Page 1817
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
Development of Smart Water IoT System to Assess and Monitor the
Quality of Indian River Water
E. Amrutha
1*
, Dinesh Ram S P
1
, Ranil Vikram P
1
1
Electronics and Communication Engineering Department Mepco Schlenk Engineering College
Sivakasi, India
DOI:
https://doi.org/10.51583/IJLTEMAS.2026.150600128
Received: 26 June 2026; Accepted: 01 July 2026; Published: 17 July 2026
ABSTRACT
The growing threats to river water quality demand innovative approaches for effective monitoring and protection.
This paper proposes an Internet of Things (IoT)-based river water quality monitoring system to address this
challenge. The proposed system utilizes a network of sensors strategically deployed within the river, measuring
crucial parameters like temperature, pH, dissolved oxygen, turbidity, and conductivity. Sensor data is
continuously transmitted wirelessly to a central hub for processing and analysis. Utilizing cloud computing
platforms, the system enables real-time data visualization and analysis, allowing for prompt identification of
potential pollution events. Additionally, the system integrates alerting mechanisms to notify relevant authorities,
facilitating timely interventions. This paper presents the design, implementation, and field testing of the proposed
system, along with a thorough evaluation of its performance. The results demonstrate the system's effectiveness
in capturing comprehensive water quality data, facilitating real-time monitoring, and enabling proactive water
management strategies.
Keywords: Water Quality Index (WQI), Total Dissolved Solids (TDS), Turbidity, Extreme Gradient Boosting
(XGBoost)
INTRODUCTION
The escalating pressures of population growth, industrial activity, and climate change have exacerbated concerns
about the quality of our freshwater resources. Rivers, playing a vital role in supporting ecosystems and human
well-being, are particularly vulnerable to pollution. To proactively manage and protect these critical waterways,
real-time and efficient monitoring of river water quality is paramount. This paper presents the development and
implementation of an Internet of Things (IoT)-based river water quality monitoring system. This system
leverages the power of sensor technology, wireless communication, and cloud computing to provide continuous,
cost-effective, and geographically distributed data collection, enabling timely assessments of potential pollution
threats and informed decision-making for sustainable river management.
Water is one of the most important natural resources in the world. Although 71% of the world is filled with
unusable salt water, only less than 1% of water is available in a freshwater form (Wikipedia, Water distribution
on Earth). The freshwater sources include rivers, lakes, ponds, and underground aquifers. India is a country that
mainly depends on rivers for its daily water needs. In recent years, Indian rivers have been subjected to overload.
The main reason is the mineral-rich basins themselves, which cause the over exploitation and thus results in the
pollution of river water. The toxic wastes, such as sewage, industry, and agricultural waste, are dumped into the
river, causing pollution, and rendering the water unusable for daily use. In India, water quality monitoring
(WQM) is carried out according to an old traditional technique, which is to collect the samples from the site,
bring them to the laboratory and perform the analysis of the samples[ ]. This technique is time consuming and
takes a day or two to get the results, so the available data are not real time. Consumption of such water can lead
to waterborne diseases in people around the basins. The advent of the Internet of Things (IoT) has been a blessing
to overcome the situation described above. IoT can help obtain real-time data, especially in the river basin region.
This idea can be accomplished with the help of the IoT system called the WQM system. WQM generally consists
Page 1818
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
of different water quality sensors, such as Temperature, pH, turbidity and total dissolved solids (TDSs) to monitor
water quality in the deployed region. Water quality sensors assess the physicochemical parameters that are
essential for overall water quality. WQM system collects data from the designated site in real time and
immediately analyzes the quality of the sample and informs the data center about the wellbeing of the water. If
the data received is in the normal range, then no action is taken, but if the data are above or below the normal
range, people around the river basins are informed about the water abnormality along with the precautions to be
taken, thus avoiding any endemic related to water.
