Scribd
Upload
49 views10 pages

Traffic Prediction Using Dataset

Uploaded by

Vijay Sarathi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
49 views10 pages

Traffic Prediction Using Dataset

Uploaded by

Vijay Sarathi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

TRAFFIC

PREDICTION USING
DATASET
~MATHAN KAARTHIK AR
2117230040068
~PRASANTH S
2117230040081
ECE B 2ND YEAR
Introduction

Old Dataset Overview

New Dataset Overview

AGENDA Training type

Outcome

Conclusion

Reference
INTRODUCTION TO TRAFFIC
PREDICTION USING HISTORICAL DATA
Overview: Traffic prediction is essential for managing congestion and ensuring smooth traffic flow in urban areas.
With increasing urbanization, the number of vehicles on roads has grown significantly, leading to frequent traffic jams.
Accurate traffic prediction helps optimize traffic management and reduce congestion by forecasting traffic conditions at diff erent
junctions.
Historical Data: In this project, we use traffic data from 2015 to 2017,
containing information such as the number of vehicles passing through junctions, the time of day,
and other variables. By analyzing this historical data, we can understand traffic patterns and build a model that predicts
future traffic conditions.

ANFIS (adaptive-network-based fuzzy interference system) ------ SUPERVISED LEARING


OLD
DATASET
OVERVIEW
(2015-2017)
T HE TRA FF IC DAT ASE T (20 15 -2 01 7) CONT AINS
T IME-ST AMP ED RE COR DS O F VEH ICLE COUNT S
AC ROSS MU LT IP LE J UNCT IONS. IT I NCL UDES
KE Y FI EL DS LI KE DAT ET IME , J UNCT ION, AND
T HE NUMBE R OF VE HICLE S P ER HOUR . T HIS
DAT A I S U SED TO ANAL YZ E TRA FF IC PA TT ERNS
AND PR EDI CT FU TUR E C ONGE STI ON T RE NDS.
NEW
DATASET
OVERVIEW
(2023-2026)
(TRAINED DATA)

THE TRAFFIC DATASET (2023-2026) CONTAINS PREDICTED VEHICLE COUNTS


AT VARIOUS JUNCTIONS BASED ON HISTORICAL DATA FROM 2015-2017. IT
INCLUDES FIELDS LIKE DATETIME, JUNCTION, PREDICTED VEHICLES, AND
TRAFFIC CONDITION (LOW, MODERATE, OR HIGH), PROVIDING INSIGHTS INTO
FUTURE TRAFFIC FLOW TRENDS TO ASSIST IN URBAN PLANNING AND
TRAFFIC MANAGEMENT.
TRAINING TYPE : SUPERVISED LEARNING
• The traffic prediction model uses supervised learning for training.

• Historical traffic data from 2015 to 2017 is used as input to train the model, with the number of vehicles and traffic
conditions as the target output.

• The model learns patterns from this data using regression techniques in combination with machine learning
algorithms like neural networks (TensorFlow).

• After training, it predicts future traffic conditions for 2023 to 2026 based on learned trends.
OUTCOME
Input:

•Enter the date (YYYY-MM-DD): 2024-05-01

•Junction selected: Automatically chosen (e.g., Junction 1)

Output: •Date and Time: 2024-05- •Date and Time: 2024-05- •Date and Time: 2024-05-
01 08:00:00 01 09:00:00 01 10:00:00
•Predicted Vehicles: 50 •Predicted Vehicles: 75 •Predicted Vehicles: 40
•Traffic Condition: •Traffic Condition: High •Traffic Condition: Low
Moderate Traffic Traffic Traffic
CONCLUSION
1. Summary: Traffic prediction models provide a powerful tool for managing urban traffic. By predicting traffic flow based
on historical data, authorities can take proactive measures to reduce congestion and improve overall road safety.

2. Practical Applications:

• Intelligent Traffic Systems (ITS): Traffic predictions can be integrated into ITS to automate traffic signal control,
manage road closures, and reroute traffic based on real-time conditions.

• Navigation Apps: Predictive traffic models can be used in navigation apps like Google Maps or Waze to suggest
alternative routes and provide estimated arrival times based on traffic conditions.

3. Closing Remarks: Accurate traffic prediction is critical to developing smarter cities. As more data becomes available
and models improve, predictive traffic systems will play an even greater role in shaping urban transportation.
REFERENCE RESEARCH PAPER

Short-Term Traffic Flow Prediction Based on ANFIS

LINK: https://ieeexplore.ieee.org/document/5076964
THANK YOU
~MATHAN KAARTHIK AR
~PRASANTH S

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy