Claim Missing Document
Check
Articles

Found 12 Documents
Search

Klasifikasi Citra Lubang pada Permukaan Jalan Beraspal dengan Metode Convolutional Neural Networks (CNN): Image Classification of Potholes on Paved Road Surfaces with the Convolutional Neural Networks (CNN) Method Ni Nyoman Citariani Sumartha; I Gede Pasek Suta Wijaya; Fitri Bimantoro; Gibran Satya Nugraha
Journal of Computer Science and Informatics Engineering (J-Cosine) Vol 8 No 1 (2024): Juni 2024
Publisher : Informatics Engineering Dept., Faculty of Engineering, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jcosine.v8i1.557

Abstract

A pothole is a bowl-shaped indentation in the road surface, less than 1 meter in diameter. The presence of potholes on the highway can endanger the safety of road users, so repairs need to be done as soon as possible. Images of potholed roads have high complexity, variations consisting of color contrast, hole size, presence of puddles or not, lighting when taking pictures, background and others. For this reason, an approach is needed that can classify images with a high degree of variation by extracting the important information contained in them. Judging from the potential success of using the Convolutional Neural Networks (CNN) approach in identifying images of potholes that will be reported for entry into the Public Works Service's road improvement record, the authors propose the idea of "Pothole Image Classification on Asphalt Road Surfaces with the Convolutional Neural Networks (CNN) Method”.
Analisis Kebutuhan Dataset Algoritma Speech To Text Bahasa Sasak Menggunakan Perbandingan Data Suara Bahasa Inggris Pada Metode CNN: Analysis of Sasak Language Speech To Text Algorithm Dataset Requirements Using English Voice Data Comparison on CNN Method Widya Bayu Pratiwi; Arik Aranta; Gibran Satya Nugraha
Journal of Computer Science and Informatics Engineering (J-Cosine) Vol 7 No 2 (2023): Desember 2023
Publisher : Informatics Engineering Dept., Faculty of Engineering, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jcosine.v7i2.568

Abstract

Currently, there have been many studies on speech recognition or speech to text. Speech to text is a technology used to convert human speech or voice and translate it into written text. Some speech to text research that has been done, has obtained an accuracy rate of up to 95% with English datasets using the Mel Frequency Coefficient (MFCC) feature extraction method and the Convolutional Neural Network (CNN) classification method. This research will apply similar algorithms, namely MFCC and CNN by displaying the training process and the resulting accuracy in its processing with an analysis scenario using datasets in multiples of 50, 150, 250, and 350 voice data. The results obtained have achieved 95% accuracy on the training data of 350 English voice data. The analysis carried out is to find the best composition on the Sasak language dataset by comparing the accuracy of the test results with the accuracy of the previous training results on the English dataset. From the training and testing process that has been carried out, the results obtained show that the best dataset composition for Sasak language is with nine speakers. This illustrates that the Sasak language requires less human resources compared to the English dataset which involves more than 30 speakers in 50 words. This has a positive impact on saving resources and time required in the development of Sasak language speech recognition system.