GPS-BASED to take some immediate precaution and

GPS-BASED
DENGUE RISK INDEX APP

P.Pavithran1  V.Saranya2  R.Shalini3  G.S.Shruthii4  P.Chitra5

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

1,2,3,4 UGStudents,  5 Professor

       12345Department of Information Technology,
Prathyusha Engineering College, Chennai, India

                                                               

ABSTRACT:

 Mosquitoes that transmit dengue virus
are caused because of population growth and  uncontrolled urbanization in tropical and
subtropical countries. In India, the most affected part is Kerala, Karnataka
and TamilNadu. In TamilNadu the past 4 years nearly 22,000 people were affected
by dengue and 38 people have died. In order to prevent people from this
dreadful disease GPS-based Dengue Risk Index App has been developed. GPS-based
Dengue Risk Index App which is mainly used to predict the outburst of dengue
diseases in specific Location. The prediction is mainly based on
analyzing climatic condition and spatial data. The climatic parameters
that are used in analysis are temperature, rainfall and humidity. Regression
algorithm is used to extrapolate in the multidimensional space to predict the
threat of Dengue exploration at user’s location. Dengue risk index in the
neighbouring area are analyzed using k-nearest neighbour algorithm for
prediction of spreading of disease at the user location. The Dengue Risk
Index’s core will indicate and alert the user to take some immediate precaution
and measures to prevent from Dengue infection.

INTRODUCTION:              

Dengue is the
most prevalent arthropod borne virus affecting humans today. Dengue causes a
spectrum of disease, ranging from a mild febrile illness to a life threatening
dengue hemorrhagic fever. Mosquitoes that transmit dengue virus are caused
because of population growth &uncontrolled urbanization in tropical
&subtropical countries. In India, the most affected part is Kerala,
Karnataka and TamilNadu. In TamilNadu the past 4 years nearly 22,000 people were
affected by dengue and 38 people had died .In order   to prevent from dreadful disease, this
application can be used to indicate before the outburst of disease

ARCHITECTURAL
DIAGRAM:

MODULES:

Application
UI:

The
application can be used by all the individuals by installing and registering in
the application.

 

Register:

 New user needs to register themselves order to
use the application.  Once the user completes the registration process he/she will set their
own user id and password.

Sign-In:Once the
registration process gets completed the user can login into the application
using the own id and password. Existing users can directly login into the  system by using their own id and password

FORGET
PASSWORD:

 

PREDICTION BASED
ON CLIMATIC CONDITION:

Prediction for the day

The
Prediction of disease is done based on climatic condition. The major disease
transmission is  done through Aedes
Mosquito, which is a climate sensitive vector. If the Temperatures lie in the
range of 22 to 31 degrees C, relative humidity of 70% to 90%, and rainfall,
provided a suitable environment for breeding and abundance of Aedes
mosquito species this result in increase the risk of dengue diseases. Hence by
processing the climatic parameters like temperature, humidity & rainfall
the prediction of the disease can be done easily.

Prediction in near future  

Based
on the previous three years data’s, the outburst the disease in near future can
be identified by using linear Regression algorithm. Main advantage
of Regression Algorithm is predicting the future, supporting future and
correcting errors

PREDICTION BASED
ON SPATIAL DATA:

Processing information about
dengue affected areas

The
prediction of disease is done based on spatial data. Already dengue affected
area details are gathered and  by using
these details the prediction of occurrence
of disease in nearby area can be
identified. By this the range at which the disease spreads, can be found .The
algorithm used in prediction is nearest neighbour algorithm.

LITERATURE
REVIEW:

Climatic
factors influencing dengue cases in Dhaka city: a model for dengue
prediction

 Md. Nazmul
Karim and et. al. 1 have used linear regression to normalize the
data. Average monthly humidity, rainfall, minimum and maximum temperature were
used as independent variables and number of dengue cases reported monthly was
used as dependent variable. Accuracy of the model for predicting outbreak was assessed
through receiver operative characteristics (ROC) curve. The prediction model
had some limitations in predicting the monthly number of dengue cases, it could
forecast possible outbreak two months in advance with considerable accuracy.

