The COVID-19 case that infected humans was first discovered in China at the end of 2019. Since then, COVID-19 has spread to almost all countries in the world. To overcome this problem, it takes a quick effort to identify humans infected with COVID-19 more quickly. One of the alternative diagnoses for potential COVID-19 disease is Recurrent Neural Network (RNN). In this paper, RNN is implemented using the Elman network and applied to the COVID-19 dataset from Kaggle. The dataset consists of 70% training data and 30% test data. The learning parameters used were the maximum epoch, learning late, and hidden nodes. The research results show the percentage of accuracy is 88.

Purpose: Halal tourism or muslim friendly tourism has big potential for the tourism industry in Indonesia. According to Cresent Rating, the world’s leading authority on halal-friendly travel, one of the indicators for halal tourism is the availability of choices for halal foods. To support halal tourism, unfortunately, not all restaurants around the tourism object or in the city where the tourism object is located have labels or information that makes people know about halal food in the restaurant easily.Methods/Study design/approach: The data in this research was obtained from online media such as Google Maps, TripAdvisor, and Zoomato. The data consists of 870 data with the classification of halal food restaurants and 590 data with the reverse classification. Machine learning methods were chosen as classifiers. Some of them were Naive Bayes, Support Vector Machine, and K-Nearest Neighbor. Result/Findings: The result from this research shows that the proposed method achieved an accuracy of 95,9% for Support Vector Machine, 93,8% for Multinomial Naive Bayes, and 91% for K-Nearest Neighbor. In the future, our result will be to support the halal tourism environment in terms of technology. Novelty/Originality/Value: In this study, we utilize restaurant reviews done by visitors to get information about the classification of halal food restaurants.

No abstract

In the case study of weather prediction, there are several tests that have been carried out by several figures using the fuzzy method, such as the Tsukamoto fuzzy, Adaptive Neuro Fuzzy Inference System (ANFIS), Time Series, and Sugeno. And each method has its own advantages and disadvantages. For example, the Tsukamoto fuzzy has a weakness, this method does not follow the rules strictly, the composition of the rules where the output is always crisp even though the input is fuzzy, ANFIS has the disadvantage of requiring a large amount of data. which is used as a reference for calculating data patterns and the number of intervals when calculating data patterns and Sugeno has the disadvantage of having less stable accuracy results even though some tests have been able to get fairly accurate results. In research on the implementation of the Mamdani fuzzy inference system method using the climatological dataset of Blora Regency to predict rainfall, it can be concluded as follows: (1) The fuzzy logic of the Mamdani method can be used to predict the level of rainfall in the city of Blora by taking into account the factors that affect the weather, including temperature, wind speed, humidity, duration of irradiation and rainfall. (2) Fuzzy logic for prediction with uncertain input values is able to produce crisp output because fuzzy logic has tolerance for inaccurate data. (3) The results of the accuracy of calculations using the Mamdani fuzzy inference system method to predict rainfall in Blora Regency are 66%.