IJEIS (Indonesian Journal of Electronics and Instrumentation Systems)
Not a member yet
300 research outputs found
Sort by
Rancang Bangun Tempat Sampah Pintar untuk Meningkatkan Manajemen Sampah Berbasis Mikrokontroler
Full text linkSampah merupakan masalah yang sering dihadapi olah warga Indonesia terutama dalam melakukan pengelolahan sampah, sampah yang tidak dikelolah dengan baik akan menyebabkan mudahnya penyebaran penyakit dan tempat yang bau serta kotor. Pada penelitian ini dibuat sebuah alat untuk mengatasi masalah tersebut yaitu tempat sampah pintar berbasis Arduino uno sebagai mikrokontroler dan sensor proximity dan infrared sebagai pemilah sampah. Tempat sampah pintar ini berguna untuk memilah sampah sesuai dengan jenisnya yaitu dibagi dalam 3 jenis, dimulai dengan sampah logam, sampah organik dan sampah non-organik. Metode yang digunakan dalam melakukan penelitian ini yaitu metode sekunder atau dengan mencari refrensi seperti jurnal maupun buku-buku. Sedangkan metode dalam melakukan pengumpulan data yaitu menggunakan metode SDLC (System Development Live Cycle) yang dimulai dari planing hingga maintance. Alat tempat sampah pintar ini dilakukan 30 kali pengujian dan memiliki status berhasil semua, dengan dilakukan 10 kali pengujian sampah jenis logam, 10 kali pengujian sampah jenis organic dan 10 kali sampah jenis non-organik. Pengujian dilakukan guna untuk mengetahui alat berjalan sesuai dengan yang diinginkan
Klasifikasi Eritrosit Pada Thalasemia Minor Menggunakan Fitur Konvolusi dan Multi-Layer Perceptron
Full text link Thalassemia blood disorder is a condition that can affect the blood's ability to function normally and can lead to erythropoiesis. In this blood disorder, there are nine types of abnormal erythrocytes, namely elliptocytes, pencils, teardrops, acanthocytes, stomatocytes, targets, spherocytes, hypochromic and normal. At present, thalassemia examination is carried out using Hb electrophoresis and is done manually so it will be subjective and take a long time. Therefore, this research implements the Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) algorithms. This study aims to determine the performance of convolution features as image feature extraction and MLP as an image classification method and then implemented on NVIDIA Jetson Nano. The convolution features used in this study apply the CNN VGG16 architecture. Then model learning is carried out on 7245 data by configuring hyperparameters. The best accuracy with the hyperparameter configuration is a batch that is 16, the epoch is 400, the learning rate is 0.0001, the dropout1 layer is 0.1 and the dropout2 layer is 0.1. From this configuration it produces optimal accuracy at 96.175%. In the following, the model that has been made is then implemented on the NVIDIA Jetson Nano as a mobile media to be applied to the medical world resulting in an average prediction speed for each class of 48.330 seconds. The obtained performance time and accuracy are suitable for use by medical personnel to predict the class of abnormal erythrocytes
SCADA Sistem Pengisian dan Pengepakan Kemasan Multigrain Rice Berisi 2-3 Macam Biji-bijian
Full text linkThe process of packing food products manually raises many problems, including inefficiency, quality of hygiene, changing the composition according to market demand, and monitoring, that are difficult to do remotely in real-time. This research builds SCADA for filling and packing Multi-grain rice packages containing 2-3 kinds of grains.The composition of the grain be filled in the package through the HMI. The conveyor moves to carry the packing bags and stops at each grain container. The rotary vane feeder of the container will rotate so that the packaging bag will be filled with grains and then glued together. The position of the packaging bag is detected by 3 pairs of photosensors. The actuator control uses a Schneider M221 PLC via ethernet port. The communication system between the I/O devices and the PLC uses a cable, while the communication between the PLC and the HMI is via the internet network.The system is capable of filling the material according to the desired composition, sealing, and packing to the number of packages. HMI feeds composition input to the system, displays animations correctly, raises an alarm when the material in the tub is running low, and record production as a daily report
Implementasi Sistem Kendali Keseimbangan Statis Pada Robot Quadruped Menggunakan Reinforcement Learning
