Conference PaperPDF Available

Smart Water Quality Monitoring System

Authors:

Abstract and Figures

Nowadays Internet of Things (IoT) and Remote Sensing (RS) techniques are used in different area of research for monitoring, collecting and analysis data from remote locations. Due to the vast increase in global industrial output, rural to urban drift and the over-utilization of land and sea resources, the quality of water available to people has deteriorated greatly. The high use of fertilizers in farms and also other chemicals in sectors such as mining and construction have contributed immensely to the overall reduction of water quality globally. Water is an essential need for human survival and therefore there must be mechanisms put in place to vigorously test the quality of water that made available for drinking in town and city articulated supplies and as well as the rivers, creeks and shoreline that surround our towns and cities. The availability of good quality water is paramount in preventing outbreaks of water-borne diseases as well as improving the quality of life. Fiji Islands are located in the vast Pacific Ocean which requires a frequent data collecting network for the water quality monitoring and IoT and RS can improve the existing measurement. This paper presents a smart water quality monitoring system for Fiji, using IoT and remote_sensing_technology.
Content may be subject to copyright.
Smart Water Quality Monitoring System
A.N.Prasad, K. A. Mamun, F. R. Islam, H. Haqva
School of Engineering and Physics
University of the South Pacific
Laucala, Fiji Islands
Email: avneetp@live.com
Abstract Nowadays Internet of Things (IoT) and
Remote Sensing (RS) techniques are used in different area of
research for monitoring, collecting and analysis data from
remote locations. Due to the vast increase in global industrial
output, rural to urban drift and the over-utilization of land
and sea resources, the quality of water available to people has
deteriorated greatly. The high use of fertilizers in farms and
also other chemicals in sectors such as mining and
construction have contributed immensely to the overall
reduction of water quality globally. Water is an essential
need for human survival and therefore there must be
mechanisms put in place to vigorously test the quality of
water that made available for drinking in town and city
articulated supplies and as well as the rivers, creeks and
shoreline that surround our towns and cities. The availability
of good quality water is paramount in preventing outbreaks
of water-borne diseases as well as improving the quality of
life. Fiji Islands are located in the vast Pacific Ocean which
requires a frequent data collecting network for the water
quality monitoring and IoT and RS can improve the existing
measurement. This paper presents a smart water quality
monitoring system for Fiji, using IoT and remote sensing
technology.
KeywordsSmart Water Quality Monitoring; Internetof
Things; Remote Sensing.
I. INTRODUCTION
Over the past few decades, waters in and around Fiji
have gradually succumbed to a fair degree of pollution.
Chemical waste and oil spills are the major, primary forms
of water pollution threatening Fiji’s waterways. For
example, an article published in the Fiji Times on 24
December, 2014 reported on raw sewage seeping into the
Samabula River at a rate of 200 liters per second due to
broken pipes [1]. Eliminating pollution altogether may
seem like an unfathomable notion but limiting its effects
when it does happen is certainly possible. The primary
objective of this project is to devise a method to monitor
seawater quality in an effort to aid in water pollution
control in Fiji with the help of IoT and RS technology.
The Smart Water Quality Monitoring System will
measure the following water parameters for analysis;
Potential Hydrogen (pH), Oxidation and Reduction
Potential (ORP), Conductivity and Temperature using a RS
technology. While monitoring these parameters, it is
perceived that one should receive a stable set of results.
Therefore a continuous series of anomalous measurements
would indicate the potential introduction of a water
pollutant and the user will be notified of this activity with
the aid of IoT technology. False positives, such as
anomalous readings over a short period of time, will be
recorded but not treated as an alert. Hence, with the
successful implementation of this monitoring approach, a
water pollution early warning system can be achieved with
a fully realized system utilising multiple monitoring
stations.
II. BACKGROUND
Initiatives have been taken all over the globe to develop
projects based on sampling water to aid in controlling
marine environments. It may not be specific to water
pollution monitoring but similar concepts are involved.
Libeliums Smart Water device monitors the status of an
aquarium’s health in Europe [2]. It specifically monitors
parameters like pH, electro conductivity,
oxidation/reduction potential (ORP) and temperature. A
cloud based solution is developed to help in monitoring
data in real time providing a fast and effective reaction in
case of rising abnormalities.
