WO2016064735A1

WO2016064735A1 - Wireless sensor system for mosquito population growth analysis, logging, and reporting

Info

Publication number: WO2016064735A1
Application number: PCT/US2015/056221
Authority: WO
Inventors: William R. Eisenstadt; Byul Hur; Devin S. MORRIS
Original assignee: University Of Florida Research Foundation, Incorporated
Priority date: 2014-10-20
Filing date: 2015-10-19
Publication date: 2016-04-28

Abstract

A wireless sensing system and method for determining mosquito breeding population and mosquito breeding behavior in an identified region using a server having a Predictive Modeling Software application that collects environmental parameters sensed at a wireless sensor (along with other environmental and historical data) and uses a predictive breeding rule to generate a predictive breeding model for determining the population and behavior are described.

Description

WIRELESS SENSOR SYSTEM FOR MOSQUITO POPULATION GROWTH ANALYSIS,

LOGGING, AND REPORTING

CROSS-REFERENCE TO A RELATED APPLICATION

[0001] This application claims the benefit of U.S. provisional application Serial No. 62/065,989, filed October 20, 2014, which is incorporated herein by reference in its entirety.

BACKGROUND

[0002] Mosquitos carry pathogens may that cause extremely harmful human and livestock diseases such as the West Nile virus, malaria, encephalitis, and Dengue Fever. These diseases come with some startling statistics. For example, according to the Centers of Disease Control (CDC), the West Nile Virus has sickened close to 40,000 people in the United States to date, leading to approximately 1,600 deaths. Another mosquito-transmitted viral disease, encephalitis, causes brain inflammation and has a 33% mortality rate. Further, in 2010, malaria infected over 219 million worldwide, with 660,000 resulting in death.

[0003] In general, although all mosquitoes do not carry deadly disease, these blood consuming insects are considered a public nuisance to those trying to enjoy the great outdoors by gardening, picnicking, fishing, hiking, swimming, etc. Accordingly, the proximity of suburban and metropolitan areas to insect breeding areas, such as swamps, marshes, and wetlands require the constant monitoring of environmental conditions that promote insect breeding with an eye towards abating large insect population growth.

[0004] Mosquito breeding occurs in four stages: the laying of the egg (embryo); the transformation into larva; the transformation into pupa; and finally, the maturation into an adult (imago). Mosquitoes lay eggs in almost any body of standing water. In the United States, the greatest concentration of mosquitoes resides in Florida's coastal marshes since Florida's warm humid climate makes it a perfect location for breeding. As a result, there are up to 80 mosquito species in Florida.

[0005] Insect spraying is used by many counties and states to control the insect population. Presently, field personnel of the Mosquito Control Districts manually set and monitor CDC mosquito surveillance traps, which are used to determine the actual mosquito activity at a particular area or location. These Mosquito Control Districts also use two forms of insecticides; where application of larvacides is used to kill larva, while the spraying of pesticides (adulticides) is used to kill the adult mosquito. Some districts apply pesticides and larvacides based upon the mosquito activity detected at these surveillance traps.

BRIEF SUMMARY

[0006] Systems and methods for wireless sensing of mosquito population growth using local weather conditions, such as measurements of temperature, wind, humidity, rainfall, and depth of water in retention ponds or marshes, are described herein. The described server system may enable the sensing, recording, and reporting of weather conditions, along with the generation of a predicted mosquito breeding population for a corresponding user-identified region.

[0007] In one implementation, the server collects data such as environmental parametric data, historical data, mapping data, field trap assessment data, community input data and data sensed by a mosquito sensing network to generate a customized mosquito breeding model from a user selected prediction rule or set of equations. When this model is run, the server generates a prediction map of mosquito population and breeding behavior. The prediction map can be used by the server to alert and/or initiate the application of insecticides. In certain embodiments, the server may manage surveillance and the application of insecticides, reducing cost through its derivation of the best times to spray or dispense larvacides or other chemical based upon the aforementioned data feeds from the variety of sources.

[0008] The described devices and techniques can be used to determine the mosquito breeding population, whether to apply larvacides or pesticides, and what are the most beneficial times to such applications. In particular, an embodiment of the server system includes a Predictive Modeling Software application that, when executed on the centralized server, uses the environmental parameters sensed at a microclimate weather station having a network of wireless sensors including at least one weather station sensor system (WSSS) sensor along with one or more of weather forecasting data, mapping data, field trap assessment data, historical mosquito population data and community input data to predict mosquito population for a particular region. In another embodiment, the software further enables a user to define and change various variables corresponding to a user-selected predictive breeding rule, which is used by the software to generate a predicted population value.

[0009] Advantageously, manual trap checking (and the costs associated therewith) may be reduced or eliminated. Consequently, monitoring and detection of anticipated mosquito breeding in remote locations where data collection efforts have been previously neglected is now possible. [0010] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 illustrates an example of an operating environment of a wireless sensor system for predictive mosquito breeding in Mosquito Control Districts.

[0012] Figure 2 illustrates a block diagram of a computing system for a computer device that may be used to implement certain techniques described herein.

[0013] Figure 3 shows a diagram of a predictive mosquito breeding server system that may be used to implement certain techniques described herein.

[0014] Figure 4 shows a block diagram for a wireless WSSS that may be used to implement the wireless sensor system described herein.

[0015] Figure 5 A illustrates a flow chart of an example process for the Predictive Modeling Software.

[0016] Figure 5B illustrates a continuation of the process for the Predictive Modeling Software as shown in Figure 5A.

[0017] Figure 5C illustrates a further continuation of the process for the Predictive Modeling Software as shown in Figure 5A.

[0018] Figure 6 is a graphic representation of a mosquito breeding map reporting feature of the Predictive Modeling Software interface.

[0019] Figure 7 is a graphic representation of a weather-breeding relationship reporting feature of the Predictive Modeling Software interface.

[0020] Figure 8 is a graphic representation of a spray zone reporting feature of the Predictive Modeling Software interface.

[0021] Figure 9 is a graphic representation of a reporting feature of the Predictive Modeling Software interface for estimated error patterns corresponding to errors in mosquito breeding predictions, weather conditions, and zones of larvacides and adulticides.

[0022] Figure 10A is a graphic representation of a community data reporting feature of the Predictive Modeling Software interface.

[0023] Figure 10B is a graphic representation of a pop-up window having associated select community data, as an additional feature of the reporting feature of Figure 10A. [0024] Figure 11 is a graphic representation of a cost map reporting feature of the Predictive Modeling Software interface.

DETAILED DESCRIPTION

[0025] Systems and techniques for wireless monitoring, logging, and reporting of mosquito population and breeding are described herein. In addition, the described system may include remote application of larvacides and pesticides. Generally, a wireless sensor system, including a network of weather station sensor systems (WSSS), can be deployed at various locations to monitor and transmit weather and mosquito surveillance data to a centralized server that can predict where and when to apply larvacides and pesticides. In some cases, the centralized server can remotely control the application of larvacide or pesticide by activating a spray function of at least one of the sensors or other devices.

