Jurnal Nasional Teknik Elektro dan Teknologi Informasi
Topics cover the fields of (but not limited to): 1. Information Technology: Software Engineering, Knowledge and Data Mining, Multimedia Technologies, Mobile Computing, Parallel/Distributed Computing, Artificial Intelligence, Computer Graphics, Virtual Reality 2. Power Systems: Power Generation, Power Distribution, Power Conversion, Protection Systems, Electrical Material 3. Signals, Systems, and Electronics: Digital Signal Processing Algorithm, Robotic Systems and Image Processing, Biomedical Instrumentation, Microelectronics, Instrumentation and Control 4. Communication Systems: Management and Protocol Network, Telecommunication Systems, Wireless Communications, Optoelectronics, Fuzzy Sensor and Network
Articles
14 Documents
Search results for
, issue
"Vol 10 No 3: Agustus 2021"
:
14 Documents
clear
<![CDATA[Optimalisasi Keluaran Panel Surya Menggunakan Solar Tracker Berbasis Kamera Terintegrasi Raspberry Pi ]]>
<![CDATA[Agus Suryanto]]>;
<![CDATA[Noor Hudallah]]>;
<![CDATA[Tatyantoro Andrasto]]>;
<![CDATA[Cahyo Fajar Adhiningtyas]]>;
<![CDATA[Seftriana Anifa Khusniasari]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1268.265 KB)
|
DOI: 10.22146/jnteti.v10i3.1142
<![CDATA[Maximum output from the operation of solar cell depends on the temperature of the solar cell, solar radiation, wind speed, the state of the earth's atmosphere, the orientation of the solar cell and the position of the location of the solar cell against the sun (tilt angle). Solar Tracker is a device that automatically change the orientation of a solar panel towards the position of the sun and increasing the insolation. Initially the solar tracker is set up using LDR then image processing-based settings can reduce tracking errors. Image-based solar tracker still uses a full-sized computer that requires a lot of energy and space. This research aims to improve the accuracy of the direction of the solar panel and optimize the output of the solar panel by increasing the angle of solar radiation (insolation) using the Solar Tracker with a camera sensor and a Raspberry Pi minicomputer. The use of cameras is intended to reduce errors from LDR-based systems and the use of Raspberry Pi replaces full-sized computer. The method to track position of the sun is by tracking the pixel with highest value. From the output analysis the solar panel proved to be optimized by the application of Raspberry Pi-integrated camera solar tracker. The comparison of the output power between the stationary solar panel and the solar panel installed on the Raspberry Pi-integrated camera solar tracker is 1: 1,389 (21,5487W: 29,8822W) in the no-load test and 1: 1,2042 (6,0344W: 7, 2671W) in tests with a 12V-5W bulb load.]]>
<![CDATA[Klasifikasi Aktivitas Manusia Menggunakan Extreme Learning Machine dan Seleksi Fitur Information Gain ]]>
<![CDATA[Fitra Bachtiar]]>;
<![CDATA[Fajar Pradana]]>;
<![CDATA[Issa Arwani]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1438.672 KB)
|
DOI: 10.22146/jnteti.v10i3.1451
<![CDATA[Human activity recognition has various benefits in daily lives. However, research in this area is still facing problems that is, unobtrusive data gathering, high dimensionality features, and the algorithm used to classify human activities. Those problems could impact in the result of the developed model. This research is a preliminary study in human activity recognition. Five common human activity will be recognized that is, walking, walking upstairs, walking downstairs, sitting, and standing. The dataset used in this study consist of 1500 data rows and 561 features. Feature selection is performed prior to the modeling step. Information Gain is used as the feature selection in which percentile method is used to subset the number of features in the dataset. The features are then normalized and will classified using ELM. Number of optimal hidden neuron will be searched to yield high predictive accuracy. The results show 240 feature subsets return the higher accuracy. A number of 100 hidden neuron results in highest predictive classification of human activity recognition. The classification results yield accuracy, precision, recall, and F1-score of 0.85.]]>
<![CDATA[Perancangan Kontrol Pelacakan Lintasan untuk Robot Otonom Bergerak Beroda dengan Penggerak Diferensial ]]>
<![CDATA[Stephen I.C. Gulo]]>;
<![CDATA[Tua Tamba]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1520.954 KB)
|
DOI: 10.22146/jnteti.v10i3.1454
<![CDATA[Differential drive wheeled mobile robots (DDWMR) is a class of mobile robots which has been used in various applications due to its mobile abilities. One important issue in the development of DDWMR is regarding the design of control methods to ensure the DDWMR can move autonomously from initial to final poses. The main challenge in such an issue is the need to design a controller which respects the nonholonomic constraint of DDWMR movements. To address such a challenge, this paper proposes a control method which combines techniques in smooth reference trajectory generation and Lyapunov-based tracking control designs. In the proposed method, a reference trajectory that is represented as polynomial function is first generated to connect the initial and final poses based on some waypoints information between them. A feedback control law based on Lyapunov’s stability method is then design to help control the DDWMR in tracking the generated reference trajectory with minimum error. Numerical simulation results are given to illustrate the effectiveness of the proposed method,]]>
