METHODAND SYSTEM FOR PREDICTING DISEASE OUTBREAK AND REAL TIME POLLUTION MONITORING
The present invention is generally related to electronic health record (EHR) devices. More specifically, the present invention discloses a system and method for predicting outbreak of contagious diseases and real time pollution monitoring
FIELD OF THE INVENTION
The spread of infectious diseases such as Dengue Fever, Malaria, Cholera, Influenza etc., occurs rapidly if left uninhibited. In recent years mobility of human population has increased manifold, thereby further increasing the rapid spread of infectious diseases. Spread of infectious and other diseases can be inhibited if the geographical locations of occurrence of the diseases can be ascertained.
BACKGROUND OF THE INVENTION
Additionally, urban air pollution is a global challenge. The exponential rise in the number of vehicles, prevalent usage of dirty diesel, coal-fired power plants, and the steady increase in construction has together contributed to air pollution. Polluted air contains dangerously high level of particulates known as PM2.5 and PM10 which lodge deep in human pulmonary system and raise cancer risks.
Hence, there is a need for a system and method for predicting chances of disease outbreak as well as monitoring pollution levels that is efficient and may be easily implemented.
In an embodiment, the present specification provides a method of predicting pollution concentration and disease outbreak in a predefined area. The method comprises: obtaining geographical parameters of the area, the geographical parameters comprising data identifying one or more of areas representing water bodies, forest, slums, and high population density; obtaining climatic parameters of the area over a predefined period of time; obtaining atmospheric parameters of the area over a predefined period of time; obtaining historical disease trend data of the area; and determining pollution concentration and chances of disease outbreak in the predefined area by using one or more of the obtained geographical parameters, climatic
SUMMARY
3
parameters, atmospheric parameters and the historical disease trend data and a mathematical model at least partially based on the use of partial differential equations.
In an embodiment, obtaining climatic parameters comprises measuring one or more of temperature, humidity, rainfall, and wind velocity of the area over a predefined period of time by using one or more of temperature sensors and humidity sensors. In an embodiment, obtaining atmospheric parameters comprises measuring pressure, altitude, concentration of dust particles, and concentration of gasses in the area over a predefined period of time, by using one or more of sensors used for measuring pressure, altitude, concentration of dust particles in air, and concentration of predefined gases in air.
In an embodiment, at least one of the climatic parameters, and the atmospheric parameters are obtained by using sensors placed at predefined locations determined by using k-mean algorithms; spatial coordinates (longitude and latitude) of the locations of placement of the sensors being determined by using global positioning system (GPS). In an embodiment, the climatic parameters, atmospheric parameters and historical disease trend data is obtained from one or more of: electronic health records (EHR) of medical professionals, social networking websites, and predefined medical databases hosted on the Internet.
In an embodiment, determining chances of disease outbreak comprises using a compartmental model for dividing humans into groups labelled as susceptible, exposed, infectious and recovered (SEIR) and a vector population into groups labelled as susceptible, exposed, and infectious (SEI) for prediction of diseases spread by biting of insects. In another embodiment, determining chances of disease outbreak comprises using a compartmental model for dividing humans into groups labelled as one of susceptible, infectious, transmitter, and recovered (SITR) and susceptible, exposed, infectious, transmitter, and recovered (SEITR) and a vector population into groups labelled as susceptible, exposed, and infectious (SEI) for prediction of infectious diseases outbreak. In yet another embodiment, determining chances of disease outbreak comprises using a compartmental model for dividing humans into groups labelled as susceptible, vaccinated, exposed, infectious, transmitter and recovered (SVEITR) and a vector population into groups labelled as susceptible, exposed, and infectious (SEI) for prediction of infectious diseases outbreak.
In an embodiment, the method further comprises discretizing the mathematical model by using one of a spatial discretization scheme and a temporal discretization scheme, the spatial
4
discretization scheme being one of Finite Difference Methods (FDM), Finite Volume Methods (FVM), and Finite Element Methods (FEM), the temporal discretization scheme comprising Euler schemes.
