Short-term passenger flow forecasting is an essential component in urban rail transit operation. Emerging deep learning models provide good insight into improving prediction precision. Therefore, we propose a architecture combining the residual network (ResNet), graph convolutional (GCN), and long short-term memory (LSTM) (called "ResLSTM") to forecast on scale. First, improved methodologies of ResNet, GCN, attention LSTM are presented. Then, model proposed, wherein ResNet used capture...

To enhance firefighters' safety in fire environments, new phase-change protective clothing was developed using a drip molding process to improve thermal protection and comfort. The effects of the droplet interval (1, 1.5 2 cm) diameter (4, 6 8 mm) on performance under low radiation were examined by stored energy tester (SET). results demonstrate that extended second-degree burn time compared phase change material-coated fabrics, reducing skin heat absorption alleviating storage injuries....

Crowding force is an important index in evaluating the safety of those within high density crowds. However, studies on crowd simulation models have not been sufficiently developed, and related experimental are detailed to guide modeling research. Models that can reproduce real crowds enable calibration key parameters lacking. In this study, we improved typical social model simulate motion with calculation crowding forces. To crowds, pedestrians were modeled using three-circle model,...

A growing number of megacities have been experiencing changes to their landscape due rapid urbanization trajectories and travel behavior dynamics. Therefore, it is great significance investigate the distribution evolution a city's urban functional areas over different periods time. Although smart card automated fare collection system already widely used, few studies used data infer information about in areas, particularly developing countries. Thus, this research aims delineate dynamic that...

Crowd analysis and management is a key area of study for transit agencies seeking to optimize their operations facilitate safety risk activities. Key features crowd analytics include passenger flow volume, density, walking speed. This proposes generalized artificial intelligence (AI)-based model framework rail stations, by analyzing visualizing data from video records high-density crowds. Specifically, we propose AI-aided methodological (AI-Crowd) calculating You Only Look Once (YOLO) Deep...

Operational planning in China is perhaps more important today than ever before owing to the ongoing expansion of urban rail country. As networks increase size and complexity, new lines added them significantly alter both their topologies operational characteristics. Thus, appraisal alternative from perspective operation while crucial. In this study, a method forecast demands for obviate effects addition, terms overcrowding networks, was developed based on smart card data existing networks....

Socioeconomic attributes are essential characteristics of people, and many studies on economic attribute inference focus data that contain user profile information. For without profiles, like smart card data, there is no validated method for inferring individual attributes. This study aims to bridge this gap by formulating a mobility framework infer passengers’ based the relationship between personal integrates shop consumer prices, house using three steps: extraction, location feature...

We present a sustainable multimodal transit system that integrates taxi-sharing with subways to alleviate traffic congestion and restore the cooperative relationship between taxis subways. This study proposes two-phase matching model based on optimization theory, in which pick-up/drop-off sequences for participants, as well their motivation shift TSS service, were considered. For transportation system, achieving reduction vehicle miles is considered be objective. tested using empirical taxi...

In the design and evacuation evaluation of highly crowded places such as metro stations, continuous-space particle models have gained increasing attention because they are capable simulating normal crowd self-organisation phenomena including lane formation without need for complex walking rules. However, do not consider pedestrians' high level automatic control. The paper introduces a new method to original social force model based on smart agent using object-oriented programming. A...

The Chinese national rail transit design specification decides the size of urban platforms in China. This suggested method treats passengers as homogeneous individuals when calculating walking area within a platform. However, heterogeneity passenger behavior hub station has not been considered. It is reasonable to see individuals. In this study, by observing characteristics at platforms, two parameters were obtained, speed and luggage size. Passengers then accordingly put into different...

Fire evacuation simulations are essential for assessing schemes in subway stations. However, most studies and practical solutions have primarily focused on the effects of fire smoke behaviour evacuees. Moreover, these overlook movement evacuees fire-smoke diffusion; hence, they do not adequately reflect fire–pedestrian interaction. This study addresses this problem by formulating a evolution model using lattice Boltzmann method to simulate from mesoscopic perspective. The proposed can...

With the increase of travel demands in networked metro system, more and transfer stations are suffering from oversaturated situations, leading to accumulation passengers corridor boarding area with potential accident risks. To further improve efficiency passenger safety at stations, joint operation strategy is adopted. Metro trains allowed run across different lines switch other without transfer. This paper proposes 1) a meaningful, yet simple, way for defining running two intersecting 2) an...