Jurnal ELTIKOM
Not a member yet
154 research outputs found
Sort by
Analysis of Digital Television Signal Reception in Combined Transmitter Antenna Systems
Full text linkThe Indonesian broadcasting sector has undergone significant transformation with the implementation of the Analogue Switch Off (ASO) program. By July 2023, approximately 97.23% of television stations in Indonesia had migrated to digital broadcasting. However, this figure does not reflect an equitable distribution of normal broadcasts. Data from Transmission Station X indicate that 6.77% of broadcasts are blank, 12.24% experience freezing, and only 80.99% are classified as normal for channel X in the Jabodetabek region. These statistics suggest that the primary objective of the ASO program—providing an enhanced television viewing experience—has not yet been universally achieved. Therefore, efforts are required to ensure the equitable distribution of normal broadcasts. Transitioning from a lower transmitter antenna system to a combined transmitter antenna system is proposed as a potential solution. This study evaluates the Modulation Error Ratio (MER) values in the Jabodetabek region when channel X uses a combined transmitter antenna system. Measurements, conducted using the drive test method, reveal that 99.703% of MER data are above the threshold (normal broadcasts), 0.042% are at the threshold (freeze broadcasts), and 0.255% are below the threshold (blank broadcasts). These results demonstrate that adopting a combined transmitter antenna system can help address the uneven distribution of normal broadcasts in the Jabodetabek region
Enhancing Power Transformer Oil Quality Weight Factor using A Genetic Algorithm
Full text linkPower transformers are critical to electrical power systems but are prone to failures due to factors such as heat, electricity, chemical reactions, mechanical stress, and adverse environmental conditions. Moni-toring the insulating oil effectively is key to preventing these failures. A major challenge in this process is determining the optimal weights for the oil quality index, which lacks a standardized benchmark and often relies on subjective expert assessments. To reduce expert bias and subjectivity, this research utilizes a genetic algorithm to optimize the weightings for five essential parameters: color, water content, break-down voltage (BDV), interfacial tension (IFT), and acidity. The algorithm operates through three stages: crossover, mutation, and selection, and analyzes data from 504 oil tests across various transformers. The mean absolute percentage error (MAPE) is used as the fitness value to assess the algorithm\u27s effective-ness. The optimization process determined the best conditions as 132 iterations, a population size of 180, a crossover rate of 0.2, and a mutation rate of 0.8. These parameters achieved an average MAPE of 1.799% over ten trials, indicating high accuracy. This research not only optimizes the weighting of the oil quality index but also significantly reduces the need for expert input and subjective judgments in trans-former maintenance. The findings are expected to improve the efficiency and reliability of power trans-formers, thereby minimizing failures and associated economic costs
Optimizing Goods Placement in Logistics Transportation using Machine Learning Algorithms based on Delivery Data
Full text linkThis study addresses the challenge of predicting the optimal placement of goods for expeditionary transportation. Efficient placement is crucial to ensure that goods are transported in a manner that maximizes space and minimizes the risk of damage. This study aims to develop a prediction system using the K-Nearest Neighbor (KNN) method, which is based on expert data from expedition vehicles. To evaluate the effectiveness of the KNN method, the researcher compared it with the Support Vector Machine (SVM) method. By doing so, they sought to determine which method delivers more accurate predictions for the optimal placement of goods. The test results revealed that the KNN method outperformed SVM, achieving a higher accuracy of 95.97% compared to SVM\u27s 92.85%. Additionally, KNN demonstrated a lower Root Mean Square Error (RMSE) of 0.18, indicating more precise predictions, while SVM had an RMSE of 0.271. These findings suggest that KNN is the more effective method for predicting the optimal placement of goods in expeditionary transportation
Heart Sound Processing for Early Diagnostic of Heart Abnormalities using Support Vector Machine