In an embodiment the present specification provides a system for predicting pollution concentration and disease outbreak in a predefined area. The system comprises one or more sensors for obtaining geographical parameters of the area; one or more of temperature sensors and humidity sensors for obtaining climatic parameters of the area over a predefined period of time; one or more of sensors for measuring pressure, altitude, concentration of dust particles in air, and concentration of predefined gases in air for obtaining atmospheric parameters of the area over a predefined period of time by using; a mathematical model for determining a model conveying pollution concentration and chances of disease outbreak in the predefined area by using one or more of the obtained geographical parameters, climatic parameters, atmospheric parameters and historical disease trend parameter; the mathematical model at least partially based on the use of partial differential equations, the model being determined by using one of a spatial discretization scheme and a temporal discretization scheme, the spatial discretization scheme being one of Finite Difference Methods (FDM), Finite Volume Methods (FVM), and Finite Element Methods (FEM), the temporal discretization scheme comprising Euler schemes
In an embodiment, at least one of the sensors used for obtaining geographical parameters, climatic parameters, and the atmospheric parameters are placed at predefined locations determined by using k-mean algorithms; spatial coordinates (longitude and latitude) of the locations of placement of the sensors being determined by using global positioning system (GPS).
These and other features and advantages of the present invention will be appreciated, as they become better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein:
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1A illustrates distribution of sensors corresponding to climatic condition, pollution and disease trend, in accordance with an embodiment of the present specification;
FIG. 1B is a block diagram illustrating a system for predicting pollution concentration and disease outbreak, in accordance with an embodiment of the present specification;
5
FIG. 2 illustrates a susceptible, exposed, infectious and recovered (SEIR)- susceptible, exposed, and infectious (SEI) compartment model for Dengue Fever, in accordance with an embodiment of the present invention;
FIG. 3 illustrates a SEIR-SEI compartment model for Malaria, in accordance with an embodiment of the present invention;
FIG. 4 illustrates a susceptible, infectious, transmitter, and recovered (SITR)-SEI compartment model for Cholera, in accordance with an embodiment of the present invention;
FIG. 5 illustrates a susceptible, exposed, infectious, transmitter, and recovered (SEITR)-SEI compartment model for Cholera, in accordance with an embodiment of the present invention;
FIG. 6 illustrates a susceptible, vaccinated, exposed, infectious, transmitter and recovered (SVEITR) compartment model for Influenza, in accordance with an embodiment of the present invention; and
FIG. 7 illustrates a SVEITR-SEI compartment model for Influenza, in accordance with an embodiment of the present invention.
The present invention is an EHR product that predicts contagious disease outbreaks and high concentrates of pollutants by using local climatic conditions and sensor data such as Temperature, Relative Humidity, Rainfall, Past Disease Trends, Pollution Level, etc. The method of prediction makes use of partial differential equation (PDE) models and takes into account space (longitude & latitude) and time parameters.
DETAILED DESCRIPTION OF THE INVENTION
The method of disease prediction (including asthma attacks) and pollution may be implemented by using portable digital computing devices such as tablets and such other devices. In various embodiments, a plurality of computing devices such as desktop computers, clusters of computers and supercomputers may be used for implementing the method of disease prediction disclosed herein.
The EHR product of the present invention builds, learns and shares patterns of diseases and pollution through similar devices, news media, and social networking sites (Twitter, Facebook, etc.).
6
The present specification provides a real time model for predicting a contagious disease and high concentration of pollutants, which is easily accessible to public. Further, in order to reduce the cost of the sensor network, the present invention also provides a method for finding strategic locations for placing the sensors which optimizes the cost of sensor network without compromising the data needed for building the disease prediction model.
In various embodiments, the sensors may be placed in static locations such as buildings, poles, etc., as well as in mobile locations such as within bicycles, vehicles, drones, Unmanned Ariel Vehicles (UAV), mobile phone/tablets, wearable technology or any external sensor device/hardware which can be integrated to mobile phones/tablets. Placement of the sensors in mobile devices enables quick and efficient re-distribution of sensors.
The present invention is directed towards multiple embodiments. The following disclosure is provided in order to enable a person having ordinary skill in the art to practice the invention. Language used in this specification should not be interpreted as a general disavowal of any one specific embodiment or used to limit the claims beyond the meaning of the terms used therein. The general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the invention. Also, the terminology and phraseology used is for the purpose of describing exemplary embodiments and should not be considered limiting. Thus, the present invention is to be accorded the widest scope encompassing numerous alternatives, modifications and equivalents consistent with the principles and features disclosed. For purpose of clarity, details relating to technical material that is known in the technical fields related to the invention have not been described in detail so as not to unnecessarily obscure the present invention.
