Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Reduced multivariate polynomial-based neural network for automated traffic incident detection.

D Srinivasan¹, V Sharma, K A Toh

¹Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore 117576, Singapore. dipti@nus.edu.sg

Neural Networks : the Official Journal of the International Neural Network Society

|February 16, 2008

Summary

This study introduces a novel neural network model using a reduced multivariate polynomial pattern classifier for effective freeway incident detection. The proposed method efficiently captures complex traffic data relationships, outperforming other classification strategies.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Prognostic Implications of HPV Cell-Free DNA Serial Testing During Follow-Up of p16 Positive Oropharyngeal Squamous Cell Carcinoma After Curative-Intent Treatment.

Clinical oncology (Royal College of Radiologists (Great Britain))·2025

Same author

The UK Divide: Does Having a Pembrolizumab-Chemotherapy Option in Head and Neck Cancer Matter? Real-world Experience of First-line Palliative Pembrolizumab Monotherapy and Pembrolizumab-Chemotherapy Combination in Scotland.

Clinical oncology (Royal College of Radiologists (Great Britain))·2024

Same author

Challenging common misconceptions in vasa previa screening and diagnosis.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2023

Same author

Intensive Blood Pressure Management Preserves Functional Connectivity in Patients with Hypertension from the Systolic Blood Pressure Intervention Randomized Trial.

AJNR. American journal of neuroradiology·2023

Same author

Neoadjuvant tyrosine kinase inhibitor therapy in locally advanced differentiated thyroid cancer: a single centre case series.

The Journal of laryngology and otology·2023

Same author

Building capacity for cancer care infrastructure in Karnataka - the present and the future.

Klinicka onkologie : casopis Ceske a Slovenske onkologicke spolecnosti·2023

Area of Science:

Artificial Intelligence
Machine Learning
Transportation Engineering

Background:

Freeway incident detection is crucial for traffic management and safety.
Existing methods may struggle with the complex, nonlinear patterns in traffic data.
Pattern classification offers a promising approach for accurate incident identification.

Purpose of the Study:

To propose and evaluate a neural network model employing a reduced multivariate polynomial pattern classifier for freeway incident detection.
To demonstrate the suitability of the reduced multivariate model (RM) for two-category pattern classification tasks in traffic management.
To compare the performance of the proposed RM classifier against other established classification strategies.

Main Methods:

Development of a neural network model incorporating the reduced multivariate polynomial pattern classifier.

Related Experiment Videos

Implementation of Recursive Singular Value Decomposition (RSVD)-based least square estimators for classifier training.

Application of gradient descent-based least square estimators for classifier learning.

Comparative analysis of the RM model's performance with other classification techniques.

Main Results:

The reduced multivariate polynomial model effectively captures nonlinear input-output relationships in traffic data.
Both RSVD-based and gradient descent-based estimators successfully learned the RM classifier.
The proposed RM model demonstrated superior efficacy in freeway traffic incident detection compared to alternative methods.

Conclusions:

The proposed neural network model based on the reduced multivariate polynomial classifier is highly effective for freeway incident detection.
The RM classifier's ability to handle nonlinearities makes it well-suited for complex traffic pattern analysis.
This approach offers a significant advancement in intelligent transportation systems for enhanced traffic safety and management.