IOT Technology Based Vehicle Pollution Monitoring and Control

O. Pandithurai1,*, M Jawahar2, S Arockiaraj3, and R Bhavani4

1
Associate Professor, Department of Computer Science and Engineering, Rajalakshmi Institute of

Technology, Poonamallee, Chennai - 600 124.

2
Assistant Professor (Senior Grade) Department of Electrical and Electronics Engineering, Mepco

Schlenk Engineering College, Sivakasi, Tamilnadu, India - 626005

3
Assistant Professor (Senior Grade), Department of Electrical and Electronics Engineering, Mepco

Schlenk Engineering College, Sivakasi, Tamilnadu, India – 626005.

4
Associate Professor, Department of Electrical and Electronics Engineering, Mepco Schlenk

Engineering College, Sivakasi, Tamilnadu, India – 626005

*
Corresponding author: O. Pandithurai

E-mail: pandithurai.cse.o@gmail.com, tel: +91 91598 30828

GRAPHICAL ABSTRACT

ABSTRACT

Every year, the number of people who die because of pollution rises. Air pollution is generated by a

variety of factors, which is pollution caused by automobiles. Technological improvements make

great efforts to detect accidents and monitor pollution. In this paper, a novel Internet of Things-
1
based Vehicle Gas Emission Monitoring System (IoT-VGEMS) to monitor and control the

reduction of gas emissions. The overall work is categorized into two sections: One is Transmission

Part, and the other is receiving part. The Transmitting Part consists of Arduino UNO, MQ-135

Sensor, and nRF24L01 transmitter. The Receiving Part consists of Arduino UNO, LCD Display,

GSM, and nRF24L01 receiver. Initially, creating code to sense the data from the MQ-135 sensor to

the Arduino UNO and store the data in Arduino 1 is fetched to transfer with the help of the

nRF24L01 module. Using an Arduino UNO to interface with a GSM module. GSM module that

would deliver the warning and intimation messages to the vehicle owner and display them on LCD.

Finally, GSM can able to send a message to the respective user if the pollution level exceeds the

threshold. Hence the message from our device will give information about the emission and the user

could rectify it. `

Keywords: Arduino UNO, MQ-135 sensor, nRF24L01, GSM, Transmission, Receiving, Data.

1. Introduction

In recent years, pollution has had a direct influence on human health. To rising levels of noise and

air pollution, people are more susceptible to different health issues [1]. Growing industrialization

and urbanization are the main contributors to noise and air pollution. The primary factors that harm

both human health and the environment [2]. Monitoring and limiting such emissions are crucial.

Monitoring contamination using traditional methods was time-consuming and ineffective [3]. With

the development of technology, quick and effective pollution monitoring has been developed in the

Internet of Things (IoT) [4, 5]. With the aid of many sensors, it allows data exchange between the

internet, electrical and electronic appliances, and people. IoT is successful because it is affordable,

effective, and feasible [6]. Pollutants from cars, vehicles, and buses are causing an increase in

environmental issues, which is why asthma attacks and respiratory illnesses are on the rise. The

only traffic is responsible for 50% of the carbon monoxide in the air [7].

According to data statistics, India is at the top of the list of nations with pollution-related transience

in 2016, with 2.51 million people dying ahead of time due to illnesses connected to air, water, and

2
other kinds of pollution [8,9]. The Lancet investigation found that air pollution, followed by water

pollution (1.76 million) and industrial pollution (0.83 million), were the main causes of 6.49 million

catastrophes in 2016. Examples of air pollutants include volatile organic compounds (VOCs),

oxides of carbon, nitrogen, and sulphur, as well as other contaminants [10, 11]. Statistics also

suggest that automotive emissions account for around 30% of total air pollution as shown in Figure

1.

Figure 1. Lancet Statistics

Delhi, India's capital, is widely regarded as one of the world's most polluted cities [12]. Air

pollution disrupts the maintenance of normal air quality and causes various problems for animals,

plants, and humans. When external substances such as CO and CO2 enter the air, it leads to air

pollution. Poor air quality can cause eye, nose, and throat irritation, shortness of breath, and other

respiratory, heart, and cardiovascular diseases [13, 14]. To overcome the problem a novel IoT

VGEMS model has been proposed to reduce BC emissions and mitigate climate change by

proposing an IoT model that estimates his current CO2 levels and performs historical analysis of the

measurements. This will help drive investment in more healthy towns and purifier kinds of energy.