A similar example to that of this project can be seen in
the coastal water pollution monitoring initiative in the Gulf
of Kachchh [3] with the only difference being in terms of it
having a much larger scope and vastly more expensive
protocols deployed to counter the effects of the industrial
development.
Furthermore, locally there have been projects based
around the conservation of the coral reefs. The Mamanuca
Environment society’s (MES) Biannual Sea Water
Monitoring Program has been around for 4 years whereby
tests are carried out on seawater for faecal coliform (FC)
bacteria, salinity and nutrients which helps in ascertaining
the health of the surrounding reefs [4].
Research indicates that projects of this nature are
developed on a large scale with generous funding from
reputable organizations. There is little indication of small-
scale and inexpensive projects that have a similar role in
places like marine jetties, cities and industrial rivers to
preserve aquaculture and public health. By applying a
strategic, cheap and methodical technique this project
hopes to achieve this in an effort to sanitize our oceans.
III. INTERNET OF THINGS
The internet of Things (IoT) is a revolutionary new
concept that has the potential to turn virtually anything
“smart”. A Thing in this context could be defined as an
object such as a cardiac monitor to a temperature sensor.
This extraordinary event has captured the attention of
millions. Why is this so big today? So imagine a world
where machines function without any notion of human
interaction. A future where machines communicate with
other machines and make decisions based on the data
collected and all independent of an end user.
To understand how this revolution took shape we have
to travel back to the 1900’s with a profound prediction
from a well renowned inventor Nicolai Tesla in which he
stated that the world will be wirelessly connected to a
single brain. Every invention starts with a simple thought,
that’s all it takes to define history. Alan Turing, the
inventor of the computer, spoke about machines having
sensors and humans teaching the machines, what we know
today as Artificial Intelligence (AI). Then came the World
Wide Web (www), the flow of information that is available
to the public and this was exactly what was missing to
realise Teslas prediction. The term itself “internet of
things” was coined in 1999 by Kevin Ashton for linking
the idea of sensors with the internet [5]. The IoT journey
has taken over a century to see light and it will undoubtedly
not stop here.
Fig. 1: The proposed schematic diagram of the smart
water quality monitoring system.
It might be difficult to see the significance of the IoT
but every advancement made is to make everyday life
simpler and safer. Examples of these are a baby monitor to
keep track of a baby’s health in real time [6], an IoT for
caregivers which collects behavioral data to improve care
[7] and a heart monitoring system that collects biometrics
data to track an aging patient’s health [8]. These are just a
few examples of how IoT projects can improve the way of
life. Fig. 1 shows the proposed schematic diagram of the
smart water quality monitoring system using the IoT
concept.
IV. APPROACH
The first task and a very integral one was to determine
which water parameters would provide a close indication
for water pollution. Through extensive research [9-11] the
parameters were chosen to be composed of pH, oxidation
and reduction potential (ORP) and temperature. The
reasoning behind these selections is discussed in section V
Water Parameters.
Independently these parameters provide very little
information in terms of how polluted the seawater actually
is. Therefore, analysis will consider collective parameter
behavior in order to generate a valid output, which is either
polluted or not unpolluted. To put this into perspective, a
drop in pH of tap water alone is not a valid indication of
pollution, this only indicates a formation of acids but it
may still be consumable (e.g adding lemon juice to tap
water).
The second step was the selection of locales that will
provide useful data. The area in question should be
susceptible to some chemical fluctuations by either marine
life or human interference since performing data readings
on clean, untouched waters would produce known results.
Therefore, the locations were narrowed down to industrial
areas, marine jetties, sewer waste openings and city lines
where human interference had a considerable impact.
Given that security was a factor, the site was chosen as the
USP jetty since the area is completely secure from theft and
vandals.
The third obstacle was which form of data logging
would produce an acceptable format. An FTP solution was
developed initially on a local network, however without the
intervention of local Internet Service Providers this seemed
like the least convenient option. A cloud server has also
been considered to act as an intuitive and a more permanent
solution. Work is still in progress on this matter. Moving
on, since the equipment has an SD storage option, data
logging was ultimately done on the hardware itself in text
format which can easily be read by practically any
application.
