Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Not a member yet
1071 research outputs found
Sort by
Studi Perbandingan Jaringan Blockchain sebagai Platform Sistem Rating
Get PDFIn the tourism industry, reputation is important information that influence customer behavior. Some services, such as hotels, take advantage of feedback from customers. This research aims to develop a review system by utilizing blockchain and machine learning for sustainable tourism. As proof of concept, a comparison method is carried out between several existing Blockchain networks. The system prototype then implemented using Hyperledger blockchain network, so that measurement of its performance is possible. The results show the feasibility of the blockchain network to be used for a rating system, although several aspects need to be considered in its implementation.Dalam industri pariwisata, reputasi merupakan informasi penting mempengaruhi perilaku pelanggan. Beberapa layanan wisata, seperti hotel, memanfaatkan reputasi dan review pengguna untuk mendapatkan umpan balik dari pelanggan. Penelitian ini bertujuan untuk mengembangkan sistem review industri pariwisata dengan memanfaatkan blockchain dan machine learning bagi parisiwata yang berkelanjutan. Dalam rangka proof of concept, dilakukan metode perbandingan antara beberapa jaringan Blockchain yang ada. Prototipe sistem diimplementasikan dengan menggunakan jaringan blockchain Hyperledger, sehingga pengukuran kinerjanya dimungkinkan. Hasil penelitian menunjukkan kelayakan jaringan blockchain tersebut untuk sistem rating meskipun beberapa pertimbangan perlu diperhatikan dalam implementasinya
Sistem Pemantau Kondisi Lingkungan Pertanian Tanaman Pangan dengan NodeMCU ESP8266 dan Raspberry Pi Berbasis IoT
Get PDFThe increasing need for food is not in line with the clearing of agricultural land for food crops. So that the effort to increase the productivity of agricultural products is by applying precision agriculture. However, in reality, precision agriculture is difficult to apply to conventional processes, where farmers come to the farm, collect data, then carry out maintenance. This method will make production results not optimal because maintenance is not done accurately. This study introduces a monitoring system for environmental conditions based on the Internet of Things (IoT) for agricultural land, where trials are carried out in a greenhouse. The system that has been developed consists of several sensors designed to collect information related to agricultural environmental conditions, including DHT22 sensor (temperature and humidity), DS18B20 sensor (soil temperature), soil moisture sensor (moisture content in the soil), and BH1750 sensor (light intensity). Based on the Message Queuing Telemetry Transport (MQTT) protocol, the data is sent to a gateway (Raspberry Pi) and a local server via a wireless network to be stored in a database. By using the Node-RED Dashboard, the received sensor data is then displayed on the browser every time the sensor sends data. In addition, the local server also publishes sensor data to the public MQTT broker so that sensor data can be accessed through the MQTT Dashboard application on a smartphone. The results of testing for 25 days of the system running obtained an average success of the system in storing data of 99.64%.Kebutuhan pangan yang semakin meningkat tidak sejalan dengan pembukaan lahan pertanian untuk tanaman pangan. Sehingga upaya untuk meningkatkan produktivitas hasil pertanian yaitu dengan menerapkan pertanian presisi. Namun, pada kenyataannya pertanian presisi sulit diterapkan pada proses konvensional, dimana petani mendatangi lahan pertanian, mengambil data, lalu melakukan pemeliharaan. Cara tersebut akan membuat hasil produksi tidak maksimal karena pemeliharan tidak dilakukan secara akurat. Penelitian ini memperkenalkan sistem pemantau kondisi lingkungan berbasis Internet of Things (IoT) untuk lahan pertanian, dimana ujicoba dilakukan di dalam greenhouse. Sistem yang telah dikembangkan terdiri dari beberapa sensor yang didesain untuk mengumpulkan informasi terkait kondisi lingkungan pertanian, diantaranya sensor DHT22 (suhu dan kelembaban udara), sensor DS18B20 (suhu tanah), sensor soil moisture (kadar air pada tanah), dan sensor BH1750 (intensitas cahaya). Berbasis protokol Message Queuing Telemetry Transport (MQTT), data tersebut dikirim ke gateway (Raspberry Pi) dan server lokal melalui jaringan nirkabel untuk disimpan di dalam database. Dengan menggunakan Node-RED Dashboard, data sensor yang diterima kemudian ditampilkan pada browser setiap sensor mengirimkan data. Selain itu, server lokal juga melakukan publish data sensor ke public MQTT broker agar data sensor dapat diakses melalui aplikasi MQTT Dashboard di smartphone. Hasil pengujian selama 25 hari sistem berjalan, diperoleh rata-rata keberhasilan sistem dalam menyimpan data sebesar 99.64%
Support Vector Machine to Predict Electricity Consumption in the Energy Management Laboratory
Get PDFPredicted electricity consumption is needed to perform energy management. Electricity consumption prediction is also very important in the development of intelligent power grids and advanced electrification network information. we implement a Support Vector Machine (SVM) to predict electrical loads and results compared to measurable electrical loads. Laboratory electrical loads have their own characteristics when compared to residential, commercial, or industrial, we use electrical load data in energy management laboratories to be used to be predicted. C and Gamma as searchable parameters use GridSearchCV to get optimal SVM input parameters. Our prediction data is compared to measurement data and is searched for accuracy based on RMSE (Root Square Mean Error), MAE (Mean Absolute Error) and MSE (Mean Squared Error) values. Based on this we get the optimal parameter values C 1e6 and Gamma 2.97e-07, with the result RSME (Root Square Mean Error) ; 0.37, MAE (meaning absolute error); 0.21 and MSE (Mean Squared Error); 0.14.Predicted electricity consumption is needed to perform energy management. Electricity consumption prediction is also very important in the development of intelligent power grids and advanced electrification network information. we implement a Support Vector Machine (SVM) to predict electrical loads and results compared to measurable electrical loads. Laboratory electrical loads have their own characteristics when compared to residential, commercial, or industrial, we use electrical load data in energy management laboratories to be used to be predicted. C and Gamma as searchable parameters use GridSearchCV to get optimal SVM input parameters. Our prediction data is compared to measurement data and is searched for accuracy based on RMSE (Root Square Mean Error), MAE (Mean Absolute Error) and MSE (Mean Squared Error) values. Based on this we get the optimal parameter values C 1e6 and Gamma 2.97e-07, with the result RSME (Root Square Mean Error) ; 0.37, MAE (meaning absolute error); 0.21 and MSE (Mean Squared Error); 0.14
Penentuan Klaster Koridor TransJakarta dengan Metode Majority Voting pada Algoritma Data Mining
Get PDFThe Covid-19 pandemic has made many changes in the patterns of community activity. Large-Scale Social Restrictions were implemented to reduce the number of transmission of the virus. This clearly affects the mode of transportation. The mode of transportation makes new regulations to reduce the number of passenger capacities in each fleet, for example, TransJakarta services. This study will categorize the TransJakarta corridors before and during the Covid-19 pandemic. The clustering method of K-Means and K-Medoids is used to obtain accurate calculation results. The calculations are performed using Microsoft Excel, Rapid Miner, and Python programming language. The clustering results obtained that using K-Means algorithm before Covid-19 pandemic, an optimum number of clusters is 3 clusters with DBI (Davies Bouldin Index) value is 0.184, and during Covid-19 pandemic, the optimum number of clusters is 2 clusters with DBI value is 0.188. Meanwhile, when using the K-Medoids algorithm before the Covid-19 pandemic, an optimum number of clusters is 3 clusters with the DBI value is 0.200, and during the Covid-19 pandemic, an optimum number of clusters is 4 clusters with the DBI value is 0.190. The final cluster is determined using the majority voting approach from all the tools used.