<![CDATA[Alokasi Optimal DG Sumber Energi Terbarukan Menggunakan Algoritme Multi-Verse Optimizer ]]>
<![CDATA[Firdaus Firdaus]]>;
<![CDATA[Ontoseno Penangsang]]>;
<![CDATA[Rony Seto Wibowo]]>;
<![CDATA[Umar]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1319.612 KB)
|
DOI: 10.22146/jnteti.v10i3.1462
<![CDATA[In the current situation, minimizing power loss in the distribution and transmission network is one of the research challenges. The distribution system has more losses than the transmission system. High power losses occur when loads connected to the distribution network are removed from the distribution substation. The optimal allocation for Distributed Generation (DG) renewable energy sources is one way to minimize distribution power loss and improve the distribution voltage profile. Inaccurate placement causes increased power losses, lowers the voltage profile and can adversely affect system performance. The Multi Verse Optimization (MVO) method is used to place DG renewable energy sources in the right location. In this work the MVO algorithm is implemented to optimize the location and type of DG for renewable energy sources. The implementation of the MVO algorithm was tested on the IEEE 33 bus radial distribution system. The results obtained indicate that the use of the MVO algorithm method for the optimal allocation of renewable DG is able to minimize power losses and increase the voltage profile.]]>
<![CDATA[Pengembangan Sistem Deteksi Kantuk Menggunakan Pengklasifikasi Random Forest pada Sinyal Elektrokardiogram ]]>
<![CDATA[nuryani nuryani]]>;
<![CDATA[Khoirun Nisak]]>;
<![CDATA[Artono Dwijo Sutomo]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1253.633 KB)
|
DOI: 10.22146/jnteti.v10i3.1469
<![CDATA[Drowsiness is suggested as the most frequent factor in traffic and manufacture accidents. Therefore, a system which can early detect drowsiness is important for an effort to reduce accident number. This article presents a new method for drowsiness detection. The method uses electrocardiogram (ECG) and a Random Forest. Features of normal-to-normal interval (NNI) from ECG for the input of the detection system are investigated. The features include NNI characteristics in terms of time domain i.e the statictics of NNI, and in terms of frequency domain i.e. NNI signal characteristics in VLF until HF band. The level of drowsiness is categorized using Karolinska Sleepiness Scale (KSS) becoming two groups i.e. drowsy and awake. Classification algorithm used is the detection is Random Forest. In the Random Forest, the effect of the number of estimator and maximum feature to the detection performance is evaluated. The detection system is tested using data of drowsy study. The test show that the detection system performs 94.61%, 96.67% and 91.67% in terms of accuracy, sensitivity and specificity, respectively.]]>
<![CDATA[Evaluasi Penerapan Smart Mobility di Jakarta ]]>
<![CDATA[Sifa Novwidia Agni]]>;
<![CDATA[Manzila Izniardi Djomiy]]>;
<![CDATA[Roki Fernando]]>;
<![CDATA[Catur Apriono]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1296.243 KB)
|
DOI: 10.22146/jnteti.v10i3.1730
<![CDATA[Urban problems such as congestion caused by the very rapid population growth and high urbanization flows are common problems in big cities like Jakarta. The concept of smart city has developed and started to be implemented in several big cities in Indonesia, including Jakarta. One part of the concept of smart city is smart mobility, which is currently developing to solve various urban problems, especially in public transportation to improve the quality of services that are effective and efficient. This study discusses solutions for implementing the concept of smart mobility in Jakarta based on the level of readiness of each indicator according to the indicators found on the Boyd Cohen Smart City Wheel. The purpose of this study is to provide an overview of the level of readiness for implementing smart mobility in Jakarta and the improvements that need to be made. This study used the literature study method to get an initial picture of conditions in Jakarta, then the assessment used survey data assessment and descriptive qualitative analysis. The results show that basically Jakarta can be said to be ready to implement smart mobility, however, there needs to be improvements and procurement in several aspects of smart mobility.]]>
<![CDATA[Data Benchmark pada Google BigQuery dan Elasticsearch ]]>
<![CDATA[Nisrina Akbar Rizky Putri]]>;
<![CDATA[Widyawan]]>;
<![CDATA[Teguh Bharata Adji]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1334.058 KB)
|
DOI: 10.22146/jnteti.v10i3.1745
