Electrical Engineering

Nowadays, social media is growing rapidly and globally until it finally became an important part of society. During campaign period for the regional head election in Indonesia, the candidates and their supporting parties actively use social media as a campaign tool. Social media like Twitter has been known as a political microblogging media that can provide data about current political event based on users’ tweets. By using Twitter as a data source, this study analyzes public participation during campaign period for 2018 Central Java regional head election. The purpose is to observe how much reaction is given to each candidate who advanced in the election. By using the crawling program, all tweets containing certain candidate names will be downloaded. After going through a series of preprocessing stages, data can be classified using Naive Bayes. Predictor features in classification datasets are the number of replies, retweets, and likes. While the target variable is reaction that is...

Pola komunikasi antar manusia menjadi semakin berkembang di masa kini. Semula pola komunikasi dilakukan secara langsung dan melakukan percakapan (voice), berkembang menjadi komunikasi melalui pengiriman pesan. Pengiriman pesan ini sekaligus ditandai dengan munculnya aplikasi jejaring sosial dalam jaringan (Online Social Network). Aplikasi yang dibangun berbasis kebutuhan dalam komunitas, sehingga aplikasi ini disebut sebagai Community Messenger. Kebutuhan komunitas dan karakteristiknya akan didapatkan dalam tahapan Requirement Gathering. Perancangan aplikasi dilakukan dengan Use Case Diagram sesuai dengan konsep aplikasi yang ringan (lightweight) dan sederhana (simple). Selain itu perlu juga diperhatikan aspek desain dari User Interface mengingat aplikasi ini berupa mobile application yang akan digunakan dalam sebuah smartphone yang memiliki keterbatasan pada ukuran layar. Penempatan menu diusahakan memudahkan pengguna dalam mengoperasionalkan aplikasi ini. Selanjutnya aplikasi ini ...

Proses pengendalian persediaan merupakan bagian penting bagi perusahaan untuk melakukan penyediaan barang. Pengendalian persediaan dilakukan untuk memenuhi jumlah barang yang dibutuhkan pada saat pemasaran dilakukan, namun perusahaan memiliki permasalahan dalam menentukan jumlah persediaan barang dikarenakan jumlah barang yang dibutuhkan pada saat pemasaran berubah setiap waktu. Penelitian ini melakukan data mining guna membantu perusahaan agar dapat mengukur jumlah persediaan barang sebelum dipasarkan dengan melakukan penggalian data menggunakan salah satu metode data mining yaitu pengelompokan data. Pada penelitian ini melakukan mengelompokkan data laporan distribusi dan laporan penjualan pada perusahaan aki, data tersebut di kelompokkan menjadi 3 kelompok dengan menggunakan salah satu algoritma pengelompokan data yaitu K-Means, dari hasil pengelompokan digunakan untuk mengetahui kelompok produk yang diminati, sedang dan kurang diminati kemudian kelompok tersebut digunakan sebagai...

The development of technology also influences changes in campaign patterns. Campaign activities are part of the process of Election of Regional Heads. The aim of the campaign is to mobilize public participation, which is carried out directly or through social media. Social media becomes a channel for interaction between candidates and their supporters. Interactions that occur during the campaign period can be one indicator of the success of the closeness between voters and candidates. This study aims to get the pattern of campaign interactions that occur on Twitter social media channels. This interaction pattern is classified as a model in measuring the success of campaigns on social media. The research begins with obtaining data through the data retrieval process using the API feature provided by Twitter. Furthermore, pre-processing is carried out before data can be processed in an algorithmic method. This stage is done to improve data quality so as to improve accuracy. Naive Bayes Classifier was chosen because of a simple procedure, then Kernel Estimator (KE) was used to improve performance. The use of naive Bayes Kernel Estimator can improve model performance from 76.74% to 80.14%. Testing models with split percentage methods on several combinations get satisfactory results.

Message Queuing Telemetry Transport (MQTT) is a connectivity protocol between machines or now better known as the Internet of Things (IoT). This protocol recognizes two basic functions of M2M communication, namely publish and subscribe (pub/sub). The MQTT protocol is designed as a very simple and very lightweight message delivery protocol, designed for devices that are limited and with low bandwidth capacity, high latency or on an unreliable network. The design principles are to minimize bandwidth requirements and device resource requirements, and keep trying to ensure reliability and guaranteed delivery rates. In this paper, VerneMQ performance reliability is tested - one of the MQTT brokers, with several stressing levels using ESP-32 as a publisher and notebook with the python application as a subscriber.