Pandemi Covid-19 menjadikan banyak perubahan dalam pola aktifitas masyarakat. Pembatasan Sosial Berskala Besar (PSBB) diimplementasi guna menekan angka penularan virus tersebut. Hal ini jelas berpengaruh terhadap moda transportasi. Moda transportasi membuat aturan baru untuk mengurangi jumlah kapasitas penumpang di setiap armada, sebagai contoh layanan Transjakarta. Penelitian ini akan mengelompokkan koridor TransJakarta sebelum dan selama masa pandemi Covid-19. Metode klasterisasi K-Means dan K-Medoids digunakan untuk mendapatkan hasil perhitungan yang akurat. Perhitungan dilakukan menggunakan tools Microsoft Excel, Rapid Miner dan bahasa pemrograman Python. Berdasarkan hasil pengelompokan yang diperoleh dari penggunaan algoritma K-Means sebelum masa pandemi, jumlah cluster optimal adalah 3 cluster dengan nilai DBI (Davies Bouldin Index) 0,184, dan selama masa pandemi, jumlah cluster optimal adalah 2 cluster dengan nilai DBI 0,188. Sementara itu, bila menggunakan algoritma K-Medoids sebelum masa pandemi, jumlah cluster optimal adalah 3 cluster dengan nilai DBI 0,200, dan selama masa pandemi, jumlah cluster optimal adalah 4 cluster dengan nilai DBI 0,190. Penentuan cluster akhir menggunakan pendekatan metode majority voting dari semua tools yang digunakan.
 
Identifikasi Level Pengelolaan Tata Kelola SIPERUMKIM Kota Salatiga berdasarkan COBIT 2019
Get PDFSIPERUMKIM is the digitization process of public service licensing recommendations for housing implementation. The utilization of information technology governance is used to facilitate monitoring and evaluating the performance of SIPERUMKIM information technology which has been implemented in Housing and Settlement Area in Salatiga city. Information technology governance is a process that can manage investment decisions related to information technology within the company to achieve goals and meet company needs. The use of COBIT 2019 analysis in information technology governance aims to help organizations achieve risk optimization, governance, and information technology management. The results of this study are in the design form of corporate information technology governance and knowing the important process recommendations for the Department of Housing and Settlement of the City of Salatiga. These three important process recommendations are APO12, DSS02, and DSS03.
SIPERUMKIM adalah proses digitalisasi pelayanan publik rekomendasi perizinan penyelenggaraan perumahan. Pemanfaatan tata kelola teknologi informasi digunakan mempermudah dalam monitoring dan mengevaluasi kinerja teknologi informasi SIPERUMKIM yang sudah diterapkan dalam Dinas Perumahan dan Kawasan Permukiman Kota Salatiga. Tata kelola teknologi informasi merupakan proses yang dapat mengelola investasi keputusan yang berhubungan dengan teknologi informasi di dalam perusahaan untuk mencapai tujuan dan memenui kebutuhan perusahaan. Penggunaan analisis COBIT 2019 dalam tata kelola teknologi informasi yang bertujuan membantu organisasi mencapai optimalisasi resiko, tata kelola dan manajemen teknologi informasi. Hasil dari penelitian ini berupa desain tata kelola teknologi informasi perusahaan dan mengetahui rekomendasi proses yang penting bagi Dinas Perumahan dan Kawasan Permukiman Kota Salatiga. Rekomendasi 5 proses penting tersebut diantaranya adalah APO12, DSS02, dan DSS03
Pengenalan Logo Kendaraan Menggunakan Metode Local Binary Pattern dan Random Forest
Get PDFThe vehicle logo is one of the features that can be used to identify a vehicle. Even so, a lot of Intelligent Transport System which are developed nowadays has yet to use a vehicle logo recognition system as one of its vehicle identification tools. Hence there are still cases of traffic crimes that haven't been able to be examined by the system, such as cases of counterfeiting vehicle license plates. Vehicle logo recognition itself could be done by using various feature extraction and classification methods. This research project uses the Local Binary Pattern feature extraction method which is often used for many kinds of image recognition systems. Then, the classification method used is Random Forest which is known to be effective and accurate for various classification problems. The data used for this study were as many as 2000 vehicle logo images consisting