Tezislər / Theses



Yüklə 17,55 Mb.
Pdf görüntüsü
səhifə111/493
tarix02.10.2023
ölçüsü17,55 Mb.
#151572
1   ...   107   108   109   110   111   112   113   114   ...   493
BHOS Tezisler 2022 17x24sm

 


THE 3
rd
 INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS 
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
121
EMERGENCY ALERT SYSTEM USING CONVOLUTIONAL 
NEURAL NETWORKS 
Alikram Masimzada 
Baku Higher Oil School
Baku, Azerbaijan 
elikram.mesimzade.std@bhos.edu.az
Supervisor: Ph.D Associate Professor Leyla Muradkhanli 
Keywords: 
Machine Learning, Crash analysis, Deep Learning, Convolutional Neural 
Network
Introduction 
Compared to previous decade, it is not complicated to find out traffic 
offender by the use of both radar and surveillance cameras. However, 
despite the reduced amount of traffic offender, but still they are dangerous 
and statistic is 4000 deaths and more than 100000 injuries in a day by car 
accidents. In modern countries, mostly all roads are controlled by surveillance 
cameras, but again there are some considerably amount problems: 
• As there are a lot of cameras, it is required plenty of operators (single 
operator can monitor several cameras in a real time).
• If any accidents occur, at that time mostly the people around whether 
think someone already called the emergency or they forget to call 
emergency. 
• Human being cannot be always reliable; operators will not monitor all 
the cameras for all of their working hours. 
These factors require to have automated solution to call emergency in 
case of any traffic accident. The use of Emergency alert system in traffic by 
Convolutional Neural Networks (CNN) will prevent such problems and by the 
applying of that emergency alert system, the death and injury rate will 
decrease. 

Yüklə 17,55 Mb.

Dostları ilə paylaş:
1   ...   107   108   109   110   111   112   113   114   ...   493




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©azkurs.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin