Jurnal Rekayasa Elektrika
Not a member yet
345 research outputs found
Sort by
Robot Beroda Pendeteksi Gas Karbon Monoksida dan Metana Berbasis IoT Menggunakan Metode Finite State Machine dan Fuzzy Logic
Full text linkOccupational Safety and Health (K3) is an important requirement needed in mining. This is because activities in mining have great risks and are associated with unpredictable natural conditions. One of them is the leakage of hazardous gas at the mine site caused by mining activities. This article proposes a wheeled robot to detect carbon monoxide gas and methane gas based on the Internet of Things (IoT) using Finite State Machine (FSM) and Fuzzy Logic. The finite state machine (FSM) in this study is used as a control of the robots movement, while fuzzy logic is used as a safety classification of the readable state of dangerous gases. The results showed that the system was capable of detecting gas and the information is successfully sent to a web server. In addition, the use of lidar can detect obstacles around the robot
Web-based Water Quality Parameter Monitoring for Bok Coy Hydroponics using Multi Sensors
Full text linkThe hydroponic planting method is one solution for supplying vegetable needs where agricultural land is limited. Hydroponics allows the growing of vegetables in stages in a limited area by utilizing water as a growing medium. Water quality greatly determines plant fertility, so monitoring must be carried out regularly. Currently, the agricultural sector in Sukabumi has a large potential for the economy of the community. Farmers develop hydroponic farming but monitoring of water quality is still done traditionally. Therefore, in this study, a water quality monitoring system is proposed including pH, turbidity, and temperature. Another parameter that is observed is the water level in the reservoir which is useful for maintaining water circulation. This system works online through the internet network, both the sensing process, data transmission, and data display using the Internet of Things (IoT) platform. The measured parameters can be observed via a web application. Performance evaluation of sensor devices is carried out by comparing the measurement values of standard devices. The test results on the system that has been implemented show that the system has high accuracy, and all parameters are successfully displayed on the web page. The applied systems can increase the fertility of vegetables on hydroponic land so that it can improve the quality of production
Simulasi Sistem PLTS Atap dan Harga Satuan Energi Listrik Untuk Skala Rumah Tangga di Surabaya
Full text linkSolar energy is a renewable energy source that can be used as a source of electricity using a photovoltaic (PV) system to reduce our dependence on fossil energy. This paper discusses an overview of the use of a rooftop PV system in accordance with applicable regulations in Indonesia. Computer simulation was conducted to determine the potential power and output energy of the rooftop PV system in the city of Surabaya. The simulation was carried out by SolarGIS Pvplanner software. Mathematical equations are derived to estimate the unit price of electric energy for the PV system, and the calculations are done numerically. The simulation results show that the total daily energy average generated from the 3 kWP roof solar PV system in Surabaya is about 13 kWh. Meanwhile, the unit price for PV system electricity is obtained between 0.08 USD - 0.11 USD / kWh
Rancang Bangun Driver PZT dan Filtering Data Akustik Pada Sonar Aktif
No full textAcoustic transducer is a source level component in the sonar equation that is indispensable as an underwater acoustic energy source, with a certain emission pattern called beamforming. In this research, we designed the construction of a driver circuit to trigger a piezoelectric (PZT) transducer to produce an acoustic energy beam for the purpose of detecting underwater targets. The manufacture of an acoustic driver with a simple working principle has been carried out to provide transmit (TX) and receive (RX) commands. The RX module will receive the acoustic signal from the TX and the results are recorded for analysis. The mixing of the information signal with noise makes the information obtained cannot be directly verified so that a signal processing process is needed to be able to separate the information signal and noise. Calibration using a spherical target was carried out to determine the detection results and the acoustic intensity level. Signal analysis and visualization methods use Fast Fourier Transform (FFT) and wavelets
Fine Tuning CNN Pre-trained Model Based on Thermal Imaging for Obesity Early Detection
Full text linkObesity is a complex disease that causes serious impact health, such as diabetes mellitus, cardiovascular disease, cancer, and stroke. An early obesity diagnosis/ detection method is required to prevent the increasing number of obese people.This study aims to: (i) fine-tune the pre-trained Convolutional Neural Network (CNN) models to build an early detection of obesity and (ii) evaluate the model performance in terms of classifying performance, computation speed, and learning performance. The thermal images acquisition procedure was conducted with 18 normal subjects and 15 obese subjects to build a thermal images dataset of obesity. Pre-trained CNN models: VGG19, MobileNet, ResNet152V, and DenseNet201 were modified and trained using the acquired dataset as the input. The training results show that the DenseNet201 model outperformed other models regarding classifying accuracy: 83.33 % and learning performances. At the same time, the MobileNet model outperformed other models in terms of computation speed with training elapsed time: 12 seconds/epoch. The proposed DenseNet201 model was suitable for implementation as an early screening system of obesity for health workers or physicians. Meanwhile, the proposed MobileNet model was suitable for mobile applications' early detection/diagnosis of obesity
Breast Cancer Detection in Mammography Image using Convolutional Neural Network