The final step was to decide on an acceptable, proficient
and accurate form of analysis. Seeing as the sea contains a
vast number of unknowns which will imminently
chemically alter the properties being measured. This will in
turn present erroneous readings. As previously mentioned,
changes in one measured parameter may be no indication
of the sea water actually being in the presence of
pollutants. The collective measured results had to be
consistent over period of time to be treated as a possible
threat. Moreover, to overcome this obstacle an intelligent
analytical system had to be designed in the manner of a
Neural Network model.
V. WATER PARAMETERS
A. Temperature
It is important to record temperature alongside the
other parameters as this will be useful in behavioral
analysis of the parameters being measured. Relating to
temperature-relation theories, pH and conductivity have an
undesirable effect with large temperature changes. In
addition to this, extreme temperatures for pacific island
climates is of understandable concern.
B. pH
The pH of a solution is the measure of the acidity or
alkalinity of that solution. The pH scale is a logarithmic
scale whose range is from 0-14 with a neutral point being
7. Values above 7 indicate a basic or alkaline solution and
values below 7 would indicate an acidic solution. The
majority of aquatic life prefers a pH level of 6.5 9.0.
Anything outside of this optimum range is considered fatal
to the marine ecosystem. Extreme pH values also increase
solubility of elements and compounds making them toxic
and therefore more likely to be absorbed by marine life.
Furthermore, temperature has an inverse relationship with
pH that is, as temperature increases pH levels decrease and
vice versa.
C. Oxidation- Reduction Potential
Oxidation-Reduction Potential is the measure of a
solutions oxidizing power. In simple terms it can be
described as the potential of a solutions ability to sanitize
itself. Higher ORP values would indicate more oxidizers
present. Likewise lower ORP equals more reducers
present.
It is understood that a typical good value for aquatic
life should be in the vicinity of 100 mV to 200 mV.
Anything outside these limits is a case to be investigated.
The same can be said about tap water whose ORP levels
are very high, usually in the high 600 mV because of the
use of disinfectants such as chlorine. Anything outside this
range should be investigated.
D. Conductivity
Conductivity signifies the ionic strength of a solution.
In other words it is the ability of a solution to conduct
electricity with the typical unit for measurement being
micro-Siemens per centimeter (uS/cm). As the dissolved
ions increase in the water, conductivity increases.
Therefore, the conductivity of tap water is perceptibly low
at around 100 uS/cm. On the other hand, expected values
for sea water are 55000-60000 uS/cm due to its high ionic
content. Any further increase in the conductivity value
may be indicative of polluted waters, such as sewer leaks
or chemical wastes flooding into the water.
Moreover, conductivity is directly related to salinity
that is conductivity improves with high salinity.
Conductivity values outside of the optimum levels indicate
a possible negative scenario. Dead Sea is a prime example
of lethal concentrations of salt.
The temperature relation with conductivity is a
proportional one. A general assumption of a temperature-
conductivity relation is taken to be linear in nature with a
deviation of 2%/°C.
VI. OVERALL STRUCTURE
The main concept behind this project can be described
in a simple block diagram shown in Fig. 2 and Fig. 3
Shows the setup with the sensors and Waspmote
microcontroller board.
.
The system as a whole comprises of sensors, an
analogue to digital convertor (ADC), a microcontroller, an
SD storage and a GSM module. The data collected can
either be stored onboard via the SD card or sent to a File
Transfer Protocol (FTP) server or a cloud server. In the
case of this project, a cloud server in conjunction with a
local machine is utilised for data analysis.
A complete bundled set provided by Libelium [6] was
used for this project and included the sensors,
microcontroller and GSM communication. Furthermore,
since the deployment duration is expected to run for
months or even years, power conservation is imperative. To
achieve this, the system design incorporates sleep mode i.e
the system gets a 15 minutes sleep time after an hour of
continuous readings. To further extend battery life any idle
modules have been set to off mode. For instance, when an
SD card operation has finished the SD module switches off.
The same is realized with the GSM and serial
communication. Further to this, alerts have been set to
notify the user of certain conditions such as battery life and
progress report.
Fig. 3: Deployment Setup with the sensors and Waspmote
microcontroller board.
VII. EXPERIMENTAL RESULTS
Four water samples from different water sources were
tested to establish a reference on the parameters for each
water type. The chosen water types were seawater, surface
water, Tap water and polluted creek water.