The main contributions are:

• A novel Internet of Things-based Vehicle Gas Emission Monitoring System (IoT-VGEMS)

has been proposed to monitor and control the reduction of gas emissions through the web

server in the vehicle based on IoT.

3
 • Initially, creating code to sense the data from the MQ-135 sensor to the Arduino UNO and

store the data in Arduino 1 is fetched to transfer with the help of the nRF24L01 module.

• Using an Arduino UNO to interface with a GSM module. Creating code for a GSM module

that would deliver the warning and intimation messages to the vehicle owner and display

them on LCD.

• GSM can able to send a message to the respective user if the pollution level exceeds the

threshold. Instead of using the Wi-Fi and GSM module, the data is uploaded to the cloud.

• Finally, the data will be sensed by the sensor and stored in the last and current variables. If

the current value exceeds the last stored value will be updated.

In this research paper, Section 2 describes the literature review in detail. The proposed IoT-VGEMS

model is discussed in Section 3. Section 4 covers the result and discussion, while Section 5 provides

a conclusion.

2. Literature Survey

Most pollution monitoring methods used today monitor and take into account a variety of

environmental factors. This section is an overview of a few recent advanced methods used to,

monitor and control the reduction of gas emissions in the vehicle.

In 2020, Hu, Z. and Tang, H., [15] suggested an IoT-based intelligent transportation system. It

features a distance-based adaptive cruise control system. The simulation's results show that the

intelligent transportation system is capable of understanding the condition of the road and

effectively realizing information flow between the vehicle and the command centre. It can increase

the speed at which cars travel while lowering the amount of air pollution brought on by petrol

emissions.

In 2022, Rauniyar, A., et al., [16] design an IoT-based car emissions monitoring system for smart

cities. Real-time monitoring of vehicle noise and pollution sensor data is done by infrastructure

managers and analysts. The data was analysed using artificial intelligence (AI) algorithms, which

4
classified the sources into high, medium, and normal emitters. the development of a complete

software solution that might work with existing intelligent transport systems in smart cities.

In 2020, Kaivonen, S. and Ngai, E.C.H., et al., [17] suggested using wireless sensors on public

vehicles for real-time air pollution monitoring. The measurements from the sensors on public

transportation cars supplement those from the stationary sensors and Uppsala's sole ground-level

monitoring station. As a result of the experiments, the system's data and communication quality

have been assessed.

In 2020, Zhang, D. and Woo, S.S., [18] suggested designing the air quality pattern in the area using

both moving and fixed IoT sensors mounted in the vehicles patrolling the area. The entire spectrum

of air quality is examined in surrounding areas. The ability of the proposed technique to accurately

measure and predict air quality using various ML algorithms and real-time data demonstrates its

effectiveness. The results show that air quality forecasting and monitoring in a smart city is efficient

and promising.

In 2020, Jo, J., et al [19] suggested an IoT-based Smart-Air method to efficiently monitor air quality

and send data to the web server in real-time via LTE. An LTE modem, sensors for tracking

pollutants, and a microprocessor make up the device. You can monitor the air quality via the web

server at any time and from anywhere. The web server can keep all the data in the cloud to give

users access to resources for additional analysis of indoor air quality.

In 2020, Shetty, C., et al [20] suggested an IoT technique for observing vehicle emission rates. The

real-time data is used to create a predictive algorithm that forecasts the levels of carbon monoxide.

To monitor the levels of pollutants, sensors are built into the vehicles. At the same time that the

emission level is being monitored, the fuel delivery to the engine is being shut off using a solenoid

valve.

In 2020, Kalia, P. and Ansari, M.A., [21] suggested an IoT-based platform is used for real-time

monitoring system of all the data to check air quality. On your smartphone or computer, Thing

Speak offers a digital dashboard that shows current air quality readings for your surroundings. The

5
collected data can be analyzed by comparing it to the standardized parameters of PM2.5 (0–30

μg/m3), PM10 (0–50 μg/m3), and AQI (0–50 PPM).