Dengue
disease prediction using weka data mining tool

 Kashishara
Shakii,Shadma Anis and Manasaf Alam2 uses Datasets that are
available for dengue describe information about the patients suffering with
dengue disease and without dengue disease along with their symptoms like: Fever
Temperature, WBC, Platelets, Severe Headache, Vomiting, Metallic Taste, Joint
Pain, Appetite,Diarrhoea, Hematocrit, Haemoglobin and how many days suffer in
different city. Weka tool is used for classification of data.

Mobile
Application for Dengue Fever Monitoring and Tracking via GPS: Case Study for
Fiji

Emmenual Reddy and et 3 al developed an mobile application based
on the symptoms details given by the user the amount of disease spread in a
particular area is found. It helps authorities to help the affected people.

Need for GIS based dengue surveillance
with Google internet real time mapping for epidemic control in India

Palaniyandi M 4
developed based on the information
relevant to the geographical site specification of
dengue vectors breeding habitats, vector abundance, vector density, etc., could be
recorded using global positioning systems (GPS). This information could be
mapped and overlay on the the climatic layers of climate variables (Temperature,
relative humidity ,saturation deficiency and Rainfall)under the geographical
information systems (GIS) software platform for spatial analysis(cluster analysis,
nearest neighbourhood analysis, fussy analysis, probability of maximum and
minimum likelihood analysis etc.,) for prediction of disease epidemics 7 days
in advance.

Dengue Fever Prediction: A Data
Mining Problem

 Kamran Shaukat and et
al 5used Dengue fever  in
classification techniques to evaluate and compare their performance. The
dataset was collected from District Headquarter Hospital (DHQ) Jhelum. For
properly categorizing our dataset, different classification techniques are
used. These techniques are Naïve Bayesian, REP Tree, Random tree, J48 and SMO.
WEKA was used as Data mining tool for classification of data.

Nation-Wide, Web-Based, Geographic Information System
for the Integrated Surveillance and Control of Dengue Fever in Mexico

Juan Eugenio Hernández and etall 6uses
Dengue-GIS which  provide the
geographical detail needed to plan, asses and evaluate the impact of control
activities. The system is beginning to be adopted as a knowledge base by vector
control programs. It is used to generate evidence on impact and
cost-effectiveness of control activities, promoting the use of information for
decision making at all levels of the vector control program. Dengue – GIS

has also been used as a hypothesis
generator for the academic community.

Spatial
Distribution of the Risk of Dengue and the Entomological Indicators in Sumaré, State
of São Paulo, Brazil

GersonLaurindoBarbosa and et al 7main
goal is to analysis was to identify
potential high-risk intra-urban areas of dengue, using data collected at
household level from surveys First survey screened 1,586 asymptomatic
individuals older than 5 years of age. Second survey 2,906 asymptomatic
volunteers, same age-groups, were selected by multistage sampling (census
tracts; blocks; households) using available digital maps. Sera from
participants were tested by dengue virus-specific IgM/IgG by EIA. A Generalized
Additive Model (GAM) was used to detect the spatial varying risk over the
region. Initially without any fixed covariates, to depict the overall risk map,
followed by a model including the main covariates and the year, where the
resulting maps show the risk associated with living place,
controlled for the individual risk factors. This method has the advantage to
generate smoothed risk factors maps, adjusted by socio-demographic covariates..Data
from household surveys pointed out that low prevalence areas.