[0026] The use of pesticides, however, may be harmful to the environment. In particular, the use of pesticides can be toxic, not only to those insects which must be controlled, but also to many other living organisms (including beneficial insect species). Further, pesticides can accumulate in water systems, air, and soil, weakening plant root and immune systems. Moreover, the use of pesticides have been linked to a wide range of human health hazards, ranging from short-term impacts, such as headaches and nausea, to chronic impacts like cancer, reproductive harm, and endocrine disruption. Second, the mosquitos can become resistant to repeated use of pesticides over time; such that, what was once an effective method for controlled breeding of mosquitoes may be rendered unsuccessful. In addition, high winds, low temperatures, rainfall, and high humidity can deter the product from getting to the target and/or alter the dispersion of the material applied; thereby, affecting the efficiency of each application.

[0027] In an effort to avoid over-application of pesticides and its detrimental effects, the Predictive Modeling Software takes into consideration the climate conditions to determine not only whether the conditions are conducive to mosquito breeding, but also whether the conditions are conducive to applying the pesticides. Further, since local weather patterns establish conditions for mosquito breeding, the Predictive Modeling Software compiles weather patterns localized in small geographical area microclimates, which are also of great concern for Mosquito Control Districts that perform mosquito surveillance and mosquito control through the use of pesticides and larvacides. In particular, these weather patterns (once detected and transmitted by the wireless sensor system) are used by the Predictive Modeling Software residing on a server to establish the timing and conditions of the application of chemicals, which control mosquito breeding (i.e. adult mosquito spraying). Thereby, the Predictive Modeling Software may greatly improve the efficacy and efficiency of insecticide application as well as reduce costs associated therewith.

[0028] The wireless sensor system can include a wireless remote spot or microclimate weather station, having at least one WSSS, which acquires data, including but not limited to the sensing of temperature, wind, humidity, rainfall, and depth of water in retention ponds or marshes. Further, separate data can be acquired by field personnel using mosquito surveillance traps or by automated techniques for measuring mosquito population using microphones or laser-based surveillance traps. This data can be uploaded automatically or manually to a Tracking and Mapping software utility within the Predictive Modeling Software to generate a predictive mosquito breeding model. The Tracking and Mapping software utility can also provide graphic output to common data display devices such as PCs, computer displays, smartphones and tablets to aid Mosquito Control Districts in efficient assignment of resources for the provisioning of surveillance and control of mosquitoes. In addition, the Predictive Modeling Software can estimate error in the breeding predictions as for greater accuracy in improving the operations of the Mosquito Control Districts.

Server System

[0029] Figure 1 illustrates an example of an operating environment of a wireless sensor system 100 for predictive mosquito breeding in Mosquito Control Districts. A hardware and software based system 100 for performing mosquito breeding predictions and spray control for within Mosquito Control Districts is shown. The system 100 illustrated in Figure 1 is suitable for wireless monitoring of pressure, temperature, humidity, movement, and time in an effort to detect favorable conditions for insect larval population growth. This system develops predictive output by collecting field information, which describes the existing local weather conditions, the future weather predictions, mosquito trap data and historical mosquito breeding data. This data can be used to make predictions either using an artificial intelligence system, a statistical correlation system, a genetic algorithm, a nonlinear regression algorithm, or algorithms from university, government and corporate research as to the future mosquito breeding patterns. The system enables storage of field data and historical data to improve the prediction capability. That is, new data can be analyzed using existing algorithms to fine tune and improve the software model parameters. This allows the models to better predict future mosquito breeding patterns.

[0030] Figure 1 illustrates a system block diagram of a first embodiment of the wireless sensor system for wireless sensing and monitoring of mosquito breeding population for logging and reporting. Previously, an obstacle to predicting future breeding of mosquito species was the inaccessibility of prior weather and mosquito trap data; where older trap data in some Mosquito Control Districts were stored on old equipment which cannot easily interface with any network or computing device. Yet, through the implementation of the wireless sensor system 100 described herein, a Predictive Modeling Software 136 is able to access historical 40, field trap assessment data 80, and other weather services data 10, using a variety of current networks 126 and computing devices 90, 92, and 94 (further detailed).

[0031] In particular, an operating environment 100 may include a server 130 that executes the Predictive Modeling Software 136. Server 130 may be a cloud server or a central computer. Server 130 includes a processor 140, an Input/Output (I/O) Interface 132, a Software Training and Analysis Interface Module 134, and a System Memory 138. There are numerous sources of data upon which the predictive mosquito control software 136 relies. These include, but are not limited to, field trap assessment data 80 acquired by the mosquito districts, spot or microclimate weather station data generated by WSSS units 30-a, 30-b, 30- c, historical mosquito breeding data maintained by Mosquito Control District archives 40, and weather prediction data from national weather sources 10. Further, various resources of community input from wired or wireless devices 90, 92, and 94, such as medical centers, hospitals, government agencies, field personnel, businesses or residents are able to connect with server 130 through a network 126, where the network can be any type of network including but not limited to the Internet, a communications network, or collection of networks (not shown). In particular, the community of people and businesses in the Mosquito Control Districts can input their mosquito surveillance data and mosquito borne disease data into the system 100. In addition, hospitals, clinics, government and non-profit groups interested in infectious disease control can provide information using a community input utility of software 136.

[0032] Field mosquito trap assessment data 80 can be communicated to server 130 by hand data entry using a computer or wireless data acquisition through an automated mosquito counting system 85. The historical mosquito breeding data 40 is generated from years of records at the Mosquito Control Districts and these records can be entered into server 130 through network 126 using hand data entry or transmission of computer files. Weather prediction data 10 is also accessible by server 130 through network 126, where server 130 is enabled to access weather services information. Spot or microclimate weather station data from the WSSS units 30-a, 30-b, 30-c is sent to server 130 directly using a cellular communications module embedded within the WSSS unit 30. In the alternative, this data is sent indirectly by wireless connection of any one of the data receivers 90, 92, or 94 and forwarded through network 126.

[0033] The data receiver can be a personal computer 94, a tablet 92, a cell phone 90, a cell tower (not shown), or other mobile communications device (not shown) or computing system (not shown). The wireless connection can be through many popular protocols such as ANT, Bluetooth™, zig bee, and cell phone system data communications. To realize cellular data communications, in some implementations each WSSS unit 30-a, 30-b, 30-c includes a cellular modem module 432 (discussed in detail with reference to Figure 4). Other community input 50 couples to software training and analysis interface module 134 to report mosquito related information through the Public Switched Telephone Network (PSTN) using a standard telephone 50.

[0034] Server 130 also couples to receive data from a mapping database 20, which provides information about local maps for the Mosquito Control District. Alternatively, the connection to mapping database 20 may couple to a hard disk (not shown), another media storage device (not shown), or through a network 126 to an on-line database (as shown). The software training and analysis interface module 134 couples to supply input for the Predictive Modeling Software 136, which generates a mapping display.

[0035] In at least one implementation, Predictive Modeling Software 136 couples to receive data from at least one of weather forecasting service 10, mapping database 20, WSSS units 30-a, 30-b, 30-c, historical database 40, field personnel 50, and field trap assessment data 80 to generate mosquito breeding population rates using various predictive breeding models. Predictive Modeling Software 136 further displays these rates on a display device 90, computer 92 such as laptop or desktop, tablet 94, and phone 96. The connections to any of the devices 90, 92, and 94 can be a wired connection, wireless connection, or a combination thereof. In some cases, the display screens of devices 90, 92, and 94 are smart and/or touchscreen displays, which allow interactions using buttons, pull down menus, touch, and data entry boxes to select, edit, manipulate and request new data presented on the displays.