In our paper, the primary focus is the development of a sophisticated model. This is designed to gather
comprehensive data from the river water by utilizing advanced sensors that are strategically placed throughout
the river. The crucial sensor data obtained is then seamlessly transmitted and stored in a secure cloud-based
platform for further processing and analysis. Harnessing the power of cutting-edge machine learning algorithms,
the gathered data is meticulously scrutinized and thoroughly evaluated to compute the Water Quality Index
(WQI) of the sampled river water. This pivotal information is seamlessly made available to authorized users and
regulatory bodies through a user-friendly website interface, ensuring easy access and transparency. Moreover,
an intelligent alert system is intricately integrated into the model so that immediate notifications are dispatched
to users in the event of any detected anomalies or deviations in the water quality parameters, enabling swift and
proactive responses to safeguard the river ecosystem. Through this comprehensive and innovative approach, our
proposed system aims to revolutionize the monitoring and management of river water quality, ultimately
contributing to the preservation and sustainability of our precious water resources.
The organization of the rest of the paper is as follows: Section 2 presents literature survey, Section 3 provides
the proposed system and its architecture, followed by experimental results in Section 4. Finally, conclusion is
presented in Section 5.
LITERATURE SURVEY
In their innovative approach, Olasupo O. Ajayi et al [2] have put forth a sophisticated network framework
designed to continuously gather real-time data on various water parameters. The crux of their proposal involves
the utilization of advanced Machine Learning (ML) tools to autonomously assess the suitability of water samples
for both drinking and irrigation purposes. On a parallel front, Harish H. Kenchannavar et al [3] have introduced
a method aimed at evaluating and scrutinizing water quality utilizing an Internet of Things (IoT) based system
dedicated to monitoring water quality. This methodology entails the extraction of water samples from the river
using the Water Quality Monitoring (WQM) system specifically from predetermined sampling sites. These
samples are then subjected to linear regression analysis to determine the correlations and level of accuracy
between the different parameters being measured. Furthermore, Quentin Quevy et al [4] have engineered an
accessible sensing system tailored for long-term and cost-effective monitoring of water quality. Their device
aims to provide a sustainable solution for ongoing assessment and surveillance of water quality parameters. In
this technique, an advanced buoy is placed in operation and overseen by a central unit equipped with
sophisticated sensors to assess environmental variables. The customized electronic circuit board facilitates
sustainable integration of electronics, focusing on power management and network connectivity. Fowzia Akhter
et al [5] have pioneered a water quality monitoring system featuring a Multifunctional sensor made of
MWCNT/PDMS tailored for agricultural use. They have innovatively designed an interdigital sensor and
conducted thorough assessments for detecting temperature, nitrate, phosphate, and pH levels in water. The results
are meticulously compared against established benchmarks for validation purposes. Yuhao Wang et al [6] have
introduced a novel approach for real-time monitoring and evaluation of water quality utilizing Artificial
Intelligence and IoT applications to preserve Freshwater Biodiversity. In the realm of Internet of Things (IoT),
both measurable and unmeasurable parameters are gauged utilizing a general regression neural network (GRNN)
model in conjunction with a multivariate polynomial regression (MPR) model, drawing insights from historical
water quality monitoring data. Manish Kumar et al [7] have pioneered the creation of a cutting-edge Smart Water
IoT kit designed specifically for the evaluation and continuous monitoring of river water utilizing IoT
infrastructure. This innovative approach involves outfitting the smart water IoT (SWIoT) kit with advanced
sensors capable of assessing crucial parameters such as pH levels, dissolved oxygen content, temperature,
conductivity, and oxidation-reduction potential in real-time. Furthermore, an algorithm has been developed to
Page 1819
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
facilitate feature selection and assign weights for a comprehensive assessment of river water quality. This method
not only ensures efficient data collection but also contributes significantly to the enhancement of water quality
management practices through technology-driven solutions. Most of the works here have used complex
algorithms and some of the models takes much time to calculate the results and some costs more to develop their
proposed model. So, we have proposed a method to overcome the limitations that are mentioned above.
