Predicting West Nile Virus (WNV) occurrences in North Dakota using data mining techniques

Campion, Mitch; Bina, Calvin; Pozniak, Martin; Hanson, Todd; Vaughan, Jeff; Mehus, Joseph O.; Hanson, Scott; Cronquist, Laura; Feist, Michelle; Ranganathan, Prakash; Kaabouch, Naima; Boetel, M. A.

doi:10.1109/ftc.2016.7821628

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to identify and distinguish between these viruses for the purpose of proper therapy, the RT-PCR assay was used for testing the blood of a patient. A web interface was created by Campion et al [ 53 ] to display information regarding the frequency of the West Nile virus, the density of mosquitoes, and the weather. Google Maps was used in the proposed interface.…”

Section: Related Workmentioning

confidence: 99%

DengueFog: A Fog Computing-Enabled Weighted Random Forest-Based Smart Health Monitoring System for Automatic Dengue Prediction

Kukkar,

Kumar,

Sandhu

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Dengue is a distinctive and fatal infectious disease that spreads through female mosquitoes called Aedes aegypti. It is a notable concern for developing countries due to its low diagnosis rate. Dengue has the most astounding mortality level as compared to other diseases due to tremendous platelet depletion. Hence, it can be categorized as a life-threatening fever as compared to the same class of fevers. Additionally, it has been shown that dengue fever shares many of the same symptoms as other flu-based fevers. On the other hand, the research community is closely monitoring the popular research fields related to IoT, fog, and cloud computing for the diagnosis and prediction of diseases. IoT, fog, and cloud-based technologies are used for constructing a number of health care systems. Accordingly, in this study, a DengueFog monitoring system was created based on fog computing for prediction and detection of dengue sickness. Additionally, the proposed DengueFog system includes a weighted random forest (WRF) classifier to monitor and predict the dengue infection. The proposed system’s efficacy was evaluated using data on dengue infection. This dataset was gathered between 2016 and 2018 from several hospitals in the Delhi-NCR region. The accuracy, F-value, recall, precision, error rate, and specificity metrics were used to assess the simulation results of the suggested monitoring system. It was demonstrated that the proposed DengueFog monitoring system with WRF outperforms the traditional classifiers.

show abstract

Section: Related Workmentioning

confidence: 99%

DengueFog: A Fog Computing-Enabled Weighted Random Forest-Based Smart Health Monitoring System for Automatic Dengue Prediction

Kukkar,

Kumar,

Sandhu

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Biosensors that are simple, accessible, and economically applicable outside the laboratory by inexperienced people have been developed to detect early malaria status [19]. In the study of M. Campion et al [20], an example predicts the number of traps and the evolution of a convenient netcommunication holding collaborative internet pages that permit operators to see North Dakota mosquitoes and climate plans WNV rate records are shown.…”

Section: Related Workmentioning

confidence: 99%

Designing A Smart Monitoring and Alert System for Malaria Patients Based on IoT in Burundi

Sabukunze

Suyoto

2021

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Malaria is an infectious disease that has a devastating effect on humans but is contagious and preventable. There were 228 million malaria cases globally in 2018, with 93% of patients and 94% dying showing up in Africa within Burundi, possessing a massive growth (51%). This study proposes an IoT design for smart monitoring and alert systems for malaria patients in Burundi. After being tested positive while they are home drinking tablets prescribed by the doctor, the patients will use a body temperature sensor. When the situation worsens, the patient shall be hospitalized and use the water level sensor to monitor the serum level, which contains quinine. Body temperature and water level sensor will be connected to Arduino Microcontroller, and all information will be gathered and sent to the IoT server through the internet. The system design is authentic and adequate in reducing mortality in Burundi. Besides, the system is equipped to set up a caution message to the medical staff in case of the patient's extreme conditions. It can be concluded that a Smart monitoring and alert system is essential for monitoring malaria patients and can alert in case of a severe condition.

show abstract

“…Poh et al identified that temperature and rainfall increase mosquito abundance [15]. In addition to temperature and precipitation, other factors such as humidity and wind velocity affect mosquito abundance [16]. Peper et al have studied WNV and mosquito surveillance records from Lubbock, TX, and have found that the probability of mosquito infection depends on the weather variables including the time in the year, wind, visibility, humidity, dew point, and the time lag of these variables [17].…”

Section: Introductionmentioning

confidence: 99%

Two-Step Light Gradient Boosted Model to identify human West Nile Virus infection risk factor in Chicago

Wan,

Allen,

et al. 2023

Preprint

View full text Add to dashboard Cite

West Nile virus (WNV), a flavivirus transmitted by mosquito bites, causes primarily mild symptoms but can also be fatal. Therefore, predicting and controlling the spread of West Nile virus is essential for public health in endemic areas. We hypothesized that socioeconomic factors may influence human risk from WNV. We analyzed a list of weather, land use, mosquito surveillance, and socioeconomic variables for predicting WNV cases in 1-km hexagonal grids across the Chicago metropolitan area. We used a two-stage lightGBM approach to perform the analysis and found that hexagons with incomes above and below the median are influenced by the same top characteristics. We found that weather factors and mosquito infection rates were the strongest common factors. Land use and socioeconomic variables had relatively small contributions in predicting WNV cases. The Light GBM handles unbalanced data sets well and provides meaningful predictions of the risk of epidemic disease outbreaks.

show abstract

Predicting West Nile Virus (WNV) occurrences in North Dakota using data mining techniques

Cited by 9 publications

References 9 publications

DengueFog: A Fog Computing-Enabled Weighted Random Forest-Based Smart Health Monitoring System for Automatic Dengue Prediction

DengueFog: A Fog Computing-Enabled Weighted Random Forest-Based Smart Health Monitoring System for Automatic Dengue Prediction

Designing A Smart Monitoring and Alert System for Malaria Patients Based on IoT in Burundi

Two-Step Light Gradient Boosted Model to identify human West Nile Virus infection risk factor in Chicago

Contact Info

Product

Resources

About