A deep neural network approach for pedestrian trajectory prediction considering flow heterogeneity

Humans, robots and artificial intelligences reconfiguring urban life in a crisis

“…Hence cities need a large array of options for coping with the unexpected (Roe, 2020) as resourceful communities can better respond to disaster events as they have more options available to come with solutions (MacKinnon and Derickson, 2013;Zona et al, 2020). For instance, the RAS operated without interruption during the major weather disruption caused by Storm Emma in 2018 (Morris et al, 2018;Pärnamaa, 2018). However, it must be noted that the RAS was not specifically designed for adverse conditions-robots are currently unable to transverse flooded areas (MKFM, 2020) and they sometimes required human assistance to complete their task in icy weather (Dempsey, 2022;Dobrosovestnova et al, 2022).…”

“…Classical mapping and navigation algorithms are considered insufficient for safe operation of robots in highdensity urban settings which are likely to require consideration of the sometimes random and sometimes linear flows of pedestrians (Du et al, 2019). Narrow AI driven by neural networks may achieve the sophistication needed to monitor and identify pedestrian trajectories (Nasr Esfahani et al, 2022) so that robots can learn to either "go with the flow" or "get out of the way". However, the ability to navigate crowded urban settings such as those that might be found in London or New York requires capacities approaching those of general AI, such as the ability to understand the social and psychological constraints on pedestrian behavior and cultural conventions of behavior in public space (Bera et al, 2017;Woo et al, 2020;Gao and Huang, 2021).…”

Mapping the knowledge domain of soft computing applications for emergency evacuation studies: A scientometric analysis and critical review

“…Especially in certain areas of crowd counting, evacuation tracking, crowd density estimation, crowd dynamics, crowd flow prediction, and evacuation video analysis, the DL can be viewed as a promising SC method. Hundreds of studies involving Convolutional Neural Networks (CNNs) and DL have shown their ubiquity in every vision sub-domain of emergency evacuations (Afiq et al, 2019;Hou and Wang, 2022;Lamba and Nain, 2017;Nasr Esfahani et al, 2022;Tripathi et al, 2019).…”

Substation equipment temperature prediction based on multivariate information fusion and deep learning network

“…In the last five years, neural networks have been widely used in substation equipment temperature prediction, such as back propagation neural network ( Liu, 2012 ), radial basis function neural network ( Wang et al, 2015 ), generalized regression neural network ( Kong & Zhang, 2016 ), adaptive neural network ( Wang, 2015 ), neural network optimized by swarm intelligence algorithm ( Xu, Hao & Zheng, 2020 ), support vector machine (SVM) and a series of other machine learning methods ( Zhang et al, 2020 ). In the past three years, deep learning networks have made breakthrough, such as pedestrian trajectoryprediction ( Esfahani, Song & Christensen, 2020 ), PM2.5 prediction ( Mohammadshirazi et al, 2022 ), traffic speed prediction ( Zheng, Chai & Katos, 2022 ), estimation of residual capacity for lithium-ion battery ( Hou et al, 2022 ) and so on ( Xu, Lin & Zhu, 2020 ). In 2021, Hou et al (2021b) solved the problem of temperature prediction of switchgear equipment in substation by using long short-term memory (LSTM) network, and achieved good results, which opens the prelude of solving the problem of substation equipment temperature prediction with deep learning network.…”