In 2021, Gautam, A., et al., [22] suggested a sensor-based embedded system that uses IoT to

manage and screen air pollution generated from anywhere in the globe. A Raspberry Pi-based

embedded system prototype that employs sensors and actuators is based on the IoT. A website is

also made to virtually check the level of gases anywhere. The outcomes show that the entire system

has been effectively tested and put into use.

In 2022, Kumar, A., et al [23] suggested an IoT-based system for monitoring vehicle pollution. The

Arduino Uno's sensors keep track of the number of pollutants coming from car exhaust. And the

prototype uses a raspberry pi for monitoring and control. Here the vehicle user will be warned by

the buzzer and if it is ignored, a challan is filed to the user and it is sent to the mail id.

In 2022, Asha, P., et al [24] suggested the ETAPM-AIT model, eight pollutants—NH3, CO, NO2,

CH4, CO2, PM2.5, temperature, and humidity are sensed using an IoT-based sensor array. The

sensor array calculates the pollutant amount and sends it, via gateways, to the cloud server for

analysis. In 5, 15, 30, and 60 minutes. The simulation analysis is complete, and the findings are

examined using the AI technique.

Existing monitoring techniques require laboratory analysis and have poor accuracy and sensitivity.

Consequently, better vehicle monitoring methods are required. To overcome the above drawbacks,

a novel IoT-VGEMS has been proposed in this paper.

3. System model

In this section, a novel IoT-VGEMS to monitor and control the reduction of gas emissions in the

vehicle based on IoT. The proposed work was completed in the following manner: Basic

understanding of all system components (Arduino UNO, MQ-135 CO and SO2 gas sensor, GSM

module, nRF24L01). MQ-135 sensor to Arduino UNO interface. Calculate the pollutant threshold

values in vehicle emissions. Creating code to sense the data from the MQ-135 sensor to the Arduino

UNO. The Stored data in Arduino 1 is fetched to transfer with the help of the nRF24L01 module.

6
Whenever the crossover near tollgates or poles is carried out, the data from Arduino1’s flash

memory will be transferred from Arduino 1's nRF24L01 to Arduino 2. Using an Arduino UNO to

interface with a GSM module. Creating code for a GSM module that would deliver warning and

intimation messages to users. For authorities, the cloud (using IOT technology) is used to deliver

fines. The numerous building blocks and components used in this project's creation each have

specific functions that are carefully examined. The different blocks include an nRF2401, a GSM

module, an MQ-135 gas sensor, and an Arduino UNO. This part provides an explanation of each

block's operation, function within the project, and technical requirements. The overall operation is

depicted in Fig 2.

Figure 2. The overall process of the proposed IoT-VGEMS method

1. MQ135 sensor

The MQ135 monitor is capable of detecting various gases, including CO, SO2, smoke, NH3, NOx,

alcohol, and benzene. It outputs data in the form of voltage levels.

2. Arduino UNO

The microcontroller board for the Arduino Uno is constructed using the ATmega328P. It has a USB

connection, a power jack, an ICSP header, a 16 MHz quartz crystal, six analogue input pins,

fourteen digital input and output pins, and a reset switch.

3. WIFI Module
7
The ESP8266 is a low-cost Wi-Fi chip with a complete TCP/IP stack and MCU (microcontroller

unit) capability. Our device can connect to Wi-Fi or the internet thanks to its 3.3-volt operation.

4. LCD

This is a basic (16x2) 16-character, the 2-line display has a green background and black lettering.

It's employed to display the air and humidity in PPM.

5. GSM Module

Communication between a computer and a GSM device is established using a GSM module. The

architecture used for mobile transmission is called the Global System for Mobile Communication

(GSM).

Figure 3. Air Pollution Monitoring System

To maintain the air quality, CO and SO2 gas sensors are used to constantly check the pollution.

Figure 3 displays the block diagram of the suggested air pollution monitoring system. RFID reader,

wireless gas sensors, and a microcontroller are incorporated at the monitoring site. The air pollution

generated by the vehicle is measured by the microcontroller. The car owner receives a warning

notification if the pollutant levels exceed the threshold levels. The LCD shows the same

information. The server of the approved agencies and the vehicle owner is also sent information

regarding the levels of CO and SO2, vehicle number, RFID, and time and date of the vehicle. For

later use, this material is kept in the server database.

