Search

Facial treatment is an important need for everyone because the first sight of meeting someone is to see their face. Generally, facial skin type is just normal skin. However, several factors such as the environment, air, food, facial hygiene, and so on can affect the type of human facial skin. In this experiment, there were 5 types of facial skin, namely normal skin, dry skin, oily skin, combination skin, and sensitive skin. With the existence of various skin types, it makes some people confused in determining the type of facial skin. This also affects the selection of skincare or facial care according to the indications of each facial skin. Therefore an expert system was created to diagnose facial skin types. An expert system is a man-made system that is used to solve problems like an expert with knowledge from human to computer, although it does not give 100% absolute results, but expert systems are still helpful.

In December 2019, an outbreak named Corona Virus (SARS-CoV-2) occurred in the city of Wuhan, China which was later known as COVID-19. News of the development of the virus spread through various media, one of which was through the well-known platform Twitter. Twitter is one of the widely used media platforms to communicate about Covid-19. Information related to Covid-19 circulating in the community can be in the form of news or opinions or opinions. Then, the circulating information will be classified into three classes, namely positive, negative or neutral. The method used to calculate the prediction of text classification on Twitter is K-nearest neighbors (KNN). The dataset used in grouping on twitter by using the account name Covid19. Firstly, the dataset by crawling data or information on twitter. Secondly, the text mining stage to determine the class distance value and calculate the Euclidean distance formula based on all the training data to be tested. After the training process is complete, the evaluation model used will be used, the Euclidean results are taken based on the value of the closest distance. The accuracy of the model will be calculated using the previous Euclidean method. The results of this study he obtained with the highest value, one of which was 78% using a 50:50 sample comparison with k-5 and k-9 values.

The Central Bureau of Statistics is a non-ministerial government institution that reports directly to the President. Based on data from The Central Bureau of Statistics in September 2019, the wealth rate in Indonesia was 9.22% and the number of indigent people in Indonesia reached 24.79 million. The poverty rate in the Bangka Belitung Islands Province was low compared to the national level. This is evidenced by 4.62% of people in Bangka Belitung Island Province were indigent people, which is lower than the national average of 9.22%. The data mining techniques using the K-Means Clustering method are used for this study. The research data was taken from the website of the BPS from 2014-2019 which consisted of 7 districts and/or cities with 3 variables. The variables used are the number of indigent people (in thousands), the average length of school education (years), and adjusted per capita expenditure (thousand rupiahs/year). All data is processed by Rapidminer and 3 clusters are carried out, namely: medium cluster level 0, high cluster level 1, and low cluster level 2. Cluster 0 contains districts/cities whose people have the longest average school time, high per capita expenditure, and a large number of indigent people. Cluster 1 contains districts/cities whose people have a short average school time, low per capita expenditure, a moderate number of indigent people. Cluster 2 contains districts/cities whose people have an average school time, moderate per capita expenditure, a small number of indigent people. Based on the result, the government can prioritize Kabupaten Bangka, Kabupaten Bangka Barat, Kabupaten Bangka Selatan in assisting, especially in the cost of education scholarships and social funds as well as other infrastructure improvements for the welfare of the inhabitants of Bangka Belitung Islands Province.