<![CDATA[Nowadays,the cloud is not only a data storage medium but can be used as a medium for managing or analyzing data. Google offers Google BigQueryas a platform capable of managing and analyzing data,while Elasticsearch itself is a search and analysis engine that can be used to analyze data using Kibana. Using a dataset in the form of tweets crawled through http://netlytic.org/,containing the hashtags #COVID19 and #coronavirus, the data will be analyzed and used to compare its performance with benchmarks. Benchmark is a process used to measure and compare performance against an activity so that the desired level of performance is achieved. Data benchmark is performed on both platforms to generate or determine the workload of the platforms. The result obtained in this study is that Google BigQueryhas superior results, both from the upload container for larger datasets than Elasticsearch and with two query testing models.The query management time on Google BigQueryis also shorter and faster than Elasticsearch. Meanwhile, the visualization results from these two platforms have the same percentage amount.]]>
<![CDATA[Deteksi Myocardial Infarction Menggunakan Fitur Statistik Segmen-ST Elektrokardiogram dan Analisis Diskriminan ]]>
<![CDATA[Dewi Cahya Fitri]]>;
<![CDATA[nuryani nuryani]]>;
<![CDATA[Anto Satriyo Nugraha]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1199.906 KB)
|
DOI: 10.22146/jnteti.v10i3.1784
<![CDATA[This article describes the detection of myocardial infarction using the statistical mean features, including the mean, median, and standard deviation. The classification used is the discriminant analysis method which is implemented using matlab software. The ECG signal obtained from the device is then processed. After that, the feature extraction is carried out. The results of the extraction is normalized so that all patient data have the same standard in amplitude wave magnitude. After normalization, the data will be used as input for discriminant analysis. In this article we try to use the mean, median, and standard deviation features. In this experiment using 15 leads consisting of 12 conventional leads and 3 posterior leads, the addition of these 3 leads has the advantage of determining the performance results obtained. Percentage of accuracy performance, the best percentage of accuracy performance is 97.73% with the mean feature. This experiment tries to compare the features of mean and standard deviation, mean and median, standard deviation and median, and mean, median, and standard deviation. The combined experiment shows that the best accuracy performance percentage value is 98.84% with standard deviation and median features.]]>
<![CDATA[Implementasi Tunnel GRE pada Jaringan Ring dan Mesh Perangkat Metro-E Nokia ]]>
<![CDATA[R. Muhammad Arifin Arifin]]>;
<![CDATA[Eni Dwi Wardhani]]>;
<![CDATA[Samuel BETA]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1439.298 KB)
|
DOI: 10.22146/jnteti.v10i3.1795
<![CDATA[Tunnel is a technique of building a local communication path between two or more routers using a public IP network. The problems faced in tunneling systems are currently lacking guidelines for choosing the right technique according to the network topology used. In the electoral field, it is done based on experience or following SOPs. The brands of devices that support tunneling are very diverse in Indonesia, one of which is Nokia. This study focuses on the tunnel owned by Nokia devices, namely the GRE in order to produce guidelines for using the GRE tunnel. The analysis is carried out with various traffic engineering scenarios including no-load conditions, and various other conditions when there is a network outage. The results showed that the GRE without load runs normally. When the load from the beginning of the GRE gets a throughput of 0.995 Mbps and an average delay of 11.484 ms, when with a sudden load it gets a throughput of 1.059 Mbps and a delay of 11.386 and when a network disturbance is carried out with the ping command it gets 1 RTO. The GRE tunnel follows the LDP protocol path so it is suitable for use in new network implementations because of its simplicity in its configuration which is enough to activate the OSPF metric to balance traffic on each particular router interface]]>
<![CDATA[Aspect Category Classification dengan Pendekatan Machine Learning Menggunakan Dataset Bahasa Indonesia ]]>
<![CDATA[SYAIFULLOH AMIEN PANDEGA PERDANA]]>;
<![CDATA[Teguh Bharata Aji]]>;
<![CDATA[Ridi Ferdiana]]>
<![CDATA[ Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 3: Agustus 2021 ]]>
Publisher : <![CDATA[Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1241.472 KB)
|
DOI: 10.22146/jnteti.v10i3.1819
<![CDATA[Customer reviews are opinions on the quality of goods or services that consumers perceive. Customer reviews contain useful information for both consumers and providers of goods or services. The availability of a large number of customer reviews on the websiterequires a framework for extracting sentiment automatically. A customer review often contains many aspects, so the Aspect Based Sentiment Analysis (ABSA) should be used to determine the polarity of each aspect. One of the important tasks in ABSA is Aspect Category Detection. The application of Machine Learning Methods for Aspect Category Detection has been mostly done in the English language domain, but in the Indonesian language domain,there are still a few. This study compares the performance of three machine learning algorithms, namely Naïve Bayes (NB), Support Vector Machine (SVM),and Random Forest (RF),on Indonesian language customer reviews using Term Frequency-Inverse Document Frequency (TF-IDF) as term weighting. The results showthat RFperformsthe best,compared to NB and SVM,in three different domains, namely restaurants, hotels,and e-commerce,with the f1-scoresfor each domainare84.3%, 85.7%, and 89.3%.]]>