Full text linkBreast cancer is one of the non-contagious diseases that tends to increase every year. This disease occurs almost entirely in women, but can also occur in men. One way to detect this disease is by observing mammography images. However, mammography images often tend to be blurry with low quality so that it is possible to detect them incorrectly. Therefore, in this study, automatic classification of breast cancer on mammographic images was carried out using the Convolutional Neural Network (CNN). This proposed system uses the VGG16 architecture with a transfer learning system. The proposed system is then optimized using Adam optimizers and RMSprop optimizers. The results of system testing for normal, benign, and malignant classifications obtained an accuracy value of 80% - 90% with the highest accuracy achieved using Adam's optimizers. With this proposed system, it is hoped that it can help in the clinical diagnosis of breast cancer
Perbandingan Kinerja Algoritma Optimasi pada Metode Random Forest untuk Deteksi Kegagalan Jantung
Full text linkAbstrak Jantung merupakan salah satu organ terpenting dalam tubuh manusia. Kegagalan jantung pada pasien dapat mengakibatkan dampak yang vital dan berujung pada kematian. Adapun kegagalan jantung bukan hanya dipengaruhi oleh faktor usia, juga dipengaruhi komorbid dan pola hidup dari pasien. Berbagai upaya medis telah banyak dilakukan untuk mendeteksi kegagalan jantung yang mengharuskan pasien dirawat intensif di rumah sakit yang tentunya membuat pasien merasa kurang nyaman. Maka dari itu, dalam penelitian ini dirancang sebuah aplikasi machine learning untuk deteksi kegagalan jantung yang dapat mengklasifikasikan kondisi pasien ke arah kematian atau bertahan berdasarkan gejala-gejala yang dimiliki pasien. Adapun algoritma machine learning yang digunakan adalah random forest yang dioptimasi dengan tiga buah algoritma optimasi yaitu grid search, random search dan Bayesian search sebagai perbandingan. Kinerja ketiga algoritma optimasi kemudian diukur menggunakan akurasi, presisi dan recall. Ada 299 sampel pasien yang digunakan dalam penelitian ini. Hasil menunjukkan bahwa random forest dengan algoritma optimasi random search mencapai kinerja yang paling unggul dengan akurasi rata-rata sebesar 85,63 %, presisi rata-rata 87,38% dan recall 85,63%
Mangosteen Flesh Condition Detector Based on Microwave Non-destructive Technique Using Spiral Resonator Sensors
Full text linkThe mangosteen fruit has a characteristic thick skin, so it is difficult to know the condition of the flesh. Farmer can only know damage to the fruit flesh after the fruit skin had opened. Detection of the quality of the mangosteen flesh can be detected using a sensor capable of penetrating the thickness of the mangosteen rind. Flesh quality detection is carried out based on the S21 value (attenuation of mangosteen flesh value) using a portable device equipped with a sensor and capable of emitting microwaves. The S21 value of the fruit's flesh was measured using a spiral resonator that functioned as a sensor. The prototype device consists of an oscillator circuit, a power splitter, and a phase detector with 2507 MHz. Fruit flesh had divided into two conditions: damaged for fruit flesh with yellow sap or Translucent Flesh Disorder, and suitable condition for clean fruit flesh. The results showed that the fruit flesh had an average S21 value of 7.041 dB for damaged flesh and 6.007 dB for good flesh condition. The difference in the value of S21 had used as a reference for detecting the shape of the fruit flesh, with the detection threshold calculated by the Support Vector Machine, resulting in a threshold value of 6.712 dB
Handling Missing Value dengan Pendekatan Regresi pada Dataset Akuakultur Berukuran Kecil
Full text linkShrimp cultivation is strongly influenced by pond water quality conditions. Farmers must know the appropriate action in regulating water quality that is suitable for shrimp survival. The state of water quality can be understood by measuring pond parameters using various sensors. Installing sensors equipped with artificial intelligence modules to inform water quality conditions is the right action. However, the sensor cannot be separated from errors, so it results in not being able to get data or missing data. In this case, the approach of 5 parameters of pond water quality from 13 available parameters is carried out. This paper proposes a technique to obtain lost data caused by sensor error and looks for the best model. A simple approach can be taken, such as the Handling Missing Value (HMV), which is commonly used, namely the mean, with the K-Nearest Neighbors (KNN) classifier optimized using a grid search. However, the accuracy of this technique is still low, reaching 0.739 at 20-fold cross-validation. Calculations were carried out with other methods to further improve the prediction accuracy. It was found that Linear Regression (LR) can increase accuracy up to 0.757, which outperforms different approaches such as the statistical approach to mean 0.739, mode 0.716, median 0.734, and regression approach KNN 0.742, Lasso 0.751, Passive Aggressive Regressor (PAR) 0.737, Support Vector Regression (SVR) 0.739, Kernel Ridge (KR) 0.731, and Stochastic Gradient Descent (SGD) 0.734
Designing an Arduino Board-based Electronic Device Driven by GRBL Gru to Operate the Mini PCB Printing Machine
Full text linkA compact integrated circuit is an intellectual property core at the heart of the decades of embedded devices on embedded systems. Using a microcontroller-based electronic module manufactured as desired or direct service of the board of Arduino as a control system for many purposes has become a certainty. Defining the problem formulations is related to the manufacture, assembly of the mechanical apparatus, and integrated wiring of several electronic modules. The acquisition of research contributions is expected to get the miniature embodiment of the physical machine equipped with a user program and perform the machine driver. The research methods consist of several steps to carry out each research objective. The miniature embodiment is carried out through (i) manufacturing and assembling to obtain the physical machine, (ii) integrating the electronic modules and all components and support systems by wiring to form an embedded system as a mini-PCB printing machine, and (iii) making a program structure based on Arduino IDE. Performing the machine driving mechanism is operating tests of calibration and moving on the axes of X, Y, and Z. Concluding based on the implementation process, testing, and analysis are carried out that the stages for performing the Mini PCB Printing Machine assisted by Arduino board with driven by GRBL Gru can be realized according to the initial design of hardware and software design