Jurnal Rekayasa Elektrika
Not a member yet
345 research outputs found
Sort by
Measurement of Ankle Brachial Index with Oscillometric Method for Early Detection of Peripheral Artery Disease
Full text linkPeripheral Arterial Disease (PAD) is a blood vessel disease caused by blockage or plaque accumulation around the artery walls. PAD is included in the category of diseases that are often diagnosed too late and affect more severe cases, such as the death of certain tissues or body parts. The Ankle Brachial Index (ABI) is an accurate non-invasive method for diagnosing PAD, in practice, ABI is usually performed in certain hospitals and is still difficult to find due to limited tools. Therefore, a tool is made that can detect the condition of a person's PAD based on the ABI value. The tool is made using two MPX5050GP sensors to detect oscillometric pulses, a DC pump and solenoid valve as an actuator to pump and deflate the cuff, ADS1115 as an external ADC to increase the accuracy of sensor readings, as well as an LCD and buzzer as tool indicators. The output is displayed in the form of a print out from a thermal printer, with an emergency stop that functions as a safety system to power off the supply when a failure occurs in the measurement process. Oscillometric method is used to detect systolic and diastolic pressure. The accuracy of the tool is 95.5%. This accuracy result is obtained by comparing the readings of systolic and diastolic values using a sphygmomanometer which is commonly used
Pengukuran Nilai Densitas pada Minyak Pelumas Sepeda Motor dengan Gelombang Ultrasonik
Full text linkDensity is a measure of the mass of each unit volume of an object, the higher the density of an object, the greater the mass of each volume. The density value can be used to distinguish the characteristics of lubricating oils that are prone to contamination with solid or liquid particles. The density value is also affected by changes in temperature, the higher the temperature of the lubricating oil, the smaller the density value. The regulations in force in Indonesia with the ASTM D1298-12b standard density test method state that the measurement uses a temperature of 15. In this study, the density measurement value was obtained at a temperature of 28 so it required a value conversion using the ASTM 53B table about the density correction factor. The technique of testing the material without damaging the test object using an ultrasonic sensor is used to measure the density value of motorcycle lubricating oil. Measurements are made by transmitting a 3 MHz ultrasonic trigger signal that can penetrate each medium with different characteristics. The received echo signal produces information about the distance between the medium, the speed of sound, and the acoustic impedance. The results of the measurement of 11 samples of motorcycle lubricating oil both in new and used conditions using the acoustic impedance method resulted in an accuracy of 93,6% or 0,058 kg/dm3 when compared to the value measured using a pycnometer. The MPX-2-C sample measurement showed the lowest error of 0,41% or 0,004 kg/dm3
Penerapan Algoritma HSV pada Autonomous Car untuk Sistem Self-Driving Berbasis Raspberry Pi 4
Full text linkPerkembangan teknologi di sektor transportasi di masa ini semakin krusial. Sehingga perusahaan berinovasi menciptakan mobil yang dapat berjalan sendiri dengan tingkat keamanan yang tinggi. Pada penelitian ini, kami merancang sistem self-driving untuk mobil RC skala 1:10 menggunakan komponen utama berupa Raspberry Pi 4 sebagai pengolahan citra untuk kendali otomatis pada autonomous car. Untuk mengatur pergerakan roda belakang dan steering menggunakan motor DC. Penelitian ini menerapkan computer vision yang dipakai untuk sistem navigasi agar dapat berjalan sesuai dengan lintasan. Permasalahan yang dijumpai pada penelitian sebelumnya adalah masih mengambil sampel lintasan terlebih dahulu yang dirasa kurang efisien karena pada jalan yang belum diambil sampelnya tidak dapat dilalui robot tersebut. Untuk memecahkan permasalahan ini maka peneliti menerapkan algoritma HSV agar dapat mengikuti lintasan secara real-time. Algoritma HSV(hue, saturation, value) merupakan sistem untuk mendeteksi tepi garis lintasan dengan memproses gambar dari kamera Raspberry Pi. Dari hasil kalibrasi nilai threshold yang digunakan adalah sebesar Hmin = 135 dan Hmax = 179, Smin = 70 dan Smax = 255, dan nilai V sebesar Vmin = 53 dan Vmax = 106 agar dapat mendeteksi jalur lintasan secara jelas, baik di dalam ruangan maupun diluar ruangan, dan HSV toleran terhadap perubahan intensitas cahaya. Itulah keuntungan dari algoritma HSV. Berdasarkan hasil pengujian dan implementasi robot ini dengan menggunakan kecerdasan buatan dapat bekerja sesuai dengan algoritma yang sudah dibuat dengan tingkat akurasi deteksi jalur yang cukup tinggi
Antena-Filter Hairpin dengan Peningkatan Perolehan untuk Aplikasi 5G