Kelurahan Utama merupakan instansi pemerintahan di cimahi selatan. Kelurahan utama menjalankan program pemerintah yaitu program Bantuan Pangan Non Tunai, dalam menjalankan program Bantuan Pangan Non Tunai sebagian warga banyak yang mengeluh karena tidak mendapat bantuan, sedangkan ada beberapa warga yang dianggap mampu justru mendapatkan bantuan. Berdasarkan latar belakang tersebut maka penulis melakukan proses pengolahan data menggunakan data mining untuk mengklasifikasi penerima dan bukan penerima bantuan pangan non tunai dengan metode klasifikasi menggunakan Algoritma NaA¯ve Bayes dan Algoritma Decision Tree sebagai pembanding. Diharapkan data yang dihasilkan dari proses data mining bisa menjadi bahan evaluasi untuk pemerintah. Dalam penelitian ini penulis mengklasifikasi data penerima dan bukan penerima bantuan pangan non tunai menggunakan teknik klasifikasi pada data mining menggunakan Algoritma NaA¯ve Bayes dan Algoritma Decision Tree sebagai pembanding. Model data mining di buat menggunakan RapidMiner, dengan hasil nilai Probabilitas untuk class ‘’PENERIMA’’ yaitu 0,481 dengan pembulatan nilai menjadi 0,48 dan nilai Probabilitas untuk class ‘’ Bukan Penerima ’’ yaitu 0,519 dengan pembulatan nilai menjadi 0,52. Algoritma NaA¯ve Bayes mempunyai tingkat Accuracy sebesar 58,29%, Precision 92,90%, Recall 21,84%, AUC 0,765, F-Measure 34.42%. Sedangkan algoritma Decision Tree mempunyai tingkat Accuracy sebesar 73,97%, Precision 85,04%, Recall 61,92%, AUC 0,746, F-Measure 71,17%. Dalam hasil pengujian T-Test antara Algoritma Naive Bayes dan Algoritma Decision Tree didapat alpha ≤ 0.000, maka dapat disimpulkan pengujian T-Test antara Algoritma NaA¯ve Bayes dan Algoritma Decision Tree hasilnya signifikan.

Submission of Semaphore material at Mutiara 5 Lembang Middle School is available in the boy scout book and is only in the form of 2-dimensional images and can also be delivered by the scoutmaster. In this case the delivery of the material for the Semaphore still has shortcomings. Therefore this study aims to build visual learning media to convey information about semaphore code using augmented reality. In order to provide more detailed knowledge about semaphore code actively, creatively and educatively. It is expected that with the function of converting text into semaphore code, students can see the visualization of semaphore code movements in real time. So that this application can be a new tool in improving the semaphore code learning method than before in the form of books. By using the Multimedia Develpoment Life Cycle method, in the testing phase by distributing UAT to 25 scout students and one coach showed 86.5% of results stated very good.

World currency market trading has become one of the many types of work that has been done by the public due to the convenience offered, big profits and the flexibility of time and place in trading. This study aims to predict the movement of EUR / USD currency trends using data mining techniques combined with neural network algorithms compared by linear regression algorithm that can be used as one of the references for traders as an open trading position. Attributes were used in this study namely Open (Opening Price), Close (Closing Price), Highest (Highest Price), Lowest (Lowest Price), for time frame price used is with time frame 1 day and the time period is taken from 3 January 2011 to 15 November 2016. The result of this research is Root Mean Squared Error (RMSE) percentage number as well as additional label prediction result that obtained after validation using sliding windows validation. Best result obtained from testing phase using neural network algorithm which uses 0.006 and 0.003 windowing which results is equal to testing phase that does not use windowing. In other hands, testing phase on linear regression algorithm using windowing resulted in 0.007 and testing phase that does not use windowing that is equal to 0.004. T-test showed that neural network has insignificant result compared with linear regression. T-test result value is 1.00 for testing with windowing and 0.077 for windowless test.

