期刊
IET INTELLIGENT TRANSPORT SYSTEMS
卷 13, 期 1, 页码 48-54出版社
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-its.2018.5093
关键词
driver information systems; traffic engineering computing; optimisation; principal component analysis; neural nets; behavioural sciences computing; learning (artificial intelligence); gated branch neural network; GBNN algorithm; mandatory lane changing suggestion; on-ramps-of-highway; mandatory lane changing behaviour modelling; MLC behaviour modelling; MLC suggestion system; advanced driver assistance systems; ADAS; nonmerge event; merge event; correlation analysis; scaled exponential linear units activation function; adaptive moment estimation optimiser; real-world dataset; U; S; Highway 101; U; S; Interstate 80; Federal Highway Administration Next Generation Simulation; NGSIM; principal component analysis; TensorFlow framework; Python; Pearson correlation method; receiver operating characteristic score; merge accuracy; nonmerge accuracy; deep learning algorithm
资金
- NSERC Discovery grant
- NSERC Strategic Partnership grant
- China Scholarship Council
A gated branch neural network (GBNN) is proposed for modelling mandatory lane changing (MLC) behaviour at the on-ramps of highways. It provides a core algorithm for an MLC suggestion system for advanced driver assistance systems (ADAS), where the main challenge is the trade-off between computational speed and prediction accuracy for both non-merge and merge events. The GBNN algorithm employs a gated branch based on correlation analysis, scaled exponential linear units activation function, and adaptive moment estimation optimiser. The algorithm has been evaluated using the real-world dataset of U.S. Highway 101 and Interstate 80 from Federal Highway Administration's Next Generation Simulation (NGSIM). Input features are extracted from NGSIM and pre-processed by standardisation and principal component analysis. TensorFlow framework and Python are used as the development platform. Results show that the proposed GBNN algorithm with the Pearson correlation method has values of 97.7%, 96.3%, and 0.990 for non-merge accuracy, merge accuracy, and receiver operating characteristic score, respectively. It outperforms other traditional binary classifiers for MLC applications, and is more light-weight than a convolutional neural network (AlexNet) of deep learning algorithm. Owing to its compact architecture, the GBNN provides high accuracy and efficiency, demonstrating promising usage as an MLC suggestion system in ADAS.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据