Journal Article10.1109/TITS.2014.2311123
Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning
1.1K
TL;DR: It is presented that MTL can improve the generalization performance of shared tasks and a grouping method based on the weights in the top layer to make MTL more effective is proposed to take full advantage of weight sharing in the deep architecture.
read more
Abstract: Traffic flow prediction is a fundamental problem in transportation modeling and management. Many existing approaches fail to provide favorable results due to being: 1) shallow in architecture; 2) hand engineered in features; and 3) separate in learning. In this paper we propose a deep architecture that consists of two parts, i.e., a deep belief network (DBN) at the bottom and a multitask regression layer at the top. A DBN is employed here for unsupervised feature learning. It can learn effective features for traffic flow prediction in an unsupervised fashion, which has been examined and found to be effective for many areas such as image and audio classification. To the best of our knowledge, this is the first paper that applies the deep learning approach to transportation research. To incorporate multitask learning (MTL) in our deep architecture, a multitask regression layer is used above the DBN for supervised prediction. We further investigate homogeneous MTL and heterogeneous MTL for traffic flow prediction. To take full advantage of weight sharing in our deep architecture, we propose a grouping method based on the weights in the top layer to make MTL more effective. Experiments on transportation data sets show good performance of our deep architecture. Abundant experiments show that our approach achieved close to 5% improvements over the state of the art. It is also presented that MTL can improve the generalization performance of shared tasks. These positive results demonstrate that deep learning and MTL are promising in transportation research.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Predicting Traffic Path Recommendation Using Spatiotemporal Graph Convolutional Neural Network
Hitendra Shankarrao Khairnar,Balwant Sonkamble +1 more
TL;DR: This paper proposes a novel spatiotemporal graph convolutional neural network (STGCN) framework for predicting traffic path recommendations, incorporating spatial reliance and temporal dependence of traffic parameters to optimize path recommendations across origin-destination locations.
DeepUrbanMomentum: An Online Deep-Learning System for Short-Term Urban Mobility Prediction.
Renhe Jiang,Xuan Song,Zipei Fan,Tianqi Xia,Quanjun Chen,Satoshi Miyazawa,Ryosuke Shibasaki +6 more
TL;DR: This study presents DeepUrbanMomentum, an online deep-learning system for short-term urban mobility prediction using streaming data and recurrent neural networks, demonstrating superior performance in predicting human mobility during rare events and emergencies.
A Risk Analysis and Prediction Model of Electric Power GIS Based on Deep Learning
Jianyong Xue,Kehe Wu,Yan Zhou +2 more
TL;DR: A deep learning-based risk analysis model for electric power GIS is developed, utilizing equipment dynamic analysis and nonlinear network structure to predict power grid risk, achieving high accuracy and outperforming modern optimization algorithms with historical grid data and prior training.
Short-Term Traffic Speed Prediction Based on Fundamental and Cointegration Relationship of Speed–Density in Non-Congested and Congested States
Ryo Inoue,Akihisa Miyashita +1 more
TL;DR: This study proposes a short-term traffic speed prediction model based on a threshold error correction model, utilizing fundamental and cointegration relationships between speed and density in non-congested and congested states, improving prediction accuracy using sensor data from 96 arterial road links in Naha City, Japan.
Predictive complex event processing based on evolving Bayesian networks
TL;DR: Experimental evaluations show that this method is effective for predictive complex event processing and it outperforms other popular methods when processing traffic prediction in intelligent transportation systems.
References
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Multitask Learning
Rich Caruana
- 01 Jul 1997
TL;DR: Multi-task Learning (MTL) as mentioned in this paper is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias.