A Multi Stream Feature Fusion Approach For Traffic Prediction
Keywords:
decision-making, Support Vector Machines (SVM), Logistic Regression, Decision Tree, ClassifierAbstract
Traffic prediction plays a crucial role in
urban planning, transportation
management, and public safety.
Traditional methods often rely on
single data sources and simplistic
models, leading to limited accuracy and
reliability. This paper proposes a novel
Multi-Stream Feature Fusion Approach
for Traffic Prediction, leveraging
diverse data streams and advanced
machine learning algorithms. By
integrating information from multiple
sources such as historical traffic data,
weather conditions, road infrastructure,
and special events, the system enhances
prediction accuracy and robustness.
Feature fusion techniques, including
concatenation and attention
mechanisms, are employed to integrate
features from different streams
effectively. Furthermore, various
machine learning algorithms such as
Support Vector Machines (SVM),
Logistic Regression, and Decision Tree
Classifier ,Naive bayes are utilized to
train predictive models, capturing
complex patterns in the data. Real-time
prediction capabilities enable timely
decision-making, while visualization
tools provide intuitive insights into
predicted traffic patterns. Experimental
results demonstrate the superiority of
the proposed approach over traditional
methods, highlighting its potential for
improving traffic prediction accuracy
and supporting efficient urban mobility
management
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