The method of disease prediction takes into account geographic landmarks (water bodies, forest, slums, high population density regions etc), past disease trends, and past climatic conditions. In an embodiment, temperature and humidity sensors such as DHT11, DHT21, DHT22, LM35DT, and TMP35/TMP36/TMP37 are used for measuring local climatic conditions. A pressure and altitude sensor such as BMP085, BMP180, commonly known in the art, may be used for measuring barometric conditions. Concentration of dust particles and gasses in the atmosphere may be measured by using sensors such as TGS2600, Shinyei PPD42 and MQ-2/MQ-9 respectively. Moreover, due to dynamic nature of sensors, GPS Sensor is used to accurately register the spatial coordinates (longitude and latitude) of the locations of placement of the sensors. As would be appreciated by persons of skill in the art, various different sensors
7
other than those specified herein may also be used to measure local atmospheric and climatic conditions.
In an embodiment, the method of the present specification makes use of three parameters. These include climatic conditions (i.e. temperature, humidity, wind velocity), pollution, and past disease trend. In an embodiment, the sensors are positioned in accordance with these three categories. FIG. 1 illustrates distribution of sensors corresponding to climatic condition, pollution and disease trend, in accordance with an embodiment of the present specification. As shown in the sensor distribution model 100, sensors 102, 104 and 106 correspond to climatic conditions, pollution and disease trend respectively. In an embodiment, k-mean algorithm, commonly known in the art, is used to determine placement of the sensors. In addition to the known k-mean algorithm, additional constraints given by the following equation are imposed in order to obtain sensor positions:
kc + kp + kd = k (1.2)
kc < kd (1.3)
kp < kc (1.4)
where k denotes the total number of sensors to be used. kc, kp and kd denote number of sensors corresponding to climatic, pollution and past disease trend categories, respectively.
In order to strategically place sensors: for the climatic condition parameters a mathematical model involving diffusion and convection equations (Partial Differential Equations) is used to obtain the temperature and wind velocity for a geographical region; for the pollution parameter a mathematical Model involving diffusion and convection equation (Partial Differential Equations) is used to obtain the pollution concentration for the geographical region; and for the disease trend data a priori information of disease is used. Important locations both from mathematical models and a priori disease trends are identified and then k-mean algorithm is employed to optimize the location of sensors.
FIG. 1B is a block diagram illustrating a system for predicting pollution concentration and disease outbreak, in accordance with an embodiment of the present specification. System 110 comprises a module 112 for obtaining geographical parameters of a predefined area; a plurality of sensors 114 such as temperature and altitude sensors for obtaining climatic parameters of the area over a predefined period of time; and a plurality of sensors 116 for measuring pressure, altitude, concentration of dust particles in air, and concentration of
8
predefined gases in air for obtaining atmospheric parameters of the area over a predefined period of time. In an embodiment, the geographical data parameters are obtained via existing geographical information system (GIS) databases or by collecting manually. The data obtained from module 112, sensors 114, 116 as well as historical disease trend data is fed to a mathematical model 120 for determining a model 122 conveying pollution concentration and chances of disease outbreak in the predefined area. The mathematical model 120 is based on the use of partial differential equations as described below. In an embodiment, the sensors 112, 114 and 116 are placed at predefined locations determined by using k-mean algorithms; and spatial coordinates (longitude and latitude) of the locations of placement of the sensors is determined by using global positioning system (GPS).
In an embodiment, the present invention provides a method for modelling Dengue Fever by using input parameters such as local temperature, relative humidity, rainfall, past disease treads, etc., in order to obtain a spatial probability distribution for the likelihood of a Dengue Fever outbreak in the region.
Dengue fever (DF) and dengue haemorrhagic fever (DHF) are caused by any one of the four (DEN-1, DEN-2, DEN-3, and DEN-4) virus serotypes. DF and DHF are diseases primarily found in tropical and sub-tropical areas. The four dengue serotypes maintain a cycle between humans and the Aedes mosquito. The Aedes aegypti is a domestic, day-biting female mosquito and is the most common Aedes species. Dengue causing mosquitos (vectors) are usually found in cities.
