Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal Jurnal Buana Informatika Jurnal Teknologi Informasi dan Ilmu Komputer IJID (International Journal on Informatics for Development)
Mustafid, Ahmad
Unknown Affiliation
Computer Science & IT Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Segmentasi Citra Sapi Berbasis Deteksi Tepi Menggunakan Algoritma Canny Edge Detection Mustafid, Ahmad; 'Uyun, Shofwatul
Jurnal Buana Informatika Vol 8, No 1 (2017): Jurnal Buana Informatika Volume 8 Nomor 1 Januari 2017
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v8i1.1074

Abstract

Abstract. The determination of the cattle price is generally agreed through bargaining, it is not based on the weight of the cows being sold. Most people mainly use rough calculation. There are formulas to calculate the weight but they require perimeter information of chest size and body length. It is necessary to measure the cow manually, but in reality it is not easy to do because the cow is difficult to control. Therefore, it requires a tool that can help measure easily. This article represents the early stages of research to determine the weight of cows from the cow image acquisition. It focuses on segmentation and image processing. The image acquisition results are processed using five scenarios. The results of the evaluation show that scenario 3 (Median Blur and Canny) has the best result with the value of 230,051 MSE and 24,524 dB PSNR.Keywords: Edge Detection, Canny, Segmentation, Cow, Image Processing Abstrak. Penentuan harga sapi umumnya disepakati melalui tawar menawar bukan didasarkan pada bobot sapi yang dijual. Kebanyakan menggunakan perhitungan secara kasar maupun secara kira-kira. Terdapat rumus untuk menghitung bobot sapi, rumus yang ada memerlukan informasi terkait lingkar dada dan panjang badan. Untuk mendapatkan nilai lingkar dada dan panjang badan perlu dilakukan pengukuran secara manual, namun di lapangan hal tersebut tidak mudah dilakukan karena sapi sulit dikondisikan. Oleh karena itu diperlukan alat yang dapat mengukur secara mudah. Tulisan ini merupakan tahap awal dari penelitian untuk menentukan bobot sapi dari hasil akuisisi citra sapi. Oleh sebab itu pada tahap awal ini difokuskan pada segmentasi serta pengolahan citra sapi untuk menentukan deteksi tepi terbaik yang nantinya digunakan pada penelitian selanjutnya. Citra sapi hasil akuisisi diproses menggunakan lima buah skenario deteksi tepi. Hasil evaluasi menujukkan bahwa Skenario 3 (Median Blur dan Canny) memiliki hasil yang terbaik dengan nilai MSE sebesar 230.051 dan PSNR sebesar 24.524 dB.Kata Kunci: Deteksi Tepi, Canny, Segmentasi, Sapi, Pengolahan Citra Digital.
A Comparative Study of Transfer Learning and Fine-Tuning Method on Deep Learning Models for Wayang Dataset Classification Mustafid, Ahmad; Pamuji, Muhammad Murah; Helmiyah, Siti
IJID (International Journal on Informatics for Development) Vol. 9 No. 2 (2020): IJID December
Publisher : Faculty of Science and Technology, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2020.09207

Abstract

Deep Learning is an essential technique in the classification problem in machine learning based on artificial neural networks. The general issue in deep learning is data-hungry, which require a plethora of data to train some model. Wayang is a shadow puppet art theater from Indonesia, especially in the Javanese culture. It has several indistinguishable characters. In this paper, We tried proposing some steps and techniques on how to classify the characters and handle the issue on a small wayang dataset by using model selection, transfer learning, and fine-tuning to obtain efficient and precise accuracy on our classification problem. The research used 50 images for each class and a total of 24 wayang characters classes. We collected and implemented various architectures from the initial version of deep learning to the latest proposed model and their state-of-art. The transfer learning and fine-tuning method showed a significant increase in accuracy, validation accuracy. By using Transfer Learning, it was possible to design the deep learning model with good classifiers within a short number of times on a small dataset. It performed 100% on their training on both EfficientNetB0 and MobileNetV3-small. On validation accuracy, gave 98.33% and 98.75%, respectively.
Sistem Pengolahan Citra Digital untuk Menentukan Bobot Sapi Menggunakan Metode Titik Berat Mustafid, Ahmad; 'Uyun, Shofwatul
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 6: Desember 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3672.809 KB) | DOI: 10.25126/jtiik.201856841

Abstract

AbstrakPenentuan harga sapi umumnya disepakati melalui tawar menawar dan interaksi antara permintaan dan penawaran untuk menentukan harga bukan didasarkan pada bobot sapi yang dijual. Kebanyakan menggunakan perhitungan secara kasar maupun secara kira-kira. Terdapat rumus untuk menghitung bobot sapi, rumus yang ada memerlukan informasi terkait lingkar dada dan panjang badan. Untuk mendapatkan nilai lingkar dada dan panjang badan perlu dilakukan pengukuran secara manual, namun di lapangan hal tersebut tidak mudah dilakukan karena sapi sulit dikondisikan. Oleh karena itu diperlukan alat yang dapat mengukur secara mudah. Tulisan ini merupakan tahap kedua dari penelitian untuk menentukan bobot sapi dari hasil akuisisi citra sapi. Oleh sebab itu pada tahap kedua ini difokuskan pada pemilihan rumus penentuan bobot sapi dan usulan algoritma untuk menentukan bobot dari gambar hasil akuisisi citra. Hasil analisis penentuan bobot sapi menggunakan rumus Schoorl dan rumus Modifikasi memiliki nilai penyimpangan bobot badan sebesar 16,87% untuk rumus Schoorl dan nilai penyimpangan bobot badan sebesar 10,58 % untuk rumus Modifikasi. Hasil perhitungan citra tidak berbeda secara signifikan yaitu dengan faktor ketelitian secara statistis dengan nilai MAE (Mean Absolute Error) sebesar 8,15% untuk panjang badan dan sebesar 4,10% untuk lingkar dada. Aplikasi pengolahan citra digital yang dibagun dapat mengetahui berat badan/bobot sapi dengan nilai MAE (Mean Absolute Error) sebesar 8,97% terhadap rumus Modifikasi. Abstract The price determination of cows is generally agreed through bargaining and interacting with demand and supply to establish the general level of the price but it is not based on the weight of the cow itself. The tool that the most commonly used is by rough calculation or approximation. There were formulas to measure the weight, but it required chest circumference and the length of the body information. The values ware obtained manually using the measuring tool, but the reality is inconvenient to do, because of the difficulty conditioning the cows. Therefore, it required a tool that can calculate easily. This article represented the second stages of the research to determine the weight of cows from the image acquisition. Consequently, at this second stage has been focused on the selection of the cow weighting formula and the proposed algorithm to determine the weight from the result of images that had been processed in the early stages. The result of cow weighting analysis using Schoorl formula and Modification/Lambourne formula had the value of body weight deviation of 16.87% and 10.58. The results of image calculation did not differ significantly with MAE (Mean Absolute Error) equal to 8,15% and 4,10% for body length and chest circumference, respectively. Digital image processing application that has been built was able to know the weight of cow with MAE (Mean Absolute Error) equal to 8,97% towards Modification/Lambourne formula. 
Co-Authors Helmiyah, Siti Pamuji, Muhammad Murah Shofwatul ‘Uyun