Full text linkAntena-filter mikrostrip merupakan gabungan antara antena dengan filter yang terintegrasi dan multifungsi. Sebagaimana antena mikrostrip lainnya, antena-filter mikrostrip memiliki kekurangan yaitu perolehan yang rendah dan lebar pita yang sempit. Untuk mengatasi perolehan yang rendah, maka penelitian ini mengusulkan penambahan Artificial Magnetic Conductor (AMC) yang diberi lapisan celah udara. Antena-filter terdiri dari sebuah radiator lingkaran yang diintegrasikan dengan dua buah resonator hairpin. Resonator terhubung dengan radiator secara langsung sedangkan antara resonator dengan pencatu 50-ohm terhubung secara kopel. AMC dengan struktur split ring resonator ditambahkan pada bagian atas antena dan diberi celah udara antara keduanya. AMC dirancang sebagai reflektor, fungsi reflektor ini menerima dan memantulkan gelombang ke radiator antena-filter sehingga dapat meningkatkan perolehan. Antena difabrikasi dan diukur dimana hasil pengukuran dengan penambahan AMC berhasil meningkatkan perolehan dari 6,4 dBi menjadi 13,88 dBi pada frekuensi 4,45 GHz. Selain peningkatan perolehan, AMC juga memperbesar lebar pita yang semula 105 MHz menjadi 125 MHz pada rentang frekuensi 3,99 - 4,525 GHz
Antenna MIMO 4 Elemen Untuk Komunikasi 5G pada Frekuensi 3.5 GHZ
No full textCellular communication technology is experiencing rapid development with the arrival of 5G. This generation targets an increase in data rates and better capacity than the previous generation. MIMO is a technique that can be used to improve the performance of 5G communications. The frequency used this time is the middle frequency because it is considered more likely to be used as a 5G service frequency in Indonesia and has a larger coverage so as to save network development costs. In this study, the design and realization of a four-element MIMO antenna for 5G communication at a frequency of 3.5 GHz was carried out. The antenna used this time is a four-element MIMO antenna that has a monopole-based patch form which is then miniaturized so that the antenna has smaller dimensions. This design produces parameters, such as Return Loss on element one of -10.513 dB, for element two of -10.215 dB, for element three of -17.229 dB, and for element four of -14 dB. The value of element one is 1.84, element two is 1.31, element three is 1.31, and element four is 1.49. Bandwidth value 1500 MHz, and Mutual Coupling value -19.254 dB
Seleksi Fitur dan Perbandingan Algoritma Klasifikasi untuk Prediksi Kelulusan Mahasiswa
Full text linkStudents are a major part of the life cycle of a university. The number of students graduating from a university often has a small ratio when compared to the number of students obtained in the same academic year. This small student graduation rate can be caused by several aspects, such as the many student activities accompanied by economic aspects, as well as other aspects. This makes it mandatory for a university to have a model that can take into account whether the student can graduate on time or not. One of the main factors that determine the reputation of a university is student graduation on time. The higher the level of new students at a university, with the same ratio, there must also be students who graduate on time. An increase in the number of student data and academic data occurs if many students do not graduate on time from all registered students. So that it will affect the image and reputation of the university which can later threaten the accreditation value of the university. To overcome this, we need a model that can predict student graduation so that it can be used as policy making later. The purpose of this study is to propose the best classification model by comparing the highest level of accuracy of several classification algorithms including Nave Bayes, Random Forest, Decision Tree, K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) to predict student graduation. In addition, the feature selection process is also used before the classification process to optimize the model. The use of feature selection in this model with the best features using 12 regular attribute features and 1 attribute as a label. It was found that the classification model using the Random Forest algorithm was chosen, with the highest accuracy value reaching 77.35% better than other algorithms
Substraksi Latar Menggunakan Nilai Mean Untuk Klasifikasi Kendaraan Bergerak Berbasis Deep Learning
No full textMoving object detection systems have been widely used in everyday life. Currently, research in the field of background subtraction is still being carried out to achieve maximum accuracy results. This study aims to model the background subtraction of an image using the mean value with the concept of non-overlapping block. Furthermore, the background abstraction results will be used in deep learning-based moving object detection. Specifically, the input image will be divided into several blocks, then the mean value of each block will be calculated to later produce a binary block (binary map). The binary blocks that have been generated will be used as input for background modeling. The background model aims to separate moving objects from the background in the input image. The resulting moving object (object localization) will be sent to the object classification stage using deep learning. The dataset used in this study is CDNet 2014. The results of the study were able to produce a more accurate moving object detection system. Quantitative tests carried out resulted in an accuracy of above 90%
