• Home
  • Search
  • Cross-State Traffic Accident Risk Prediction Using Self-Supervised Representation Learning on the US-Accidents Dataset
  • https://doi.org/10.63908/hmw5tk26Copy DOI Icon

Cross-State Traffic Accident Risk Prediction Using Self-Supervised Representation Learning on the US-Accidents Dataset

  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Traffic accident risk prediction is critical for intelligent transportation systems; however, models trained in one region often degrade when applied to other states due to heterogeneous traffic patterns, weather and infrastructure. This study evaluates cross-state accident risk prediction on the US-Accidents dataset (2016-2023; 7.7M records) under four transfer protocols: state-to-state, state-to-region, region-to-state, and region-to-region. A self-supervised learning with fine-tuning (SSL+FT) framework is proposed, where an encoder is pretrained on unlabeled data using a hybrid contrastive and masked reconstruction objective, then fine-tuned for binary risk classification. The approach is compared with traditional machine learning models (logistic regression, random forest, XGBoost) and deep learning models (multilayer perceptron (MLP), long short-term memory (LSTM), bidirectional LSTM (BiLSTM)). Results confirm significant performance degradation under cross-state distribution shift. Random forest and XGBoost achieve the best overall performance, with F1-scores up to 78% and 77%, respectively, while deep learning models show competitive but less stable performance across regions. In contrast, the proposed SSL+FT approach demonstrates consistent robustness, achieving up to 74% F1-score and 90% recall in region-to-region transfer. These findings indicate that self-supervised representation learning provides a scalable and generalizable solution for cross-state accident risk prediction under distribution shift.

Similar Papers
  • Conference Article
  • Citations16

A Novel Solution for EEG-based Emotion Recognition

  • Oct 13, 2021
  • Zhuofan Xie +2
  • Research Article

Development and Comparative Evaluation of Traditional Machine Learning and Deep Learning Models for Rainfall Prediction in Bimodal Rainfall Regions: A Case of Kilimanjaro Region, Tanzania

  • Sep 26, 2025
  • International Journal of Advanced Research
  • Gift Johnson Swai +2
  • Book Chapter
  • Citations7

CaSS: A Channel-Aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification

  • Jan 01, 2022
  • Yijiang Chen +4
  • Research Article
  • Citations32

Deep learning based classification of sheep behaviour from accelerometer data with imbalance

  • Apr 18, 2022
  • Information Processing in Agriculture
  • Kirk E Turner +4
  • PDF
  • Research Article
  • Citations45

Detection of maternal and fetal stress from the electrocardiogram with self-supervised representation learning

  • Dec 01, 2021
  • Scientific Reports
  • Pritam Sarkar +7
  • Conference Article
  • Citations2

A Novel Multi-Task Self-Supervised Representation Learning Paradigm

  • May 28, 2021
  • Control theory & applications
  • Yinggang Li +5
  • Book Chapter
  • Citations1

Gujarati Task Oriented Dialogue Slot Tagging Using Deep Neural Network Models

  • Jan 01, 2021
  • Rachana Parikh +1
  • PDF
  • Research Article

Using self-supervised feature learning to improve the use of pulse oximeter signals to predict paediatric hospitalization

  • Sep 28, 2021
  • Wellcome Open Research
  • Paul Mwaniki +5
  • Research Article
  • Citations1

Can Generative Models Improve Self-Supervised Representation Learning?

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Sana Ayromlou +3
  • Research Article

Using self-supervised feature learning to improve the use of pulse oximeter signals to predict paediatric hospitalization.

  • Feb 01, 2023
  • Wellcome Open Research
  • Paul Mwaniki +5
  • Conference Article
  • Citations6

Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?

  • Oct 02, 2023
  • Prakash Chandra Chhipa +4
  • Research Article
  • Citations9

One-step progressive representation transfer learning for bird sound classification

  • Sep 01, 2023
  • Applied Acoustics
  • Chengyun Zhang +4
  • Research Article

SELF-SUPERVISED REPRESENTATION LEARNING IMPROVING ROBUSTNESS AND GENERALIZATION IN MEDICAL IMAGE ANALYSIS TASKS

  • Jan 01, 2026
  • Journal of Emerging Technologies and Innovative Research
  • Mr.Chitikela Srinivas +2
  • Research Article

Predictive Analysis of Breast Cancer Survival Using Machine Learning, Deep Learning, and GPT-4

  • Jan 01, 2025
  • African Journal of Biomedical Research
  • Sulaiman Khan +9
  • PDF
  • Research Article
  • Citations194

Rice Crop Detection Using LSTM, Bi-LSTM, and Machine Learning Models from Sentinel-1 Time Series

  • Aug 18, 2020
  • Remote Sensing
  • Hugo Crisóstomo De Castro Filho +9
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.