Spatial point analysis based on dengue surveys at
household level in central Brazil

Joao B Siqueira
and et al8 have reached this conclusion after evaluating the relationship of
climatic factors to the spread of dengue in different climatic zones in India —
Punjab, Haryana, Rajasthan, Gujarat, and Kerala. They focussed on changes in a
factor called extrinsic incubation period (EIP) of the dengue virus, by taking
into account daily and monthly mean temperatures in these areas The EIP is the
time taken for incubation of the virus in the mosquito. Lower temperatures
(17-18°C) result in longer EIPs thereby leading to decreased virus
transmission. With increasing temperatures, feeding increases because of the
enhanced metabolism of the mosquito, leading to shorter EIPs. Even a five-day
decrease in the incubation period can hike the transmission rate by three
times, and with an increase in temperature from 17 to 30°C, dengue transmission
increases fourfold. A further increase in temperature beyond 35°C is
detrimental to the mosquito’s survival.

Experimental
setup:

 Five years climatic data such as temperature, humidity,
rainfall and data of disease outburst is collected. The collected data is used
as training set and those training set are used for predicting the outburst of disease.
The threat at user’s location is predicted using Regression Algorithm.. K-nearest
neighbour Algorithm is used for predicting the spread of disease. Android
Studio IDE (version 2.3.3) is used for developing the application.  Firebase is used for storing the data’s in a
secured manner .The synchronisation and authentication is done automaticallyinfirebase.

References:

1.      
http://icmr.nic.in/ijmr/2012/july/0705.pdf

2.      
https://pdfs.semanticscholar.org/1d1c/8ea500ca91038d6d43e337ef025bafb0bbda.pdf

3.      
http://www.academia.edu/21350876/Mobile_Application_for_Dengue_Fever_Monitoring_and_Tracking_via_GPS_Case_Study_for_Fiji

4.      
https://www.researchgate.net/publication/265602757_Need_for_GIS_based_dengue_surveillance_with_Google_internet_real_time_mapping_for_epidemic_control_in_India

5.      
https://www.omicsonline.org/open-access/dengue-fever-prediction-a-data-mining-problem-2153-0602-1000181.php?aid=62375

6.      
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0070231

7.      
http://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0002873

8.      
https://bmcpublichealth.biomedcentral.com/articles/10.1186/1471-2458-8-361

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 GPS-BASED
DENGUE RISK INDEX APP

P.Pavithran1  V.Saranya2  R.Shalini3  G.S.Shruthii4  P.Chitra5

1,2,3,4 UGStudents,  5 Professor

       12345Department of Information Technology,
Prathyusha Engineering College, Chennai, India

                                                               

ABSTRACT:

 Mosquitoes that transmit dengue virus
are caused because of population growth and  uncontrolled urbanization in tropical and
subtropical countries. In India, the most affected part is Kerala, Karnataka
and TamilNadu. In TamilNadu the past 4 years nearly 22,000 people were affected
by dengue and 38 people have died. In order to prevent people from this
dreadful disease GPS-based Dengue Risk Index App has been developed. GPS-based
Dengue Risk Index App which is mainly used to predict the outburst of dengue
diseases in specific Location. The prediction is mainly based on
analyzing climatic condition and spatial data. The climatic parameters
that are used in analysis are temperature, rainfall and humidity. Regression
algorithm is used to extrapolate in the multidimensional space to predict the
threat of Dengue exploration at user’s location. Dengue risk index in the
neighbouring area are analyzed using k-nearest neighbour algorithm for
prediction of spreading of disease at the user location. The Dengue Risk
Index’s core will indicate and alert the user to take some immediate precaution
and measures to prevent from Dengue infection.

INTRODUCTION:              

Dengue is the
most prevalent arthropod borne virus affecting humans today. Dengue causes a
spectrum of disease, ranging from a mild febrile illness to a life threatening
dengue hemorrhagic fever. Mosquitoes that transmit dengue virus are caused
because of population growth &uncontrolled urbanization in tropical
&subtropical countries. In India, the most affected part is Kerala,
Karnataka and TamilNadu. In TamilNadu the past 4 years nearly 22,000 people were
affected by dengue and 38 people had died .In order   to prevent from dreadful disease, this
application can be used to indicate before the outburst of disease

ARCHITECTURAL
DIAGRAM:

MODULES:

Application
UI:

The
application can be used by all the individuals by installing and registering in
the application.