The four water samples were tested simultaneously
with four separate, identical systems at indoor ambient
temperature. Readings were taken at 1 hour intervals for a
total period of 12 hours. For security reasons the systems
were not deployed in the specific areas of interest, instead
water samples were collected and tested in a safe controlled
environment. However, the tap water sample was changed
every hour to see the consistency of Fiji tap water (supplied
by Fiji Water Authority) readings.
A. Reference for tap water
Fig. 4-7 shown the trends of the acquired data and are
consistent with the globally accepted values for pH,
conductivity and ORP. The temperature effect on pH and
conductivity is clearly observed.
Fig. 2 : Shows the overall block diagram of system operation.
Redox
ADC
Controller
GSM
SD
FTP
Cloud
pH
Conductivity
Temperature
Fig. 4: Graph of the solutions ambient temperature.
Fig. 5: Conductivity for tap water is shown.
Fig. 6: PH trend for tap water.
Fig. 7: ORP trend for tap water.
In addition, Temperature- Conductivity relation can be
seen to be linearly proportional.
B. Reference on sea water
A sample of fresh seawater, collected from the
shores of Sigatoka, was tested to provide a reference
on healthy sea water with little to no contamination.
Fig. 8: Temperature trend for seawater.
Fig. 9: Conductivity trend for seawater.
Fig. 10: PH trend for seawater.
Fig. 11: ORP trend for seawater.
The results shown in Fig. 8-11 indicate values
that are near to the researched data for acceptable sea
water parameters that can sustain aquaculture [9].
C. Reference on surface water
A sample of water was taken from Rewa River
(Suva, Fiji) to provide a reference on surface water.
The results obtained (Fig. 12-15) from Rewa River
were also consistent with the researched data available
on acceptable surface water parameters [10].
Fig. 12: Temperature trend for Surface water.
Fig. 13: Conductivity trend for surface water.
Fig. 14: PH trend for surface water.
Fig. 25: ORP trend for surface water.
D. Polluted water test
To get a fair idea of how the parameters of polluted
water should look a sample of water was collected from
the Nabukalou Creek an extremely polluted waterway in
the heart of Suva City. The results are shown in Fig. 16-
19.
Fig. 36: Temperature trend for Nabukulau creek.
Fig. 47: Conductivity trend for Nabukalou Creek.
Fig. 58: PH trend for Nabukalou Creek
Fig. 69: ORP trend for Nabukulau Creek.
E. Summary of the tested properties between the water
samples
A comparison can be made with the collected data
between tap water, river water, seawater and polluted
creek water. The pH levels for all were fairly similar with
the only change being in relation with temperature.
Conductivity for the water samples differed significantly
because of the different salinity concentrations for
different water types. The highest conductivity being
58000 uS/cm for sea water and the lowest being that of tap
water with conductivity value of 58 uS/cm. ORP for sea
water and river water were similar with results being in the
low 100-200mV range. ORP for tap water was observed to
be 350 mV which is fine considering that the acceptable
range is from 300-650mV.
The data obtained for polluted water has some
interesting values for ORP and conductivity. A very low
ORP value was observed, averaging at -2mV which is an
indication of overpowering reductants. This is an expected
value considering the background of Nabukalou Creek
having waste lines connected to the creek. The
conductivity value was in the 40000 range indicating that
water samples likely contained traces of pollution. A
summary is also presented in table format shown in Table
I.
TABLE I. SUMMARIZED RESULTS
VIII. CONCLUSION
This research demonstrates a smart water quality
monitoring system. Four different water sources were
tested within a period of 12 hours at hourly intervals to
validate the system measurement accuracy. The results
obtained matched with the expected results obtained
through research. The temperature relation with pH and
conductivity were also observed for all the water samples.
GSM technology has been successfully implemented to
send alarm based on reference parameter to the ultimate
user for immediate action to ensure water quality.
Additionally, the parameter references obtained from all
the different water sources will be used to build classifiers
which will be used to perform automated water analysis in
the form of Neural Network Analysis.
In a nutshell, the system has proved its worth by
delivering accurate and consistent data throughout the
testing period and with the added feature of incorporating
IoT platforms for real time water monitoring, this should
be an excellent contender in real time water monitoring
solutions.