In an embodiment, a standard compartmental model commonly known in the art is used to divide the humans into groups labelled as susceptible, exposed, infectious and recovered (SEIR) and the vector population into groups labelled as susceptible, exposed, and infectious (SEI). The group labelled exposed refers to the humans and vectors that have been exposed to the infection but are not infectious as they may be in an incubation period of the infection. The model assumes that only infected vectors and infected humans can transmit the Dengue virus to susceptible population. The exposed population is infected with the vector, however, they cannot transmit the Dengue virus.
The model assumes two sub-population of the Aedes aegypti: (1) the winged form Nv (mature female mosquitoes) and (2) an aquatic form Na (including eggs, larvae, and pupae).
9
The model takes into account spatial information. Diffusion coupled with constant advection (i.e. wind velocity) are the primary transport phenomena for the vector (mature female mosquitoes). Diffusion process for human population is also taken into account.
An SEIR model for the human population, in accordance with an embodiment of the present invention may be represented as:
An SEI model for the vector population, in accordance with an embodiment of the present invention may be represented as:
The relationship between winged mature female mosquitos with respect to immature mosquitos may be defined by means of the following equations. The equations further take into account diffusion processes, constant advection due to wind velocity, oviposition due to winged vector, maturity of immature aquatic vector.
Table 1 provides definitions of variables used in the prediction model for Dengue Fever represented by equations 1.1 to 1.9.
10
Table 1
In an embodiment, variables Nh, Sh, Eh, Ih, Rh, Nv, Sv, Ev, Iv, and Na are solved at time = t and position vector:
Table 2 provides description of parameters used in the prediction model for Dengue Fever represented by equations 1.1 to 1.9.
Table 2
11
In an embodiment, parameters such as wind velocity are obtained by using a sensor network. Also, geographical features defining urban landscapes are obtained from Geographical Information Systems (GIS).
FIG. 2 illustrates a SEIR-SEI compartment model for Dengue Fever, in accordance with an embodiment of the present invention. The model 200 is a pictorial representation of the model defined by the partial differential equations 1.1 to1.9 illustrated above.
In another exemplary embodiment, the present invention provides a method for modelling Malaria by using input parameters such as local temperature, relative humidity, rainfall, past disease treads, etc., in order to obtain a spatial probability distribution for the likelihood of a Malaria outbreak in the region.
Malaria is caused by P.falciparum, P.malariae, P.ovale, P.vivax, and P.knowlesi. These parasites belong to the genus of Plasmodium. The disease is primarily found in tropical and sub-tropical areas. Malaria maintains a cycle between humans and the Anopheles mosquito. The Anopheles is a night-biting female mosquito and is usually found near forests or regions with dense vegetation.
In an embodiment, a standard compartmental model commonly known in the art is used to divide the humans into groups labelled as susceptible, exposed, infectious and recovered (SEIR) and the vector population into groups labelled as susceptible, exposed, and infectious (SEI). The group labelled exposed refers to the humans and vectors that have been exposed to the infection but are not infectious as they may be in an incubation period of the infection. The model assumes that only infected vectors and infected humans can transmit the Plasmodium parasite to susceptible population. The exposed population is infected with the vector, however, they cannot transmit Malaria.
The model assumes two sub-population of the Anopheles: (1) the winged form Nv (mature female mosquitoes) and (2) an aquatic form Na (including eggs, larvae, and pupae). The model takes into account spatial information. Diffusion coupled with constant advection (i.e. wind velocity) are the primary transport phenomena for the vector (mature female mosquitoes). Diffusion process for human population is also taken into account.
An SEIR model for the human population, in accordance with an embodiment of the present invention may be represented as:
12
An SEI model for the vector population, in accordance with an embodiment of the present invention may be represented as:
The relationship between winged mature female mosquitos with respect to immature mosquitos may be defined by means of the following equations. The equations further take into account diffusion processes, constant advection due to wind velocity, oviposition due to winged vector, maturity of immature aquatic vector.
Table 3 provides definitions of variables used in the prediction model for Malaria represented by equations 1.10 to 1.18.
Table 3
13
In an embodiment, variables Nh, Sh, Eh, Ih, Rh, Nv, Sv, Ev, Iv, and Na are solved at time = t and position vector:
Table 4 provides description of parameters used in the prediction model for Malaria represented by equations 1.10 to 1.18.
Table 4
In an embodiment, parameters such as wind velocity are obtained by using a sensor network. Also, geographical features defining urban landscapes are obtained from Geographical Information Systems (GIS).