Full text linkThis paper addresses the critical issue of cardiovascular disease (CVD), the leading cause of global mortality, emphasizing the imperative for effective and early detection to mitigate CVD-related deaths. The research problem underscores the urgency of developing advanced diagnostic tools to identify heart abnormalities promptly. The primary objective is to create a Support Vector Machine (SVM) algorithm for accurate classification of different heart conditions, namely Normal heart, Mitral Stenosis, and Mitral Regurgitation. To achieve this objective, the study utilizes a dataset of heart sounds available online using a 10-fold cross-validation method. The focus is on evaluating the efficacy of various kernel functions within the SVM framework for heart sound classification. The findings demonstrate that the linear kernel exhibits superior accuracy and robustness in effectively classifying heart conditions. Notably, the proposed classification method attains an impressive 96% accuracy, highlighting its potential as a reliable tool for early detection of cardiovascular diseases. This research contributes to the ongoing efforts to enhance diagnostic capabilities and ultimately reduce the global burden of CVD-related fatalities
Range and Velocity Resolution of Linear- Frequency-Modulated Signals on Subarray-Mimo Radar
Full text linkThe most important radar system performance is determining the range-velocity of the detected target. This performance is obtained from processing an ambiguity-function (AF) between signals from target reflections and radar radiation signals. Selection of the appropriate waveform transmitted by the radar is a key factor in supporting high resolution radar performance in the AF. There are many waveforms that have been studied in radar systems, especially for multi-antenna radars, i.e., subarray-MIMO (SMIMO) radar which can form phased array (PA) and MIMO radars simultaneously, in the form of linear-frequency-modulated (LFM) signals. In this paper, we examine the use of LFM waveforms combined with SMIMO radar to produce plots of three-dimensional AF as a function of time delay and Doppler shift. The results of the comparison with the Hadamard signal determine the effectiveness of the observed AF performance on parameters such as magnitude, range-velocity resolution, peak sidelobe level ratio, and integrated sidelobe ratio by taking into account the factors of the number of Tx antennas on the PA radar and the number of Tx subarrays on the MIMO radar. The evaluation results of the SMIMO radar configuration (M = 6) with the number of Tx-Rx antenna elements the being 8 provide the best mainlobe magnitude, sidelobe magnitude, range resolution, velocity resolution, PSLR, and ISLR of AF LFM signals compared to conventional radars are 235.2dB, 7.54dB, 37.5m, 75km/s, 29.89dB, and 29.8dB, respectively. Meanwhile, the LFM signal is far superior to the Hadamard signal which has PSLR and ISLR 1.16dB and -3.36dB, respectively
Application of Faster R-CNN Deep Learning Method for Rice Plant Disease Detection
Full text linkPlant diseases, particularly in staple crops like rice, significantly affect the stability of rice production in Indonesia. Crop failure caused by rice plant diseases present a critical challenge for farmers. Early diagnosis is crucial for preventing and managing rice diseases, as it facilitates more effective preventive measures, reduces yield losses, and boosts overall agricultural production. This study aims to apply the Faster Region Convolutional Neural Network (Faster R-CNN), a deep learning approach, to detect rice plant diseases. The Grid Search method was employed as a hyperparameter tuning technique to identify the optimal parameter combination for enhancing algorithm performance. Experimental results demonstrate the model\u27s performance, achieving an accuracy rate of 88%, recall and precision of 100%, and an F1 Score of 93%. These findings indicate that the Faster R-CNN method effectively recognizes and classifies rice plant diseases with a high degree of accuracy
Disease Detection in Tropical Tomato Leaves via Machine Learning Models
Full text linkThis study addresses the significant threat of tomato diseases to production in Ghana, which has led to substantial yield and quality losses, adversely affecting the livelihoods of local farmers and the availability of this essential dietary staple. Traditional disease identification methods are time-consuming and rely on subjective visual inspections, hindering early detection and control. This study develops a machine learning model capable of accurately identifying tomato plant diseases through image processing. The methodology involves processing a dataset of tomato plant images displaying healthy and diseased symptoms. The proposed model employs the YOLOv5 architecture and is deployed on a mobile platform for accessible disease identification. The model achieved a validation [email protected] of 0.715, demonstrating strong performance during live, on-site testing. This system provides a swift, accurate, and automated solution for detecting tomato diseases, supporting the sustainability of tomato production in Ghana