The contributions of our proposed work are as follows: We have successfully designed a cutting-edge, cost-
effective, self-sufficient, and wireless water-quality monitoring system to address challenges related to scaling,
energy consumption, affordability, and other crucial aspects. This innovative model is programmed to gather
data at intervals of every 10 minutes, ensuring continuous monitoring. Moreover, the collected data can be
conveniently accessed remotely, enabling prompt detection of any potential issues as they arise. This expeditious
access to real-time information plays a pivotal role in quickly identifying and resolving any water-quality-related
concerns that may arise, thereby contributing to more efficient and effective monitoring of water resources.
Proposed System and Architecture
Proposed Block Diagram
The proposed block diagram is depicted in Figure 1. The water quality sensors are placed in the water sources.
These specialized sensors are responsible for gathering data related to a variety of parameters, including pH
levels, temperature variations, turbidity measurements, and the presence of dissolved solids. Subsequently, the
sensor-generated data is wirelessly transmitted to a centralized server or cloud-based service through the
utilization of a communication protocol such as Wi-Fi. Upon reaching the central server or cloud environment,
the sensor data is stored for further analysis. This stored information is processed and comprehensive analysis is
done using sophisticated algorithms or software tools, aiming to discern significant trends and patterns within
the water quality data. When the sensor data indicates any anomalies related to water quality, a notification is
promptly dispatched to the designated authorities. These authorities possess the capability to intervene by taking
necessary measures, such as adjusting the pH levels within the water treatment facility. Moreover, the sensor
data can be effectively presented through user-friendly dashboards or similar visualization tools, enabling
stakeholders to monitor the current state of water quality along with its historical trends. Furthermore, the data
acquired and analyzed from Internet of Things (IoT) sensors can be shared with the general public, relevant
governmental bodies, non-governmental organizations, or other responsible individuals.
Figure 1. Conceptual Framework for proposed Water Quality Monitoring System
Hardware Block Diagram
Figure 2 illustrates the hardware block diagram employed to implement the proposed methodology. The
approach entails the utilization of four distinct sensors to acquire essential water quality metrics, including
temperature, Total Dissolved Solids (TDS), turbidity, and pH levels. This system relies on the integration of
Page 1820
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
these sensors to precisely monitor and assess the water quality parameters mentioned. In the process, the initial
sensor data undergoes amplification through specialized amplifiers to enhance its signal strength. Subsequently,
the amplified data is transmitted to an Arduino Uno microcontroller for further processing. From the Arduino
Uno, the data is then routed to a Wi-Fi module, specifically the ESP8266 module, for wireless communication.
This module is pivotal in transmitting the data to the Adafruit cloud platform for centralized storage and
accessibility. The retrieval of the data from the cloud to the software is facilitated through the utilization of the
MQTT (Message Queuing Telemetry Transport) protocol.
