Dengue Outbreak Prediction: A Least Squares Support Vector Machines Approach

Yusof, Yuhanis; Mustaffa, Zuriani

doi:10.7763/ijcte.2011.v3.355

Cited by 46 publications

(13 citation statements)

References 12 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data scaling refers to the method used to normalize the range of features or independent variables of a data mining model. This approach can ensure that data are not overwhelmed by each other in terms of distance measures [ 33 ]. We used a standardization technique ( Eq 8 ) to rescale both the training and testing data: where x ′ is a standardized value, x is an original value, and mean and stddev are a median and a standard deviation value of each feature ( f ), respectively.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Morbidity Rate Prediction of Dengue Hemorrhagic Fever (DHF) Using the Support Vector Machine and the Aedes aegypti Infection Rate in Similar Climates and Geographical Areas

et al. 2015

View full text Add to dashboard Cite

BackgroundIn the past few decades, several researchers have proposed highly accurate prediction models that have typically relied on climate parameters. However, climate factors can be unreliable and can lower the effectiveness of prediction when they are applied in locations where climate factors do not differ significantly. The purpose of this study was to improve a dengue surveillance system in areas with similar climate by exploiting the infection rate in the Aedes aegypti mosquito and using the support vector machine (SVM) technique for forecasting the dengue morbidity rate.Methods and FindingsAreas with high incidence of dengue outbreaks in central Thailand were studied. The proposed framework consisted of the following three major parts: 1) data integration, 2) model construction, and 3) model evaluation. We discovered that the Ae. aegypti female and larvae mosquito infection rates were significantly positively associated with the morbidity rate. Thus, the increasing infection rate of female mosquitoes and larvae led to a higher number of dengue cases, and the prediction performance increased when those predictors were integrated into a predictive model. In this research, we applied the SVM with the radial basis function (RBF) kernel to forecast the high morbidity rate and take precautions to prevent the development of pervasive dengue epidemics. The experimental results showed that the introduced parameters significantly increased the prediction accuracy to 88.37% when used on the test set data, and these parameters led to the highest performance compared to state-of-the-art forecasting models.ConclusionsThe infection rates of the Ae. aegypti female mosquitoes and larvae improved the morbidity rate forecasting efficiency better than the climate parameters used in classical frameworks. We demonstrated that the SVM-R-based model has high generalization performance and obtained the highest prediction performance compared to classical models as measured by the accuracy, sensitivity, specificity, and mean absolute error (MAE).

show abstract

Section: Methodsmentioning

confidence: 99%

“…The SVM can solve several problems of classification techniques such as the overfitting problem and the curse of dimensionality. The SVM has been proven to provide more solutions to boundaries compared to the neural network (NN) and can solve local minimum problems found in the NN [ 33 ].…”

Section: Introductionmentioning

confidence: 99%

Morbidity Rate Prediction of Dengue Hemorrhagic Fever (DHF) Using the Support Vector Machine and the Aedes aegypti Infection Rate in Similar Climates and Geographical Areas

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Yusof and Mustaffa [21] observed that neural network (NN) and least square SVM (LS-SVM) require simpler calculations and less complexity in training than the regular SVM. Their comparison on applying the NN and LS-SVM to data collected from five Malaysian cities showed that the LS-SVM outperformed the NN in accuracy and runtime.…”

Section: Related Workmentioning

confidence: 99%

“…Due to the relation between weather conditions and the proliferation of the dengue vector mosquito, statistical and machine-learning models can be used for forecasting the number of dengue cases based on weather conditions [11,12,21]. The detection of such outbreaks in advance would give to public health agencies time for dealing with the high number of cases and even decrease them.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics

Souza

Leung

Cuzzocrea

2020

Advanced Information Networking and Applications

View full text Add to dashboard Cite

Nowadays, big data are everywhere. Examples of big data include weather data, web-search data, disease reports, as well as epidemic data and statistics. These big data can be easily generated and collected from a wide variety of data sources. A data science frameworksuch as predictive analytics framework-helps mining data from various big data sources to find useful information and discover knowledge, which can then be transformed into wisdom for appropriate actions. In this paper, we present an innovative big data predictive analytics framework over hybrid big data sources. To demonstrate the effectiveness and practicality of our framework, we conduct several case studies, including one on applying the framework to disease analytics. More specifically, we integrate, incorporate and analyze weather data and web-search data to predict and forecast dengue cases based on a hybrid of three kernels in support vector machine (SVM) ensemble. Results show how our predictive analytics framework benefits health agencies in disease control and prevention.

show abstract

“…model [27,28] which only has the objective of shortterm forecasting of the ongoing outbreak or model early warning system [16,29,30] which aims to be a descriptive analysis of the region that has the potential to endemic but no regional cluster patterns in each area are predicted. The research that has been carried out is still limited to descriptive analysis in the form of a numerical table of each variable characteristic.…”

Section: Related Workmentioning

confidence: 99%

Early Identification Model for Dengue Haemorrhagic Fever (DHF) Outbreak Areas Using Rule-Based Stratification Approach

Munir¹,

Hartati²,

Musdholifah³

2019

IJIES

View full text Add to dashboard Cite

The spread of dengue hemorrhagic fever (DHF) globally with a frequency level that tends to be high in the past 50 years raises a systematic idea of prevention. One of the efforts to prevent DHF is the need for early identification of areas that are potentially epidemic. Early identification is carried out by getting an overview of the incident one step ahead by data forecasting. The focus of the study was the development of area stratification algorithms as an early identification of DHF outbreak areas by using data forecasting methods with surveillance data variables. Surveillance data which became the references for system modeling were DHF case data, rainfall, humidity, air temperature, wind speed and Larva-free Number (ABJ) for the span of 2010-2016 in 17 districts in Sleman Regency, Special Region of Yogyakarta. There were four steps during the study, i.e., 1) Forecasting of DHF case for the period of 12 months, 2) Forecasting of Larva-free Number (ABJ), 3) Determination of DHF case pattern for the last three years and the average of ABJ in the third year and 4) Area classification into stratification class. A method used for data forecasting of DHF case was seasonal autoregressive moving average (SARIMA), and the determination of area class pattern was conducted by using a neural network, meanwhile to obtain area stratification class used rule-based approach referring to guidelines controlling DHF outbreaks of the Ministry of Health of the Republic of Indonesia. Early identification was carried out by dividing into 4 area classes. Area class target included endemic (K1), sporadic (K2), a potential (K3) and free (K4). The testing of accuracy forecasting used relative mean absolute error (RMAE) for 12 months period. The results of the forecasting accuracy test on 17 districts in Sleman Regency showed RMAE average of 1.46 was considered low for it was still below 10%. Furthermore, the results of the early identification of area stratification classes in 2014 and 2015 from 17 districts showed that 3 of the four regions were endemic areas while in 2016 almost all districts were endemic areas and only one area was classified as sporadic.

show abstract

Dengue Outbreak Prediction: A Least Squares Support Vector Machines Approach

Cited by 46 publications

References 12 publications

Morbidity Rate Prediction of Dengue Hemorrhagic Fever (DHF) Using the Support Vector Machine and the Aedes aegypti Infection Rate in Similar Climates and Geographical Areas

Morbidity Rate Prediction of Dengue Hemorrhagic Fever (DHF) Using the Support Vector Machine and the Aedes aegypti Infection Rate in Similar Climates and Geographical Areas

An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics

Early Identification Model for Dengue Haemorrhagic Fever (DHF) Outbreak Areas Using Rule-Based Stratification Approach

Contact Info

Product

Resources

About