ACKNOWLEDGMENT
The research team would like to thank the School of
Engineering at the University of the South Pacific for
funding this research project.
REFERENCE
[1] Madigibuli, A., Sewere Spill, Retrieved from Fiji Times Online:
http://www.fijitimes.com/story.aspx?id=289915, Accessed on:
November 4, 2015.
[2] Libelium., “Water Quality Monitoring in Europe’s Largest Fluvial
Aquarium, Retrieved from Libelium:
http://www.libelium.com/water-quality-monitoring-europe-largest-
fluvial-aquarium-zaragoza/, Accessed on: November 4, 2015.
[3] Sea Water Monitoring For Chemical Parameters, Retrieved from
Gujarat State Project Management Unit:
http://www.geciczmp.com/Sea-water-monitoring-for-chemical-
parameters.aspx, Accessed on: November 4, 2015.
[4] Vakacola, M., Biannual Sea Water Monitoring Program, Retrieved
from Mamanuca Environment Society: http://mesfiji.org/biannual-
sea-water-monitoring-program, Accessed on: November 4, 2015.
[5] Postscapes, Retrieved from History of the Internet of Things,
Retrived from Online: http://postscapes.com/internet-of-things-
history, Accessed on: November 4, 2015.
[6] K. A. Mamun, Sharma, A., A. S. M. Hoque, T. Szecsi, Remote
Patient Physical Condition Monitoring Service Module for iWARD
Hospital Robots, Asia-Pacific World Congress on Computer
Science and Engineering, 2014.
[7] Atzori, Luigi, Antonio Iera, and Giacomo Morabito. "The internet of
things: A survey." Computer networks 54, no. 15, 2787-2805, 2010.
[8] Preventive Solutions, Retrieved from
http://www.preventicesolutions.com, Accessed on: November 4,
2015.
[9] Luke Mosley, S. S., Water Quality Monitoring in the Pacific Island
Countries, Report, University of the South Pacific, 2005.
[10] 3riversquest.org., Sampling Parameters and Descriptions, Online:
3riversquest.org, Accessed on: November 4, 2015.
[11] Ministry of health, Fiji Island, Fiji National Drinking Water Quality
Standards, 2005.
Source
Readings
Temperature
pH
ORP
Conductivity
Rewa
River
20-30 °C
7.7-8.2 pH
190-220 mV
70-80 uS/cm
Central
Tap water
20-30 °C
7.7-8.1 pH
300-600 mV
55-70
uS/cm
Sigatoka
coast
20-30 °C
7.7-7.9 pH
100-150 mV
50-60
mS/cm
Nabukula
u Creek
20-30 C
7.7-7.9 pH
0 to -3mV
42-45
mS/cm
... Contrary to manual methods, the fuzzy approach employed in this paper is an effective way to detect drinking water quality in real time. They expected to introduce the Internet of Things (IoT) framework for online monitoring of drinking water quality in the distribution networks in the future (continued) [7] 2019 ...
... We can connect any device to IoT, provided it has sensors and an Internet connection. Specific IoTequipped devices, to name a few, include laptops, smartphones, refrigerators, coffee machines, Google Home, Fitbits, and Apple Watches [7]. ...
... Much marine life requires a pH of 6.5-9.0. Something beyond this ideal range is lethal to the aquatic environment [7]. High pH values also maximize the viscosity of compounds and elements, which make them toxic and thus influence them to be absorbed by aquatic life in most cases. ...
Chapter
Full-text available
The Internet of Things (IoT) is used for tracking, gathering, and analyzing data from remote locations in various research areas. Because of the massive rise in global industrialization production, small town to city migration, and overuse of state land and resources of the ocean, the standard of water accessible by humans has significantly degraded. Around 5 million people worldwide die from waterborne diseases (Water Management Information System of India, 2017). The bad quality of water spreads disease, causes loss of life, and hinders socioeconomic development. On the other hand, infrastructure such as pipes deteriorates due to water aging. Under such circumstances, modern automation in the infrastructure of the water was needed to provide the delivery of great standard water to consumers securely and at a low in cost way, to make efficient use of the precious water resources of our world. Water is an important requirement for human continuity. Thus, systems must be placed to test strenuously the water standard at hand for consumption in industrial, natural recommended sources, including the water bodies like shores surrounding our municipality and metropolis. Water is used in different food production levels, and poor water quality can also affect food and consumer health. Food quality can be monitored in real time by converging different IoT technologies. A provision that a high standard of water is important in the prevention and spread of waterborne disease and the enhancement of quality of life.