 

Register:

 New user needs to register themselves order to
use the application.  Once the user completes the registration process he/she will set their
own user id and password.

Sign-In:Once the
registration process gets completed the user can login into the application
using the own id and password. Existing users can directly login into the  system by using their own id and password

FORGET
PASSWORD:

 

PREDICTION BASED
ON CLIMATIC CONDITION:

Prediction for the day

The
Prediction of disease is done based on climatic condition. The major disease
transmission is  done through Aedes
Mosquito, which is a climate sensitive vector. If the Temperatures lie in the
range of 22 to 31 degrees C, relative humidity of 70% to 90%, and rainfall,
provided a suitable environment for breeding and abundance of Aedes
mosquito species this result in increase the risk of dengue diseases. Hence by
processing the climatic parameters like temperature, humidity & rainfall
the prediction of the disease can be done easily.

Prediction in near future  

Based
on the previous three years data’s, the outburst the disease in near future can
be identified by using linear Regression algorithm. Main advantage
of Regression Algorithm is predicting the future, supporting future and
correcting errors

PREDICTION BASED
ON SPATIAL DATA:

Processing information about
dengue affected areas

The
prediction of disease is done based on spatial data. Already dengue affected
area details are gathered and  by using
these details the prediction of occurrence
of disease in nearby area can be
identified. By this the range at which the disease spreads, can be found .The
algorithm used in prediction is nearest neighbour algorithm.

LITERATURE
REVIEW:

Climatic
factors influencing dengue cases in Dhaka city: a model for dengue
prediction

 Md. Nazmul
Karim and et. al. 1 have used linear regression to normalize the
data. Average monthly humidity, rainfall, minimum and maximum temperature were
used as independent variables and number of dengue cases reported monthly was
used as dependent variable. Accuracy of the model for predicting outbreak was assessed
through receiver operative characteristics (ROC) curve. The prediction model
had some limitations in predicting the monthly number of dengue cases, it could
forecast possible outbreak two months in advance with considerable accuracy.

Dengue
disease prediction using weka data mining tool

 Kashishara
Shakii,Shadma Anis and Manasaf Alam2 uses Datasets that are
available for dengue describe information about the patients suffering with
dengue disease and without dengue disease along with their symptoms like: Fever
Temperature, WBC, Platelets, Severe Headache, Vomiting, Metallic Taste, Joint
Pain, Appetite,Diarrhoea, Hematocrit, Haemoglobin and how many days suffer in
different city. Weka tool is used for classification of data.

Mobile
Application for Dengue Fever Monitoring and Tracking via GPS: Case Study for
Fiji

Emmenual Reddy and et 3 al developed an mobile application based
on the symptoms details given by the user the amount of disease spread in a
particular area is found. It helps authorities to help the affected people.

Need for GIS based dengue surveillance
with Google internet real time mapping for epidemic control in India

Palaniyandi M 4
developed based on the information
relevant to the geographical site specification of
dengue vectors breeding habitats, vector abundance, vector density, etc., could be
recorded using global positioning systems (GPS). This information could be
mapped and overlay on the the climatic layers of climate variables (Temperature,
relative humidity ,saturation deficiency and Rainfall)under the geographical
information systems (GIS) software platform for spatial analysis(cluster analysis,
nearest neighbourhood analysis, fussy analysis, probability of maximum and
minimum likelihood analysis etc.,) for prediction of disease epidemics 7 days
in advance.

Dengue Fever Prediction: A Data
Mining Problem

 Kamran Shaukat and et
al 5used Dengue fever  in
classification techniques to evaluate and compare their performance. The
dataset was collected from District Headquarter Hospital (DHQ) Jhelum. For
properly categorizing our dataset, different classification techniques are
used. These techniques are Naïve Bayesian, REP Tree, Random tree, J48 and SMO.
WEKA was used as Data mining tool for classification of data.