South East Asian Ministers of Education Organization Regional Open Learning Centre (SEAMOLEC) merupakan salah satu instansi yang memiliki 500 mitra kerjasama baik dalam dan luar negeri. Saat ini data kerjasama pada SEAMOLEC belum terintegrasi dengan baik. Data antara pihak penyelenggara kerjasama atau dalam hal ini disebut mitra SEAMOLEC dicatat dalam bentuk file berupa excel/word yang terpisah. Proses penyusunan dan pencarian data instansi yang melangsungkan kerjasama dalam periode waktu tertentu membutuhkan proses dan waktu yang lama. Selain itu work plan kerjasama masih mengalami kendala, pihak SEAMOLEC harus menanyakan dan mencatat keinginan work plan masing-masing pihak dan mengumpulkan laporan kegiatan dari tiap work plan. Penelitian ini bertujuan untuk menganalisis dan merancang sistem informasi kerjasama berbasis website untuk memudahkan penyusunan dokumen kerjasama, membantu mempercepat pencarian arsip dan memantau rencana kegiatan (work plan). Metode yang digunakan adalah waterfall. Perancangan database menggunakan MySQL dan bahasa pemrograman yang digunakan PHP. Hasil penelitian menunjukkan bahwa dengan adanya sistem informasi kerjasama maka dapat membantu dalam penyusunan dokumen, mempercepat pencarian arsip dan memantau work plan secara online sehingga lebih terkontrol. Hasil pengujian sistem menggunakan metode black box menunjukkan hasil bahwa semua fitur sistem berjalan dengan baik dan hasil pengujian User Acceptance Test (UAT) sistem ini memperoleh nilai dengan presentasi 94%.

Blood donation is a voluntary process of giving blood for purposes of blood transfusion for others in need. Based on data from PMI in 2013 we still lack 600,000 liters of blood stocks. The process of delivering information related to blood donation, the community must always come PMI, so inefficient and less effective. Many who want to donate blood to help others, but because the information is still lacking, people do not know how to find out information, schedules and activities of existing blood donor. From the above problems, the author of the building android application design regarding blood donation, which is equipped with information / news donor activity, blood stock, schedules and locations, as well as a question and answer directly to the PMI. The methodology used to construct this system using the waterfall method and perform with Object Oriented design are visualized with UML include the Use Case Diagrams and Activity Diagrams. Results from reseach is the application of blood donors who are able to provide stock data bags of blood, donor activity schedules and locations, as well as a blood donor information, frequently asked questions with the PMI Bandung District online. Making it easier for users to be able to find out information about how, where, and terms requirements for blood donors.

When the rainy season arrives, flooding is a common phenomenon. Almost every street, housing, village, river, even in the city center, wherever floods can occur. One effort to prevent the flooding is to create a floodgate on reservoirs or dams that are used to control the water distribution. The water level at this dam must be checked frequently to anticipate if the water level is at a dangerous level. The inspection of water levels will be very difficult if it must be conducted by humans who must be available in the field at any time. This research aims to create a prototype system that can replace the human role in monitoring the dam water level condition at any time by developing an integrated system between hardware and software using IoT (Internet of Things) technology approach and social media (twitter and telegram). The developed system consists of the height sensor (distance), microcontroller and wifi module, which is placed on the water gate. This system serves to measure the water level at any time and send data in real time to the server. The results of system testing performed shows that when the system is in normal circumstances, the system sends data to the server every minute, and updates the status of water level in twitter every 5 minutes. In case the water level has exceeded a predetermined limit, the system sends data to the server every 5 seconds and passes the warning message to all registered telegram contacts.

This paper aims to facilitate the owner to control water pump machine from the vacuum, and the condition of the water is it full or not in house or apartment. The current control system still has many limitations in controlling the water pump machine at home or apartment. The water machine control system was designed with device that has a smart surveillance system that can be accessed with Android smartphone and all information from or to machine control system will command by using SMS, this device create a development of Arduino UNO microcontroller technology that allows the reading of the GSM Module and connected with SMS Gateway. Experiment results facilitate real-time water control and much easy for the owner to control water tank.

The Consumer Price Index is an index which calculates the average change in prices over a period, of a set of goods and services consumed by the population/households within a specific time. In this paper will be discussed about the forecasting of consumer price index of Indonesia using forecast package with R Software. The forecasting process this data using algorithms popularized by Rob J. Hyndman and Yeasmin Khandakar in 2008. By using this method, it is obtained a suitable ARIMA model to forecast CPI data Indonesia. The model most suitable time series is ARIMA (1,0,0).