FIG. 3 illustrates a SEIR-SEI compartment model for Malaria, in accordance with an embodiment of the present invention. The model 300 is a pictorial representation of the model defined by the partial differential equations 1.10 to1.18 illustrated above.
In another exemplary embodiment, the present invention provides a method for modelling Cholera by using input parameters such as local temperature, relative humidity, rainfall, past disease treads, etc., in order to obtain a spatial probability distribution for the likelihood of a Cholera outbreak in the region.
Cholera is caused by the bacterium Vibrio Cholerae and is a waterborne disease The cholera bacterium is usually found in water or food sources that have been contaminated by feces
14
from a person infected with cholera. Cholera is likely to be found and might spread in places with inadequate water treatment, lack of water hygiene, and poor environmental sanitation.
In an embodiment, two standard compartmental models commonly known in the art are used to divide the human and vector population. The susceptible, exposed, infectious, transmitter, and recovered (SITR) – susceptible, exposed, and infectious (SEI) model is used to divide the humans into groups labelled as SITR and the vector population into groups labelled as susceptible, exposed, and infectious (SEI). The SEITR–SEI model is used to divide the humans into groups labelled as SEITR and the vector population into groups labelled as susceptible, exposed, and infectious (SEI).
The models assume that only infected vectors and infected humans can transmit the Vibiro Cholerae to susceptible population. Further, the models assume that the infected population decreases through natural recovery and/or treatment.
An SITR model for the human population, in accordance with an embodiment of the present invention may be represented as:
An SEI model for the vector population, in accordance with an embodiment of the present invention may be represented as:
An SEITR model for the human population, in accordance with an embodiment of the present invention may be represented as:
15
An SEI model for the vector population, in accordance with an embodiment of the present invention may be represented as:
Both the models incorporate water hygiene and environmental sanitation. Thus βvh and βhv may be obtained by using the following equations:
Table 5 provides definitions of variables used in the prediction model for Cholera represented by equations 1.19 to 1.35.
Table 5
16
In an embodiment, variables Nh, Sh, Eh, Ih, Th, Rh, Nv, Sv, and Iv, are solved at time = t and position vector:
Table 6 provides description of parameters used in the prediction model for Cholera represented by equations 1.19 to 1.35
Table 6
In an embodiment, parameters such as temperature and humidity which impact bacterial growth are obtained by using a sensor network.
FIG. 4 illustrates a SITR-SEI compartment model for Cholera, in accordance with an embodiment of the present invention. The model 400 is a pictorial representation of the model defined by the partial differential equations 1.19 to1.25 illustrated above.
FIG. 5 illustrates a SEITR-SEI compartment model for Cholera, in accordance with an embodiment of the present invention. The model 500 is a pictorial representation of the model defined by the partial differential equations 1.26 to1.33 illustrated above.
In another exemplary embodiment, the present invention provides a method for modelling Influenza by using input parameters such as local temperature, relative humidity, rainfall, past disease treads, etc., in order to obtain a spatial probability distribution for the likelihood of an Influenza outbreak in the region.
Influenza is an acute infectious disease caused by the Influenza virus Orthomyxoviruses. The three genera of Influenza virus that infect vertebrates include Type A, B, and C. Type A
17
infects humans, other mammals, and birds. Type B infects humans and seals. Type C infects humans, pigs, and dogs. Occurrences of Type A and B are most frequent as compared to Type C thus seasonal Influenza vaccines are designed for Type A and B.
Influenza viruses circulate in all parts of the world. In tropical regions, Influenza may occur throughout the year, causing spasmodic outbreaks. While in temperate regions, seasonal epidemics are observed during winter. Influenza is an airborne disease and spreads through coughing. The virus can also spread by hands contaminated with Influenza virus.
According to WHO, children (6 months to 5 years of age), elderly individuals (> 65 years of age), pregnant women at any stage of pregnancy, individuals with chronic medical conditions are most prone to the virus. Vaccination is the most effective way to prevent the disease. Some Influenza viruses develop resistance to the antiviral medicines thus limiting the effectiveness of treatment.
