TrafficBERT: Pre-trained model with large-scale data for long-range traffic flow forecasting

计算机科学 自编码 深度学习 人工智能 概括性 航程(航空) 机器学习 人工神经网络 流量(计算机网络) 嵌入 数据挖掘 计算机安全 心理学 材料科学 复合材料 心理治疗师
作者
Kyohoon Jin,JeongA Wi,Eunju Lee,Shin-Jin Kang,Soo Kyun Kim,Youngbin Kim
出处
期刊:Expert Systems With Applications [Elsevier BV]
卷期号:186: 115738-115738 被引量:36
标识
DOI:10.1016/j.eswa.2021.115738
摘要

Traffic flow prediction has various applications such as in traffic systems and autonomous driving. Road conditions have become increasingly complex, and this, in turn, has increased the demand for effective traffic volume predictions. Statistical models and conventional machine-learning models have been employed for this purpose more recently, deep learning has been widely used. However, most deep learning-based models require data additional to traffic information, such as information on adjacent roads or road weather conditions. Therefore, the effectiveness of these models is typically restricted to certain roads. Even if such information were available, there is a possibility of bias toward a specific road. To overcome this limitation, based on the bidirectional encoder representations from transformers (BERT), we propose trafficBERT, a model that is suitable for use on various roads because it is pre-trained with large-scale traffic data. Our model captures time-series information by employing multi-head self-attention in place of the commonly used recurrent neural network. In addition, the autocorrelation between the states before and after each time step is determined more efficiently via factorized embedding parameterization. Our results indicate that trafficBERT outperforms models trained using data for specific roads, as well as commonly used statistical and deep learning models, such as Stacked Autoencoder, and models based on long short-term memory, in terms of accuracy. • Proposing a deep learning model to predict long-range traffic flow forecasting. • TrafficBERT is a modifies of the BERT structure for traffic flow forecasting. • Increasing the generality of the model by pre-training data on various roads.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
pw发布了新的文献求助50
1秒前
雾影觅光发布了新的文献求助10
1秒前
yar应助科研鸟采纳,获得10
1秒前
CC发布了新的文献求助10
1秒前
muyingleng完成签到,获得积分10
2秒前
隐形曼青应助强健的冰棍采纳,获得10
2秒前
研友_nV2pkn发布了新的文献求助10
3秒前
大个应助iiiid采纳,获得10
3秒前
微笑访枫完成签到,获得积分20
4秒前
完美世界应助小李叭叭采纳,获得10
4秒前
4秒前
QZZ发布了新的文献求助10
4秒前
4秒前
桐桐应助yingqing采纳,获得10
5秒前
5秒前
呆萌枕头完成签到,获得积分10
6秒前
yongtao完成签到,获得积分10
6秒前
科研通AI5应助wxt采纳,获得10
8秒前
8秒前
simey发布了新的文献求助10
8秒前
10秒前
gujian发布了新的文献求助10
10秒前
12秒前
Ava应助小任性采纳,获得10
12秒前
专注的乐荷给专注的乐荷的求助进行了留言
12秒前
英俊的铭应助Diffileft采纳,获得10
13秒前
14秒前
Zzz完成签到,获得积分10
14秒前
端庄蚂蚁完成签到,获得积分10
15秒前
15秒前
15秒前
科研通AI2S应助啦啦啦采纳,获得10
16秒前
Oil完成签到,获得积分10
16秒前
16秒前
Hello应助雾影觅光采纳,获得10
16秒前
17秒前
Ava应助jnum1采纳,获得10
17秒前
17秒前
丘比特应助俭朴的一曲采纳,获得10
17秒前
比伯的小杨完成签到,获得积分10
18秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3971078
求助须知:如何正确求助?哪些是违规求助? 3515742
关于积分的说明 11179305
捐赠科研通 3250852
什么是DOI,文献DOI怎么找? 1795501
邀请新用户注册赠送积分活动 875868
科研通“疑难数据库(出版商)”最低求助积分说明 805207