8
The Overall Working is categorized into two sections: One is Transmission Part, and the other is

receiving part. The Transmitting Part consists of Arduino UNO, MQ-135 Sensor, and nRF24L01

transmitter. The Receiving Part consists of Arduino UNO, LCD Display, GSM, and nRF24L01

receiver. The Outline of the system can be explained in detail using the flow chart depicted in

Figure 3.

Figure 4. Diagram of Suggested System

3.1. Working of Suggested system

9
This system can be installed in any automobile that contributes to air pollution in the environment.

Our model installation is as follows: The MQ-135 sensor is connected to the Arduino. The Arduino

is then interfaced with nRF24L01 which acts as a transmitter. A Code should be uploaded to the

Arduino to create a communication of nRF24L01.The Header files for the sensor, memory, and

nRF module are set up and the pins are initialized. The Transmission memory address is fixed, to

create a handshake with the receiver. The nRF24L01 pins are initialized and the Arduino is set to

test whether the RF module is initialized or not. The Variable for sensing is initialized to zero. The

Values will be sensed by the sensor and stored in the last and current variables. If the current value

exceeds the last stored value will be updated. This process runs continuously and the nRF

transmitter module will look for the receiving module as shown in Figure 4.

10
 Figure 5. Flow Chart of Transmission Part

When the transmitter is ready, it will be transmitting the data continuously. On the other hand,

another Arduino is interfaced with an nRF receiver and LCD Display. Whenever the transmission

side nRF module comes in the communication range of the receiving side nRF module, the data will

be transmitted from transmitter to receiver.

11
 Figure 6. Flow Chart of Receiving Part

The Communication between two nRF modules is done using GFSK Modulation. In GFSK

(Gaussian Frequency Shift Keying modulation) where baseband pulses (consisting of -1 and 1) are

made to pass through the Gaussian filter before the modulation. This Gaussian filter helps to

smooth out the pulses and, as a result, reduces the spectrum's breadth, a process known as pulse

shaping. After the data is received, the information is sent through GSM Module. GSM is a digital

mobile network that is used by mobile phone users throughout the world. GSM is designed to be a

safe wireless system. It has considered user authentication via a pre-shared key and challenge-

response, as well as over-the-air encryption. Using GSM, it can able to send a message to the

respective user if the pollution level exceeds the threshold. To upload the data into the cloud,

instead of using the Wi-Fi module, and GSM Module. In this project, we use GSM sim800l to

upload data to the cloud because SIM800L supports General Packet Radio Service (GPRS) for

12
internet access via HTTP. AT commands can be used to access the module's built-in TCP/IP stack.

This can be very useful for long-term data logging on low-bandwidth networks. The Data is sent to

the cloud and the overall work on receiving side is shown in Figure 6.

4. Result and Discussion

4.1. Hardware Implementation

In this section, a novel proposed has been described in detail. The significance of the sensor node

for real-time analysis of the nodes’ filling state will be discussed. MQ-135 gas sensor is used to

detect the SO2 and CO gas released from the vehicle. Continuous comparisons are made between

the detected gas and the predetermined threshold values. The sensed value and benchmark value are

compared using an Arduino controller, and if the sensed value exceeds the threshold value, a

warning is sent to the user (GSM Module) and authorities (IOT Technology) with the help of the

nRF24L01 trans-receiver. The electrical connection is used to charge the sensor node using its built-

in batteries. The sensor node and gateway are combined with the +5 V and +3.3 V voltage

converters to supply the necessary voltage.

The Proposed Project was tested. The Proposed System measures the real-time pollution level of

various automobiles. The Overall proposed prototype is shown in Fig 7.

Figure 7. Simulation setup

13
Figure 8 depicts the monitoring device, which shows the vehicle's levels of pollution. To track the

vehicle's pollution levels, the controller transmits to the server the specifics of the vehicle and the

pollutant values.

Figure 8. Displaying sensor values on an LCD

Data in general is uploaded to the cloud whenever there is a handshake between the transmission

and receiving parts. On the Webpage, the location is indicated to denote the place at which the

vehicle crosses the receiver setup Here two data are used to display the pollution range of the

vehicle. The first one of the vehicles remains stationary and the second is the vehicle which starts

and emits pollution. For a vehicle that remains stationary, the webpage is displayed with a green

widget and data is stored in the database as shown in Figure 9.

