lives, provides quicker road openings, hence decreases wasted time and resources.
0
0
0
Fri Jan 04 2019
Computer Vision
Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video
Real-time systems that monitor and analyze road users become increasingly critical as we march toward the smart city era. Vision-based frameworks for Object Detection, Multiple Object Tracking, and Traffic Near Accident Detection are important applications of Intelligent Transportation System.
0
0
0
Mon Aug 22 2016
Machine Learning
Survey of resampling techniques for improving classification performance in unbalanced datasets
A number of classification problems need to deal with data imbalance. Often it is desired to have a high recall on the minority class while maintaining a high precision on the majority class. In this paper, we review anumber of resampling techniques proposed in literature to handle unbalanced datasets.
0
0
0
Sat Dec 22 2012
Machine Learning
ADADELTA: An Adaptive Learning Rate Method
ADADELTA is a novel per-dimension learning rate method for gradient descent. The method dynamically adapts over time using only first order information. It requires no manual tuning of the learning rate.
0
0
0