Until now, cancer is one that suffered by the people of Indonesia, especially in cervical cancer (cervix) suffered by Indonesian women. Not only cervical cancer suffered by Indonesian women, but also other diseases that attack the female reproductive organs. Such diseases, cervical cancer, ovarian cancer, endometrial cancer, vaginal cancer, ovarian cysts and myomas. To prevent the number of deaths of patients, of course the initial diagnosis as one of the solutions. As used in this study in development an early diagnosis system of female reproductive cancer. This expert system adds value to the technology to assist in the handling of an increasingly sophisticated information age. This Expert System Application generates an Update that enables patients who suffer from symptoms that are felt by the patient. This system is also a result of the necessity of women suffering from cancer experienced by patients. The amount of trust value is the result of calculation using Certainty Factor method.
Evaluation of learning systems based on e-learning is very important to determine learning success. The purpose of this study is to obtain predictive results from evaluating students who follow e-learning based learning systems. The data used is the result of logs of student learning activities taken from the LMS. The data used in this study were 641 user logs of student activity. In predicting the evaluation results based on the learning system on e-learning we use a neural network method based on swarm particle optimization. Neural Network has a problem in optimizing very large data so using swarm particle optimization can solve this problem. From the data testing we have done, the results obtained by the Neural Network method get an accuracy value of 95.47%, and the results of the AUC value of 97.90%. The observation of variables C, ∊ and population of Neural Network and particle swarm optimization use the K-Fold Cross Validation method. Then the researchers tested several choices on the attributes used. By using the Neural Network method based on the swarm particle optimization attribute, there are 9 predictor variables so that as many as 6 attributes are used, namely sports, chat, discussion, messages, Quiz exercises and total logs. The results show an accuracy rate higher than 97.50%, and an AUC value of 98.20%. So the accuracy value increased by 2.03% and the AUC increased by 0.3%. With accuracy and AUC values, the Artificial Neural Network algorithm based on particle optimization is very well categorized.
Prediction is a systematic estimate that identifies past and future information, we predict student learning success with e-learning based on a log of student activities. In this study, we use the Support vector Machine (SVM) method, which is compared with Particle Swarm Optimization. The problem with this algorithm is that the SVM has a very good generalization that can solve a problem. However, some of the attributes in the data can reduce accuracy and add complexity to the SVM algorithm. For this reason, attribute selection for existing data is needed, therefore Particle Swarm Optimization (PSO) method is applied for the right attribute selection in determining the success of elearning learning based on student activity logs, because the PSO method can improve accuracy in determining selection of attributes. The SVM algorithm produces an accuracy value of 88.00% and AUC with a value of 0.8120, while with SVM Based on PSO the accuracy value is 88.50% and the AUC value is 0.8460. Therefore, there is an increase from the result of an accuracy value of 0.50% and an AUC value of 3.40%, and then the result is in good classification.
Dental and oral disease is one of the diseases that has been felt by most of the people. Insufficient information and the limited level of public awareness of the prevention of dental and oral diseases make the impact quite dangerous if not handled properly. An appropriate information system is needed in overcoming and providing solutions for handling a disease as early as possible. Expert systems can be used as a means of information on the treatment of dental and oral diseases. The manufacture of the expert system in this study initially used the forward chaining method, which is a method that searches based on information that is made into a set of rules so as to get a conclusion. However, after re-analysis, two other methods, namely certainty factor and dempster shafer, were also applied in this study with the aim of overcoming the shortcomings of the forward chaining method, one of which is uncertainty in producing a conclusion or diagnosis of disease. Determining the type of dental and oral disease can be known by looking at the symptoms experienced by the patient. The use of an expert system for diagnosing dental and oral diseases can be used as an initial solution in helping someone to treat the disease. The existence of this expert system can be used as consideration in making decisions to determine the type of dental and oral disease quickly, precisely and accurately.
In our current study, we are doing a comparison of several algorithms that we have tested, namely in searching for the accuracy level of learning performance in students, the problem of this research is how to get the results of excellent generalization abilities so that a higher accuracy value is obtained. Our goal is to get the best-performing accuracy level results and then to identify features that can affect student learning performance. From the results of the algorithm that we have tested, four of them are Naïve Bayes, Support Vectore Machine, Neural Network and KNN contained in machine learning. The results of the four algorithms for the Naïve Bayes algorithm have an accuracy value of 96.30%, the Support Vectore Machine algorithm has an accuracy of 98.70%, and the Naural Network algorithm has an accuracy of 99.50% and the last one with the KNN algorithm produces an accuracy of 94.80%. it can be concluded that using the Neural Network algorithm is an algorithm with the best performance than using other algorithms in evaluating student learning performance, besides that the Neural Network can be used as an excellent alternative to be used as predictions, especially in the field of education.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.