[0036] Predictive Modeling Software 136 includes an algorithm for predicting the mosquito breeding/population within a given range of time using specific parameters. The algorithm may include statistical algorithms, genetic algorithms, and artificial intelligence algorithms; as well as scientific models used in mosquito breeding data analysis and modeling breeding behavior (such as Linear and Non- linear regression models).

[0037] For example, the mosquito population determined by the count in mosquito traps can be statistically compared to the temperature and ground water history at nearby wireless WSSS at different times. Then, the correlation between temperatures and levels of ground water can be made for the growth in mosquito population. A similar set of data can be presented to an artificial intelligence system, which trains and makes "rules" for mosquito population versus the history of the temperature and the ground water. Advantageously, many variables can be examined against various predictive models to improve the overall outcome. Also, relevant locations and species can be specifically targeted using this approach so that truly local predictions with high accuracy can be achieved. Local prediction of breeding enables a targeted solution, particularly where mosquito control is handled as a local community issue and spraying is performed block-by-block.

[0038] All models may include initial conditions and parametric biological assumptions about the mosquito breeding process. The accuracy and reliability of these models may be improved through the inclusion of new data. In some cases, the software analysis and training interface 134 to the predictive modeling software 136 allows mosquito experts at various districts to select the appropriate predictive algorithms, rules and/or models to use in calculating the mosquito population. In particular, rules for spraying can be derived from an artificial intelligence package or input by a mosquito expert. These experts can also remotely fine tune these predictive algorithms through any of the communication means shown in Figure 1. For instance, the historical data for the month of May for a geographical location can be used to build a breeding model for May, illustrating various temperature conditions. Consequently, the current data for the month of May can be compared with the predictions generated using historical data. Mosquito experts can look at the various predictions using the display screens of devices 90, 92, and 94 and make decisions about spraying in the districts each day.

[0039] Predictive Modeling Software 136 analyzes many physical weather related variables in pairs, where software 136 makes correlations between these variables. Additionally, software 136 evaluates the validity of the scientific models for a specific set of historical conditions within a geographical area. Models, statistics, and training can be applied to specific species of mosquitos, so that software 136 can determine the individual predictive breeding patterns of numerous species of mosquitos; where special interest and importance is placed upon mosquito species which carry communicable diseases such as malaria, west Nile virus, dengue fever, and Chikungunya.

[0040] Additionally, system 100 can be used to explore mosquito breeding responses to weather. Field trap assessment data 80 can assess the growth of individual mosquito species. Accordingly, models of individual mosquito species breeding behavior and population growth and weather patterns can be developed, stored, and improved upon using updated field trap assessment data 80. Resources for weather measurement can be allocated to focus upon monitoring and controlling species that carry particular mosquito borne health hazards to the humans. In particular, the data collected by server 130 can be stored and used to improve the modeling accuracy as new trap data becomes available through the software analysis and training interface 134.

[0041] As new data is received, the software training and analysis interface module 134 can be used to select between various mosquito predictive breeding models. In addition, wireless traps owned by businesses and home owners may provide data to the system 100. This will give businesses and homeowners input into the mosquito control practices of their respective Mosquito Control District and enable them to receive information about the mosquito breeding potential in their vicinity.

[0042] Since public health can be improved by identifying future weather conditions given the existing mosquito breeding state that will lead to explosive growth of mosquitos, Predictive Modeling Software 136 can be used to schedule less expensive and preventative resources such as mosquito larvacides in ponds and bodies of water instead of expensive spraying after the mosquito population becomes intolerable, when a continuation of hot moist weather with frequent rainfall leading to an uncomfortable level of mosquito breeding exists, for example. Given this scenario, the use of mosquito larvacides is much more desirable from an environmental point of view. Since mosquitos become tolerant of sprayed pesticides after repeated use, the Predictive Modeling Software 136 can keep track of the amount of pesticide sprayed over a given time period and use this amount as a variable in determining whether to spray a pesticide or not. Accordingly, software 136 is programmed to reflect that the best control strategy is to use a minimal amount of sprayed pesticides to maintain their usefulness in mosquito control.

[0043] Predictive Modeling Software 136 also keeps track of community input, which plays a significant role in guiding Mosquito Control District predictive models and spraying activities. In particular, a series of phone calls from community homeowners can indicate a mosquito breeding source that needs to be larvacided, as well as a need for spraying across that local community. Further, local medical clinics and hospitals become a useful source of information for software 136; wherein, hospitals, medical clinics and doctor's practices can report individuals with mosquito borne diseases such as West Nile Virus, Malaria, Dengue Fever and Chikungunya to the system 100. Using these reports, an implementation of the Predictive Modeling Software 136 can build an aggregate picture of the infectious disease spread in the district, which can be used to target areas for insecticide spraying, to prevent further spread of disease.

[0044] In some implementations, Predictive Modeling Software 136 can also display these reports on the display screens of devices 90, 92, and 94, including devices for anyone in the public sector such as businesses and home owners, government sector, specially public health and safety providers, schools and parks recreation organizations, as well as the field personnel at the Mosquito Control Districts. Thereby, medical organizations can report mosquito borne disease cases to each other through the system 100, looking at the mosquito breeding potential near their physical location.

Computing Device

[0045] Figure 2 illustrates a block diagram of a computing system for a computer device that may be used to implement certain techniques described herein; and Figure 3 shows a diagram of a predictive mosquito breeding server system that may be used to implement certain techniques described herein.

[0046] Computing system 200 can represent the system of devices 90, 92, and 94. In particular, data acquisition software runs on personal computing devices 90, 92, and 94, and wirelessly logs data from multiple sensors 30. In a specific implementation, sensors 30 can report up to 6 months of data, indicating significant temperature change; where data is then uploaded to a spreadsheet or database application which can be transferred to server 130 through network 126 to generate data graphs to be displayed on computers or other hand-held computer operated devices 90, 92, and 94.

[0047] Referring to Figure 2, system 200 may represent a computing device such as, but not limited to, a personal computer, a tablet computer, a reader, a mobile device, a personal digital assistant, a wearable computer, a smartphone, a tablet, a laptop computer (notebook or netbook), a gaming device or console, a desktop computer, or a smart television. Accordingly, more or fewer elements described with respect to system 200 may be incorporated to implement a particular computing device.

[0048] Computing system 200 may include a Input/Output (I/O) controller 202, a system memory 210, memory controller 230, processing system 240, user interface system 260 and network/communications interface 250, each of which may be interconnected using a communication infrastructure 270, Communication infrastructure 270 generally represents any type or form of infrastructure capable of facilitating communication between one or more components of a computing device. Examples of communication infrastructure 270 include, without limitation, a communication bus (such as an International Standard Architecture (ISA), Parallel Communication Interface (PCI), PCI-Express (PCIe), or similar bus) or any network.