Social Network Analysis (SNA) merupakan suatu cabang ilmu komputer yang menganalisis fenomena atau pola hubungan pada suatu  jejaring sosial. Pada penelitian ini Twitter merupakan salah satu media jejaring sosial yang akan digunakan sebagai objek penelitian dikarenakan jumlah pengguna aktif setiap bulan yang mencapai 330 juta lebih serta dengan akses informasi yang tak terbatas. Selanjutnya metode analisis yang digunakan pada penelitian ini adalah menggunakan metode GraphML dan perhitungan algoritma pendekatan sentralistas (Centrality Measure). Dimana dengan metode GraphML ini mampu memvisualisasikan hubungan jejaring sosial individu dengan individu lain kedalam bentuk grafik dan mampu digunakan untuk menentukan bobot ikatan indvidu terhadap individu lain atau seberapa kuat hubungan individu tersebut terjalin.  Dalam analisis ini diperoleh hasil berupa diagram derajat sentralitas dengan aktor yang paling dominan yakni aktor 5 dengan jumlah ikatan sebanyak 54, aktor 12 dengan jumlah ...

Mesin pendeteksi uang kertas menjadi salah satu objek yang diperhatikan untuk diteliti dan dikembangkan. Mesin pendeteksi uang kertas Indonesia yang ditemukan seperti di stasiun kereta api di suatu kota, terdapat kegagalan dalam mengenali nilai uang kertas tertentu. Tujuan dari penelitian ini adalah membangun model dari pengenalan nilai uang kertas menggunakan K-Nearest Neighbor (KNN) yang merupakan metode yang paling sederhana dan paling penting dalam pengenalan pola, hal ini ditunjukkan pada akurasi yang diperoleh lebih tinggi dibandingkan metode lainnya seperti Artificial Neural Networks (ANN) dan Feedforward Neural Network (FNN). Model yang diusulkan menggunakan ekstraksi fitur, terdapat beberapa fitur yang digunakan untuk pengenalan uang kertas seperti yang pernah dilakukan menggunakan ekstraksi fitur tekstur. Penelitian ini menggunakan ekstraksi fitur warna. Warna memberikan informasi yang berarti dan nilai-nilai yang penting dalam proses mendeskripsikan suatu objek. Warna yan...

Smartphone users are increasingly diverse in using their phones. Some tasks that monitored through the bulletin boards or computer screens, lately it can be done anywhere with a mobile phone while on the move. Similarly, the features in smartphones are increasingly following the development of communication technology. One of them is Bluetooth version 4, which currently can always be available on all types of smartphones. Even for entry-level phones that commonly used by students, nowadays are equipped with the new version of Bluetooth. In this paper discussed the application of BLE or Bluetooth Low Energy, which is part of Bluetooth version 4, to provide the information about availability, lecture schedule, and lecture room at the University Narotama. By using this BLE communication technology all smartphones equipped with BLE, enabling the NARO-MOBILE application and residing in the campus environment, will receive all the latest information provided by SIMNARO-Narotama University Management Information System, in a real-time.

Coronary heart disease included a group of cardiovascular, and it is a leading cause of death in low and middle-income countries. Risk factors for coronary heart disease are divided into two, namely primary and secondary risk factors. The need to identify characteristics or risk factors in heart disease patients by making the classification model. The modeling of heart disease classification to know how the system can able to reach the best prediction accuracy. Fisher's Discriminant Ratio is one of the methods for feature selection, which is used to get high discriminant features. While Backpropagation is one of the classification models to recognize patterns in heart disease patients. The experiment results showed that the accuracy of the classification model using 13 original features reached 92%. By reducing the features based on the score of the feature selection, then the lowest feature was removed from original features and left there were 12 features involved in the class...

The problem that is in store right now is the difficulty to find out which products are currently in high demand or most used by consumers so that it can be known from each variable the characteristics of consumers are more likely to choose the preferred product. Therefore, in the research grouping with the K-Means method for product selection is one way to determine customer choices for the products consumed. Because the K-Means method has a more accurate division. This research conducted a data mining process to help stores to be able to know the characteristics of consumers towards product selection tendencies by extracting data using one of the data mining methods, namely grouping data. In this study, the grouping of data from questionnaires or questionnaires spread in stores, then the data is grouped into 2 groups using one of the clustering algorithms, K-Means. The data used are data collected as many as 366 store customer response data. After the data is processed using the K-Means algorithm, it shows that cluster 1 is a type A consumer group with a percentage of 33%, while cluster 2 is a type B consumer group with a percentage of 67%.

