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
11 Documents
Search results for
, issue
"Vol 10 No 4: November 2021"
:
11 Documents
clear
Klasifikasi Tingkat Kematangan Pisang Berdasarkan Ekstraksi Fitur Tekstur dan Algoritme KNN
Rifki Kosasih
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1138.146 KB)
|
DOI: 10.22146/jnteti.v10i4.462
Bananas are fruits that are rich in vitamins, minerals, and carbohydrates. Banana trees are often cultivated as they have many benefits. In growing banana trees, it is necessary to consider the ripeness level of bananas since it can determine the quality of bananas when harvested. The ripeness level of bananas is related to marketing reach. If the marketing reach is far, the banana should be harvested when it is still raw. Therefore, a system that can classify bananas’ ripeness levels is needed. In this study, 45 banana images were collected, with a composition of 30 images as training data and 15 images as test data. Afterwards, the texture feature extraction method was utilized to determine the parameters affecting the ripeness level of bananas. The texture feature extraction used was based on a histogram that generated several parameters i.e., average intensity, skewness, energy descriptor, and smoothness in the image. In the subsequent stage, the classification based on the features obtained using KNN algorithm was conducted. Based on the results, it was found that the classification accuracy rate was 88.89%.
Teknologi Game untuk Pembelajaran bagi Anak dengan ADHD: Tinjauan Literatur
Rahadian Kurniawan;
Raden Bagoes Yudha Rangga Sanjaya;
Restu Rakhmawati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1276.126 KB)
|
DOI: 10.22146/jnteti.v10i4.2001
The use of game technology in the learning domain for children with Attention Deficit Hyperactivity Disorder (ADHD) has begun to emerge. Until recently, many studies have been conducted to prove game technology usage’s effectiveness in the learning process for children with ADHD. This paper is a systematic literature review aimed to map the use of game technology in the learning process for children with ADHD and identify a future research roadmap. Based on the exploration of the literature obtained by applying the inclusion criteria, 30 primary studies were selected. The analysis yielded a mapping of game technology goals, game technology genres, game technology platforms, and game technology testing. The literature review results indicate that the use of game technology to improve attention in children with ADHD is proven to be relevant and can be the right choice to enhance the focus skills and learning processes. In addition, this literature review identified three roadmaps for future research, namely paying more attention to other ADHD’s comorbidities as the future research’s goal, paying more attention to variations in the respondents’ background involved in the learning game design process, and using other platforms as media for future learning.
Analisis Kinerja Per Connection Classifier dan Failover pada Multiple Gateway Internet Networks
Faris Agil Putra;
Alif Subardono
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1809.025 KB)
|
DOI: 10.22146/jnteti.v10i4.2065
A good design for the internet network is needed to create a good internet network. The problem that often occurs is the availability of the internet network. A solution that can be applied to this problem is to implement Load Balancing and Failover. The network concept used was Load Balancing with the Per Connection Classifier method and Failover. Load Balancing is a technique used to optimally distribute traffic loads on a network with two or more connections. The method used was the Per Connection Classifier which could group connections. The Failover technique was also applied to the redundancy function. The test scenario would test the distribution of traffic loads, Failover testing, and comparative analysis of QoS with parameters jitter, packet loss, throughput, and delay on the performance of the system with Per Connection Classifier method based on Classifier Both Addresses, Both Ports, and Both Addresses and Ports. The results of the test show that the system is able to distribute the traffic, the system can create redundancy, while for overall QoS testing, Both Addresses gets better performance than other classifiers.