[0049] System 200 includes a processing system 240 of one or more processors to transform or manipulate data according to the instructions of software 220 stored on in a system memory 210. Examples of processors of the processing system 240 include general purpose central processing units, application specific processors, and logic devices, as well as any other type of processing device, combinations, or variations thereof. The processing system 240 may be, or is included in, a system-on-chip (SoC) along with one or more other components such as network connectivity components, sensors, video display components.

[0050] The software 220 can include an operating system and application programs such as a native predictive modeling application 222 and/or web browsing application 226 (which may be used to access a cloud based predictive modeling application). Device operating systems generally control and coordinate the functions of the various components in the computing device, providing an easier way for applications to connect with lower level interfaces like the networking interface. Non-limiting examples of operating systems include Windows® from Microsoft Corp., Apple® iOS™ from Apple, Inc., Android® OS from Google, Inc., and the Ubuntu variety of the Linux OS from Canonical.

[0051] It should be noted that the operating system may be implemented both natively on the computing device and on software virtualization layers running atop the native device operating system (OS). Virtualized OS layers, while not depicted in Figure 2, can be thought of as additional, nested groupings within the operating system space, each containing an OS, application programs, and APIs.

[0052] System memory 210 may comprise any computer readable storage media readable by the processing system 240 and capable of storing software 220 including the native predictive modeling application 222 and/or web browsing application 226.

[0053] System memory 210 may include volatile and nonvolatile, removable and nonremovable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. Examples of storage media of system memory 210 include random access memory, read only memory, magnetic disks, optical disks, CDs, DVDs, flash memory, virtual memory and non-virtual memory, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other suitable storage media. In no case is the storage medium a propagated signal or carrier wave. [0054] In addition to storage media, in some implementations, system memory 210 may also include communication media over which software may be communicated internally or externally. System memory 210 may be implemented as a single storage device but may also be implemented across multiple storage devices or sub-systems co-located or distributed relative to each other. System memory 210 may include additional elements, such as a controller, capable of communicating with processing system 240.

[0055] Software 220 may be implemented in program instructions and among other functions may, when executed by system 200 in general or processing system 240 in particular, direct system 200 or the one or more processors of processing system 240 to operate as described herein.

[0056] In general, software may, when loaded into processing system 240 and executed, transform computing system 200 overall from a general-purpose computing system into a special-purpose computing system customized to retrieve and process the information for mosquito monitoring and control as described herein for each implementation. Indeed, encoding software on system memory 210 may transform the physical structure of system memory 210. The specific transformation of the physical structure may depend on various factors in different implementations of this description. Examples of such factors may include, but are not limited to the technology used to implement the storage media of system memory 210 and whether the computer-storage media are characterized as primary or secondary storage.

[0057] The system can further include user interface system 260, which may include input/output (I/O) devices and components that enable communication between a user and the system 200. User interface system 260 can include input devices such as a mouse 262, track pad (not shown), keyboard 264, a touch device 270 for receiving a touch gesture from a user, a motion input device 272 for detecting non-touch gestures and other motions by a user, a microphone for detecting speech (not shown), and other types of input devices and their associated processing elements capable of receiving user input.

[0058] The user interface system 260 may also include output devices such as display screens 268, speakers 274, haptic devices for tactile feedback (not shown), and other types of output devices. In certain cases, the input and output devices may be combined in a single device, such as a touchscreen display which both depicts images and receives touch gesture input from the user. A touchscreen (which may be associated with or form part of the display) is an input device configured to detect the presence and location of a touch. The touchscreen may be a resistive touchscreen, a capacitive touchscreen, a surface acoustic wave touchscreen, an infrared touchscreen, an optical imaging touchscreen, a dispersive signal touchscreen, an acoustic pulse recognition touchscreen, or may utilize any other touchscreen technology. In some embodiments, the touchscreen is incorporated on top of a display as a transparent layer to enable a user to use one or more touches to interact with objects or other information presented on the display.

[0059] Visual output may be depicted on the display 268 in myriad ways, presenting graphical user interface elements, text, images, video, notifications, virtual buttons, virtual keyboards, or any other type of information capable of being depicted in visual form.

[0060] The user interface system 260 may also include user interface software and associated software (e.g., for graphics chips and input devices) executed by the OS in support of the various user input and output devices. The associated software assists the OS in communicating user interface hardware events to application programs using defined mechanisms. The user interface system 260 including user interface software may support a graphical user interface, a natural user interface, or any other type of user interface. For example, the interfaces for users to access the predictive mosquito software and the monitoring and control systems described herein may be presented through user interface system 260.

[0061] Communications interface 250 may include communications connections and devices that allow for communication with other computing systems over one or more communication networks (not shown). Examples of connections and devices that together allow for inter-system communication may include network interface cards, antennas, power amplifiers, RF circuitry, transceivers, and other communication circuitry. The connections and devices may communicate over communication media (such as metal, glass, air, or any other suitable communication media) to exchange communications with other computing systems or networks of systems. Transmissions to and from the communications interface are controlled by the OS, which informs applications of communications events when necessary.

[0062] Computing system 200 is generally intended to represent a computing system with which software is deployed and executed in order to implement an application, component, or service for a productivity tool for assisted content authoring as described herein. In some cases, aspects of computing system 200 may also represent a computing system on which software may be staged and from where software may be distributed, transported, downloaded, or otherwise provided to yet another computing system for deployment and execution, or yet additional distribution.

Server System [0063] Referring to Figure 3, server system 300 may be implemented within a single computing device or distributed across multiple computing devices or sub-systems that cooperate in executing program instructions. The system 300 can include one or more blade server devices, standalone server devices, personal computers, routers, hubs, switches, bridges, firewall devices, intrusion detection devices, mainframe computers, network- attached storage devices, and other types of computing devices. The system hardware can be configured according to any suitable computer architectures such as a Symmetric Multi- Processing (SMP) architecture or a Non-Uniform Memory Access (NUMA) architecture.

[0064] The system 300 can include a processing system 340, which may include one or more processors and/or other circuitry that retrieves and executes software 320 from system memory 310. Processing system 340 may be implemented within a single processing device but may also be distributed across multiple processing devices or sub-systems that cooperate in executing program instructions.

[0065] System memory 310 can include any computer readable storage media readable by processing system 340 and capable of storing software 320. System memory 310 may be implemented as a single storage device but may also be implemented across multiple storage devices or sub-systems co-located or distributed relative to each other. System memory 310 may include additional elements, such as a controller, capable of communicating with processing system 340. System memory 310 may also include storage devices and/or subsystems on which data such as entity-related information is stored.

[0066] Software 320 may be implemented in program instructions and among other functions may, when executed by system 300 in general or processing system 340 in particular, direct the system 300 or processing system 340 to operate as described herein for monitoring and controlling mosquito populations (including providing predictive modeling application 322).

[0067] System 300 may represent any computing system on which software 320 may be staged and from where software 320 may be distributed, transported, downloaded, or otherwise provided to yet another computing system for deployment and execution, or yet additional distribution.