Figure 2. Proposed Hardware for Water Quality Management
A visual representation of the project's circuit configuration is illustrated in Figure 3. Notably, the incorporation
of a step-down transformer enables the direct connection of the system to a standard 230V power supply,
ensuring efficient power distribution. The sensors that are used in this project are Turbidity sensor, TDS sensor,
LM35 and pH sensor. Turbidity sensor is a device that measures the cloudiness or haziness of a liquid, typically
to assess water quality. They work by shining a light through a sample of the liquid and measuring how much
light is scattered by suspended particles. The more light that is scattered, the more turbid the liquid is. LM35 is
a popular integrated circuit (IC) for measuring temperature. It is a linear temperature sensor, meaning the output
voltage is directly proportional to the Celsius temperature it's measuring. Every degree Celsius increase in
temperature results in a 10mV increase in output voltage. (10mV/°C). This linear relationship makes it
straightforward to convert the voltage reading to temperature. TDS sensor, also known as Total Dissolved Solids
sensor, is a device used to estimate the amount of dissolved solids present in a water sample. It is a handy tool
for various applications where water quality is a concern. TDS sensors do not directly measure the total dissolved
solids themselves. Instead, they indirectly estimate the TDS level by measuring the electrical conductivity (EC)
of the water. The sensor produces an electrical signal proportional to the EC. This signal is often converted to a
TDS value in parts per million (ppm) by a meter or a microcontroller it is connected to. And finally, pH sensor,
which is a crucial tool for measuring the acidity or alkalinity of a liquid solution. It plays a vital role in various
fields by ensuring optimal conditions in processes and applications. A typical pH sensor consists of two main
electrodes. Measuring electrode and Reference electrode. Measuring electrode is usually made of glass with a
special membrane sensitive to hydrogen ions. As the H+ concentration in the solution changes, the voltage across
this membrane changes as well. Reference electrode provides a stable reference voltage and completes the
electrical circuit. It does not interact directly with the solution being measured. The difference in voltage between
the measuring electrode and the reference electrode creates an output signal that corresponds to the H+
concentration and, consequently, the pH level of the solution. We have used an LCD display in the hardware to
display the current values of the water quality parameters. In terms of software utilization, our team implemented
Visual Studio Code as the primary tool for conducting our data analysis efficiently. Furthermore, our data
gathering and analysis processes heavily relied on Python and Jupyter Python, allowing us to seamlessly extract
information from the cloud and derive valuable insights from our datasets. In addition, the development of a
Page 1821
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
real-time river water quality monitoring website was facilitated through the integration of PHP. This website
serves as a crucial platform to track and oversee the condition of the river water continually. Moreover, to ensure
prompt action in cases of irregular sensor data readings, an automated alert system embedded within the Adafruit
io website has been established. This system is designed to instantly notify users via email upon the detection of
any anomalies in the sensor data, enabling swift responses and interventions as needed.
Figure 3. Proposed Circuit Diagram
Water Quality Index
The Water Quality Index, or WQI, is a handy way to communicate the overall health of water at a specific
location and time. It takes multiple measurements of water quality, like temperature, oxygen levels, and presence
of contaminants, and combines them into a single score, often on a scale of 0 to 100. This easy-to-understand
value helps people quickly grasp how suitable the water is for drinking, recreation, or aquatic life. By simplifying
complex data, the WQI is a valuable tool for public awareness, pollution monitoring, and prioritizing water
treatment efforts. This is the formula that is used to calculate the Water Quality Index.
The figure 4 displays graphs that aid in determining the Q value necessary for the calculation of the Water Quality
Index (WQI) utilizing data sourced from the cloud. The Q value for sensor data falls within the range of 0 to
100, and this information will be extracted from the graphs. Furthermore, a fixed value of ‘1’ will be assigned to
the parameter W across all four data parameters.
DIGITAL (PWM~)
ANALOG IN
AREF
13
12
~11
~10
RX < 0
~9
8
7
~6
~5
4
~3
2
TX > 1
SIMULINO
ARDUINO
A0
A1
A2
A3
A4
A5
RESET
5V
GND
POWER
ATMEGA328P
ATMEL
www.arduino.cc
blogembarcado.blogspot.com
SIM1
SIMULINO UNO
D7
14
D6
13
D5
12
D4
11
D3
10
D2
9
D1
8
D0
7
E
6
RW
5
RS
4
VSS
1
VDD
2
VEE
3
LCD1
LM044L
PH SENSOR
O\P
+
27.0
3
1
VOUT
2
U3
LM35
R5
10K
R6
10K
R7
10K
3
2
6
7
4
1
5
U4
R8
10K
LM
35
+5V
100K
10K
741
R9
100R
R10
10K
RV1
R11
47K
LM35 TEMPERATURE SENSOR
TDS SENSOR
O\P
PROBE
VCC
VCC
PROBE
VCC
RX
TX
0
1
WI-FI MODULE
ESP8266
POWER PORT
RELAY
1 2 3 4 12V
VCC
GND
1
2
VI
1
VO
3
GND
2
C2
1000mf
C1
100mf
R1
470k
D1 D2
D3 D4
TRANSFORMER
RECTIFIER
REGULATOR
LED
FILTERI\P
O\P
7805
12V
POWER SUPPLY
ARDUINO UNO
TURBITY SENSOR
O\P
WATER INSET
Page 1822
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
Figure 4. Graph to calculate the Q value
Table 1 provides a comprehensive overview of the water quality rating based on the WQI derived through the
implementation of a machine learning algorithm.
