摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-调查人员讨论人工智能的新发现。根据NewsRx记者来自捷克共和国布尔诺的新闻，研究表明，"基于代理的疏散模型提供了疏散过程的有用数据，但它们主要不是在紧急情况下设计或使用的。"这项研究的资助者包括捷克共和国技术局；Fakul ta Stavebni,Vysoke Uceni Technicke V Brne；布尔诺技术大学。我们的新闻记者从Brno Technology大学的研究中获得了一句话：“本文旨在使用在60个样本的模拟数据集上训练的代理ML模式L来测试预测RSET。总共在3个简单的几何形状上测试了9种机器学习算法：瓶颈，楼梯和走道。一组由7个空间特征组成的模型被用来训练替代模型。结果显示，人工神经网络在涉及瓶颈和楼梯的场景中具有相对良好的学习能力，测试数据为2：0.99.在人行道场景中，所有模型的性能都有明显下降，梯度提升表现最好(2：0.92)。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news originating from Brno, Czech Republic , by NewsRx correspondents, research stated, “Agent-based evacuation models prov ide useful data of the evacuation process, but they are not primarily designed f or use during an emergency.” Funders for this research include Technology Agency of The Czech Republic; Fakul ta Stavebni, Vysoke Uceni Technicke V Brne; Brno University of Technology. Our news correspondents obtained a quote from the research from Brno University of Technology: “The paper aims to test predicting RSET using a surrogate ML mode l trained on a simulation dataset with 60 samples. A total of 9 machine learning algorithms were tested on 3 simple geometries: bottleneck, stairway and walkway . A set of 7 spatial features was used to train the surrogate models. The result s showed a relatively good ability of Artificial Neural Network to learn in scen arios involving bottlenecks and stairways, with an R2: 0.99 on the testing datas et. In the walkway scenario, all models experienced a significant drop in perfor mance, with Gradient Boost performing the best (R2: 0.92).”
NETL
NSTL