[0068] In embodiments where the system 300 includes multiple computing devices, the server can include one or more communications networks that facilitate communication among the computing devices. For example, the one or more communications networks can include a local or wide area network that facilitates communication among the computing devices. One or more direct communication links can be included between the computing devices. In addition, in some cases, the computing devices can be installed at geographically distributed locations. In other cases, the multiple computing devices can be installed at a single geographic location, such as a server farm or an office.

[0069] A communication interface 350 may be included, providing communication connections and devices that allow for communication between system 300 and other computing systems (not shown) over a communication network or collection of networks (not shown) or the air.

[0070] Certain techniques set forth herein with respect to assisted content authoring may be described in the general context of computer-executable instructions, such as program modules, executed by one or more computing devices. Generally, program modules include routines, programs, objects, components, and data structures that perform particular tasks or implement particular abstract data types.

[0071] Alternatively, or in addition, the functionality, methods and processes described herein can be implemented, at least in part, by one or more hardware modules (or logic components). For example, the hardware modules can include, but are not limited to, application-specific integrated circuit (ASIC) chips, field programmable gate arrays (FPGAs), system-on-a-chip (SoC) systems, complex programmable logic devices (CPLDs) and other programmable logic devices now known or later developed. When the hardware modules are activated, the hardware modules perform the functionality, methods and processes included within the hardware modules.

[0072] Embodiments may be implemented as a computer process, a computing system, or as an article of manufacture, such as a computer program product or computer-readable medium. Certain methods and processes described herein can be embodied as software, code and/or data, which may be stored on one or more storage media. Certain embodiments of the invention contemplate the use of a machine in the form of a computer system within which a set of instructions, when executed, can cause the system to perform any one or more of the methodologies discussed above. Certain computer program products may be one or more computer-readable storage media readable by a computer system and encoding a computer program of instructions for executing a computer process.

[0073] Computer-readable media can be any available computer-readable storage media or communication media that can be accessed by the computer system.

[0074] Communication media include the media by which a communication signal containing, for example, computer-readable instructions, data structures, program modules, or other data, is transmitted from one system to another system. The communication media can include guided transmission media, such as cables and wires (e.g., fiber optic, coaxial, and the like), and wireless (unguided transmission) media, such as acoustic, electromagnetic, RF, microwave and infrared, that can propagate energy waves. Although described with respect to communication media, carrier waves and other propagating signals that may contain data usable by a computer system are not considered computer-readable "storage media."

[0075] By way of example, and not limitation, computer-readable storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include volatile memory such as random access memories (RAM, DRAM, SRAM); nonvolatile memory such as flash memory, various read-only-memories (ROM, PROM, EPROM, EEPROM), phase change memory, magnetic and ferromagnetic/ferroelectric memories (MRAM, FeRAM), and magnetic and optical storage devices (hard drives, magnetic tape, CDs, DVDs). As used herein, in no case does the term "storage media" consist of carrier waves or propagating signals.

Wireless Weather Station Sensor System

[0076] Figure 4 shows a block diagram for a wireless WSSS that may be used to implement the wireless sensor system described herein. In Figure 4, a specific implementation of wireless WSSS 400 (also shown in Figure 1 as WSSS units 30-a, 30-b, 30-c) is illustrated. The WSSS can be placed in insect breeding areas, such as swamps, wetlands, and stagnant bodies of water, for gathering information regarding environmental conditions. A WSSS can also be placed in communities which will undergo spraying to gather information to control pesticide spraying. In the implementation illustrated in Figure 4, WSSS 400 includes an antenna 424, transceiver 402, I/O interface 418, microcontroller 420, Read Accessible Memory (RAM) 425, Read Only Memory (ROM) 422, an off-board sensor 428, clock 416, vial assembly 428, nozzle 430, and a multisensory board 426, including a thermistor 404, barometric pressure sensing module 406, anemometer 408, humidity sensing module 410, wind direction detection module 412, and water level detection module 414. Multisensory board 426 may comprise one or more of a vast array of sensors, including but not limited to, pressure, temperature, humidity, movement and time, in an effort to determine metrics that relate to favorable insect larval population growth (i.e. water/air temperature relative to humidity, water turbidity, and corresponding time period of these conditions). Optionally, WSSS 400 may couple to a cellular communications module 432, having antenna 434, or may include the cellular communications module 432 as an embedded component therein. [0077] Remotely accessible WSSS 400 is capable of delivering diverse and accurate data upon command. The design goals of WSSS 400 are low power consumption, user friendly interface, and scalability, where the sensor's capabilities may be expanded. In one embodiment, wireless WSSS 400 may detect ambient temperature, which is stored using microcontroller 420 on RAM 425 and sent using either antenna 424 or 434; thereby, allowing this data to be accessed by another computer 90, 92, and 94. At the heart of WSSS 400 is microcontroller 420 which fetches data from multisensory board 426, stores the data in RAM 425, and communicates with any computer device 90, 92, and 94, or server 130.

[0078] Multi-sensor board 426 may contain both digital and analog sensors. Off-board sensor 428 connects to the multi-sensor board 426 by tethering. The WSSS can be encased in a rugged, waterproof casing (not shown) to provide hardware robustness and allow placement in specific areas of interest without performance degradation. Further, this WSSS 400 is designed for minimal field maintenance, long battery life-extendable from a few months to a year and accurate/reliable data logging. In operations for longer than a year, WSSS 400 can be designed for solar power, for example, by being equipped with a battery charger and rechargeable battery.

[0079] Regarding weather, wireless WSSS 400 senses data associated with the microclimate within close proximity to the mosquito trap; and hence, enables a much more refined combination of weather and trap data for mosquito population modeling purposes. Previously, Mosquito Control District personnel would use data from weather services, which tends to be quite sparse geographically. For example, the rainfall measurement for Gainesville, FL is typically reported from the Gainesville airport which is one point in a city of 62.4 square miles. Thereby, wireless WSSS 400 more accurately detects data within a given region.

[0080] In operation, wireless WSSS 400 relays calculated data and data sensed by boards 426 and 428, using its transceiver 402 to a wireless mesh network of other WSSSs 400 located in close proximity. This data can be forwarded to a remote computer (such as server 130 or computing devices 90, 92, and 94 as shown in Figure 1) or base station (not shown) to provide instantaneous field data of hundreds of sensors simultaneously without direct interaction with the environment being investigated. In particular, through the use of a base station, wireless WSSSs 400 can transmit successive iterations of the data to an end user computing device 90, 92, and 94 through the cellular network grid, with minimal hardware to allow for remote monitoring. As noted previously, cellular communication module 432 may be coupled to microcontroller 420 to provide connectivity to the cellular network grid; where, module 432 may be included within the housing of WSSS 400 or external thereto (as shown). In this way, researchers and technicians may periodically poll the data to provide a comprehensive assessment of the potential for mosquito blooms; thereby, using the data to justify, coordinate and localize insecticide spraying for effective population control quickly and efficiently.

