AI Article Synopsis
- Pedestrian two-stage crossings are designed to improve safety and efficiency at busy intersections by allowing pedestrians to cross in two separate stages, handling one direction of traffic at a time.
- This paper introduces a new model using Physics-Informed Neural Networks (PINNs) to analyze pedestrian behavior during these crossings, leveraging fluid dynamics principles to assess aspects like speed and density.
- The study reveals that PINNs provide better predictions of pedestrian flow compared to traditional methods, offering valuable insights for enhancing pedestrian safety and facilitating interactions with autonomous vehicles in smart transportation systems.
Article Abstract
Pedestrian two-stage crossings are common at large, busy signalized intersections with long crosswalks and high traffic volumes. This design aims to address pedestrian operation and safety by allowing navigation in two stages, negotiating each traffic direction separately. Understanding crosswalk behavior, especially during bidirectional interactions, is essential. This paper presents a two-stage pedestrian crossing model based on Physics-Informed Neural Networks (PINNs), incorporating fluid dynamics equations to determine characteristics such as speed, density, acceleration, and Reynolds number during crossings. The study shows that PINNs outperform traditional deep learning methods in calculating and predicting pedestrian fluid properties, achieving a mean squared error as low as 10. The model effectively captures dynamic pedestrian flow characteristics and provides insights into pedestrian behavior impacts. The results are significant for designing pedestrian facilities to ensure comfort and optimizing signal timing to enhance mobility and safety. Additionally, these findings can aid autonomous vehicles in better understanding pedestrian intentions in intelligent transportation systems.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11390893 | PMC |
| http://dx.doi.org/10.1038/s41598-024-72155-y | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Intelligent in-cell electrophysiology: Reconstructing intracellular action potentials using a physics-informed deep learning model trained on nanoelectrode array recordings.
Nat Commun
January 2025
Aiiso Yufeng Li Family Department of Chemical and Nano Engineering, University of California San Diego, La Jolla, CA, USA.
Intracellular electrophysiology is essential in neuroscience, cardiology, and pharmacology for studying cells' electrical properties. Traditional methods like patch-clamp are precise but low-throughput and invasive. Nanoelectrode Arrays (NEAs) offer a promising alternative by enabling simultaneous intracellular and extracellular action potential (iAP and eAP) recordings with high throughput.
View Article and Find Full Text PDFPhysics-Constrained Deep Learning for Security Ink Colorimetry with Attention-Based Spectral Sensing.
Sensors (Basel)
December 2024
Department of Electrical Engineering, Lunghwa University of Science and Technology, Taoyuan 333326, Taiwan.
The proliferation of sophisticated counterfeiting poses critical challenges to global security and commerce, with annual losses exceeding $2.2 trillion. This paper presents a novel physics-constrained deep learning framework for high-precision security ink colorimetry, integrating three key innovations: a physics-informed neural architecture achieving unprecedented color prediction accuracy (CIEDE2000 (ΔE00): 0.
View Article and Find Full Text PDFNeural network emulator for atmospheric chemical ODE.
Neural Netw
January 2025
School of Engineering Sciences, Lappeenranta-Lahti University of Technology LUT, Lahti, 15110, Finland; Atmospheric Modelling Centre Lahti, Lahti University Campus, Lahti, 15140, Finland; Institute for Atmospheric and Earth System Research (INAR), The University of Helsinki, Helsinki, 00014, Finland.
Article Synopsis
- Modelling atmospheric chemistry is complicated and involves intensive computations; however, the proposed ChemNNE uses Deep Neural Networks to quickly simulate chemical concentrations by treating them as time-dependent equations.
- This emulator employs an attention-based mechanism, sinusoidal time embedding for capturing periodic patterns, and a Fourier neural operator to improve efficiency and handle complex behaviors in the chemical processes.
- The model is trained with three physics-informed loss functions to adhere to conservation laws and reaction rates, and it is validated using a large-scale dataset that sets a benchmark for accuracy and speed in future research.
Light microscopy is a practical tool for advancing biomedical research and diagnostics, offering invaluable insights into the cellular and subcellular structures of living organisms. However, diffraction and optical imperfections actively hinder the attainment of high-quality images. In recent years, there has been a growing interest in applying deep learning techniques to overcome these challenges in light microscopy imaging.
View Article and Find Full Text PDFThree-Dimensional Thermal Tomography with Physics-Informed Neural Networks.
Tomography
November 2024
KYAMOS Ltd., 37 Polyneikis Street, Strovolos, Nicosia 2047, Cyprus.
: Accurate reconstruction of internal temperature fields from surface temperature data is critical for applications such as non-invasive thermal imaging, particularly in scenarios involving small temperature gradients, like those in the human body. : In this study, we employed 3D convolutional neural networks (CNNs) to predict internal temperature fields. The network's performance was evaluated under both ideal and non-ideal conditions, incorporating noise and background temperature variations.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!