of 5 brand classes, namely Honda, Kia, Mazda, Mitsubishi, and Toyota. The results of the tests carried out obtained the best accuracy value of 88.89% for the front view logo image dataset, 77.03% for the side view logo image dataset, and 83% for the dataset with both types of images.Logo kendaraan merupakan salah satu ciri yang dapat digunakan untuk mengidentifikasi kendaraan. Meski begitu, banyak dari Sistem Transportasi Cerdas yang dikembangkan saat ini masih belum menggunakan sistem pengenalan logo kendaraan sebagai bagian dari alat identifikasi kendaraan. Karenanya masih ada kasus kejahatan lalu lintas yang luput dari pemeriksaan oleh sistem, seperti kasus pemalsuan pelat nomor kendaraan. Pengenalan logo kendaraan sendiri dapat dilakukan dengan menggunakan berbagai metode ekstraksi ciri dan klasifikasi. Penelitian ini menggunakan metode ekstraksi ciri Local Binary Pattern yang sudah sering digunakan untuk berbagai jenis sistem pengenalan citra. Kemudian, untuk metode klasifikasi yang digunakan adalah Random Forest yang dikenal efektif dan akurat untuk berbagai kasus klasifikasi. Data yang digunakan untuk penelitian ini adalah sebanyak 2000 citra logo kendaraan yang terdiri dari 5 kelas merek yaitu Honda, Kia, Mazda, Mitsubishi, dan Toyota. Hasil dari pengujian yang dilakukan memperoleh nilai akurasi terbaik sebesar 88,89% untuk dataset citra logo tampak depan, 77,03% untuk dataset citra logo tampak samping, dan 83% untuk dataset dengan kedua jenis citra
Analisis Hybrid DSS untuk Menentukan Lokasi Wisata Terbaik
Get PDFTourism is an activity carried out by humans to a place alone or together to have fun to get rid of the burden of thoughts that were previously acquired. The Mandeh area is a leading tourist area in West Sumatra which has 10 alternative tourist attractions. With the many tourist locations in the area, tourists are confused about what places to visit in the Mande area. In this study, a combined analysis or Hybrid Decision Support System (DSS) was carried out using a combination of the Analytical Hierarchy Process (AHP) method with the Simple Additive Weighting (SAW) method. The purpose of this research is to be able to combine AHP and SAW methods in one DSS analysis and then be able to recommend the decision results to tourists in the form of the best tourist locations in the Mandeh area. With the recommendation, it can increase the interest of tourists to come and increase the opinions of tourist location owners and the surrounding community. The result of this research is to obtain a recommendation for the best tourist location decision in the Mande area of West Sumatra, namely the location of Manjunto Beach with the highest value of 0.895.Wisata adalah kegiatan yang dilakukan manusia ke suatu tempat secara sendirian maupun bersama-sama dengan tujuan untuk bersenang-senang agar dapat menghilangkan beban pikiran yang didapat sebelumnya. Daerah Mandeh merupakan kawasan wisata unggulan di Sumbar yang memiliki 10 alternatif objek wisata. Dengan banyak nya lokasi wisata di daerah tersebut membuat wisatawan bingung mau berkunjung ke tempat apa di daerah Mande. Dalam penelitian ini dilakukan analisa SPK gabungan atau Hybrid Decision Support System (DSS) menggunakan pengabungan metode Analytical Hierarchy Process (AHP) dengan metode Simple Additive Weighting (SAW). Tujuan penelitian ini adalah dapat menggabungkan metode AHP dan SAW dalam satu analisa DSS kemudian dapat merekomendasikan hasil keputusan kepada wisatawan berupa lokasi wisata terbaik di daerah mandeh. Dengan adanya rekomendasi maka dapat meningkatkan minat wisatawan untuk datang dan meningkatkan pendapat pemilik lokasi wisata dan masyarakat sekitar. Hasil dari penelitian ini adalah didapatkannya rekomendasi keputusan lokasi wisata terbaik di daerah Mande Sumatera Barat yaitu lokasi Manjunto Beach dengan nilai tertinggi 0,895
Random Forest Algorithm to Investigate the Case of Acute Coronary Syndrome