Figure 9. Display of vehicle data when the vehicle is stationary

The Threshold is set at 50 ppm. When the vehicle starts, it displays 50% and above level on the

webpage because testing usually takes an initial value of CO and SO2, which is 50 ppm. The

webpage is displayed with a red widget and the pollution level, which is sent to the vehicle owner
14
and advises the pollution level of the vehicle as well as the penalty for causing pollution, as shown

in Figure 10.

Figure 10. Indication of vehicle owner about the pollution level

Figure 9 illustrates, the display of vehicle data. It displays the date, time, detection location, user

name, registration number, mobile number, and detection level. In Figure 11 the air pollution

monitoring system will place in the vehicle, which indicates 61% of the pollution level when the

vehicle is started. All the data is stored in the cloud.

Figure 11. Display of vehicle data when the vehicle is started

The Experimental results are tabulated as shown in Table 1. It gives the pollution level of the

various vehicle. Pollution levels were 50 in Raju's vehicle, 55 in Joel's vehicle, 53 in Vishnu's

vehicle, and 61 in Naveen's vehicle.

15
 Table 1. Real-Time Results

S. No Name of the vehicle owner Pollution level

1 Raju 50
2 Joel 55
3 Vishnu 53
4 Naveen 61

Table 2. Sample data

S. No AQI Time
1 100 0
2 50 4
3 100 7
4 400 9
5 423 11
6 150 14
7 300 18
8 104 20
9 130 0
10 80 4
11 110 6
12 440 9
According to Table 2, the high concentration of dots between hours 12 and 15 indicates that the area

is particularly polluted during this period. Figure 12's graphical depiction of pollution levels, AQI

(Air Quality Index), and time are two examples of sample statistics from Table 2. Pollution levels

during normal hours of the day.

16
 Figure 12. Histogram representing the Pollution Level

The information gathered includes the local temperature and humidity, particulate matter, and the

quantity of toxic and harmful gases like CO and SO2. The information gathered outdoors will be in

analog format. The data will be routed, digitalized, and then stored on a server from which the

controlling and monitoring devices can readily access it using the IoT. The IoT enables the

collection and transmission of data in a more readable format to websites or mobile applications,

not only increasing people's awareness of pollution levels in their area but also assisting them in

understanding when and how to take precautions to protect themselves from various health risks.

4.2 Comparative Analysis

The performance of the existing techniques was compared with the performance of the proposed

strategy to demonstrate that it is more effective. In a comparative study, the proposed IoT-VGEMS

model is compared with existing approaches. Compares the overall performance of the proposed

method is shown in Figure 13.

Figure 13: Comparison analysis of the proposed IoT-VGEMS model

17
Figure 13 shows the outcomes of the overall accuracy rate. In comparison, the proposed IoT-

VGEMS achieve a high accuracy range of 97.98%. It shows that the accuracy obtained by the IoT-

based Smart-Air technique, sensor-based embedded system, and AI Technique is 95.34%, 94.39%,

and 92.92% respectively. The specificity obtained by IoT-based Smart-Air technique, sensor-based

embedded system, and AI Technique is 91.19%, 93.98%, and 93.18%. Precision is obtained by IoT-

based Smart-Air technique, sensor-based embedded system, and AI Technique is 90.58%, 93.87%,

and 91.49%. Recall is obtained by IoT-based Smart-Air technique, sensor-based embedded system,

and AI Technique is 93.51%, 90.59%, and 92.87%. F1 score is obtained by IoT-based Smart-Air

technique, sensor-based embedded system, and AI Technique is 90.31%, 89.98%, and 90.89%. The

proposed IoT-VGEMS achieves a higher accuracy rate than the currently used models.

