Jurnal Ilmiah Teknik Elektro Komputer dan Informatika

Journal Information
ISSN / EISSN : 2338-3070 / 2338-3062
Published by: Universitas Ahmad Dahlan, Kampus 3 (10.26555)
Total articles ≅ 127

Latest articles in this journal

Puput Dani Prasetyo Adi, Akio Kitagawa, Dwi Arman Prasetya, Rahman Arifuddin, Stanislaus Yoseph
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 522-538; https://doi.org/10.26555/jiteki.v7i3.22258

Currently, agricultural technology or Farming development is increasingly sophisticated by applying LoRaWAN-based IoT technology, ignoring quality agricultural products. LoRaWAN used in this research uses Long-Range Frequency 915 MHz and 920 MHz. The case study in this research is a case of river water quality that enters agricultural land or irrigation in Temas, Batu City, where the river water has been contaminated by household waste. The prototype installed on this farm uses an Arduino and Dragino LoRa 915 MHz microcontroller as transceivers and input and output devices consisting of ultrasonic sensors and water pH sensors, and outputs such as Solenoid valves mounted on tub one and tub 2. In contrast, tub 3 is a unique tub for distributing water to agricultural land with normal water pH quality. In this research, real-time monitoring, especially on the conditions of water turbidity, water pH, and water level.
Mungki Astiningrum, Vivi Nur Wijayaningrum, Ika Kusumaning Putri
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 441-452; https://doi.org/10.26555/jiteki.v7i3.22010

The large number of Indonesians who consume rice as their primary food makes rice price a benchmark for determining the other staple food prices. The instability of rice prices due to climate change or other uncontrollable factors makes it difficult for Indonesians to estimate the rice prices, especially for the poor. This study proposes the usage of the Improved Crow Search Algorithm (ICSA) to optimize the Support Vector Regression (SVR) parameter in building a regression model to predict the price of staple foods. The forecasting process is carried out based on time series data of 11 staples for four years. The proposed ICSA optimizes the six parameters used in the SVR to form a regression model, consisting of lambda, epsilon, sigma, learning rate, soft margin constant, and the number of iterations. Algorithm performance is measured using MAPE and NRMSE by comparing the actual price of staple foods and forecasting results to get the error rate. With this parameter optimization mechanism, the forecasting results given are good enough with a small error value, in the form of MAPE of 17.081 and NRMSE of 1.594. A MAPE value between 10 and 20 indicates that the forecasting result is acceptable, while an NRMSE value of less than 10 indicates that the forecasting accuracy is excellent. The improvised technique on Crow Search Algorithm is proven to improve the performance of Support Vector Regression in forecasting the price of staple foods.
Supriyanto Praptodiyono, Hari Maghfiroh, Muhammad Nizam, Chico Hermanu, Arif Wibowo
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 461-471; https://doi.org/10.26555/jiteki.v7i3.22271

A hydroelectric power plant is an electrical energy generator that utilizes water energy to drive a water turbine coupled to a generator. The main problem in hydroelectric power plants is the frequency and voltage fluctuations in the generator due to fluctuations in consumer loads. The purpose of this research is to make a prototype of the Electronic Load Controller (ELC) system at the Pico Hydropower Plant. The main part of ELC is the frequency sensor and gating system. The first part is made by a Zero Crossing Detector, which detects the generator frequency. The gating system was developed with TRIAC. The method used is the addition of a complement load which is controlled by delaying the TRIAC. Load control is intended to maintain the stability of the electrical energy produced by the generator. The PID algorithm is used in frequency control. The results of the frequency sensor accuracy test are 99.78%, and the precision is 99.99%. The ELC system can adjust the frequency automatically by setting the firing delay on the TRIAC to distribute unused power by consumer loads to complementary loads so that the load used remains stable. The ELC is tested with increasing and decreasing load. The proposed ELC gives a stable frequency at 50Hz. Whereas at the first test, the mean voltage is 183V, and in the second test is 182.17V.
Purwono Purwono, , Iis Setiawan Mangku Negara, Wahyu Rahmaniar, Jihad Rahmawan
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 423-432; https://doi.org/10.26555/jiteki.v7i3.22237