Nation-Wide, Web-Based, Geographic Information System
for the Integrated Surveillance and Control of Dengue Fever in Mexico

Juan Eugenio Hernández and etall 6uses
Dengue-GIS which  provide the
geographical detail needed to plan, asses and evaluate the impact of control
activities. The system is beginning to be adopted as a knowledge base by vector
control programs. It is used to generate evidence on impact and
cost-effectiveness of control activities, promoting the use of information for
decision making at all levels of the vector control program. Dengue – GIS

has also been used as a hypothesis
generator for the academic community.

Spatial
Distribution of the Risk of Dengue and the Entomological Indicators in Sumaré, State
of São Paulo, Brazil

GersonLaurindoBarbosa and et al 7main
goal is to analysis was to identify
potential high-risk intra-urban areas of dengue, using data collected at
household level from surveys First survey screened 1,586 asymptomatic
individuals older than 5 years of age. Second survey 2,906 asymptomatic
volunteers, same age-groups, were selected by multistage sampling (census
tracts; blocks; households) using available digital maps. Sera from
participants were tested by dengue virus-specific IgM/IgG by EIA. A Generalized
Additive Model (GAM) was used to detect the spatial varying risk over the
region. Initially without any fixed covariates, to depict the overall risk map,
followed by a model including the main covariates and the year, where the
resulting maps show the risk associated with living place,
controlled for the individual risk factors. This method has the advantage to
generate smoothed risk factors maps, adjusted by socio-demographic covariates..Data
from household surveys pointed out that low prevalence areas.

Spatial point analysis based on dengue surveys at
household level in central Brazil

Joao B Siqueira
and et al8 have reached this conclusion after evaluating the relationship of
climatic factors to the spread of dengue in different climatic zones in India —
Punjab, Haryana, Rajasthan, Gujarat, and Kerala. They focussed on changes in a
factor called extrinsic incubation period (EIP) of the dengue virus, by taking
into account daily and monthly mean temperatures in these areas The EIP is the
time taken for incubation of the virus in the mosquito. Lower temperatures
(17-18°C) result in longer EIPs thereby leading to decreased virus
transmission. With increasing temperatures, feeding increases because of the
enhanced metabolism of the mosquito, leading to shorter EIPs. Even a five-day
decrease in the incubation period can hike the transmission rate by three
times, and with an increase in temperature from 17 to 30°C, dengue transmission
increases fourfold. A further increase in temperature beyond 35°C is
detrimental to the mosquito’s survival.

Experimental
setup:

 Five years climatic data such as temperature, humidity,
rainfall and data of disease outburst is collected. The collected data is used
as training set and those training set are used for predicting the outburst of disease.
The threat at user’s location is predicted using Regression Algorithm.. K-nearest
neighbour Algorithm is used for predicting the spread of disease. Android
Studio IDE (version 2.3.3) is used for developing the application.  Firebase is used for storing the data’s in a
secured manner .The synchronisation and authentication is done automaticallyinfirebase.

References:

1.      
http://icmr.nic.in/ijmr/2012/july/0705.pdf

2.      
https://pdfs.semanticscholar.org/1d1c/8ea500ca91038d6d43e337ef025bafb0bbda.pdf

3.      
http://www.academia.edu/21350876/Mobile_Application_for_Dengue_Fever_Monitoring_and_Tracking_via_GPS_Case_Study_for_Fiji

4.      
https://www.researchgate.net/publication/265602757_Need_for_GIS_based_dengue_surveillance_with_Google_internet_real_time_mapping_for_epidemic_control_in_India

5.      
https://www.omicsonline.org/open-access/dengue-fever-prediction-a-data-mining-problem-2153-0602-1000181.php?aid=62375

6.      
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0070231

7.      
http://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0002873

8.      
https://bmcpublichealth.biomedcentral.com/articles/10.1186/1471-2458-8-361