Design of A Cataract Detection System based on The Convolutional Neural Network
Full text linkCataract, a condition characterized by clouding of the eye\u27s lens, leads to decreased vision and potentially blindness. In Indonesia, it is the predominant cause of blindness, accounting for 81.2% of cases. Given the rising life expectancy, the incidence of degenerative diseases like cataracts is expected to increase. This research aims to develop a cataract detection system capable of classifying eye images as either indicative of cataracts or normal. Utilizing Convolutional Neural Networks (CNN) and RGB-based image processing—including edge detection techniques such as Canny and Prewitt—the system identifies eye contours. This facilitates image segmentation to ascertain the eye\u27s condition. Therefore, image collection and processing models play a crucial role in this study. The research findings indicate that the system functions effectively, with a 98% success rate in accurately processing normal eye images through the CNN model without detecting cataracts. When tested using grayscale imaging, cataract-afflicted eyes—characterized by red spots in the images—were also successfully identified by the CNN model. These test results demonstrate that the designed cataract detection system can accurately classify images into normal or cataract-afflicted eyes with high precision. This system shows promise for use in early cataract detection, potentially helping to reduce the prevalence of cataract-related blindness in Indonesia
Design of A Thermoelectric Generator for Battery Charging using Heat from A Steam Iron Base
Full text linkThis study explores an alternative method of generating electrical energy using a thermoelectric generator that utilizes heat from the soleplate of a steam iron and six thermoelectric units connected in series. Based on the Seebeck effect, the thermoelectric modules convert the temperature difference into voltage. An increase in the heat source temperature leads to higher voltage production by the series-connected thermoelectric modules, although the electrical power output depends on the connected load. The power generator design includes thermoelectric modules, a buck-boost converter, an 18650 lithium-ion battery, and a 5-watt, 12-volt DC lamp. The study addresses key aspects such as the impact of temperature on power output in series-connected and parallel-connected thermoelectric circuits, and the efficient conversion of heat from the steam iron soleplate into electrical energy. The research objectives are threefold: to determine power and temperature values for series-connected thermoelectric circuits, to evaluate power and temperature values for parallel-connected thermoelectric circuits, and to utilize heat from the steam iron soleplate as a thermoelectric heat source for generating electrical energy. Testing involved a buck-boost converter connected to a battery, producing 12.35 volts with a temperature difference of 49°C. Design enhancements, such as integrating heatsinks or coolers on the cold side of the modules to maintain a significant temperature differential, are critical for optimizing performance
Design and Implementation of A Dual-Axis Solar Tracking System using Arduino Uno Microcontroller
Full text linkThis paper presents a dual-axis solar tracking system developed and evaluated using LDR sensors and stepper motors, controlled by an Arduino Uno microcontroller. The aim was to enhance photovoltaic energy efficiency by designing a system capable of automatically adjusting the position of solar panels to follow the sun\u27s movement throughout the day. Comparative testing between static solar panels and those equipped with solar trackers demonstrated that the latter produced 35% more power on average. Additionally, the dual tracking system showed a 14% improvement in efficiency over previous averages noted in existing references. Analysis of azimuth and elevation angles confirmed that the solar tracker accurately adjusted the panels\u27 position, significantly boosting solar energy capture. This finding is consistent with prior research, which also supports the efficacy of solar trackers in enhancing photovoltaic efficiency. Future research should expand testing to include various weather and environmental conditions and focus on developing more advanced control algorithms to enhance system responsiveness. Continuous advancements in solar tracking technology are vital for maximizing solar energy potential and facilitating a transition to a more sustainable society