Scribd
Upload
4 views1 page

Literature Survey and Uniqueness

Chapter 2 discusses various methods for monitoring and reducing vehicular emissions, highlighting the limitations of existing systems that rely on centralized processing and lack intelligent decision-making. The proposed system introduces a hybrid architecture using TinyML for real-time emission classification on microcontrollers, allowing for efficient data transmission and enhanced monitoring capabilities. This innovative approach aims to provide low-power, real-time, and intelligent solutions for vehicular pollution monitoring.

Uploaded by

Sajib Chowdhury
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
4 views1 page

Literature Survey and Uniqueness

Chapter 2 discusses various methods for monitoring and reducing vehicular emissions, highlighting the limitations of existing systems that rely on centralized processing and lack intelligent decision-making. The proposed system introduces a hybrid architecture using TinyML for real-time emission classification on microcontrollers, allowing for efficient data transmission and enhanced monitoring capabilities. This innovative approach aims to provide low-power, real-time, and intelligent solutions for vehicular pollution monitoring.

Uploaded by

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

Chapter 2: Literature Survey

Vehicular pollution is a leading cause of environmental degradation, especially in urban


areas where traffic congestion is frequent. Various studies have explored methods to
monitor and reduce emissions from vehicles using IoT, cloud computing, and machine
learning. In [1], an IoT-based real-time emission monitoring system was introduced using
gas sensors and a central server. Although the system allowed real-time data transmission
and monitoring, it lacked intelligent processing, edge-based analytics, and real-time
decision making.

A study in [2] presented a cloud-based air quality monitoring framework with a dashboard
to visualize pollutant levels in metropolitan cities. While effective in presenting macro-level
data, it relied on centralized processing and could not handle high-frequency real-time data
from numerous moving vehicles. Other works, such as [3], implemented mobile sensor
networks on public transport vehicles for large-scale pollution mapping. However, they
were limited to data collection and visualization, without edge inference or proactive alerts.

The use of Firebase as a real-time database for sensor data logging and display has been
explored in [4]. Although this offers real-time synchronization and simple deployment, most
applications are limited to passive logging without intelligent decision-making or inference.
The emergence of TinyML has enabled machine learning inference on microcontrollers like
the ESP32. In [5], a low-power gesture recognition system was deployed on a
microcontroller using TensorFlow Lite. While this demonstrated the potential of edge
inference, its application in vehicular pollution monitoring was unexplored.

In comparison to these works, the proposed system offers a unique combination of


technologies and innovations. It adopts a hybrid architecture that splits responsibilities
between edge and cloud, with lightweight machine learning inference deployed directly on
the ESP32 microcontroller using TinyML. This allows classification of emission severity into
“Normal”, “Warning”, and “Critical” categories in real time, directly at the vehicle level.
Instead of transmitting all sensor data, the system filters and transmits only high-severity
information to Firebase, reducing data bandwidth, enhancing response time, and enabling
scalable monitoring. These innovations set this system apart from existing models and
demonstrate its uniqueness in achieving low-power, real-time, and intelligent vehicular
emission monitoring.

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