Dengue fever is a disease that must be watched out and early preventive measures are taken so the spread of this disease can be reduced. An early preventive dengue fever can be controlled by a mathematical model. The article proposes a model of fuzzy inference system with optimal fuzzy rule bases generated by fuzzy c-means and optimized by ordinary least square (OLS). The developing system is done by forming a data structure in the form of input-output pairs. Factors that influence the number of dengue fever cases are used as the system input and the number of dengue fever cases as the system output. Based on the input-output pairs, the fuzzy rule bases is generated by using the fuzzy c-means method. The consequent part of the rule bases is optimized by the OLS method to produce the optimal rule bases. The resulted system is able to predict the level of dengue fever in the villages with an accuracy of 90% and can be used to predict the level of dengue fever in a village by inputting factors that influence the level of dengue fever.
2 January 2024 in Journal of Advances in Information Technology
JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.
Imbalanced classes can cause machine learning models to classify positive class instances poorly, and the models require hyperparameter sets to optimal values. This study aims to develop random forest (RF) and support vector machine (SVM) models that use the optimal hyperparameters obtained through 5-fold cross-validation data. Both models were trained using optimal hyperparameter pairs that fit two data scenarios, the original and oversampling training sets, to produce the benchmark and best models. The model's performance was evaluated using six metrics, including training and testing data. The acquired optimal RF hyperparameter pair was (500, 10) for the minimum number of instances and tree depth level. In contrast, the acquired optimal SVM hyperparameter pair was (0.001, 500) for the gamma and constant values. The benchmark model performed approximately 98% on Accuracy, Precision, Recall, and F1 score metrics but failed to deliver any performance on Mathew's Correlation Coefficient (MC) and Area under Curve (AUC) metrics. The best RF and SVM perform less than both benchmark models in four famous metrics. Both best models have performance improvements of approximately 6% and 11% for the MCC and AUC metrics, respectively. The best RF performance was slightly better than the best SVM performance.