Table 1. WQI Interpretation
WQI Range
Water Quality Rating
Possible Usage
90 - 100
Excellent
Drinking, Irrigation & Industrialization
70 - 89
Good
Domestic, Irrigation & Industrialization
50 - 69
Moderate
Irrigation & Industrialization
25 - 49
Bad
Irrigation & Hydroelectric Power
0 - 24
Very Bad
Hydroelectric Power
Experimental Setup and Results
Data Processing
In our project, the dataset utilized for training the algorithm comprises four distinct features, namely pH level,
Temperature, Total Dissolved Solids (TDS), and Turbidity, with the target variable being the potability status of
water samples. The dataset is substantial, consisting of a total of 3277 rows of data entries. From this dataset,
the training and testing data will be automatically taken by the module used in python. To effectively process
and analyze this data set, a comprehensive evaluation was conducted by testing six different machine learning
algorithms. These algorithms include Logistic Regression, K-Nearest Neighbors (KNN), Support Vector
Machine (SVM), Random Forest, Decision Tree, AdaBoost, and XGBoost. Following rigorous testing, the
algorithm that demonstrated the most promising performance amongst the others was identified as XGBoost.
This selection was based on thorough evaluation and analysis of the algorithms' results, ultimately highlighting
XGBoost as the most effective choice for our predictive modeling application. XGBoost, short for Extreme
Gradient Boosting, is a machine learning powerhouse known for its speed, accuracy, and versatility. This
algorithm excels at supervised learning tasks, particularly regression and classification problems. It builds a
robust model by combining multiple weak decision trees, sequentially improving upon each one to enhance
Page 1823
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
overall accuracy. XGBoost's strength lies in its ability to handle complex data and efficiently leverage resources,
making it a favorite tool for data scientists across various domains.
Before training the machine learning model, data in the dataset is usually normalized to ensure consistent scaling
across different features. Normalizing involves applying the specified formula to adjust the range of values so
that the model can more effectively learn patterns and relationships within the data. By normalizing the dataset
before training, the model can converge faster and provide more accurate predictions or classifications based on
the input data. This preprocessing step is essential in enhancing the performance and stability of the machine
learning model, as it helps prevent certain features from dominating others due to differing scales or units.
Overall, proper data normalization plays a crucial role in producing reliable results and improving the overall
efficiency of the machine learning process.. Normalizing is done by using the following formula.
Normalized Value
Figure 5 illustrates the accuracy outcomes attained by executing machine learning algorithms via the Jupyter
Python code. This visual representation showcases the results obtained from the application of these algorithms
and emphasizes the importance of leveraging technological tools to enhance data analysis practices. The
accuracy figures serve as a vital indicator of the efficacy and reliability of the machine learning models deployed
in this study.
Figure 5. Accuracy Score
In summary, the figures and tables presented offer a holistic view of the data analysis process, ranging from the
initial calculation of the WQI to the evaluation of water quality ratings and the assessment of algorithmic
accuracy. This detailed examination highlights the significance of adopting advanced computational techniques
for optimizing data interpretation and decision-making processes.
The Figures 6.a and 6.b provide a visual representation of a website that has been meticulously designed using
PHP. This platform aims to keep users informed about the real-time status of river water. It effectively showcases
the 12 most recent data points related to various parameters such as water quality, potability, and the Water
Quality Index (WQI). The inclusion of these extensive data points allows users to gain a comprehensive
understanding of the current river water conditions.
