scholarly journals Predicting dengue in the Philippines using artificial neural network

2020 ◽  
Author(s):  
Bryan Zafra
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Predictive Models ◽  
Dengue Infection ◽  
Specific Treatment ◽  
The Philippines ◽  
Aedes Mosquito ◽  
Independent Variables ◽  
Average Global Temperature ◽  
Artificial Neural

AbstractDengue fever is an infectious disease caused by Flavivirus transmitted by Aedes mosquito. This disease predominantly occurs in the tropical and subtropical regions. With no specific treatment, the most effective way to prevent dengue is vector control. The dependence of Aedes mosquito population on meteorological variables make prediction of dengue infection possible using conventional statistical and epidemiologic models. However, with increasing average global temperature, the predictability of these models may be lessened employing the need for artificial neural network. This study uses artificial neural network to predict dengue incidence in the entire Philippines with humidity, rainfall, and temperature as independent variables. All generated predictive models have mean squared logarithmic error of less than 0.04.

scholarly journals The effect of Kurtosis on the accuracy of artificial neural network predictive model

2018 ◽  
Vol 204 ◽  
pp. 02018
Author(s):  
Aisyah Larasati ◽  
Anik Dwiastutik ◽  
Darin Ramadhanti ◽  
Aal Mahardika
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Predictive Model ◽  
Predictive Models ◽  
Output Layer ◽  
Input Layer ◽  
Artificial Neural ◽  
Misclassification Rates ◽  
Hidden Layer ◽  
Program Data

This study aims to explore the effect of kurtosis level of the data in the output layer on the accuracy of artificial neural network predictive models. The artificial neural network predictive models are comprised of one node in the output layer and six nodes in the input layer. The number of hidden layer is automatically built by the program. Data are generated using simulation approach. The results show that the kurtosis level of the node in the output layer is significantly affect the accuracy of the artificial neural network predictive model. Platycurtic and leptocurtic data has significantly higher misclassification rates than mesocurtic data. However, the misclassification rates between platycurtic and leptocurtic is not significantly different. Thus, data distribution with kurtosis nearly to zero results in a better ANN predictive model.

scholarly journals Artificial neural network based antenna sensitivity assignments for chaotic internet service provider network architecture

2018 ◽  
Vol 7 (2.3) ◽  
pp. 14 ◽  
Author(s):  
Lolit Villanueva ◽  
Reggie C. Gustilo
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Service Provider ◽  
Network Architecture ◽  
The Philippines ◽  
Internet Service Provider ◽  
The Internet ◽  
Internet Service ◽  
Access Points ◽  
Artificial Neural

The connectivity and grade of service of an Internet Service Provider (ISP) in the Philippines is observed and analysed in this research. Traditionally, the sensitivity of the antennas for wireless access points are done manually by monitoring the signal levels onsite during the installation process. Ten subscriber locations are randomly selected as test points. The connectivity of these subscribers is observed given that their sensitivities are set manually. Finally, a proposed artificial neural network algorithm is presented to improve the availability of the internet link. The proposed algorithm incorporates the random variations of the received signal levels of the internet access points and possible degradation of signals from attenuation due to rain. Experiment results show that at least 75% increase in availability is observed using the proposed algorithm during rainy events. 

scholarly journals Comparison of Predictive Models in Classification of Nutritional Status among Arsenic Affected People in Rural Areas in Bangladesh: An Artificial Neural Network (ANN) and Logistic Regression Approach

2017 ◽  
Vol 6 (2) ◽  
pp. 71-75
Author(s):  
Azizur Rahman ◽  
Mariam Akter ◽  
Ajit Kumar Majumder ◽  
Md Atiqul Islam ◽  
AFM Arshedi Sattar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Logistic Regression ◽  
Clinical Data ◽  
Predictive Models ◽  
Rural Areas ◽  
Binary Logistic Regression ◽  
Binary Outcome ◽  
Artificial Neural

Background: Clinical data play an important role in medical sector for binary outcome variables. Various methods can be applied to build predictive models for the clinical data with binary outcome variables.Objective: This research was aimed to explore and compare the process of constructing common predictive models.Methodology: Models based on an artificial neural network (the connectionist approach) and binary logistic regressions were compared in their ability to classifying malnourished subjects and those with over-weighted participants in rural areas of Bangladesh. Subjects were classified according to the indicator of nutritional status measured by body mass index (BMI). This study also investigated the effects of different factors on the BMI level of adults of six Villages in Bangladesh. Demographic, anthropometric and clinical data were collected based on aged over 30 years from six Villages in Bangladesh that were identified as mainly dependent on wells contaminated with arsenic.Result: A total of 460 participants were recruited for this study. Out of 460(140 male and 320 females) participants 186(40.44%) were identified as malnourished (BMK18.5 gm), and the remainder 274(59.56%) were found as over-weighted (BMI>18.5 gm). Among other factors, arsenic exposures were found as significant risk factors for low body mass index (BMI) with a higher value of odds ratio. This study shows that, binary logistic regression correctly classified 72.85% of cases with malnourished in the training datasets, 76.08% in the testing datasets and 75.26% of all subjects. The sensitivities of the neural network architecture for the training and testing datasets and for all subjects were 84.28%, 84.78% and 81 .72% respectively, indicate better performance than binary logistic regression model.Conclusion: This study demonstrates a significant performance of artificial neural network than the binary logistic regression models in classification of malnourished participants from over-weighted ones.J Shaheed Suhrawardy Med Coll, 2014; 6(2):71-75

By Using Logarithmic Regression and Artificial Neural Network to Improve Prediction Model of Dead Number Resulted from Road Traffic Accidents in Turkey

2018 ◽  
pp. 446-453
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Traffic Accidents ◽  
Road Traffic ◽  
Data Sets ◽  
Damage Prediction ◽  
Independent Variables ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Traffic accidents occurred on highway in Turkey cause materially and morally damage. To decrease the damage, prediction model developed. In this study, demographic and traffic data which from 1970 to 2007 are used. These data are consist of dependent and independent variables. Dependent variable is formed Number of Dead (ND). As for independent variables are comprised Population (P), Registered Number of Vehicle (VN), Vehicle-km (VK), Number of Drivers (DN). Models are developed using Artificial Neural Network (ANN) and Logarithmic Regression (LR) enhanced by Smeed. PVNVKDN model developed taking real values logarithm is the best performance of models in LR technique. VKDN created by using historical data sets is the best model in ANN technique. As for models created by randomly selected data, the best model is VKDN. When performances of best models are compared, VKDN is the best model because of lowest error rate.

Sign in / Sign up

Export Citation Format

Share Document