5. Conclusion

In this paper, a novel Internet of Things-based Vehicle Gas Emission Monitoring System (IoT-

VGEMS) to monitor and control the reduction of gas emissions. The overall work is categorized

into two sections: One is Transmission Part, and the other is receiving part. The Transmitting Part

consists of Arduino UNO, MQ-135 Sensor, and nRF24L01 transmitter. The Receiving Part consists

of Arduino UNO, LCD Display, GSM, and nRF24L01 receiver. Initially, creating code to sense the

data from the MQ-135 sensor to the Arduino UNO and store the data in Arduino 1 is fetched to

transfer with the help of the nRF24L01 module. Using an Arduino UNO to interface with a GSM

module. GSM module that would deliver the warning and intimation messages to the vehicle owner

and display them on LCD. Finally, GSM can able to send a message to the respective user if the

pollution level exceeds the threshold. Hence the message from our device will give information

about the emission and the user could rectify it. Few people will not take any action even if they

receive a warning from transport officials, they will be penalized further. The monitoring system is

battery-based. In the future, since sunlight is pure and free of pollutants, we can design small and

compact monitoring systems based on solar energy and add other low-cost sensors to detect

accidents.
18
References

1. Muthukumar, S., Mary, W. S., Jayanthi, S., Kiruthiga, R., & Mahalakshmi, M. (2018, July),

IoT-based air pollution monitoring and control system. In 2018 International Conference on

inventive research in computing applications (ICIRCA) (pp. 1286-1288). IEEE.

2. Janeera, D.A., Poovizhi, H., Haseena, S.S. and Nivetha, S., (2021, March), Smart embedded

framework using arduino and IoT for real-time noise and air pollution monitoring and alert

system. In 2021 International Conference on Artificial Intelligence and Smart Systems

(ICAIS) (pp. 1416-1420). IEEE.

3. Bhuvaneswari, T., Hossen, J., Asyiqinbt, N., Hamzah, A., Velrajkumar, P. and Jack, O.H.,

(2020), Internet of things (IoT) based smart garbage monitoring system. Indonesian Journal

of Electrical Engineering and Computer Science, 20, 736-743.

4. Nižetić, S., Šolić, P., González-De, D.L.D.I. and Patrono, L., (2020), Internet of Things

(IoT): Opportunities, issues and challenges towards a smart and sustainable future. Journal

of Cleaner Production, 274, 122877.

5. Abid, M.A., Afaqui, N., Khan, M.A., Akhtar, M.W., Malik, A.W., Munir, A., Ahmad, J. and

Shabir, B., (2022), Evolution towards smart and software-defined internet of things. AI, 3,

100-123.

6. Sasikumar, A., Vairavasundaram, S., Kotecha, K., Indragandhi, V., Ravi, L., Selvachandran,

G. and Abraham, A., (2023), Blockchain-based trust mechanism for digital twin empowered

Industrial Internet of Things. Future Generation Computer Systems, 141, 16-27.

7. Rakhonde, M.A., Khoje, S.A. and Komati, R.D., (2018, November), Vehicle collision

detection and avoidance with pollution monitoring system using IoT. In 2018 IEEE Global

Conference on Wireless Computing and Networking (GCWCN) (pp. 75-79). IEEE.

8. Ravindra, K., Singh, T. and Mor, S., (2022), Preventable mortality attributable to exposure

to air pollution at the rural district of Punjab, India. Environmental Science and Pollution

Research, 29, 32271-32278.

19
9. Li, X., Li, Y., Yu, B., Zhu, H., Zonglei, Z., Yang, Y., Shunjin, L., Yunyun, T., Junjie, X.,

Xiangyi, X. and Li, Y., (2022), Health and economic impacts of ambient air pollution on

hospital admissions for overall and specific cardiovascular diseases in Panzhihua,

Southwestern China. Journal of Global Health, 12.

10. Zhang, Y., Yin, Z. and Wang, H., (2020), Roles of climate variability on the rapid increases

of early winter haze pollution in North China after 2010. Atmospheric Chemistry and

Physics, 20, 12211-12221.

11. Teixeira, P., Salvador, D., Brandão, J., Ahmed, W., Sadowsky, M.J. and Valério, E., (2020)

Environmental and adaptive changes necessitate a paradigm shift for indicators of fecal

contamination. Microbiology Spectrum, 8, 8-2.

12. Krishan, M., Jha, S., Das, J., Singh, A., Goyal, M.K. and Sekar, C., (2019), Air quality

modelling using long short-term memory (LSTM) over NCT-Delhi, India. Air Quality,

Atmosphere & Health, 12, pp.899-908.

13. Billings, M.E., Hale, L. and Johnson, D.A., (2020), Physical and social environment

relationship with sleep health and disorders. Chest, 157, 1304-1312.