... La empresa Libelium, fabricante de dispositivos de IoT, utilizó estas cinco variables en el monitoreo de la calidad del agua del Acuario Fluvial de Zaragoza, el más grande de su tipo en Europa [6]. Asimismo, las variables temperatura, pH, ORP y conductividad formaron parte de una propuesta de IoT para un "Sistema inteligente de monitoreo de la calidad del agua" [7]. En la selección de variables atmosféricas, se incluyeron contaminantes reconocidos por sus efectos sobre la salud por la OMS [3] e incluidos dentro del índice AQI (Air Quality Index) definido por EPA [8], y el contaminante dióxido de carbono (CO 2 ) reconocido por sus efectos nocivos sobre el medio ambiente al ser uno de los principales gases de efecto invernadero (GEI) [9]. ...
... Potencial de oxidación-reducción (Redox o ORP): es un índice de la capacidad oxidante (valores positivos) o reductora (negativos) de una solución. Para la vida acuática son adecuados valores de ORP entre 100 µV y 200 µV (micro voltios) [7]. Para el agua potable, la Organización Mundial de la Salud (OMS) estableció en el año 1971 un valor de ORP de 650 µV indicando que "provocarsá la casi instantánea desactivación de los virus incluso en altas concentraciones" [13]. ...
... uS/cm. Valores por fuera de esas escalas pueden indicar contaminación [7]. ...
Conference Paper
Full-text available
Resumen. Se desarrolló un software de visualización para facilitar el análisis de la calidad de los recursos hídricos y atmosféricos a partir de datos públicos del medio ambiente. Se describen los sistemas de calidad del aire y del agua que el software permite integrar en las visualizaciones. Se explica el procedimiento de extracción de los datos desde cinco plataformas de datos abiertos. El software se distribuye en formato open source para facilitar su extensión, por ejemplo, en la visualización de datos generados por soluciones de IoT o recolectados mediante el uso de drones equipados con sensores. Palabras claves: open data, visualización, recursos hídricos, recursos atmosféricos. 1 Introducción La gestión de los recursos naturales es un ámbito específico donde las tecnologías de la información contribuyen a generar información de valor para la toma de decisiones. Gracias a la evolución tecnológica, los datos son cada vez más abundantes en volumen, en variedad y se generan a mayor velocidad. En medio de un entorno complejo para obtener información de valor, las herramientas de visualización aportan claridad, siempre que reflejen con veracidad los datos que están representando [1]. La visualización de los datos de los recursos hídricos y atmosféricos presenta desafíos que es necesario abordar con el asesoramiento de especialistas en medio ambiente y conociendo la bibliografía especializada. Para realizar visualizaciones adecuadas se debe entender, por ejemplo, como se determina la calidad para el uso sustentable de los recursos naturales, como se seleccionan las variables de un sistema de calidad o como varían los valores guía según el uso definido como apto para un recurso natural. Respecto a los niveles de calidad, se deben considerar estándares internacionales, como los definidos por la Agencia de Protección Ambiental de los Estados Unidos (US EPA) [2] o las guías de calidad de la Organización Mundial de la Salud (OMS) [ 3]. En relación al lugar donde fueron tomados los datos, se debe tener en cuenta que dice la normativa nacional, provincial o municipal respecto a la calidad de los recursos naturales en su ámbito de competencia. Y como parte del análisis, después de representar los datos de las variables hídricas y atmosféricas como una serie temporal en un gráfico, resulta importante poder identificar sus atributos, es decir, la tendencia, la estacionalidad, los ciclos, el "ruido", la presencia de valores atípicos (los "outliers"), las discontinuaciones repentinas, además de la necesidad de poder ajustar adecuadamente la escala de los datos [4].
... Prasad et al. [11] article shows the WQM system by means of remote sensing and Internet of Things technologies. ...