In an embodiment, two standard compartmental models are used, one being based on susceptible, vaccinated, exposed, infectious and recovered SVEITR classification while the second model on SVEITR-SEI classification. Both the models take into account the vaccination process. The first model is designed under assumption that only infected humans can transmit Influenza virus, while the second model is designed under assumption that infected vectors and infected humans can transmit the Influenza virus to susceptible population. The models further assume that the infected population decreases through natural recovery and due to proper treatment.
The models take into account spatial information. Diffusion is one of the primary transport phenomena for the vector. In case of Influenza, vector could be pigs, birds or other mammals. Diffusion process for human population is also taken into account.
An SVEITR model for the human population, in accordance with an embodiment of the present invention may be represented as:
18
An SVEITR model for the human population which is part of an SVEITR-SEI model, in accordance with an embodiment of the present invention may be represented as:
An SEI model for the vector population, in accordance with an embodiment of the present invention may be represented as:
In an embodiment, variables Nh, Sh, Eh, Ih, Th, Rh, Nv, Sv, and Iv, are solved at time = t and position vector:
Table 7 provides definitions of variables used in the prediction model for Influenza represented by equations 1.36 to 1.50.
19
Table 7
Table 8 provides description of parameters used in the prediction model for Influenza represented by equations 1.36 to 1.50.
Table 8
FIG. 6 illustrates a SVEITR compartment model for Influenza, in accordance with an embodiment of the present invention. The model 600 is a pictorial representation of the model defined by the partial differential equations 1.36 to 1.41 illustrated above.
FIG. 7 illustrates a SVEITR-SEI compartment model for Influenza, in accordance with an embodiment of the present invention. The model 700 is a pictorial representation of the model defined by the partial differential equations 1.42 to1.50 illustrated above.
The exemplary embodiments provided above are for illustrative purposes only. As would be apparent to persons of skill in the art, the method of the present invention may be used for modelling many other diseases such as but not limited to gastroenteritis; as well as diseases
20
caused due to air pollution such as but not limited to asthma, by using partial differential equations.
In an embodiment, the present invention provides a method of modelling epidemics, pandemics and related epidemiological phenomena that are usually described by partial differential (or integro-differential) equations. Such partial differential equations cannot be analytically solved in most cases. The present invention uses numerical schemes which have a standard solution procedure involving numerous steps from an initial mathematical formulation to a final numerical simulation.
The present invention also provides a method for discretization of the initial mathematical model. In context of numerical analysis, discretization refers to a process of transferring a continuous model into its discrete counterpart i.e. one having a finite number of points. Mathematically, the discretization method of the present invention reduces the differential equation to a system of algebraic equations which can then be solved on a computer.
In various embodiments, spatial discretization schemes such as Finite Difference Methods (FDM), Finite Volume Methods (FVM), and Finite Element Methods (FEM) are applied. In an embodiment, for performing temporal discretization Euler (Forward & Backward) Schemes known in the art are applied. As is known, the FDM is derived from Taylor Expansions and is a straightforward application of the definition of derivatives. The FDM estimates the derivative by the ratio of two differences according to the definition of the derivative.
In another embodiment of the present invention the Finite Volume Method (FVM) is used for spatial discretization of the disease modelling. In the FVM, the problem domain is decomposed into a number of control volumes. The differential equation is then integrated over these control volumes and the Divergence Theorem is applied which transforms the volume integrals into surface integrals.
In yet another embodiment, the Finite Element Method (FEM) is used for spatial discretization of the disease modelling. In the FEM, the problem domain is broken into a finite number of elements which usually comprise of triangles or quadrilaterals in two dimensions (2D) or tetrahedrals or hexahedrals in three dimensions (3D). A first step of FEM comprises working with a residual form which implies bringing all the terms of the PDE on one side of the equation. The solution of such a rearranged equation is considered to be a strong formulation. Next a weak formulation (also referred as the method of weighted residuals) is computed which satisfies the
21
PDE in its integral form multiplied by an arbitrary test function. The final step involves discretization of this weak formulation by replacing the infinite dimensional problem with a finite dimensional subspace. Although, there are many possible choices for the subspace, the method of the present invention involves choosing a space of piecewise polynomial functions.
In various embodiments of the present invention, for performing temporal discretization, Euler Schemes comprising both explicit (i.e. Forward) and Implicit (i.e. Backward) Euler are used.