Identifikasi Citra Kualitas Minyak Kelapa Sawit Berbasis Android Menggunakan Algoritma Convolutional Neural Network
Full text linkThe Central Statistics Agency reports that the average development of palm cooking oil consumption at the household level in Indonesia during the 2015-2020 period has increased by 2.32% per year. The use of cooking oil repeatedly is commonplace among the people of Indonesia and quite a lot. Even though the use of cooking oil can endanger health because the frying process at high temperatures can damage the chemical structure of the oil. Therefore, in this study, image processing was carried out to identify the quality of palm oil using the Convolutional Neural Network (CNN) algorithm. This research was conducted through several stages, namely dataset collection, dataset preprocessing, CNN algorithm implementation, testing, and development of information systems. The dataset consists of image data of palm cooking oil that has not been used, palm cooking oil used for frying twice, and palm cooking oil used for frying more than twice. The total amount of data is 3000 image data. Distribution of training data and test data using the Pareto division of 80:20. Based on the test, the best accuracy is 97.08%. This research produces an android-based information system that can identify the quality of cooking oil based on the classification
Perancangan Automated Guided Vehicle Menggunakan Penggerak Motor DC dan Motor Servo Berbasis Raspberry Pi 4
Full text linkThe influence of the industrial revolution 4.0 resulted in very significant changes. Many companies compete to produce robots that facilitate human work, in terms of energy and time in the process of producing goods. One of the robots being developed is the Automated Guided Vehicle (AGV), a vehicle with automatic control. AGV has high accuracy, easy maintenance, and a long operating time. This study discusses the design and implementation of AGV using 2 motors. The front motor using a servo motor is used for steering to turn right and turn left, while the rear motor in the form of a DC motor is used to regulate the speed of the AGV. The AGV movement system is controlled by computer vision. The AGV problem encountered is that the camera reading distance is close, which makes it less efficient in industrial use. This problem can be solved with a camera connected to a raspberry pi capable of capturing text and images from a distance of 100 cm. The use of computer vision makes the AGV robot easy to move. In this study, the accuracy of the movement of the AGV robot to the trajectory pattern has an average angle difference of 3.09. The difference in the angle indicates a small error so that the AGV can operate optimally. Infield applications, this AGV is used in the manufacturing industry to move goods. Therefore, the use of AGV is needed because it has high accuracy and small error
Automation Storage System Based On SCADA Using PLC CP1H and CP1L
Full text linkThe warehousing system is a means of supporting production activities and industrial operations that function to store goods to be distributed, which are still using a manual system and must adapt to technological developments. The problem that often arises in the warehousing system that is still done manually is that the flow of goods into the warehouse is not well organized, and this makes it difficult when the goods are about to be removed, so it requires a longer search time. Previous research has shown actual data on storage racks that use Arduino Mega as a controller and VB as an interface, but there is no actual data on the state of the lifter or the selection of lifter movement speed modes to facilitate operators in monitoring and operating goods storage. Control systems with industry standards greatly affect the effectiveness and optimization of the production process. Based on these problems, this research aims to simplify the managerial and monitoring process in the warehouse with a prototype of automatic multilevel storage using PLC CP1H and CP1L as system control and Wonderware Intouch as an interface with the SCADA system. The prototype has 12 cells, and each cell can accommodate 2 boxes; each cell is distinguished by the height and color of the box. In testing this research, the SCADA system can work optimally. The interface is capable of displaying the actual data of the rack with a success rate of 100%, the hardware error rate is less than 1%, and the interface can display the actual data on the state of the lifter