Chapter
Full-text available
Communication through wireless developments plays a key role in creating the capability of new sensors. In the present scenario, the environment applications are critical in the field of sensor network developments. IoT has the capability to control the environmental issues like air and water pollution, commercial farming, etc. Water is the basic need for sustainability of any living being, so timely detection and monitoring the water quality is required. In this paper by using IoT technology, monitoring system of quality of the drinking water is designed as it is cost-effective. In this system, the basic sensors used are turbidity, pH, TDS and temperature. The above-mentioned sensors are interfaced with the microcontroller unit and further the process is performed. Finally, the received data is uploaded in the cloud and the quality of the water is viewed by using Internet of Things in ThingSpeak application.KeywordsSensor networksContamination of waterInternet of ThingsTDS sensorpH sensorTurbidity sensorThingSpeak
... is study looks into the approaches that were used to help solve water quality challenges [1]. In most studies, traditional analyses in the laboratory and data analysis are two types of analyses and utilized to help determine the quality of water, but other studies apply machine learning approaches to help find an optimal solution to the water quality problem. ...
Article
Full-text available
During the last few decades, the quality of water has deteriorated significantly due to pollution and many other issues. As a consequence of this, there is a need for a model that can make accurate projections about water quality. This work shows the comparative analysis of different machine learning approaches like Support Vector Machine (SVM), Decision Tree (DT), Random Forest, Gradient Boost, and Ada Boost, used for the water quality classification. The model is trained on the Water Quality Index dataset available on Kaggle. Z-score is used to normalize the dataset before beginning the training process for the model. Because the given dataset is unbalanced, Synthetic Minority Oversampling Technique (SMOTE) is used to balance the dataset. Experiments results depict that Random Forest and Gradient Boost give the highest accuracy of 81%. One of the major issues with the machine learning model is lack of transparency which makes it impossible to evaluate the results of the model. To address this issue, explainable AI (XAI) is used which assists us in determining which features are the most important. Within the context of this investigation, Local Interpretable Model-agnostic Explanations (LIME) is utilized to ascertain the significance of the features.
... The aquatic environment is deemed lethal to everything outside of this optimum range. In addition, extreme pH values increase the solubility of components andcompounds, making them toxic and therefore more likely to be consumed by marine organisms[75]. ...
... Water quality data have been collected using Internet of Things (IoT) technologies. Water quality sensors have been deployed to monitor river (Chen & Han, 2018) as well as inland water and maritime environments (Prasad et al., 2015) and have also been deployed on a robotic boat to obtain spatial estimates of water quality (Li et al., 2017). Commercial IoT sensor platforms have been utilized for this purpose (Wong & Kerkez, 2016). ...
Preprint
Full-text available
A measurement and development platform for collecting water quality data (the WaterWatcher) was developed. The platform includes sensors to measure turbidity, total dissolved solids (TDS), and water temperature as variables that are often collected to assess water quality. The design is extensible for research and monitoring purposes, and all design files are provided under open-source permissive licenses for further development. System design and operation are discussed for illustrative purposes. A block diagram indicates elements of mechanical, electrical, and software design for this system. The mechanical assembly used to house circuit boards and sensors is designed using 3D printing for rapid prototyping. The electronic circuit board acts as a carrier for an Arduino 32-bit microcontroller board and an associated cellular module along with a GPS for geolocation of water quality measurements. The cellular module permits data transfer for Internet of Things (IoT) functionality. System operation is set up using a command line interface (CLI) and C++ code that allows for calibration coefficients and human readable transfer functions to be defined so that sensor voltages are related to physical quantities. Data are cached on a secure digital (SD) card for backup. The circuit was calibrated, and system operation assessed by deployment on an urban reservoir. Biogeochemical cycles were identified in the collected data using spectrogram and semivariogram analyses to validate system operation. As a system with hardware and software released under an open source license, the WaterWatcher platform reduces the time and effort required to build and deploy low-cost water quality measurement sensors and provides an example of the basic hardware design that can be used for measurements of water quality.