14. Kendzerska, T., Szyszkowicz, M., Alvarez, J.V., Mallick, R., Carlsten, C., Ayas, N., Laratta,

C.R., Jovic, B., Orach, J., Smith-Doiron, M. and Dales, R., (2022), Air Pollution and the

Effectiveness of Positive Airway Pressure Therapy in Individuals with Sleep Apnea: A

Retrospective Community-Based Repeated-Measures Longitudinal Study. Chest, 162, 1176-

1187.

15. Hu, Z. and Tang, H., 2022. Design and Implementation of Intelligent Vehicle Control

System Based on Internet of Things and Intelligent Transportation. Scientific

Programming, 2022, pp.1-11.

16. Rauniyar, A., Berge, T. and Håkegård, J.E., 2022, June. NEMO: Internet of Things based

Real-time Noise and Emissions MOnitoring System for Smart Cities. In 2022 IEEE 12th

Sensor Array and Multichannel Signal Processing Workshop (SAM) (pp. 206-210). IEEE.

20
17. Kaivonen, S. and Ngai, E.C.H., (2020), Real-time air pollution monitoring with sensors on

city bus. Digital Communications and Networks, 6, 23-30.

18. Zhang, D. and Woo, S.S., (2020), Real time localized air quality monitoring and prediction

through mobile and fixed IoT sensing network. IEEE Access, 8, 89584-89594.

19. Jo, J., Jo, B., Kim, J., Kim, S. and Han, W., (2020), Development of an IoT-based indoor air

quality monitoring platform. Journal of Sensors, 2020, 1-14.

20. Shetty, C., Sowmya, B.J., Seema, S. and Srinivasa, K.G., (2020), Air pollution control

model using machine learning and IoT techniques. In Advances in Computers, 117, 187-

218, Elsevier.

21. Kalia, P. and Ansari, M.A., (2020), IOT based air quality and particulate matter

concentration monitoring system. Materials Today: Proceedings, 32, 468-475.

22. Gautam, A., Verma, G., Qamar, S. and Shekhar, S., (2021), Vehicle pollution monitoring,

control and challan system using MQ2 sensor based on internet of things. Wireless Personal

Communications, 116, 1071-1085.

23. Kumar, A., Kesarwani, S., Mishra, T. and Verma, Y.K., (2022), Vehicle Pollutant Control

System using IOT. i-Manager's Journal on Instrumentation & Control Engineering, 10, 16.

24. Asha, P., Natrayan, L.B.T.J.R.R.G.S., Geetha, B.T., Beulah, J.R., Sumathy, R.,

Varalakshmi, G. and Neelakandan, S., (2022), IoT enabled environmental toxicology for air

pollution monitoring using AI techniques. Environmental research, 205, 112574.

25. Aguado J., Arsuaga J.M., Arencibia A., Lindo M. and Gascón V. (2009), Aqueous heavy

metals removal by adsorption on amine-functionalized mesoporous silica, Journal of

Hazardous Materials, 163, 213-221.

26. Allen S.J., McKay G. and Khader K.Y.H. (1989), Intraparticle diffusion of a basic dye

during adsorption onto Sphagnum Peat, Environmental Pollution, 56, 39-50.

21
27. Areco M.M. and Afonso M.S. (2010), Copper, zinc, cadmium and lead biosorption by

Gymnogongrus torulosus. Thermodynamics and kinetics studies, Colloids and Surfaces B:

Biointerfaces, 81, 620-628.

28. Jiyal, S., Sheethlani, J., Bhopal, M.P. and Saini, R.K., 2022. INTERNET OF THINGS

BASED AIR POLLUTION PREDICTION AND MONITORING SYSTEM. Ann. For.

Res, 65(1), pp.7599-7614.

29. Akhila, R., Amoghavarsha, B.M., Karthik, B.C. and Prajwal, Y.M., 2022, January. Internet

of Things based Detection and Analysis of Harmful Vehicular Emissions. In 2022 4th

International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 630-

636). IEEE.

30. Alshahrani, A., Mahmoud, A., El-Sappagh, S. and Elbelkasy, M.A., 2023. An Internet of

Things Based Air Pollution Detection Device for Mitigating Climate Changes.

22