[0081] WSSS 400's real time weather reporting of the trap conditions using thermistor 404, barometric pressure sensing module 406, and anemometer 408 can be used by Predictive Modeling Software 136 to make a proper determination of effective application of pesticide spray to high infestation areas. Additionally, since wind direction can play a significant factor in the direction of the application of pesticides from mobile spray trucks onto areas where a high level of mosquitoes exist, the detection of the wind pattern using the wind direction detection module 412 aids Predictive Modeling Software 136 in the determination of more effective spraying and data collection efforts. Further, detection of daily rainfall and water level in retention ponds or other places having standing water by the water level detection module 414 are key indicators of mosquito larva development. Accordingly, WSSS 400 can also provide this information to server 130 and any other computing device 90, 92, and 94.

[0082] Additionally, wireless WSSS 400 may operatively dispense solid or liquid material (such as insecticide), color dye, or other desirable biological agent into the environment. In particular, when the Predictive Modeling Software 136 determines that desirable conditions exist for application of insecticides, it will generate and send a signal initiating the spraying of insecticides at WSSS 400. WSSS 400 may comprise a vial assembly 428 having a nozzle 430 that dispenses the insecticide stored in the vial. In the alternative, WSSS 400 can dispense biological agents such as bacteria that target a specific insect species when directed to do so externally or by a predictive breeding rule or model. The color dye as a marker is dispensed when WSSS 400 is located in a pond environment where the WSSS 400 is hard to locate. This feature is beneficial when trying to locate the WSSS 400 for relocation and/or repair. Further, WSSS 400 can be commanded and controlled by a remote controller (not shown) that communicates with the microcontroller 420 through the I/O interface 418. Moreover, WSSS 400 can capture water samples at desirable times for later inspection of field personnel.

[0083] In some cases, WSSS 400 may be implemented in a floating package; wherein the sensor floats and includes a mechanism (not shown) to control its buoyancy (vertical mobility), such that it can go to a targeted depth. This mechanism may be realized by a compressed air bladder (not shown) and a volume filled with a water/ballast mixture. For example, when the air in the airbladder goes into the water volume to displace the water, the sensor is made to float. In the alternative, when the air is forced back into the airbladder, then the water returns and the module loses buoyancy, sinking downward. A mechanical technique using a motor and a vertical track to move the sensor up and down in the water may be used as another means for realization of the buoyancy mechanism. Accordingly, the sensor is enabled to sense the water temperature at different depths during the day and night.

[0084] The horizontal mobility of WSSS 400 can be enabled by a motor and a track (not shown); wherein the track is placed in the pond with the motorized sensor on top of the track. Thereby, WSSS 400 is enabled to sense different variables of the environment as it is repositions in different places around the track. Further, the difference between temperature in the shade and temperature in the sun can be measured, when the embodiment of WSSS 400 includes a photocell to detect sunlight. Moreover, the difference of water temperature at the shallow edge or the deeper middle can be measured and logged. Accordingly, using the vertical and horizontal motion mechanisms, WSSS 400 can be remotely commanded to float and traverse to the outer edge of the water for ease of retrieval.

[0085] Another embodiment of WSSS 400 may include a wireless temperature pole having multiple temperature sensors, which are used to sense the temperature at these various heights. Since the local temperature can vary at different heights above ground, WSSS 400 will sense temperature readings at a height just above the ground, at three feet and at six feet, so that Predictive Modeling Software 136 may determine whether or not to spray.

Software of Server System

[0086] Figures 5A-C disclose a flow chart of an example of a method for Predictive Modeling Software 136 within server 130 of Figure 1, which provides monitoring and prediction of mosquito breeding populations. Figure 5A illustrates a flow chart of an example process for the Predictive Modeling Software; Figure 5B illustrates a continuation of the process for the Predictive Modeling Software as shown in Figure 5 A; and Figure 5C illustrates a further continuation of the process for the Predictive Modeling Software as shown in Figure 5A.

[0087] At the start of process 500 for generating a predictive breeding model (at step 510), server 130 can collect various sensor data, including but not limited to weather forecast data 10, mapping data 20, historical data 40, field trap assessment data 80, and/or other data from the various resources, such as those shown in Figure 1. In addition, data from community input at wired or wireless devices 90, 92, and 94 may be sent to and received by the server 130 in step 512. In the alternative, data from community input may be continuously received and stored in the system memory 138 of the server 130; wherein, this data is later retrieved by software 136, at the start of this predictive process 500. Further, the server 130 collects data regarding the current temperature from the WSSS units 30-a, 30-b, 30-c at step 514.

[0088] Simultaneously at steps 512 and 514, server 130 solicits or receives a response from the user regarding which predictive breeding rule the user would like to use. In the alternative, server 130 can select a default predictive breeding rule. In addition, the user may alter the variables of the rule, along with selecting which type of predictive algorithms will be used. The user may be stationed at one of the wired or wireless devices 90, 92, and 94 or a caller at phone 50 which accesses server 130 through the Public Switched Telecommunication Network (PSTN).

[0089] Server 130 uses the data from the various sources described above as input to the Predictive Modeling Software 136 in accordance with the invention at step 518 to generate a predictive breeding model. At step 520, server 130 generates the mosquito population growth and breeding behavior using the data collected at step 510 and the model generated at step 518 using the user selected predictive rule or the default rule associated with the Predictive Modeling Software 136. Using the collected data, the population growth and breeding behavior, Predictive Modeling Software 136 makes a determination as to whether the conditions are conducive to mosquito breeding and the best times to either spray pesticides or apply larvacides. Predictive Modeling Software 136 may make a determination is made as to whether the mosquito population is above a predetermined value Xp and if so, software 136 determines whether the temperature and humidity are within a predetermined temperature range RT and humidity range RH at steps 522 and 524. If the temperature and humidity are within the predetermined ranges RT and RH for mosquito breeding, a further determination is made as to whether the wind pattern is above a predetermine value Xw in step 526. Further, software 136 determines from the sensed water levels from WSSS units 30-a, 30-b, 30-c whether the daily rainfall and water level is over a predetermined level XR at step 530; and, if so the process continues on the portion B of the process as shown in Figure 5B. It is noted that the determinations in the aforementioned steps 522, 524, 526 and 530 may be made in any order.

[0090] All of these aforementioned conditions are indicative of whether the time is the best for chemical spraying or larvacides application. Accordingly, when the wind pattern is above the predetermined value Xw, it is best to wait for a predetermined time period Tp to spray chemicals as noted at step 528. It is also optimum to wait for the predetermined time period Tp to spray chemicals when the mosquito population is not above the predetermined value Xp; the water level is not above a predetermine level X_R and/or when the temperature and humidity are outside of a predetermined temperature and humidity ranges, R_T and R_H. AS shown, the process is looped back to the start if such is the case.

[0091] Turning to Figure 5B, in the alternative, when the wind pattern is not above the predetermined value Xw (at point B), this indicates that the time is ripe for application of the insecticide. As a result, software 136 calculates the best ranges of time for chemical spraying at step 540. The software 136 on server 130 also determines whether there has been an increase level of breeding from the historical data 40; and, if so, it generates a signal and a notice to initiate application of larvacides at the best derived times at step 544. In the alternative if the breeding level is not increased, software 136 generates a signal and a notice to initiate the spraying of chemicals at the best derived times in step 546. At step 548, these signals and notices are transmitted to the wireless WSSS units 30-a, 30-b, 30-c and field personnel devices 90, 92, and 94. Finally, WSSS units 30-a, 30-b, 30-c or other devices automatically apply chemical sprays or larvacides at step 550.