Pants material is a daily staple, a problem faced by buyer among students, employees, and college students. This aims of this study to predict the Consumer using the Naïve Bayes method. Because the Naïve Bayes method is considered good for classification and accuracy compared to the C4.5 Algorithm method has instability in doing classification. Retrieval of data in this study from the results of interviews with sellers in January to December 2019 then conducted input in Excel with a total of 731 data. By selecting data to get perfect and accurate results, trimming the variables with the 10 initial variables into 5 variables. In the preprocessing stage before conducting the data mining process to find out the amount of data per attribute then the data mining process uses the naïve Bayes algorithm, with a combination of 60 to 90 percent split percentage showing the results of each accuracy value 80.137%, 78.0822%, 81, 5060% and 83.5616%. The best is the 90% split percentage with an accuracy percentage of 83.5616%. The results of the evaluation using the confusion matrix shows that the highest and superior consumer status of the employee class and student class is to show the college student class.

Dalam penelitian ini akan dilakukan analisis sentimen terhadap calon presiden Indonesia tahun 2019 berdasarkan komentar publik di jejaring sosial Facebook. Selanjutnya akan melalui beberapa tahapan dalam melaukan analisis sentimen, antara lain adalah tahap pengumpulan data, data correction, preprocessing data, dan klasifikasi menggunakan Naïve Bayes Classifier serta dilakukan asosiasi teks. Hasil dari penelitian ini diperoleh bahwa calon presiden Joko Widodo didapatkan postingan sebanyak 40 data dan calon presiden Prabowo Subianto didapatkan 12 data postingan dengan pengumpulan data pada tanggal 17 april 2019 sampai 22 mei 2019. Dari data sebanyak 5.000 komentar yang dipilih secara acak dan melalui tahap preprocessing menghasilkan polaritas sentimen, Joko Widodo memeperoleh 85% untuk sentimen positif, 15% sentimen negatif. Sedangkan Prabowo Subianto memperoleh 76% sentimen positif, dan 24% sentimen negatif. Untuk hasil klasifikasi menggunakan Naïve Bayes Classifier memperoleh hasil ...

Permasalahan yang sedang ada di toko saat ini adalah kesulitan untuk mengetahui produk X yang saat ini banyak diminati atau paling banyak digunakan oleh konsumen agar persediaan produk x dapat dipenuhi sesuai permintaan pelanggan dan tidak terjadi out of stock. Oleh karena itu, dalam penelitian pengelompokkan dengan metode K-Means untuk pemasaran produk x merupakan salah satu cara untuk mengetahui pilihan pelanggan terhadap produk x yang dikonsumsi. Pada penelitian ini melakukan pengelompokkan dari data hasil penyebaran angket atau kusioner yang disebar di toko, kemudian data tersebut di kelompokkan menjadi 2 kelompok menggunakan salah satu algoritma klasterisasi yaitu K-Means. Data yang digunakan merupakan data yang dikumpulkan sebanyak 366 data responden pelanggan toko. Setelah data tersebut diproses menggunakan salah satu metode data mining yaitu algoritma K-Means, menunjukkan bahwa cluster 1 merupakan kelompok konsumen tipe A dengan presentase sebesar 33%, sedangkan cluster 2 me...

Mobile users are getting smarter in using their phones. Many tasks are usually completed or monitored via a computer screen, nowadays can be taken anywhere with Android phones or tablets. Likewise with features in the phone is increasingly sophisticated. Currently bluetooth version 4 is almost mandatory in all phones. Even for entry level phones are now equipped with bluetooth version 4. This paper discusses the use of Bluetooth Low Energy—which is part of bluetooth version 4, in providing information about the status of plant growth chamber conditions. By using this concept, all phones or tablets that have bluetooth version 4 and there are applications in it will be able to receive the latest chamber status. The results show that this way of broadcasting is very effective. The data required to be monitored by a laboratory technician can be continuously broadcasted so that anyone on duty will get instant information at his grasp.

Media sosial, Twitter, saat ini telah banyak memberikan dampak besar dalam membangun opini, pandangan, sentimen, dan preferensi politik publik (menjelang Pemilihan Umum) berlangsung. Penelitian ini dilakukan untuk mengetahui percakapan di Twitter pada debat pertama calon presiden Republik Indonesia melalui hashtag dari kedua pasang calon. Selain itu, juga untuk mengetahui tentang kecenderungan masyarakat di Twitter terkait dengan debat yang sedang berlangsung tersebut cenderung positif, negatif, atau netral. Data percakapan di Twitter didapatkan melalui Twitter API yang diambil dengan bahasa Pemrograman R. Proses analisis sentimen ini menggunakan metode Fined-grained Sentiment Analysis yaitu, Jika satu tweet berisi lebih banyak kalimat positif daripada negatif, maka hasil keseluruhan akan positif dan bernilai (+1). Jika jumlah kalimat negatif lebih besar dari kalimat positif, maka hasil keseluruhan negatif dan bernilai (-1). Jika ada jumlah yang sama dari kalimat positif dan negatif...