Full text linkThe basic thing to consider when building a quadruped robot is the issue of balance. These factors greatly determine the success of the quadruped robot in carrying out movements such as stabilizing the body on an inclined plane, walking movements and others. Conventional feedback control methods by performing mathematical modeling can be used to balance the robot. However, this method still has weaknesses. The application of conventional feedback control methods often results in an inaccurate controller, so it must be manually tuned for its application. In this study, reinforcement learning methods were used using Q-Learning algorithms. The use of reinforcement learning methods was chosen because no mathematical calculations are needed to control the balance of quadruped robots. The process of learning the system to train the agent's abilities is carried out using a Gazebo simulator. The learning results show that the system could run well as evidenced by the higher value of sum rewards per episode
Deteksi Onset Gamelan Bebasis DWPT dan BLSTM
Full text linkGamelan consists of various kinds of instruments that have different characteristics. Each has characteristics in terms of the basic frequency, amplitude, signal envelope, and different ways of playing it, resulting in differences in the sustain power of the signal. These characteristics cause the problem of vanishing gradient in the Elman Network model which was used in previous studies in studying the onset detection in the Saron instrument signal which has an average interval of more than 0.6 seconds. This study uses BLSTM (Bidirectional Long Short Term Memory) as a model for training and Wavelet Packet Transformation to design a psychoacoustic critical bandwidth as a model for feature extraction. For the peak picking method, this study uses a fixed threshold method with a value of 0.25. The use of the BLSTM model supported by the Wavelet Packet Transform is expected to overcome the vanishing gradient that exists in a simple RNN architecture. The model was tested based on 3 evaluation parameters, namely precision, recall and F-Measure. Based on the test scenario carried out, the model can overcome the vanishing gradient problem on the Saron instrument which has an average interval between onset of 600 ms. Out of a total of 428 onsets on the Saron instrument, the model successfully detected 426 correctly, with 4 incorrectly detected onsets and 2 undetected onsets. A thorough evaluation for each of the precision, recall, and F1-Measure algorithms obtained 0.975, 0.945 and 0.960
SISTEM KENDALI JALAN ROBOT HUMANOID PADA BIDANG TIDAK RATA MENGGUNAKAN LQR
Full text linkAbstrakPengembangan robot humanoid memiliki keunggulan yaitu mobilisasi di lingkungan manusia yang baik karena strukturnya yang mirip manusia. Robot humanoid harus mampu berjalan seimbang pada bidang yang tidak rata. Bidang yang tidak rata menyebabkan adanya perubahan pola berjalan pada robot dan menybabkan robot terjatuh. Berbagai penelitian mengemukakan bahwa robot humanoid akan stabil berjalan ketika COM atau ZMP dari robot tetap berada di area telapak kaki. Kondisi tersebut dapat diwujudkan dengan menanamkan sistem kendali pada robot humanoid.Berbagai penelitian telah dilakukan untuk mendesain sistem kendali untuk robot humanoid ketika berjalan. Kendali LQR dan strategi pengenalan bidang dapat digunakan untuk menstabilkan robot humanoid namun terbatas pada permukaan bidan tertentu dan respon sistem yang tidak konsisten. Pada setiap variasi bentuk bidang jalan, robot akan memerlukan perlakuan yang berbeda.Pada penelitian ini akan dirancang kendali LQR dan strategi pengenalan bidang jalan untuk robot humanoid ketika berjalan pada bidang tidak rata. Metode LQR dipilih karena performa yang robust. Metode ini diharapkan dapat memberikan kemampuan robot humanoid untuk mengubah nilai umpan balik sistem kendali sesuai dengan keadaan robot sehingga robot dapat berjalan pada bidang tidak rata tanpa terjatuh
Implementasi Kontrol Nutrisi Dan pH Pada Hidroponik Cerdas Berbasis Arduino Dan JST