The above examples are merely illustrative of the many applications of the system of present invention. Although only a few embodiments of the present invention have been described herein, it should be understood that the present invention might be embodied in many other specific forms without departing from the spirit or scope of the invention. Therefore, the present examples and embodiments are to be considered as illustrative and not restrictive.

We Claim:
Claims
1. A method of predicting pollution concentration and disease outbreak in a predefined area, the method comprising:
obtaining geographical parameters of the area, the geographical parameters comprising data identifying one or more of areas representing water bodies, forest, slums, and high population density;
obtaining climatic parameters of the area over a predefined period of time;
obtaining atmospheric parameters of the area over a predefined period of time;
obtaining historical disease trend data of the area; and
determining pollution concentration and chances of disease outbreak in the predefined area by using one or more of the obtained geographical parameters, climatic parameters, atmospheric parameters and the historical disease trend data and a mathematical model at least partially based on the use of partial differential equations.
2. The method of claim 1 wherein obtaining climatic parameters comprises measuring one or more of temperature, humidity, rainfall, and wind velocity of the area over a predefined period of time by using one or more of temperature sensors and humidity sensors.
3. The method of claim 1 wherein obtaining atmospheric parameters comprises measuring pressure, altitude, concentration of dust particles, and concentration of gasses in the area over a predefined period of time, by using one or more of sensors used for measuring pressure, altitude, concentration of dust particles in air, and concentration of predefined gases in air.
4. The method of claim 1 wherein at least one of the climatic parameters, and the atmospheric parameters are obtained by using sensors placed at predefined locations determined by using k-mean algorithms; spatial coordinates (longitude and latitude) of the locations of placement of the sensors being determined by using global positioning system (GPS).
5. The method of claim 1 wherein the climatic parameters, atmospheric parameters and historical disease trend data is obtained from one or more of: electronic health records (EHR) of medical professionals, social networking websites, and predefined medical databases hosted on the Internet.
6. The method of claim 1 wherein determining chances of disease outbreak comprises using a compartmental model for dividing humans into groups labelled as susceptible, exposed,
23
infectious and recovered (SEIR) and a vector population into groups labelled as susceptible, exposed, and infectious (SEI) for prediction of diseases spread by biting of insects.
7. The method of claim 1 wherein determining chances of disease outbreak comprises using a compartmental model for dividing humans into groups labelled as one of susceptible, infectious, transmitter, and recovered (SITR) and susceptible, exposed, infectious, transmitter, and recovered (SEITR) and a vector population into groups labelled as susceptible, exposed, and infectious (SEI) for prediction of infectious diseases outbreak.
8. The method of claim 1 wherein determining chances of disease outbreak comprises using a compartmental model for dividing humans into groups labelled as susceptible, vaccinated, exposed, infectious, transmitter and recovered (SVEITR) and a vector population into groups labelled as susceptible, exposed, and infectious (SEI) for prediction of infectious diseases outbreak.
9. The method of claim 1 further comprising discretizing the mathematical model by using one of a spatial discretization scheme and a temporal discretization scheme, the spatial discretization scheme being one of Finite Difference Methods (FDM), Finite Volume Methods (FVM), and Finite Element Methods (FEM), the temporal discretization scheme comprising Euler schemes.
10. A system for predicting pollution concentration and disease outbreak in a predefined area comprising:
one or more sensors for obtaining geographical parameters of the area;
one or more of temperature sensors and humidity sensors for obtaining climatic parameters of the area over a predefined period of time;
one or more of sensors for measuring pressure, altitude, concentration of dust particles in air, and concentration of predefined gases in air for obtaining atmospheric parameters of the area over a predefined period of time by using;
a mathematical model for determining a model conveying pollution concentration and chances of disease outbreak in the predefined area by using one or more of the obtained geographical parameters, climatic parameters, atmospheric parameters and historical disease trend parameter; the mathematical model at least partially based on the use of partial differential equations, the model being determined by using one of a spatial discretization scheme and a temporal discretization scheme, the spatial discretization scheme being one of Finite Difference
24
Methods (FDM), Finite Volume Methods (FVM), and Finite Element Methods (FEM), the temporal discretization scheme comprising Euler schemes;
at least one of the sensors used for obtaining geographical parameters, climatic parameters, and the atmospheric parameters being placed at predefined locations determined by using k-mean algorithms; spatial coordinates (longitude and latitude) of the locations of placement of the sensors being determined by using global positioning system (GPS).