Conference Paper
Internet of Things (IoT) technology is aggravating the paradigm shift in both industrial and personal lives. IoT, sensors, and cloud technology could be utilised better to conserve water, nature, and environmental activities. Water is one of the five elements by which the human body is made, making it a basic need for human survival. Due to massive increase in pollutants (global industrial waste, household waste, deforestation and over utilisation of land and sea), the quality and quantity of water available for living beings has declined dramatically. Water is a necessity for life, so systems must be in place to rigorously analyse the quality of water being consumed. In this paper, an IoT-based Smart in- pipe Drain Monitoring System is proposed which can act as an efficient system installed below the washbasin that segregates the water into three different containers based on water impurity. The system incorporates different sensors to analyse the level of contamination in the water, a processing unit and a global positioning system. Currently, the system is tested for wastewater segregation based on turbidity values. The segregated wastewater in container 1 and container 2 is treated and reused for daily activities like flushing, cleaning and watering the plants, whereas, wastewater in container 3 is sent to water treatment plant. The data obtained by the system is uploaded on the cloud by using an IoT-based Amazon Web Service (AWS) server to enable online monitoring of quality and quantity of wastewater and reused water.
Article
In this paper an intelligent system for remote patient physical condition monitoring service module for an Intelligent Robot Swarm for Attendance, Recognition, Cleaning and Delivery (iWARD) [1] is reported. The system algorithm and module software is implemented in C/C++, and the Orca robotics [2] components use the OpenCV[3] image analysis and processing library. The system is successfully tested on Linux (Ubuntu) platform as well as on a web server. The patient condition monitoring system can remotely measure the following body conditions: body temperature (BTemp), heart rate (HR), electrocardiogram (ECG), respiration rate (RR), body acceleration (BA) using sensors attached to the patient's body. The system also includes an RGB video camera and a 3D laser sensor, which monitor the environment in order to find any patient lying on the floor. The system deals with various image-processing and sensor fusion techniques. The iWARD patient condition monitoring module evaluation tests were carried out in front of thirty healthcare professionals (doctors, nurses, nursing lecturers and healthcare assistances etc) during the final review meeting of the consortium and in two teaching hospitals (in Newcastle and San Sebastian, 2009) in Europe. The post iWARD system improved upon the prototype by adding a 3D laser sensor and replacing the original camera with a high quality Pan-Tilt-Zoom (PTZ) camera and implementing the identity detection methods. This allowed for the use of more robust patient condition monitoring algorithms. The outcomes of this research have significant contribution to the robotics application area in the hospital environment.
Sewere Spill", Retrieved from Fiji Times
  • A Madigibuli
Biannual Sea Water Monitoring Program
  • M Vakacola
Vakacola, M., " Biannual Sea Water Monitoring Program", Retrieved from Mamanuca Environment Society: http://mesfiji.org/biannualsea-water-monitoring-program, Accessed on: November 4, 2015.
Water Quality Monitoring in the Pacific Island Countries
  • S S Luke
  • Mosley
Water Quality Monitoring in Europe's Largest Fluvial Aquarium Retrieved from Libelium: http://www.libelium.com/water-quality-monitoring-europe-largestfluvial-aquarium-zaragoza
  • Libelium
Libelium., " Water Quality Monitoring in Europe's Largest Fluvial Aquarium ", Retrieved from Libelium: http://www.libelium.com/water-quality-monitoring-europe-largestfluvial-aquarium-zaragoza/, Accessed on: November 4, 2015.
The internet of things: A survey Preventive Solutions
  • Luigi Atzori
  • Antonio Iera
  • Giacomo Morabito
Atzori, Luigi, Antonio Iera, and Giacomo Morabito. "The internet of things: A survey." Computer networks 54, no. 15, 2787-2805, 2010. [8] " Preventive Solutions ", Retrieved from http://www.preventicesolutions.com, Accessed on: November 4, 2015.
Retrieved from History of the Internet of Things Retrived from Online: http://postscapes.com/internet-of-thingshistory , Accessed on
  • Postscapes
Postscapes, " Retrieved from History of the Internet of Things ", Retrived from Online: http://postscapes.com/internet-of-thingshistory, Accessed on: November 4, 2015.
Water Quality Monitoring in Europe's Largest Fluvial Aquarium
  • Libelium
Libelium., "Water Quality Monitoring in Europe's Largest Fluvial Aquarium", Retrieved from Libelium: http://www.libelium.com/water-quality-monitoring-europe-largestfluvial-aquarium-zaragoza/, Accessed on: November 4, 2015.