The sheer usage of social media presents an opportunity for an automated analysis of a social media user based on his/her information, activities, or status updates. This opportunity is due to the abundant amount of information shared by the user. This fact is especially true for countries with high number of active social media users such as Indonesia. Extraction of information from social media can yield insightful results if done correctly. Recent studies have managed to leverage associations between language and personality and build a personality prediction system based on those associations. The current study attempts to build a personality prediction system based on a Twitter user's information for Bahasa Indonesia, the native language of Indonesia. The personality prediction system is built on Support Vector Machine and XGBoost trained with 329 instances (users). Evaluation results using 10-fold cross validation shows that the system managed to reach highest average accuracy of 76.2310% with Support Vector Machine and 97.9962% with XGBoost.

Tujuan dari penelitian ini adalah untuk memprediksi tingkat kelulusan hasil test fisik peserta atlet beladiri kempo yang diselenggarakan oleh KONI.peneliti melakukan klasifikasi berdasarkan data yang diperoleh dari pelatih fisik beladiri kempo dengan menggunakan data mining. Data mining dapat diartikan sebagai proses pengekstrakan informasi baru yang diambil dari bongkahan data besar untuk menunjang hasil pengambilan Sistem Pendukung Keputusan. Oleh karena itu menggunakan Sistem Pendukung Keputusan yang dapat membantu pengambilan keputusan untuk memilih atlet terbaik. Dalam data mining terdapat banyak metode yang dapat digunakan, salah satunya adalah metode klasifikasi dengan memanfaatkan algoritma naive bayes. Hasil yang diperoleh dari penelitian ini adalah Correctly Classified Instances 94.4% dengan speed presentase 60% dan 70% menghasilkan Correctly Classified Instances 92,85%, sedangkan speed presentase 80% menghasilkan Correctly Classified Instances 88,89%.

This study aims to determine the performance of the naive bayes model and KNN (K-Nearest Neighbor) in classifying sentiment text expedition services. Twitter user reviews on @jntexpressid, @JNE_ID, and @posindonesia will be mined and classified based on positive, neutral, and negative sentiments Data was mined for two months from October1 to December 1 2020, the results obtained on the JNT data are 46.220, JNE 5.364, and Pos Indonesia 11.194. The raw data obtained will be cleaned and labeled before entering using TF-IDF for term weighting. The clean data obtained from the pre-processing of the text will be divided into 70% training data and 30% test data. The over-sampling method is used to balance the dataset and avoid overfitting training data. Naive ayes model and KNN there was a significant increase after the over-sampling method was implemented. The greatest accuracy in naive bayes is found in JNT data of 82%, while KNN on POS data is 71%. In KNN a high K value does not determine the accuracy results, it is proven that K = 2 has the highest accuracy compared to K = 4, K = 6, K = 8, K = 10 after the resampling technique is carried out.

Technological developments that have begun the 4.0 industrial revolution have made many sectors in everyday life begin to innovate in order to be able to compete and be more efficient. It also penetrated the medical world, which was previously still done manually and requires considerable human resources. However, along with the many innovations that exist in the process that can be automated, ranging from the process of patient registration to examination of a person himself. In this study, the authors designed a tool that can retrieve data from humans for medical needs based on the Internet of Things. Data will be taken from these measurements between the body height of the patient, the body temperature of a patient and the body of a patient at the same time automatically. After data retrieval is carried out by several sensors, then the data will be sent to the broker / server which will be sent to the Node-red dashboard using the MQTT protocol and the data will be transferred to ...

Banyaknya transaksi penjualan yang terjadi setiap hari membuat data transaksi penjualan semakin bertambah. Data transaksi penjualan hanya dijadikan arsip bagi sebuah toko. Akibatnya banyak permintaan barang pelanggan mengalami kekurangan stok barang. Kekurangan atau kekosongan stok barang pada suatu toko/perusahaan akan berdampak sangat buruk untuk keberhasilan dan kelancaran transaksi jual beli, Untuk mencegah hal tersebut maka dibutuhkan sebuah system yang dapat membantu pengelola barang agar mengetahui secara dini tentang ketersediaan barang yang terdapat pada toko. Dengan memanfaatkan data transaksi penjualan akan dilakukan sebuah penambangan data (data mining). Metode yang dilakukan pada penelitian ini adalah metode association rule dengan menggunakan algoritma apriori. Algoritma apriori merupakan teknik data mining untuk menemukan kombinasi item dalam database, hasil dari penelitian yang dilakukan, algoritma apriori dapat mempermudah menemukan pola kombinasi item dalam dataset...