Blackbox Testing terhadap Prototipe Sistem Monitoring Kualitas Air Berbasis IoT
Anggita Nur Fathoni;
Unan Yusmaniar Oktiawati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1088.283 KB)
|
DOI: 10.22146/jnteti.v10i4.2095
Internet of Things is a combination of hardware and software which can carry out a communication between the two. The application of this system can be utilized to monitor water quality with temperature and pH parameters online through Blynk application. Blynk application shows data from the reading results of two sensors, namely the DS18B20 temperature sensor and the DFRobot pH sensors in the form of number and graphs. Prior to further use, the accuracy of both of sensors was examined in order to gain more accurate sensor readings. The accuracy testing resulted in an average relative error value of 0,98% for the DS18B20 temperature sensor and 0,95% for DFRobot pH sensor. In the testing, blackbox testing was used to make more use of functional things in the system designed for the user convenience in monitoring water quality based on the the application’s display. Furthermore, the system shows that the function of the hardware or Blynk application to monitor temperature and pH conditions has been running well and can be utilized by the users easily and beneficially.
Perancangan Kendali Formasi pada Multi-Robot Roda Omni dengan Kemampuan Menghindari Tabrakan
Faisal Wahab
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1527.358 KB)
|
DOI: 10.22146/jnteti.v10i4.2152
In this study, a distributed formation control was designed using multiple omni wheel robots (OMR) with the ability to avoid collisions between OMRs when forming a formation. The formation control employed a consensus algorithm consisting of four layers, namely the tracking, consensus, behavior, and the physical robot layer. The tracking layer was used to direct the OMR position at a predetermined virtual center. At the consensus layer, controllers were designed at the robot level. These controllers were an elaboration of the consensus algorithm. The behavior layer was used to augment the collision avoidance methods when OMR formed a formation using the Stipanovic method. On the physical robot layer, four OMRs with three omni wheels configurations were employed. Subsequently, the previously designed controllers were simulated using MATLAB software. The simulation results indicate that the controller applied to the OMR has succeeded in forming the desired formations, namely square and rhombus. In addition, during the process of building these formations, each OMR could maintain a distance; thus, there was no collision with various communication topologies and formations.
Penerapan Antarmuka Adaptif Berbasis Perilaku Pemain pada E-Learning Bidang Pemrograman
Fajar Pradana;
Fitra A. Bachtiar;
Retno Indah Rokhmawati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1598.883 KB)
|
DOI: 10.22146/jnteti.v10i4.2165
The pandemic has caused a significant impact on the educational sector’s implementation. The teaching and learning process that was previously carried out face-to-face now must be conducted online. Online learning utilizing e-learning is very beneficial for learners because it can be accessed online anytime, anywhere. Not only is it expected to be a medium to share material files that serve as learning supports, but e-learning is also required to replace the teachers’ or lecturers’ role in the classroom. In the teaching and learning process, it is essential to understand the students’ conditions and behaviors. This knowledge of students’ conditions and circumstances during the learning process can be used as resources for improving the quality and students’ learning process. Most of the existing e-learning has not been equipped with features to detect the students’ state while using the system. In this research, an adaptive interface was applied as a reflection of e-learning that could adapt to the characteristics of user behavior. The performance testing results showed that the time required for the log data with 950 active users was 23,35 ms. Meanwhile, based on the functionality test, the system succeeded in displaying the interface according to the cluster member.
Penerapan Augmented Reality Berbasis Android untuk Pembelajaran Organ Lambung Manusia
Fony Ferliana Widianingrum;
Sugondo Hadiyoso;
Suci Aulia
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1490.231 KB)
|
DOI: 10.22146/jnteti.v10i4.2362
The stomach is one of the digestive systems functioning as a medium to process and store food, as well as to get rid of harmful substances and absorb good substances for the body. Although elementary schools usually use the torso as a teaching aid to introduce the stomach organ, it is, in fact, very inflexible for elementary students as they have limited learning hours at school. Therefore, it is necessary to develop a stomach organ learning system that can be studied anytime and anywhere. In this study, an Android-based stomach organ learning application was designed by applying Augmented Reality (AR). To run this application, the user needs to install it first. After opening the application and selecting the desired menu, users can point the smartphone at the appropriate marker until the AR display appears. Based on the test results, the application cannot bring AR objects from the stomach organ in a dark place since the marker is not detected. The best distance for marker detection is 20 cm to 35 cm, with an average delay of 0.3 s in indoor conditions and 0.45 s in outdoor conditions.