Full text linkThis research aims to implement an automated nutrition and pH control system in NFT hydroponic system based on ANN control. NFT hydroponics involves growing plants without soil as a medium. In hydroponics, it is essential to continuously control the nutrient levels and pH of the solution. However, manual control performed by humans continuously is inefficient and time-consuming.The ANN method is used to model and predict the output actuators based on sensor input in the NFT hydroponic system. This ANN architecture consists of several layers with the following number of neurons: input layer 2, first hidden layer 128, second hidden layer 64, and output layer 3, representing multipleoutputs. The ANN training process involves classifying the data samples using various hyperparameters.The research findings demonstrate the ANN classification model successfully applied to control pH and nutrient levels through the predicted output actuators. The pump actuators are activated according to input received from the TDS and pH sensors. Through the variation of hyperparameters, the classification model with a test_size: 0.3, epoch: 400, batch_size: 32, and random_state: 42 provided the best performance in prediction. This ANN classification model achieved the best results in model testing with an accuracy rate: 97.96% from 49 data
Utilization of Sensor technology as a Sport Technology Innovation in Athlete Performance Measurement: Research Trends
Full text linkThe Industrial Revolution 4.0 has led to rapid technological advancements in sports technology, aiming to improve athlete performance and monitor developments. These innovations have had an impact on the sports industry, but have only been felt in developed countries. Existing studies on entrepreneurship, extended reality, e-textiles, and inertial movement units (IMU) have explored various aspects of sports technology. However, no review has focused on sensor technology's use in sports performance. This study bibliometrically evaluates sports technology research from 2008 through 2023, identifying trends in growth, notable publications, top authors, journals, institutions, and nations. The results give readers and researchers new information about the development and growth of sports sensor technology subjects as well as about active and potential research areas. China is the most productive country, contributing 17 publications related to sports technology, while the United Kingdom is the most impactful country with 474 citations
Perancangan dan Pembuatan Data Acquisition Device Sebagai Sistem Akuisisi Data untuk Kendali Mobil Formula Student
Full text linkData Acquisition Device (DAQ) is an electronic component used in formula student vehicles. To optimize the performance of the formula student vehicle and its driver, it is necessary to analyze and monitor the data acquisition system. Parameters acquired on the car include the position of the brake pedal/throttole and wheel speed.DAQ system has 5 input channels namely 3 analog input pins and 2 digital input pins, and 3 output channels, which is the controller pin, fault pin, and brake light pin. The DAQ system in this research is designed and made using Teensy 3.6, a signal conditioning circuit consisting of an RC low pass filter, voltage follower, non-inverting amplifier, and logic level shifter. DAQ system uses CANBUS to read and process sensor data. DAQ system can acquire data from the KTC Linear Motion Position sensor PZ-12-A-50P with an accuracy value of 99,91%; Hall-effect Rotary Position sensor RTY120LVNAX with an accuracy value of 99,94% for both the first and second sensors; and Proximity sensor LJ12A3-4-Z/BX with an accuracy value of 99,58% for the first sensor and 99,46% for the second sensor. DAQ is able to run controller signal processing, detect faults, and activate brake light signal according to FSAE rules
Pemilah Jenis Daun Mangga Melalui Deteksi RGB Menggunakan Sistem Pengolahan Citra
Full text linkKeterbatasan akan pemahaman tentang kesehatan pada tumbuhan dan kurangnya proses pemantauan akan penyakit yang ditimbulkan membuat para petani buah mangga sering mengalami kegagalan produk buah mangga, sehingga pemilahan jenis warna daun muda dan tua pada mangga menjadi salah satu hal yang penting untuk diketahui karena dapat membantu untuk mengevaluasi kesehatan pohon mangga secara keseluruhan, juga mengingat karena warna dasar daun yang relatif sama sehingga sulit bagi petani membedakan penggolongan warna muda atau tua. dengan metode pengolahan citra, yang dideteksi menjadi nilai RGB dan ditampilkan secara real time akan mempermudah proses pembuatan alat penelitian. sehingga dihasilkan nilai acuan warna hijau mangga dengan average daun tua yakni 62,2 dan daun muda yakni 113,67