[0092] Turning now to the process as shown in Figure 5C (at point C) for displaying the mosquito population on the graphical interfaces of devices 90, 92, and 94, software 136 retrieves the Global Positioning System (GPS) coordinates for the user requested region or the Mosquito Control District at step 560. A web application can be implemented on any device 90, 92, and 94, which may display a user interface of the program running on the server. A local application may be implemented on the device that communicates with the program running on the server through an Application Programming Interface (API). It is noted that Predictive Modeling Software 136 can generate and display the graphic representation of steps 566, 570, and 574 in any order. In one embodiment, software 136 uses the predictive rule to generate concentric loops and/or curves of the mosquito population and maps these onto the corresponding region of the graphical representation; wherein, the geographical view of the mosquito population and breeding is displayed on the display screen of devices 90, 92, and 94, as shown in Figure 6. Further, the software determines at step 568 the error in the predicted mosquito population and weather forecasts, presenting these to the user in graphical form at step 570 as shown in Figure 9. At steps 572 and 574, the software generates the spraying costs for each particular identified Mosquito Control District and displays these on the geographical map as shown in Figure 11. These graphical reporting features of the wireless sensor system 100 in accordance with the present invention are explained in further detail below. Graphical Representations Generated by the Predictive Modeling Software

[0093] Figures 6-11 show some of the possible graphic representations of one of many possible outputs of the interface to the Predictive Modeling Software 136 (Software Training and Analysis Interface Module 134). Figure 6 is a graphic representation of a mosquito breeding map reporting feature of the Predictive Modeling Software interface. On the geographical map 600, a series of concentric loops 610 or other lines represent the expected level of mosquito breeding. The loops or lines have expected breeding values associated with them much like isotherms in temperature maps. The loops or lines can vary in color to better illustrate the expected level of mosquito breeding. Zones of high levels of future mosquitos can be identified on the figure and an appropriate response can be planned and executed by the Mosquito Control District. In addition, the maps can show arrows that show gradients or changes in mosquito breeding potential.

[0094] In Figure 7, a graphic representation of a weather-breeding relationship reporting feature of the Predictive Modeling Software interface is shown. Geographical map 700 of Spot or Microclimate Weather Conditions is illustrated. Points A, B and C show locations of spot or microclimate weathers stations having sensors 400; or temperature poles on a geographic map. In operation, after Predictive Modeling Software 136 has sent data to a user's computing device 90, 92, or 94, by clicking on either of the Points A, B, and C, of the map display, a user can bring up a popup menu that further details the weather conditions at the respective point on the display. The user can interact with menus in the display to focus upon the data from particular spot weather stations. In addition, the user can request Predictive Modeling Software 136 to interpolate the points for a particular weather condition between measurements of the weather stations using lines that show constant weather features. This is shown by estimated error lines 910 in Figure 9. Thus, Predictive Modeling Software 136 constructs a graph of the temperature, wind speed, rainfall by extrapolating the data values between the spot weather stations using data from associated sensors 30 (represented as sensors 400 in Figure 4). In addition, the display 700 can be changed to focus upon a specific weather feature of interest, such as ground temperature, rainfall, wind direction, wind speed, accumulated ground water, etc. Further, map 700 can show arrows that show gradients or changes in a particular weather feature of interest on the concentric wave patterns shown in Figure 7.

[0095] Given the weather conditions and trap data, Predictive Modeling Software 136 can be used to optimize the spraying area by examining the areas with the largest potential for mosquito breeding. Predictive Modeling Software 136 can also help predict the best future placement of WSSS units 30 to target and effectively spray an area. The weather station data of each WSSS unit 30 can provide real time data showing the wind pattern, including its direction along with corresponding mosquito trap surveillance data. This data is of particular interest for a mosquito spray truck with a spray nozzle system; wherein, the driver can set the appropriate spray direction and velocity, along with the appropriate vehicle velocity using software analysis and training interface 134. A calculation can be made by Predictive Modeling Software 136 to optimize the direction of spraying for a particular truck route so the spray is effectively transported to the areas of mosquito infestation, not falling by the side of the road. In addition, mosquitos are very sensitive to the temperature and come out of certain times of day determined by the near ground temperature profile, the time of day and the absence of high wind. All these conditions can be relayed in real time to the display screens of computing devices 90, 92, and 94 associated with operators of trucks and aircraft performing spraying for the Mosquito Control District.

[0096] In Figure 8, a graphic representation of a spray zone reporting feature of the Predictive Modeling Software interface is shown. Predictive Modeling Software 136 may send graphical data to a computing device for displaying geographical map 800 of Zones for spraying either larvacides D or adulticides E, where these are displayed having concentric loops of breeding population illustrated on a geographical map. These zones are determined by Predictive Modeling Software 136. In particular, zone E illustrates an area where adult mosquitos will have a large population and there is a need for spraying. Zone D is a zone where there is a large breeding population of larva in ponds, pools or marshes, where the use of larvacides is recommended. Predictive Modeling Software 136 generates these concentric circles or loops indicating the population density of expected adult mosquitos or larva. As an added feature, Predictive Modeling Software 136 can display a color representation of these lines.

[0097] In Figure 9, a graphic representation of a reporting feature of the Predictive Modeling Software interface for estimated error patterns corresponding to errors in mosquito breeding predictions, weather conditions, and zones of larvacides and adulticides is shown. Predictive Modeling Software 136 may send graphical data to a computing device for displaying geographical map 900, which displays a graphic representation of the uncertainty for these estimations and predictions. As shown in local region F, Predictive Modeling Software 136 provides error bars or standard deviations for the predictions made at region G. Predictive Modeling Software 136 determines these through statistical analysis or error analysis of the data and models, gaining scientific understanding of the sources of algorithmic error. In particular, Predictive Modeling Software 136 estimates the error in the calculations and derivations shown in maps 600, 700, and 800 to be displayed on map 900. Specifically, this display can be selected to display the error or uncertainty in a mosquito breeding prediction calculation 600, the error in the weather measurements 700, and/or the error in the anticipated zones for mosquito spraying on a geographical map 800. In general, uncertainty increases as the distance from a weather station sensor 30 is increased or as the prediction is estimated to far into the future.

[0098] In an interactive exercise, "dummy" weather stations and data can be added on a map temporarily using Predictive Modeling Software 136, such that the user can see how the error and uncertainty changes. This allows the user to look at different options in deployment of weather stations and traps and to improve the mosquito breeding predictions by reducing error and uncertainty. Increasing the certainty of predictions allows the Mosquito Control District to more economically use its resources. In addition, the tool can be used to remove weather stations data from the mapping and see how the uncertainty of the data increases. Additionally, during seasons of cold weather, Predictive Modeling Software 136 allocates fewer data collection sensors.

[0099] Accordingly, software 136 helps reduce the cost of acquiring physical field data, where the cost savings results from the reduction in the use of pesticides and the increased accuracy in mosquito population prediction. In an alternative embodiment, non-linear optimization software is included within Predictive Modeling Software 136, such that calculations showing the optimal placement of a specified number of weather stations/sensors are performed in order to get an acceptable mosquito breeding result. In addition, this tool can be used to suggest to the public the best places to add new privately owned microclimate weather stations/sensors to improve mosquito breeding predictions.

