To fund the ongoing development at this time the State requires income from various sources such as income from exports. Export is an activity of sending goods abroad where the activity will produce value. And Indonesia's export value which is quite high comes from non-oil and gas exports, one of which is the export of processed tuna 160414. One of the destination countries for the export of processed tuna which is quite high is Italy. The purpose of this study is to find out the best method for predicting the value of processed tuna exports to Italy in the application of fuzzy logic in order to optimize the value of exports. The results showed that the Sugeno method is a good method. The Sugeno method has results that are quite close to the actual results with an error rate of 41%, so the Sugeno method can be used as a recommended method in predicting the optimal amount of Indonesia's 160414 HS exports to Italy.

The decline in oil and gas exports since 1990 requires the government to take policy steps to increase non-oil exports so that state revenues continue to grow. One of the non-oil and gas exports that is a mainstay of Indonesia is tunat fish which has the HS code 160414. Italy is a country where the demand for tuna is quite high. In order to maximize the value of Indonesian tuna exports to Italy, a method is needed to optimize the value of Indonesian tuna exports to Italy. The purpose of this study was to find out the best method to predict the value of tuna exports to Italy in the application of fuzzy logic in order to optimize the value of exports. The results showed that the Mamdani method was a good method. The Mamdani method has results that are close to the actual results with an error rate of 1.1%, so the Mamdani method can be used as the recommended method in optimizing the optimal amount of export HS 160414 Indonesia to Italy.

In a daily life human cannot be separated from electronic interactions, one of the example is handphone / smartphone. On a smartphone there are so many types of applications and chatting application is the most used application by smartphone users. Now using picture media is more desirable compared to other media for used in a chatting. Because of that chatting application that have a theme and sticker feature usually more desirable. line application is one of them. There are several line users that can create his own theme (creator) and then they spread the theme (unofficial theme) by timeline or official account from line@ application. But there are some problems experienced by theme users or creator, like banned account caused by line@ without obvios cause, hard for searching official account or theme that desired. Because of that writer made a system or place that can solve the problems.

Abstract   Saving electrical energy consumption in industries is crucial; hence, the prediction of industrial energy consumption needs to be performed. The random forest method can be applied to steel industry data to predict energy consumption. The purpose of this prediction is to increase energy savings in industries and optimize the performance of the random forest method. The results of the random forest show that the algorithm can predict energy consumption in industries effectively; however, it needs further optimization to achieve better predictions. Therefore, the genetic algorithm method will be used to optimize the previous method. The optimization results indicate that it is successfully conducted in terms of accuracy and kappa level. This optimization is beneficial to society, especially industrial companies.