Garuda - Garba Rujukan Digital

p-Index From 2020 - 2025

0.659

P-Index

This Author published in this journals

All Journal Indonesian Journal of Electronics and Instrumentation Systems IJCCS (Indonesian Journal of Computing and Cybernetics Systems)

Agus Harjoko

Departemen Ilmu Komputer dan Elektronika, FMIPA UGM, Yogyakarta

Author-ID : 2898875

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 11 Documents Claim Missing Document

Claim Missing Document

Articles

Title

Klasifikasi Bibit Sapi Peranakan Ongole Menggunakan Metode Pengolahan Citra Leylin Fatqiyah; Agus Harjoko
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 6, No 2 (2016): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Ongole Crossbreed cattle is the largest cattle in Indonesia. Indonesian consume it’s beef in a large amount. Classification effects beef’s quantity and quality. However, the classification process is measuring manually one by one all this time. Moreover the current standard is too high and inappropriate due to the real exist conditions. Seeing the importance of classification, it is necessary to make a system that is able to classify Ongole Crossbreed cattle stocker.This system will measure quantitative requirement parameters from the image. This system will classify using image processing. Implementation of the system is using Matlab software. This system will classify into four classes, namely class I, class II, class III, and external class III. According to the results, it is obtained that the system is able to measure the body lenght, the chest circumference, and the height with accuracy rates are 90,77%, 93,30% and 93,13%. This system is able to classify the class of Ongole Crossbreed cattle stocker with accuracy rate is 86,67%

Hybrid Power Method For Power Supply Of Public Service Computer Tri Wahyu Supardi; Agus Harjoko
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 8, No 2 (2018): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Public services require computer-based electricity supply. Not continuous electricity supply in some areas led to a power supply from an alternative power source becomes indispensable. One alternative power source is a solar cell. Solar cell is a sustainable source of electricity but power output is not constant depending on the sunlight. The power source is needed to anticipate the lack of power when the power generated by the solar cell is not enough.In this paper proposed a hybrid design that combines the power supply of electricity from the solar cell, the network provider of electricity, and batteries. This paper discusses methods of hybrid electric power from three sources. Hybrid power is usually done by PCC (Power Controlled Converter), which consists of a controlled power converter for each channel input, but in this study the method proposed hybrid power input specification in the form of a synchronization circuit PCC then replaced by a diode circuit.The design of hybrid power supply in this study resulted in the specification input from the solar cell with Vmp channels (maximum power voltage) 35VDC Voc (open circuit voltage) 43.78VDC, channels of electricity provider with the already converted with SMPS (Switched Mode Power Supply) to 35VDC, and channels of a battery with a minimum voltage of 21VDC maximum 27.6VDC. The test results showed that the implementation of the proposed hybrid method can perform a single capture or hybrid power, and can transfer power between the source retrieval without pause. Implementation of the proposed hybrid method has a 21VDC output voltage range - 43.78VDC and efficiency of 98.6% - 99.5%.

Penggunaan Deteksi Gerak untuk Pengurangan Ukuran Data Rekaman Video Kamera CCTV Jockie P Sagala; Ika Candradewi; Agus Harjoko
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 10, No 1 (2020): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Some cases the recording data of Closed Circuit Television (CCTV) is stored for future use. In the long term usage, the files size will grow larger and requiring large storage devices. In some cases, the recorded data not only image with the desired object but also the background images that may be recorded for long periods of time. This cases make data storage device usage to be less effective. So this research will design a system of CCTV devices that capable to select images to reduce the size of stored images data by image processing.The images selection of this system is based on based on adaptive median algorithm. When any object get detected, the images data to be saved is current input frame. Otherwise, the data to be saved is background model image. Background model on this system is adapted with the change visual data of background image.The results obtained from this research in the form of a CCTV system that are able to select recording data to be stored with image processing. The background model will be kept adapting with background visual data changes.

