Claim Missing Document
Check
Articles

Found 4 Documents
Search

Klasifikasi Kesegaran Daging Sapi Menggunakan Metode Ekstraksi Tekstur GLCM dan KNN Ade Prabowo; Danang Erwanto; Putri Nur Rahayu
Electro Luceat Vol 7 No 1 (2021): Electro Luceat (JEC) - July 2021
Publisher : LPPM Poltek ST Paul

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32531/jelekn.v7i1.344

Abstract

Meat is the soft part of the animal that is covered by skin and is attached to the bones which become food ingredients. This research was conducted to classify the types of fresh, inn and rotten beef using 120 samples of beef taken directly by the researcher. Before classifying the type of beef, the texture of the beef image was extracted using the GLCM method to produce texture parameters in the form of contrast, correlation, homogeneity and energy. Texture parameters are classified using the KNN method. The results in this study indicate that the extraction of beef image texture using the GLCM method can produce various values on the 4 parameters of the GLCM texture. In addition, the results of the classification of beef freshness using the KNN method to determine 3 types of meat quality, namely fresh, cooked and rotten beef, obtained an evaluation of the classification performance using the Confusion Matrix table with an Accuracy value of 0.82, Precision of 0.83, Recall of 0.82 and F-Measure of 0.82. So that the parameters of the beef image texture using the GLCM method can be classified properly using the KNN method.
KLASIFIKASI CACAT PADA KALENG KEMASAN MENGGUNAKAN METODE LACUNARITY DAN NAÏVE BAYES Danang Erwanto; Putri Nur Rahayu; Yudo Bismo Utomo
Electro Luceat Vol 7 No 2 (2021): Electro Luceat (JEC) - November 2021
Publisher : LPPM Poltek ST Paul

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32531/jelekn.v7i2.398

Abstract

Cans are steel sheets coated with tin (Sn) and used to package food and beverage products. The use of cans as packaging for food products because cans are difficult for microorganisms to pass and cannot be penetrated by ultraviolet light so that the quality of packaged food or beverage products is maintained. The cans selected as packaging must be in a non-defective condition so that an inspection process is needed on the cans. This research implements the Lacunarity and Naïve Bayes Classification methods to classify the types of cans which are grouped into 2 classes, namely Good and Reject. From the implementation of the Lacunarity method, it is able to produce 28 values of texture feature extraction that vary in each image. The results of the evaluation of the classification of the Naïve Bayes Classification method to classify the condition of packaged cans obtained an accuracy value of 0.87, a precision of 0.88, a recall of 0.86 and an f-measure of 0.87, so that the Naïve Bayes Classification method can classify the types of cans packaging in Good and Reject condition based on the value of texture extraction using the Lacunarity method.
Automatic Cash Payment System Using ESP32 Ardhan, Mohammad Ardhan Fawwaz; Noorman Rinanto; Muhammad Khoirul Hasin; Adianto; Putri Nur Rahayu
INAJEEE (Indonesian Journal of Electrical and Electronics Engineering) Vol. 8 No. 2 (2025)
Publisher : Department of Electrical Engineering, Faculty of Engineering, Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/inajeee.v8n2.p114-120

Abstract

This research evaluates an automatic cash payment system using an ESP32 microcontroller integrated with a bill acceptor, a Rp1000 coin acceptor, and a coin hopper. The system is designed to accept banknote and coin payments and dispense change automatically. The system was fully tested for 40 transactions. Results showed a success rate of 87.5% with the most problems being the incorrect reading of banknotes and coin positioning. The system shows high potential for use in vending machines or self-service platforms Keywords: Indoor Positioning System, Wi-Fi RSSI-Fingerprint, Multivariate Gaussian Mixture Model, Android Application, Accuracy.
Segmentasi Citra Pengelasan Kapal Menggunakan Convolutional Neural Network Brian, Thomas; Pujiputra, Anggarjuna Puncak; Putri Nur Rahayu; Augustino, Immanuel Freddy; Parman, Parman; Bone, Iskia Ipan Dua’
SENTRI: Jurnal Riset Ilmiah Vol. 4 No. 10 (2025): SENTRI : Jurnal Riset Ilmiah, Oktober 2025
Publisher : LPPM Institut Pendidikan Nusantara Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/sentri.v4i10.4767

Abstract

Welding inspection plays a critical role in the shipbuilding industry to ensure the integrity and quality of welded joints. However, the prevailing manual inspection procedures are inherently subjective, prone to bias, and result in inconsistent quality assessments. Therefore, there is a strong need for an automated and intelligent system capable of objectively detecting welding points. To address this, we propose an advanced segmentation model based on deep learning and computer vision techniques, specifically utilizing the enhanced Nested UNet architecture with extensive architectural modifications and comprehensive hyperparameter tuning. To further optimize the segmentation performance, we systematically compare different convolutional blocks integrated into the network architecture. The dataset used consists of 548 welding images. Each image is manually annotated using the VGG Image Annotator (VIA) application by marking the weld point areas as polygons. This research focuses on the development of a Nested UNet model, a deep learning-based image segmentation model for detecting weld points from previous models using the UNet architecture. During the training process, performance on both the training and validation datasets is continuously monitored and recorded. This results in several logs recording the training loss, validation loss, training IoU, and validation IoU for each of the three types of convolutional blocks used in the dense bottleneck. Our experimental evaluation shows that the use of VGG - Dense - VGG convolutional blocks in Nested UNet yields the highest performance, achieving a Training Dice score of 0.92970 and a Validation Dice score of 0.89695 on our collected dataset.