Get PDFThis paper explains the use of the Random Forest Algorithm to investigate the Case of Acute Coronary Syndrome (ACS). The objectives of this study are to review the evaluation of the use of data science techniques and machine learning algorithms in creating a model that can classify whether or not cases of acute coronary syndrome occur. The research method used in this study refers to the IBM Foundational Methodology for Data Science, include: i) inventorying dataset about ACS, ii) preprocessing for the data into four sub-processes, i.e. requirements, collection, understanding, and preparation, iii) determination of RFA, i.e. the "n" of the tree which will form a forest and forming trees from the random forest that has been created, and iv) determination of the model evaluation and result in analysis based on Python programming language. Based on the experiments that the learning have been conducted using a random forest machine-learning algorithm with an n-estimator value of 100 and each tree's depth (max depth) with a value of 4, learning scenarios of 70:30, 80:20, and 90:10 on 444 cases of acute coronary syndrome data. The results show that the 70:30 scenario model has the best results, with an accuracy value of 83.45%, a precision value of 85%, and a recall value of 92.4%. Conclusions obtained from the experiment results were evaluated with various statistical metrics (accuracy, precision, and recall) in each learning scenario on 444 cases of acute coronary syndrome data with a cross-validation value of 10 fold.This paper explains the use of the Random Forest Algorithm to investigate the Case of Acute Coronary Syndrome (ACS). The objectives of this study are to review the evaluation of the use of data science techniques and machine learning algorithms in creating a model that can classify whether or not cases of acute coronary syndrome occur. The research method used in this study refers to the IBM Foundational Methodology for Data Science, include: i) inventorying dataset about ACS, ii) preprocessing for the data into four sub-processes, i.e. requirements, collection, understanding, and preparation, iii) determination of RFA, i.e. the "n" of the tree which will form a forest and forming trees from the random forest that has been created, and iv) determination of the model evaluation and result in analysis based on Python programming language. Based on the experiments that the learning have been conducted using a random forest machine-learning algorithm with an n-estimator value of 100 and each tree's depth (max depth) with a value of 4, learning scenarios of 70:30, 80:20, and 90:10 on 444 cases of acute coronary syndrome data. The results show that the 70:30 scenario model has the best results, with an accuracy value of 83.45%, a precision value of 85%, and a recall value of 92.4%. Conclusions obtained from the experiment results were evaluated with various statistical metrics (accuracy, precision, and recall) in each learning scenario on 444 cases of acute coronary syndrome data with a cross-validation value of 10 fold
Modul Front-End Sistem Informasi Geospasial Patroli Terpadu Kebakaran Hutan dan Lahan
Get PDFTo prevent and handle forest and land and forest fire (karhutla), the Ministry of Environment and Forestry assembled a patrol team that conducts a daily task to observe directly to the hotspot location as an indication for land fire. Currently, the patrol team reported the investigation result into a group chat. This method consumed many storage spaces and not suitable for formal reporting. This study aims to develop a front-end module for a web GIS application that visualizes the patrol team's daily report. The application has its data recapitulation method and able to create a formal report. The data used in this study are a set of the report that collected in 2016 by Sumatera and Kalimantan patrol team. The steps to build this application include communication, integrate with the API from the back-end system, developing functional needs, software testing, and the last is software release. The application was build using HTML and CSS for its interface and Javascript and API from the back-end module for its content management. The system uses Google Maps services and library to support the functionalities of the application. The unit testing method's test result shows that the module runs well and can afford all of the required functionality. In addition, the system testing result that the ratio between actual error and expected error is equal to 1. This result indicates the functions of the system are working properly according to the use cases of the system.