Metode Imputasi pada Data Debit Daerah Aliran Sungai Opak, Provinsi DI Yogyakarta
Fahmi Dhimas Irnawan;
Indriana Hidayah;
Lukito Edi Nugroho
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1305.168 KB)
|
DOI: 10.22146/jnteti.v10i4.2430
The data availability of water resources in Indonesia has several complex problems related to the perfection of data. The problems taking place when collecting data in several Indonesian agencies are the accuracy and completeness of the data. There are several methods that can be used to handle missing value imputation, such as k-Nearest Neighbors Imputation (k-NNi) and Multivariate Imputation by Chained Equation (MICE). This study seeks to compare and find the most appropriate method using the Opak watershed dataset in Special Region of Yogyakarta. The characteristics of the Opak watershed lies in its fan shape that provides a lower concentration-time and produces a higher flow. The results of the statistical validation comparison showed that the most consistent average value of RMSE and MAE was the k-NNi method with a value of k = 28. As for the comparison of R-Squared values, the k-NNi method with a value of k = 28 obtained the best average value with 80%, followed by the k-NNi method of k = 7 as the default k value with a percentage of 73%. Among the applied methods, the MICE comparison method obtained the lowest average percentage value with 63%.
Metode Power Control sebagai Manajemen Interferensi pada Komunikasi Device to Device
Anggun Fitrian Isnawati;
Sholihah Larasati;
Indak Danil Mabar
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1234.421 KB)
|
DOI: 10.22146/jnteti.v10i4.2433
Today’s communication technology development has entered the 5th generation (5G), where one of the solutions offered is device to device (D2D) communication. The scheme used in this study was cooperative D2D with Mobile User Equipment (MUE) located far from the eNodeB (eNB). The D2D User Equipment (DUE) served as a relay that helped MUE to improve service quality. The effect caused by D2D communication was interference. Therefore, the power control method was used to overcome this problem. This study used three comparative simulations, namely Without Power Control, using Power Control 1, and using Power Control 2. The scheme used in Power Control 1 was a fixed power control, while Power Control 2 used an adaptive power control. Using the Cumulative Distribution Function (CDF), Power Control 1 scheme could improve SINR by 0.124 dB for downlink and 0.0814 dB for uplink. Meanwhile, Power Control 2 scheme could increase SINR by 0.0316 dB for downlink and 0.0627 for uplink. Based on the final results related to SINR, throughput, and CDF, the Power Control 1 method has better results than the Power Control 2 method.
Penerapan Convolutional Long Short-Term Memory untuk Klasifikasi Teks Berita Bahasa Indonesia
Yudi Widhiyasana;
Transmissia Semiawan;
Ilham Gibran Achmad Mudzakir;
Muhammad Randi Noor
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1150.961 KB)
|
DOI: 10.22146/jnteti.v10i4.2438
Text classification is now a well-studied field, particularly in Natural Language Processing (NLP). The text classification can be carried out using various methods, one of which is deep learning. Deep learning methods such as RNN, CNN, and LSTM are the most frequent methods used for text classification. This research aims to analyze the implementation of two deep learning methods combination, namely CNN and LSTM (C-LSTM), to classify Indonesian news texts. News texts used as data in this study were collected from Indonesian news portals. The obtained data were then divided into three categories based on their scope: "National," "International," and "Regional." Three research variables were tested in this study: the number of documents, the batch size value, and the learning rate value of the built C-LSTM. The experimental results showed that the F1-score obtained from the classification results using the C-LSTM method was 93.27%. The F1-score value generated by the C-LSTM method was higher than that of CNN (89.85%) and LSTM (90.87%). In summary, the combination method of two deep learning methods, namely CNN and LSTM (C-LSTM), outperforms CNN and LSTM.