Stroke is a disease caused by brain tissue damage because of blockage in the cerebrovascular system that disrupts body sensory and motoric systems Stroke disease is one of the highest death cause in the world. Data collection from Electronic Health Records (EHR) is increasing and has been included in the health service big data. It can be processed and analyzed using machine learning to determine the risk group of stroke disease. Machine learning can be used as a predictor of stroke causes, while the predictor clarifies the influence of each cause factor of the disease. Our contribution in this research is to evaluate Feyn Qlattice machine learning models to detect the influence of stroke disease's main cause features. We attempt to obtain a correlation between features of the stroke disease, especially on the gender as a feature, whether any other features can influence the gender feature. This research utilizes 4908 data of the disease predictor using the Feyn Qlattice model. The result implies that gender highly impacts age and hypertension on stroke disease causes. Autorun in Feyn Qlattice model was run with ten epochs, resulting in 17596 test models at 57s. Query string parameter that was focused on age and hypertension features resulted in 1245 models at 4s. An increase of accuracy was found in training metrics from 0.723 to 0.732 and in testing metrics from 0.695 to 0.708. Evaluation results showed that the model is reasonably good as a predictor of stroke disease, indicated with blue lines of AUC in training and testing metrics close to ROC's left side peak curve.
Rista Azizah Arilya, Yufis Azhar, Didih Rizki Chandranegara
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 433-440; https://doi.org/10.26555/jiteki.v7i3.22080

At the beginning of 2020, the world was shocked by the coronavirus, which spread rapidly in various countries, one of which was Indonesia. So that the government implemented the Work from Home policy to suppress the spread of Covid-19. This has resulted in many people writing their opinions on the Twitter social media platform and reaping many pros and cons of the community from all aspects. The data source used in this study came from tweets with keywords related to work from home. Several previous studies in this field have not implemented feature selection for sentiment analysis, although the method used is not optimal. So that the contribution in this study is to classify public opinion into positive and negative using sentiment analysis and implement PSO for feature selection and Naïve Bayes for classifiers in building sentiment analysis models. The results showed that the best accuracy was 81% in the classification using Naive Bayes and 86% in the classification using naive Bayes based on PSO through a comparison of 90% training data and 10% test data. With the addition of an accuracy of 5%, it can be concluded that the use of the Particle Swarm Optimization algorithm as a feature selection can help the classification process so that the results obtained are more effective than before.
Shofiqul Islam, Munirul Hasan, Abdur Rahim, Ali Muttaleb Hasan, Mohammad Mynuddin, Imran Khandokar, Jabbarul Islam
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 491-502; https://doi.org/10.26555/jiteki.v7i3.22327

The growth of the entertainment industry around the world may be seen in the creation of new genres and the influx of artists and musicians into this field. Every day, a large amount of music is generated and released. The classification of these music based on genres and the recommendation of music to users is a crucial task for various music streaming platforms. Many artificial intelligence methods have been created to overcome this. Inadequate data for training is one of the biggest issues when it comes to building machine learning algorithm. A certain dataset contains a large number of redundant features, which may lead the models to overfit. Data filtering could be used to solve this issue. On the GTZAN data for music genre classification, this article constructed numerous Artificial Intelligence (AI) models and used a data filtering strategy. This study does a comparative analysis and discusses the results. The models developed and evaluated are Naive Bayes, Stochastic Gradient Descent, KNN, Decision trees, Random Forest, Support Vector Machine, Logistic Regression, Neural Nets, Cross Gradient Booster, Cross Gradient Booster (Random Forest) and XGBoost. Accuracy gained by Naive Bayes is 51.95%, Stochastic Gradient Descent 65.53%, KNN 80.58%, Decision trees 63.997%, Random Forest is 81.41% , Support Vector Machine 75.41%, Logistic Regression 69.77%, Neural Nets 67.73%, Cross Gradient Booster 90.22%, Cross Gradient Booster (Random Forest) 74.87%.Finally, XGBoost is the best performed machine learning with accuracy of 90.22%. This research outcomes will help to analyse music in different areas.
Lora Khaula Amifia, Nuansa Dipa Bismoko, Philip Tobianto Daely
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 412-422; https://doi.org/10.26555/jiteki.v7i3.22199