Figure 7 exhibits the mechanisms in place to trigger email alerts whenever an irregular or abnormal value is
detected within the system. This proactive approach ensures that any deviations from expected data are
immediately flagged and communicated to the relevant stakeholders. Such timely alerts serve as a crucial
component in maintaining the integrity and accuracy of the provided information.
Lastly, Figure 8 captures the practical outcome of the alert system as it showcases an email notification generated
through the Adafruit io website. This alert was prompted by the identification of an abnormal value within one
of the water quality parameters. The prompt detection and communication of such anomalies play a pivotal role
in mitigating potential risks and ensuring the overall reliability of the system.
Page 1824
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
Figure 6.a. Screenshot of Developed Website
Figure 6.b. Screeshot of Developed Website
Figure 7. Triggers set in Adafruit io
Figure 8. Screenshot of Mail Alert
CONCLUSION
The overarching objective of this paper is centered around the evaluation of water samples. This evaluation is
achieved through the development of a cutting-edge smart water quality monitoring device, intricately integrated
within an IoT platform. This device is specifically engineered to detect and analyse four fundamental physical
parameters crucial for water quality assessment; these parameters consist of temperature, pH levels, turbidity,
and dissolved solids. Employing a variety of Arduino-based sensors, the project team diligently conducts tests
on diverse water samples to accumulate precise metric values. To derive actionable insights from these gathered
values, a suitable machine learning approach is meticulously applied. Notably, the XGBoost algorithm emerges
as the optimal choice for scrutinizing and enhancing system performance, thereby underlining its efficacy in
Page 1825
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
predicting water quality accurately. The system's proficiency in detecting water quality based on physical
parameters underscores its critical significance. Leveraging the capabilities of IoT technology, this system is
primed to revolutionize real-time water monitoring solutions, promising enhanced efficiency and precision in
environmental data analysis.
Although the proposed system has demonstrated reliable real-time monitoring under prototype deployment
conditions, further validation through long-term field experiments in diverse river environments is required.
Future work will focus on comprehensive evaluation of sensor calibration and accuracy, communication latency,
power consumption, maintenance requirements, and robustness under varying environmental conditions.
Comparative performance assessment with existing IoT-based water quality monitoring systems will also be
conducted to further establish the practical applicability and scalability of the proposed framework.
Funding information
No funds were used for the research work.
ACKNOWLEDGMENT
The authors wish to thank the management of Mepco Schlenk Engineering College for providing all the
necessary facilities to carry out the research.
Consent for publication
The authors give their full consent for publication.
Author contribution
All the authors contributed equally to the paper
Data availability statement
Data used for research will be made available after the paper is accepted for publication
Ethical approval statement and Competing interest
No ethical conflicts. The authors declare no competing interest
REFERENCES
1. S. ¸Sener, E. ¸Sener, and A. Davraz, “Evaluation of water quality using water quality index (WQI) method
and GIS in Aksu River (SW-Turkey),” Sci. Total Environ., vols. 584–585, pp. 131–144, Apr. 2017.
2. O. O. Ajayi, A. B. Bagula, H. C. Maluleke, Z. Gaffoor, N. Jovanovic and K. C. Pietersen, "WaterNet: A
Network for Monitoring and Assessing Water Quality for Drinking and Irrigation Purposes," in IEEE
Access, vol. 10, pp. 48318-48337, 2022.
3. H. H. Kenchannavar, P. M. Pujar, R. M. Kulkarni and U. P. Kulkarni, "Evaluation and Analysis of
Goodness of Fit for Water Quality Parameters Using Linear Regression Through the Internet-of-Things-
Based Water Quality Monitoring System," in IEEE Internet of Things Journal, vol. 9, no. 16, pp. 14400-
14407, 15 Aug.15, 2022.
4. Q. Quevy, M. Lamrini, M. Chkouri, G. Cornetta, A. Touhafi and A. Campo, "Open Sensing System for
Long Term, Low Cost Water Quality Monitoring," in IEEE Open Journal of the Industrial Electronics
Society, vol. 4, pp. 27-41, 2023.
