Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal POSITIF JURIKOM (Jurnal Riset Komputer)
Putro, Aditya Dwi
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 3 Documents
Search

 1 
KLASIFIKASI TINGKAT KEMATANGAN BUAH PISANG CAVENDISH MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK MODEL VGG-19 Putro, Aditya Dwi; Amrulloh, Arif
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 9 No 2 (2023): Positif : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v9i2.1778

Abstract

Bananas found in Cavendish Banana Gardens Purbalingga Regency have different levels of maturity and quality, as a local fruit that has high economic value and has a market potential that is still wide open, Cavendish bananas are one of the most reliable fruit commodities in Indonesia[1]. The government through the National Standardization Agency sets standards for bananas, maintaining the quality of bananas. The purpose of this study was to analyze the influence of light and image quality in classifying the ripeness level of bananas based on the color characteristics of bananas in the Cavendish Banana Garden, Banyumas Regency, Central Java according to SNI 7422:2009[2]. In this study the authors classify the maturity level of cavendish bananas using the Convolutional Neural Network with the Vgg-19 Model, VGG-19 is used to categorize the maturity level of cavendish bananas and the reason for choosing VGG-19 is because VGGNet is deeper and more reliable architecture for ImageNet technology.The author is also interested in learning how accurate the VGG-19 model is. With a total of 9,000 datasets, 80% of which are training data, 10% are validation data, and 10% are test data, The accuracy obtained for epochs 32, 64 and 96 varies. The accuracy results obtained using VGG-19 were 97% at epochs 32, 64 and 96.
ANALISIS KLASTERING DAMPAK LINGKUNGAN BERDASARKAN KONSUMSI ENERGI PERUSAHAAN BERBASIS INDUSTRI 4.0 MENGGUNAKAN METODE CRISP-DM Kusuma, Dewa Adji; Putro, Aditya Dwi
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 9 No 2 (2023): Positif : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v9i2.2050

Abstract

The growth of energy consumption worldwide has experienced a significant increase in the past two decades. The increase in energy consumption in a company indicates that the company generates more carbon dioxide (CO2) emissions than usual. Excessive carbon emissions have a significant impact on human health and the environment. According to the World Health Organization (WHO), greenhouse gas emissions resulting from the extraction and combustion of fossil fuels are major contributors to climate change and air pollution. It is necessary to analyze what factors contribute to high carbon emissions. This study uses the CRISP-DM (Cross-Industry Standard Process for Data Mining) method. The K-Means algorithm will be used to cluster the features that influence high carbon emissions. The feature selection process for K-Means uses Pearson correlation. The clustering model results in good evaluation scores using the Silhouette evaluation metric. Subset data 1 obtained a Silhouette score of 0.744, and subset data 2 obtained a Silhouette score of 0.7629. The evaluation results indicate that the K-Means model works quite well in creating clusters.
Sistem Absensi Guru Berbasis Pengenalan Wajah Menggunakan Algoritma YOLOv8 Prayudha, Satria Putra Dharma; Putro, Aditya Dwi
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 2 (2025): April 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i2.8511

Abstract

This research aims to design and implement a web-based teacher attendance system that utilizes facial recognition technology through the YOLOv8 algorithm as a solution to the conventional paper-based attendance system, which is prone to recording errors, data manipulation, and potential information loss. Data collection was conducted by recording short videos of 24 teachers and staff at SD Negeri 1 Purbalingga Lor under various lighting conditions and viewpoints, which were then converted into an image dataset using the Roboflow platform. The dataset was processed through several preprocessing stages including video-to-image conversion, image resizing, augmentation, and data splitting for training, validation, and testing purposes. The YOLOv8s model was chosen due to its ability to detect faces in real time with high accuracy, as demonstrated by training results showing an mAP of 98.6%, Precision of 97.8%, and Recall of 98.5%. The integration of the model into a backend Flask-based application enables the attendance process to be carried out automatically and in real time, while functional testing using the Black Box Testing method confirms that the face detection feature operates as designed, achieving an accuracy of 93% under optimal lighting conditions. Consequently, this research successfully presents an innovative digital solution that not only enhances the efficiency of attendance administration but also minimizes the risks of data manipulation and recording errors in educational environments.
Co-Authors Arif Amrulloh Kusuma, Dewa Adji Prayudha, Satria Putra Dharma