首页|Investigators from Swiss Federal Institute of Technology Release New Data on Mac hine Learning (Time-to-green Predictions for Fully-actuated Signal Control Syste ms With Supervised Learning)
Investigators from Swiss Federal Institute of Technology Release New Data on Mac hine Learning (Time-to-green Predictions for Fully-actuated Signal Control Syste ms With Supervised Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in Machine Learning. According to news reporting out of Zurich, Switzerland, by New sRx editors, research stated, “Recently, efforts have been made to standardize s ignal phase and timing (SPaT) messages. These messages contain signal phase timi ngs of all signalized intersection approaches.” Financial support for this research came from Swiss National Science Foundation (SNSF). Our news journalists obtained a quote from the research from the Swiss Federal I nstitute of Technology, “This information can thus be used for efficient motion planning, resulting in more homogeneous traffic flows and uniform speed profiles . Despite efforts to provide robust predictions for semi-actuated signal control systems, predicting signal phase timings for fully-actuated controls remains ch allenging. This paper proposes a time series prediction framework using aggregat ed traffic signal and loop detector data. We utilize state-of-the-art machine le arning models to predict future signal phases’ duration. The performance of a Li near Regression (LR), Random Forest (RF), a light gradient-boosting machine (Lig htGBM), a bidirectional Long-Short-Term-Memory neural network (BiLSTM) and a Tem poral Convolutional Network (TCOV) are assessed against a naive baseline model.”
ZurichSwitzerlandEuropeCyborgsEm erging TechnologiesMachine LearningSupervised LearningSwiss Federal Instit ute of Technology
NETL
NSTL