5. F. Akhter, H. R. Siddiquei, M. E. E. Alahi, K. P. Jayasundera and S. C. Mukhopadhyay, "An IoT-Enabled
Portable Water Quality Monitoring System With MWCNT/PDMS Multifunctional Sensor for
Agricultural Applications," in IEEE Internet of Things Journal, vol. 9, no. 16, pp. 14307-14316, 15
Aug.15, 2022.
Page 1826
www.rsisinternational.org
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026
6. Y. Wang, I. W. -H. Ho, Y. Chen, Y. Wang and Y. Lin, "Real-Time Water Quality Monitoring and
Estimation in AIoT for Freshwater Biodiversity Conservation," in IEEE Internet of Things Journal, vol.
9, no. 16, pp. 14366-14374, 15 Aug.15, 2022.
7. M. Kumar, T. Singh, M. K. Maurya, A. Shivhare, A. Raut and P. K. Singh, "Quality Assessment and
Monitoring of River Water Using IoT Infrastructure," in IEEE Internet of Things Journal, vol. 10, no.
12, pp. 10280-10290, 15 June15, 2023.
8. S. Nihalani and A. Meeruty, “Water quality index evaluation for major rivers in Gujarat,” Environ. Sci.
Pollut. Res., vol. 28, pp. 63523–63531, Dec. 2021.
9. Z. Wu, X. Wang, Y. Chen, Y. Cai, and J. Deng, “Assessing River water quality using water quality index
in Lake Taihu Basin, China,” Sci. Total Environ., vol. 612, pp. 914–922, Jan. 2018.
10. S. Bi et al., “A comprehensive method for water environment assessment considering trends of water
quality,” Adv. Civil Eng., vol. 2021, Sep. 2021, Art. no. 5548113.
11. M. Bora and D. C. Goswami, “Water quality assessment in terms of water quality index (WQI): Case
study of the Kolong River, Assam, India,” Appl. Water Sci., vol. 7, no. 6, pp. 3125–3135, 2017.
12. S. Geetha and S. Gouthami, “Internet of Things enabled real time water quality monitoring system,”
Smart Water, vol. 2, no. 1, pp. 1–19, 2016.
13. T. Srour, A. Haggag, M. A. M. El-Bendary, M. Eltokhy, and A. E. Abouelazm, “Efficient approach for
monitoring and controlling water parameters utilizing integrated treatment based on WSNs,” Wireless
Sens. Netw., vol. 11, no. 4, pp. 47–66, 2019.
14. D. Jalal and T. Ezzedine, “Towards a water quality monitoring system based on wireless sensor
networks,” in Proc. Int. Conf. Internet Things Embedded Syst. Commun. (IINTEC), vol. 2018. Gafsa,
Tunisia, Jan. 2018, pp. 38–41.
15. U. Ahmed, R. Mumtaz, H. Anwar, A. A. Shah, R. Irfan, and J. García-Nieto, “Efficient water quality
prediction using supervised,” Water, vol. 11, no. 11, pp. 1–14, 2019.
16. K. R. S. R. Raju and G. H. K. Varma, “Knowledge based real time monitoring system for aquaculture
Using IoT,” in Proc. 7th IEEE Int. Adv. Comput. Conf. (IACC), Hyderabad, India, 2017, pp. 318–321.
17. N. Kafli and K. Isa, “Internet of Things (IoT) for measuring and monitoring sensors data of water surface
platform,” in Proc. IEEE 7th Int. Conf. Underwater Syst. Technol. Theory Appl. (USYS), vol. 2018.
Kuala Lumpur, Malaysia, Jan. 2018, pp. 1–6.
18. B. Das and P. C. Jain, “Real-time water quality monitoring system using Internet of Things,” in Proc. Int.
Conf. Comput. Commun.Electron. (COMPTELIX), Jaipur, India, 2017, pp. 78–82, 2017.