Otomasi Kamera Perangkap Menggunakan Deteksi Gerak dan Komputer Papan Tunggal Habib Dwi Cahya; Agus Harjoko
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 9, No 1 (2019): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

USB camera is currently used in daily life for various purposes. On its development, the use of USB camera can be used to create camara traps and can be used to observe the development of animal with integrated systems. In this research, motion detection was used to observe animals online using Single Board Computer (SBC) Camera trap in this research using Single Board camera in form of raspberry pi 3 B. Python proggramming language is used with OpenCV library. The method used to detect motion is the Mixture of Gaussian (MOG). The result image gained by motion detection will be uploaded to the dropbox API.The test performed on 11 videos, the system can process images with 320x240 resolution. The test results show the best blut value of k = 13, the best threshold value is 100 pixel with an accuracy of 80,3%, and the maximum distance system can detect animal objects as far as 6m. The response time gained for the sytem to process frame per second have average of 0,098 seconds, while for uploading image to dropbox han an average of 1,618 seconds. The test result show the system still has room for development and improvement.

Operasi Morfologi Dan Kode Rantai Untuk Menghitung Luas Area Basah Kertas Saring Nafiatun Sholihah; Agus Harjoko
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 11, No 1 (2021): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.46130

Calculation of wet areas carried out with the help of millimeter block paper has the disadvantage of copying the edges that are less precise and the calculation time is quite long. Another problem is the consistency and accuracy that is generated depends on the subjective factors of the person and one's fatigue. In order for the process to be faster and more consistent, the calculation process using image processing is very necessary. Image preprocessing includes cropping, grayscalling, lowpass filter averaging, convertion to binary image based on otsu thresholding, and complementing images to pixel objects of value 1. Segmentation with morphological operations, including opening operations to remove small objects around objects, Holes Filling operations to fill holes in objects, opening operations again to remove objects other than wet areas. The process of calculating wet areas uses chain code. Based on the results of testing of 81 images, the use of morphological operations is able to produce segmentation of wet areas that approach the original wet area. The scale value affects the accuracy and the best scale is obtained from the use of the ruler. The use of chain code is able to calculate the wet area on filter paper with an average accuracy of 95.73%, the value is higher than extensive use by summing the pixel value even though it is not significant. The average calculation of wet areas uses a system of about 0.8 seconds or 379 times faster than using millimeter block.

Klasifikasi Sel Darah Putih dan Sel Limfoblas Menggunakan Metode Multilayer Perceptron Backpropagation Apri Nur Liyantoko; Ika Candradewi; Agus Harjoko
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 9, No 2 (2019): October
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Leukemia is a type of cancer that is on white blood cell. This disease are characterized by abundance of abnormal white blood cell called lymphoblast in the bone marrow. Classification of blood cell types, calculation of the ratio of cell types and comparison with normal blood cells can be the subject of diagnosing this disease. The diagnostic process is carried out manually by hematologists through microscopic image. This method is likely to provide a subjective result and time-consuming.The application of digital image processing techniques and machine learning in the process of classifying white blood cells can provide more objective results. This research used thresholding method as segmentation and multilayer method of back propagation perceptron with variations in the extraction of textural features, geometry, and colors. The results of segmentation testing in this study amounted to 68.70%. Whereas the classification test shows that the combination of feature extraction of GLCM features, geometry features, and color features gives the best results. This test produces an accuration value 91.43%, precision value of 50.63%, sensitivity 56.67%, F1Score 51.95%, and specitifity 94.16%.

Klasifikasi Eritrosit Pada Thalasemia Minor Menggunakan Fitur Konvolusi dan Multi-Layer Perceptron Zuhrufun Nufusy Nugroho; Agus Harjoko; Muhammad Auzan
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 13, No 1 (2023): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.83473

Â 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.

Co-Authors Abriyono Abriyono Aina Musdholifah Apri Nur Liyantoko Habib Dwi Cahya Ika Candradewi Jockie P Sagala Leylin Fatqiyah Mudinillah, Adam Muhammad Auzan Nafiatun Sholihah Nelson Rumui Radhitya, Made Leo Tri Wahyu Supardi Zuhrufun Nufusy Nugroho

Title Search

Found 7 Documents Search Journal : Indonesian Journal of Electronics and Instrumentation Systems

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search
Journal : Indonesian Journal of Electronics and Instrumentation Systems