The battery is the main component both as an energy provider and as an interface for several systems in an electric vehicle. It has three important parameters: current, voltage, and temperature that must be maintained as the battery can have a harmful reaction that can lead to overcurrent. The battery must also not overcharging or discharging for too long because it can cause damage and affect its lifetime. Another error that can arise is sensor failure due to the interference or noise that can cause an error in data reading. To prevent this problem, it needs protection by means of isolation in operating the battery. In this research, planning in optimizing battery work was conducted by designing the process of detection and isolation of faults that occurred in batteries, particularly lithium polymer battery to reach their more optimal and good performance. Battery modeling was needed as the parameter identification, and the Kalman Filter algorithm was applied to help to reduce the detection rate and fault isolation. The results of detection and isolation of overcurrent and sensor failure using Kalman Filter were found quite accurate. In overcurrent isolation, a discharge current of 6A was obtained from the maximum current limit of 10 A, and for sensor failure isolation, the Kalman Filter algorithm succeeded in improving the results of the previous reading.
Onno W. Purbo
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 453-460; https://doi.org/10.26555/jiteki.v7i3.22201

For more than ten years, SATU Indonesia Awards, with PT. Astra International Tbk's support is given to inspiring young Indonesians. Every year, more than 10,000 nominations must be short-listed to 90 nominations within one week with five (5) assessment parameters. The research contributions are (1) creating a machine learning mechanism for the awarding process from ten years of the SATU Indonesia Awards nomination archive, (2) creating two (2) models of training data for the five (5) assessed parameters, namely motivation, obstacle, outcome, outreach, and sustainability, and (3) compare machine learning prediction with 2021 judge's assessment. TEMPO Data and Analysis Center (PDAT) extracts the corpus training data from ten years' SATU Indonesia Awards data in six months. The corpus training data contains nomination texts with Judges' scores on motivation, obstacle, outcome, outreach, and sustainability. Two (2) corpus training data and two models were generated with, namely, (1) the average Judges' parameter value per instance and (2) the Judges' smallest value and stored in two (2) corpus of 1220 instances each. The classification model was generated by Random Forest, which has the slightest error among the classification algorithms tested. The first model aims to predict the nomination assessment parameters. The second model is to detect the outlier in the incoming nominees for extraordinary nominees. The machine learning predictions were compared and found to be similar to the 2021 judge's assessment in the awarding processes at SATU Indonesia Awards. The average Judges' pre-final 2021 nominees' scores are compared to the Random Forest's predictions and found to be reasonably similar, with a small RMSE error around 1.1 to 1.6 for all assessment parameters. The smallest RMSE was obtained in the Sustainability parameter. The Obstacle parameter was found to have the largest RMSE.
Mostefa Kara, Abdelkader Laouid, Muath AlShaikh, Ahcène Bounceur, Mohammad Hammoudeh
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 380-387; https://doi.org/10.26555/jiteki.v7i3.22210

One of the most famous key exchange protocols is Diffie-Hellman Protocol (DHP) which is a widely used technique on which key exchange systems around the world depend. This protocol is simple and uncomplicated, and its robustness is based on the Discrete Logarithm Problem (DLP). Despite this, he is considered weak against the man-in-the-middle attack. This article presents a completely different version of the DHP protocol. The proposed version is based on two verification stages. In the first step, we check if the pseudo-random value α that Alice sends to Bob has been manipulated! In the second step, we make sure that the random value β that Bob sends to Alice is not manipulated. The man-in-the-middle attacker Eve can impersonate neither Alice nor Bob, manipulate their exchanged values, or discover the secret encryption key.
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Volume 7, pp 479-490; https://doi.org/10.26555/jiteki.v7i3.22012

Every human being faces various episodes of events that can cause changes in mental health conditions, including this coronavirus pandemic disease. The ups and downs of the psychological turmoil dynamics resulted, and also traumatic feelings can occur continuously or for a certain period. It can cause an adverse response for those who experience it and even cause anxiety or mental disorders. The implementation of restrictions on community activities during these pandemic circumstances makes people who want to check their mental health condition difficult to meet the experts or professionals such as psychologists. Therefore, the application that can detect these anxiety disorders as early as possible to minimize unwanted effects was developed. In the making of the application, an expert system is used to determine the results of the diagnosis. The expert system requires knowledge that is produced from experts, especially in the psychology field. The data that has been obtained will be processed and then yield the results determined from the classification of anxiety types using several methods in Artificial Intelligence. Several tests were carried out 50 times using Certainty Factor methods to obtain an accuracy rate of 96%. It has similar accuracy compared to the Naïve Bayes method. This application called Mental Health Helper has a validity and reliability test to prove that this application is valid and reliable. It has better performance than previous researches, which still only has two classes of diseases.
Back to Top Top