[0100] Figure 10A is a graphic representation of a community data reporting feature of the Predictive Modeling Software interface and Figure 10B is a graphic representation of a popup window having associated select community data, as an additional feature of the reporting feature of Figure 10A. Predictive Modeling Software 136 may be used to send graphical data to a computing device for displaying geographical map 1000 of Field Trapping measurements and Community reports includes points H, I, J, and K, indicative of the location of the community input at wired or wireless devices 90, 92, and 94. For example, the report H can represent a report from a hospital or medical center about mosquito caused infectious disease; while report I can represent a mosquito surveillance report describing the presence of mosquitos from a home or business. The user can click on the area of the map, such as point I, and Predictive Modeling Software 136 will generate a popup window having the data or email communication from the supplier of the data, such as a resident or business (shown in Figure 10B). Point J can represent the trap surveillance data in the field reported by technicians or by automated trap equipment. Here, the user can click on J, and the system will generate a popup window displaying the corresponding surveillance data report. The display window data can be controlled to release different amounts of data and predictions for different user groups such as mosquito control district personnel or general public health and safety organizations.

[0101] Figure 11 illustrates a graphic representation of a cost map reporting feature of the Predictive Modeling Software interface which may be displayed on a user's computing device; where the user interactively uses Predictive Modeling Software 136 to calculate the cost of spraying the larvacides or adulticides based upon the region and zone described by the user. In particular, Predictive Modeling Software 136 may be used to send graphical data to a computing device for displaying geographical map 1100 is shown which contains the mosquito control zones of interest L, M, and N.

[0102] The user can use a graphics input device to draw and size these zones of interest on the display. Specifically, using Predictive Modeling Software 136 and an associated computing device, personnel in each Mosquito Control Districts are enabled to enter into the predictive breeding models terrain information and costs of control strategies for their districts using the software analysis and training interface 134. Historical data including manpower, equipment costs, material usage, material costs and vehicle costs can be taken from day-to-day spraying operations. As the user enters areas and zones to be controlled, the software will report the estimated cost 1110 for the mosquito control zones at the bottom of the user's display screen. In particular, each mosquito control zone has a location area and a type of chemical spraying or larvaciding. In control zone L, it can be indicated that a truck will be used to spray the area with one given chemical; in control zone M, it can be indicated that a particular larvacide will be applied to a pond by a technician; or, in control zone N, it can be indicated that a plane will be used to spray a pesticide over the area.

[0103] Advantageously, the described systems and techniques can significantly reduce expense from Mosquito Control District's logistical costs and personnel costs. More particularly, it is possible to reduce the cost of trap checking by personnel because personnel can be informed when benign weather conditions exist for mosquito breeding so that traps in those areas do not need to be surveyed. In addition, a more targeted and efficient application of expensive pesticides and larvacides can be carried out for mosquito control. Further, some physically remote data locations can be monitored and their mosquito breeding occurrences anticipated.

[0104] The microclimate weather at the mosquito surveillance trap enables the Predictive Modeling Software to report when the best times are to spray at individual trap locations. The Predictive Modeling Software can report when the mosquitos are expected to be active and flying about.

[0105] All patents, patent applications, provisional applications, and publications referred to or cited herein are incorporated by reference in their entirety, including all figures and tables, to the extent they are not inconsistent with the explicit teachings of this specification.

[0106] It should be understood that the examples and embodiments described herein are for illustrative purposes only and that various modifications or changes in light thereof will be suggested to persons skilled in the art and are to be included within the spirit and purview of this application.

Claims

CLAIMS What is claimed is:

1. A mosquito control method, comprising:

collecting environmental parametric data;

receiving user input for a selected predictive breeding rule;

generating a mosquito breeding model from the user-selected predictive breeding rule; calculating a mosquito breeding population using the mosquito breeding model and collected environmental parametric data;

generating corresponding best times to spray using the mosquito breeding population and the mosquito breeding model; and

determining an optimum insecticide application, wherein chemical spraying or application of larvacides is selected based upon the mosquito breeding model and the mosquito breeding population.

2. The method of claim 1, further comprising:

generating a signal initiating the optimum insecticide application based upon the mosquito breeding model and the corresponding best times to spray.

3. The method of claim 1, wherein the user-selected predictive breeding rule includes artificial intelligence software.

4. The method of claim 1, wherein the user-selected predictive breeding rule includes statistical correlation software.

5. The method of claim 1, wherein the user-selected predictive breeding rule includes a genetic algorithm.

6. The method of claim 1, wherein the user-selected predictive breeding rule includes a non-linear regression algorithm.

7. The method of claim 1, wherein the user-selected predictive breeding rule includes a linear regression algorithm.

8. The method of claim 1, further comprising notifying pre-selected clients of corresponding to the best times to spray at a computing device of the user and displaying the best times to spray in a trap report on the computing device.

9. The method of claim 1, further comprising generating graphic data corresponding concentric loops or curves of mosquito population.

10. The method of claim 9, further comprising sending graphic data to a user's computing device and displaying the concentric loops or curves of mosquito population on the user's computing device.

11. A computer-readable storage medium, having instructions stored thereon that are executable by a computer to:

collect environmental parametric data;

receiver user selection of a predictive mosquito rule;

generate a mosquito breeding model from the user-selected predictive breeding rule; calculate a mosquito breeding population using the mosquito breeding model and collected environmental parametric data;

generate corresponding best times to spray using the mosquito breeding population and the mosquito breeding model; and

determine an optimum insecticide application, wherein chemical spraying or application of larvacides is selected based upon the mosquito breeding model and the mosquito breeding population.

12. A system, comprising:

a wireless sensor having sensing modules for measuring environmental parameters and dispensing units of a chemical insecticide;

a database utility of weather forecasting and historical mosquito population data;

a communication network coupled to the wireless sensor and the database utility; and a server, having a software application that predicts mosquito breeding population using environmental parametric data, weather forecasting data, and historical mosquito population data; wherein, the software application predicts mosquito breeding population applying the environmental parametric data, weather forecasting, and historical mosquito population data to a user-selected predictive breeding rule and generates a signal for the wireless sensor to dispense a chemical.

13. A wireless sensor for sensing environmental conditions for mosquito breeding and dispensing a chemical insecticide, comprising:

an antenna;

a transceiver coupled to receive and send signals from the antenna;

an Input/Output (I/O) interface coupled to the transceiver;

a microcontroller coupled to the I/O interface to generate an dispense signal for dispensing the insecticide based upon a signal received requesting insecticide application;

a multi-sensor board coupled to the I/O interface to sense the environmental statistics, wherein the microcontroller generates a sensing signal based upon the environmental statistics and the memory stores the environmental statistics;

a memory unit coupled to the microcontroller for storing software associated with the microcontroller for controlling the multi-sensor board and for dispensing insecticide;

a vial assembly having insecticide coupled to receive the dispense signal from the microcontroller for dispensing insecticide; and

a nozzle coupled to the vial assembly to dispense the insecticide.