It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.
AWARDS
WORKS
ALL
SCHOOLS & OFFICES
SCHOOL OF ARTS AND SOCIAL SCIENCES
LEE SHAU KEE SCHOOL OF BUSINESS AND ADMINISTRATION
SCHOOL OF EDUCATION AND LANGUAGES
SCHOOL OF NURSING AND HEALTH STUDIES
SCHOOL OF SCIENCE AND TECHNOLOGY
LI KA SHING SCHOOL OF PROFESSIONAL AND CONTINUING EDUCATION (LiPACE)
LIBRARY
STUDENT AFFAIRS OFFICE
COLLECTIONS
ABOUT
close
×
Search
Home
S&T Best Computing Projects
Graph embeddings for predicting traffic accident black spots
/sw/islandora/object/stcompfyp%3A127/datastream/OBJ/view
Collection
S&T Best Computing Projects
Details
Record ID
stcompfyp:127
Title
Graph embeddings for predicting traffic accident black spots
Type of Work
Final Year Project/Work
Collection
S&T Best Computing Projects
Contributor
Lo, Ka Ho (group member)
Cheng, Wang To (group member)
Cheung, Hang Tak (group member)
Lui, Kwok Fai Andrew 呂國輝 (supervisor)
School / Unit
School of Science and Technology (S&T)
Program
Bachelor of Computing with Honours in Internet Technology
Date
2021
Abstract
The aim of the project is to use observational data to build a deep machine learning model to model the relation between the accident proneness and road network structure design, road installations, and road local properties. In conclusion, this model provides a basis for improving the conditions of traffic facilities and enhancing traffic safety.
Type of Resource
PDF
Language
English
Physical Description
5 pages.
Awards
1st runner-up, Final Year Project (FYP) Competition (18th), 2021 (IEEE(HK) Computational Intelligence Chapter, Institute of Electrical and Electronics Engineers Hong Kong Section)
Keywords
traffic safety; computer algorithms; deep learning (machine learning)
Access Eligibility
Public Access
Permanent Link
https://repository.lib.hkmu.edu.hk/sw/islandora/object/stcompfyp:127
Sorry, you need to enable JavaScript to visit this website.