Untuk mencegah dan menangani kasus karhutla, Kementerian Lingkungan Hidup dan Kehutanan mengambil Tindakan berupa membentuk tim patroli yang setiap harinya bertugas untuk mengamati langsung ke titik lokasi yang berpotensi mengalami kebakaran dan melaporkan hasilnya. Media pelaporan yang digunakan selama ini adalah melalui WhatsApp Group. Cara tersebut mulai dinilai tidak efektif dari segi penyimpanan dan rekapitulasi data. Penelitian ini bertujuan membuat modul front-end untuk visualisasi hasil patroli dalam bentuk web sehingga tidak bergantung pada group chat dan mampu melakukan rekapitulasi data secara mandiri. Data yang digunakan adalah rekam kegiatan patrol pada tahun 2016 di wilayah Sumatera dan Kalimantan. Tahapan pada penelitian ini adalah komunikasi, perancangan antarmuka pengguna, integrasi dengan API dari back-end system, perancangan fungsionalitas system, uji coba system dan terakhir adalah rilis sistem. Aplikasi dibangun dengan basis HTML serta CSS sebagai antarmukanya, dan Javascript serta API dari modul back-end sebagai pengelola kontennya. Service dan library yang disediakan Google digunakan untuk mendukung fungsionalitas dari aplikasi. Hasil pengujian menggunakan metode unit testing menunjukkan sistem dapat bekerja baik dan sesuai dengan fungsionalitas yang dibutuhkan. Di samping itu, hasil pengujian sistem menunjukkan bahwa rasio antara actual error dan expected error adalah 1. Hal ini menunjukkan bahwa fungsi sistem bekerja sesuai dengan use case yang telah dibuat
Implementation Word2Vec for Feature Expansion in Twitter Sentiment Analysis
Get PDFAbstract
Twitter is a microblog-based social media site launched on July 13, 2006. In March 2020, 476.696 tweets about the government policy in COVID-19 spread on Twitter were captured by the Institute for Development of Economics and Finance (Indef). Government policy has a standard meaning, namely a decision systematically made by the government with specific goals and objectives relating to the public interest, whether carried out directly or indirectly. Sentiment analysis analyzes people’s opinions, sentiments, evaluations, attitudes, and emotions from written language. In this decade, Sentiment Analysis is has become a trendy research area. The purpose of this paper is to focus how to implement word2vec using similarity word as a feature expansion for minimize the vocabulary mismatch in Twitter Sentiment Analysis using “word embeddings”. This research contains 11.395 tweets for a dataset, where the dataset will be used in two classifications: Support Vector Machine Algorithm and Artificial Neural Network Algorithm. The output of Word2Vec will be used for feature expansion in this research, where the algorithm of expansion will check in each row in the corpus where has a similarity vector with that word and will replace the word with the similarity of this words if the value is 0. The dataset in Feature Expansion is using 142.545 articles from Indonesian media. The result of this research is ANN is better than SVM, where the ANN without feature expansion gets 68.89 % and using feature expansion gets 72.58 %. For SVM, the final accuracy without feature expansion is 63.95 %, and using feature expansion gets 68.56 %. This research proves that feature expansion can improve the final accuracy.Abstract
Twitter is a microblog-based social media site launched on July 13, 2006. In March 2020, 476.696 tweets about the government policy in COVID-19 spread on Twitter were captured by the Institute for Development of Economics and Finance (Indef). Government policy has a standard meaning, namely a decision systematically made by the government with specific goals and objectives relating to the public interest, whether carried out directly or indirectly. Sentiment analysis analyzes people’s opinions, sentiments, evaluations, attitudes, and emotions from written language. In this decade, Sentiment Analysis is has become a trendy research area. The purpose of this paper is to focus how to implement word2vec using similarity word as a feature expansion for minimize the vocabulary mismatch in Twitter Sentiment Analysis using “word embeddings”. This research contains 11.395 tweets for a dataset, where the dataset will be used in two classifications: Support Vector Machine Algorithm and Artificial Neural Network Algorithm. The output of Word2Vec will be used for feature expansion in this research, where the algorithm of expansion will check in each row in the corpus where has a similarity vector with that word and will replace the word with the similarity of this words if the value is 0. The dataset in Feature Expansion is using 142.545 articles from Indonesian media. The result of this research is ANN is better than SVM, where the ANN without feature expansion gets 68.89 % and using feature expansion gets 72.58 %. For SVM, the final accuracy without feature expansion is 63.95 %, and using feature expansion gets 68.56 %. This research proves that feature expansion can improve the final accuracy