Scribd
Upload
5 views

Batch 03 Phase 1 Ppt

The project utilizes deep learning techniques to predict road accident severity and recommend hospitals for emergency response. By analyzing historical accident data, it aims to enhance decision-making for responders and improve medical assistance outcomes. Ultimately, the initiative seeks to save lives and reduce the impact of road accidents on communities.

Uploaded by

amjadali12omer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views

Batch 03 Phase 1 Ppt

The project utilizes deep learning techniques to predict road accident severity and recommend hospitals for emergency response. By analyzing historical accident data, it aims to enhance decision-making for responders and improve medical assistance outcomes. Ultimately, the initiative seeks to save lives and reduce the impact of road accidents on communities.

Uploaded by

amjadali12omer
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

LORDS INSTITUTE OF ENGINEERING AND

(UGC Autonomous
TECHNOLOGY
Accredited Institution)
by NBA, Accredited ‘A’ Grade
DEPARTMENT OF INFORMATION
by NAAC

TECHNOLOGY
MAJOR PROJECT
ROAD ACCIDENT SEVERITY &
HOSPITAL RECOMMENDATIONS
USING DEEP LEARNING
TECHNIQUES
Presented By:
Guide Name:
Amjad Ali (160921737003)
Ms. Sumayya
Sadia Habeeb Unnisa
Begum
(160921737014)
Hajira Noor (160921737302)
Assistant
CONTENT
S
Abstrac
t
Introductio
n
Literature
Survey
ABSTRAC
T
This project addresses critical challenges in road safety and emergency response
by applying advanced deep learning techniques to predict road accident severity
and recommend suitable hospitals for timely medical assistance. Through the
analysis of extensive historical accident data, the project provides accurate
severity predictions, offering emergency responders valuable insights into the
urgency and resources required for each incident. Additionally, it enhances
medical response by recommending hospitals based on proximity, facilities, and
specialties, thus reducing response times and improving outcomes for accident
victims. This initiative ultimately aims to save lives and mitigate the long-term
impacts of accidents on individuals and communities.
INTRODUCTIO
N data to accurately forecast the severity of
Predictive Modeling for Accident Severity : The project uses deep
learning techniques and historical accident
road accidents in real-time.
Enhanced Emergency Response : Real-time severity predictions allow
emergency responders to make faster, informed decisions, optimizing resource
allocation and prioritizing responses based on urgency.
Intelligent Hospital Recommendations : Beyond severity prediction,
the project recommends hospitals best suited to each incident, considering factors
like severity level, location, and medical facilities.
Impact on Community Safety : By integrating predictive analytics with
hospital recommendations, the project aims to improve emergency response
effectiveness, save lives, and reduce the broader impact of road accidents on
individuals and communities.
LITERATURE
SURVEY
Model(s)
Study Title Authors Year Performance/Results
Used

Road Accident Bi-LSTM, Bi-LSTM with 4 hidden layers provided the most
Joko Siswanto et
Predictions Using 2022 ConvLSTM, accurate predictions for medium and long-term
al.
LSTM Models Att-LSTM accidents.

Predicting Accident MobileNet,


Omar Ibrahim MobileNet achieved 98.17% accuracy, with Shapley
Severity Using 2023 CNN, LSTM,
Aboulola et al. values used for explainability.
Explainable AI etc.

Traffic Accident Risk CNN, Random Combined CNN and Random Forest outperformed
Haitao Zhao et al. 2023
Prediction Forest existing methods with better accuracy and AUC.

Neural
Severity Prediction in Wiriya Mahikul et Neural Networks achieved 90% accuracy, aiding
2023 Networks,
Emergency Centers al. emergency triage and response strategies.
XGBoost
THANK YOU

You might also like