Minicomputer raspberry pi merupakan sebuah alat yang praktis dalam segi dimensi dan memiliki fungsi yang kompleks untuk berbagai kebutuhan fungsi yang akan digunakan oleh manusia sebagai microcontroller, server sampai dengan pengolahan citra digital. Penelitian dilakukan bertujuan untuk membantu memenuhi kebutuhan sistem keamanan ruang server yang mudah untuk diaplikasikan dan murah dalam segi biaya pembuatan dan perawatan serta berteknologi, mengingat pentingnya keamanan data dan informasi yang tersimpan dalam server sehingga perlu pengamanan dalam mengakses ruang server pada suatu perusahaan. Dengan memanfaatkan minicomputer raspberry pi sebagai pemroses dan usb webcam sebagai alat pendeteksi wajah yang kemudian akan diproses oleh raspberry pi dengan menggunakan OpenCV untuk menentukan wajah manusia atau bukan, lalu wajah tersebut akan masuk pada proses pengenalan wajah dengan metode triangle face yang memanfaatkan perhitungan jarak antar fitur wajah seperti mata, hidung dan mulut. Setelah wajah dikenali maka raspberry pi akan melakukan perintah pada servo untuk membuka pintu ruang agar dapat diakses oleh admin server pada suatu perusahaan. Berdasarkan pengujian sistem yang telah dilakukan, ternyata sistem pengenalan wajah menggunakan metode Triangle Face ini memiliki tingkat keakuratan 75%, kesalahan posistif 25% dan kesalahan negatif 0% sehingga dapat disimpulkan bahwa sistem ini cukup aman untuk diaplikasikan dalam sistem keamanan pintu ruang server.
Feature selection in the classification model has a role to choose relevant and interconnected features in the data mining task. in the medical world, feature selection can help the classification model in predicting heart attack. Naive Bayes is one of the most popular classification learning methods that can help to predict patients in helping paramedics to make decisions. The addition of feature selection in the form of backward elimination can increase the accuracy of Naïve Bayes by 89.45% from 84.29% previously. The results of this study indicate the accuracy of a backward selection method in predicting heart attack is quite high in adding accuracy.
Space Weather (SW) is a field of Space Sciences which deals with the variable conditions in the Sun, the interplanetary medium and our planet's vicinity, which have an impact on human safety and technological systems. In this work we compare the information provided by several SW Information Systems, with a particular emphasis on the activity indices used to describe the SW conditions. For that purpose we analyse the daily SW conditions and forecasts for the year 2015. From this study we conclude that the SW services evaluated here present similar levels of forecast accuracy, predicting the correct SW conditions in 70 to 90% of the cases. Despite that, even when the forecasts of two warning centers are correct, differences in the activity scales used by each institution can result in divergent reports.
Tea is one of the plantation products within the Ministry of Agriculture of the Republic of Indonesia, which plays an essential role as a mainstay commodity that boosts the Indonesian economy. Each type of tea has different properties, and the aroma of each type of tea can measure the quality of the tea. The human sense of smell is still very limited in classifying pure types of tea. Therefore, a device is needed to help measure the aroma of tea from an electronic nose. The devices attached to several gas sensors help humans take data from the smell of pure tea and calculate the value of each type of tea to test datasets with data mining algorithms. This study uses the C4.5 algorithm as a classification method with advantages over noise data, missing values, and handling variables with discrete and continuous types. Meanwhile, Chi-square is used to perform attribute severing in the data preprocessing process to increase the accuracy of dataset testing. Testing a pure tea dataset with four whole attributes, namely CO2, CO, H2, and CH4, using the C4.5 algorithm resulted in an accuracy of 93.65% and an increase in the accuracy performance of the C4.5 algorithm by 94.27% with dataset testing using Chi-Square feature selection with the two highest value attributes.
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.