Claim Missing Document
Check
Articles

Found 27 Documents
Search

PERBANDINGAN PERFORMA ALGORITMA MINIMAX DAN ALPHA-BETA PRUNING PADA GAME CATUR CINA Kurniawan, Marthin Hokita; Udjulawa, Daniel
Jurnal Algoritme Vol 1 No 1 (2020): Oktober 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (793.93 KB) | DOI: 10.35957/algoritme.v1i1.443

Abstract

Algoritma merupakan urutan yang lengkap dan logis, dengan urutan yang logis banyak cara yang dilakukan dengan urutan yang berbeda. Pada kasus ini akan dibandingkan performa dari algoritma Minimax dan Alpha Beta Pruning pada game Catur Cina (XiangQi). Tujuannnya adalah sejauh mana waktu yang digunakan oleh kedua algoritma tersebut efektif dalam permainan Catur Cina. Metodologi yang digunakan dalam membangun aplikasi adalah Rapid Application Development, yaitu merupakan pengembangan dari metodologi Software Development Life Cycle. Kegiatan yang dilakukan antara lain yaitu melakukan perencanaan dan analisis terhadap pengembangan game dan melakukan pembuatan game dengan menggunakan game engine Unity dan bahasa pemograman C#, Editor yang digunakan adalah Atom. Hasil pembuatan game dan koding algoritma akan di uji coba dengan iterasi kedalaman dan preset yang ditentukan sesuai dengan Minimax dan Alpha-Beta Pruning. Data yang didapat yaitu kecepatan dan banyak putaran antara kedua algoritma. Data tersebut akan dibandingkan sehingga performa kedua algoritma akan terlihat jelas.
Perancangan Aplikasi Simulasi Penyelamatan Diri Dari Gempa Bumi Marzali, Azizurrahman; Udjulawa, Daniel; Yoannita, Yoannita
Jurnal Algoritme Vol 1 No 2 (2021): April 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (958.577 KB) | DOI: 10.35957/algoritme.v1i2.892

Abstract

Menurut The World Risk Index tahun 2019, Indonesia berada pada peringkat 37 dari 180 negara paling rentan bencana. Pada tanggal 5 Agustus 2018 gempa bumi di Lombok menelan korban sebanyak 259 orang meninggal dunia, dan 1.033 mengalami luka berat. Kurangnya kesiap siagaan dan edukasi mengenai bencana gempa bumi menjadi salah satu faktor penyebab banyaknya jumlah korban. Maka dari itu dibuatlah sebuah aplikasi simulasi yang ditujukan untuk mengedukasi masyarakat supaya dapat mengetahui apa saja yang harus dilakukan pada saat terjadi gempa bumi. Aplikasi ini dibuat menggunakan metode prototyping untuk melakukan identifikasi masalah yang ada pada setiap kejadian gempa bumi. Tujuan dari pembuatan aplikasi ini adalah untuk memberikan pengetahuan tentang bagaimana cara menyelamatkan diri dari gempa bumi. Aplikasi ini berbentuk game yang mempunyai sudut pandang First Person yang mempunyai empat stage dan setiap stage mempunyai beberapa misi. Pemain harus menyelesaikan seluruh misi pada setiap stage agar dapat melanjutkan ke stage selanjutnya. Hasil dari penelitian ini yaitu menghasilkan sebuah aplikasi simulasi dalam cara menyelamatkan diri dari gempa bumi. Berdasarkan uji Black-Box yang telah dilakukan, diperoleh hasil uji coba bahwa aplikasi ini dapat dijalankan dengan baik dan sesuai dengan tujuan.
Klasifikasi Penyakit Daun Sawit Menggunakan Metode Jaringan Saraf Tiruan Dengan Fitur Local Binary Pattern Simanjuntak, Andreas Jeremy Obet; Udjulawa, Daniel
Jurnal Algoritme Vol 3 No 1 (2022): Oktober 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3158

Abstract

Diseases on palm leaves are diseases caused by bacteria or fungi. One way to find out diseases on palm leaves is to observe the pattern on the surface of the palm leaves. The pattern on the palm leaves will be analyzed by an expert to find out whether there is disease on the palm leaves or not. This study aims to classify oil palm leaves whether there is disease or not on oil palm leaves by using a program. The right method is needed to produce good accuracy, the researcher uses the ANN (Artificial Neural Network) classification method and the LBP (Local Binary Pattern) extraction method. The steps carried out on the image before being classified are Grayscale, then extraction using LBP (Local Binary Pattern) and classification using ANN (Artificial Neural Network) using 17 train functions with the result that 5 neurons get an average accuracy of 81%, precision 95 %, and 94% recall. In 10 neurons get an average of 95% accuracy, 97% precision, and 96% recall. And the 20 neurons get an average of 97% accuracy, 97% precision, and 96% recall. Keywords: Palm leaf disease, LBP, ANN, neuron
Identifikasi Penyakit Pada Tanaman Kopi Berdasarkan Citra Daun Menggunakan Metode Convolution Neural Network Fatchurrachman, Ahmad; Udjulawa, Daniel
Jurnal Algoritme Vol 3 No 2 (2023): April 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i2.3384

Abstract

Coffee plants are usually made for drinks made from coffee beans that have been ground into powder. One of the causes of decreased coffee quality is caused by pests that can attack from the leaves, stems and roots. This study aims to identify coffee plant diseases based on leaves using the Convolution Neural Network (CNN) method with the ResNet-50 architecture with the Adam optimizer. The total data from the dataset is 1664 images, in the dataset there are 1264 train data images and 400 test images. The highest result in training in this study using 60 epochs and Adam's optimizer with a probability value of learning_rate of 0.0001 getting a probability value of 0.9969 and the lowest value getting a probability value of 0.4918. The results of testing the test data in this study obtained an accuracy rate of 99%.
Deteksi Masker Melalui Video CCTV Menggunakan You Only Look Once Darmawan, Dean; Udjulawa, Daniel; Wijaya, Novan
Jurnal Algoritme Vol 3 No 2 (2023): April 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i2.3598

Abstract

The coronavirus pandemic or known as the COVID-19 pandemic is a global pandemic of corona virus that are caused by severe acute respiratory syndrome coronavirus 2 that are started in Wuhan, China in 2019. In 30th January 2020 World Health Organization (WHO) declared an emergency situation towards COVID-19 and in 11th March 2020, WHO officially declared an ongoing global pandemic of COVID-19. COVID-19 cases in the world itself is already reaching 181 million of cases with around 3.92 million deaths. Indonesia itself is one of the country that are affected by COVID-19 spread with 2.09 million cases and 56,729 deaths. In order to decrease the amount of COVID-19 cases, WHO require each individuals to do social distancing, stay hygiene, and always wearing face mask to prevent even more spread of the virus. A method to do face mask detection is proposed using a object detection method, You Only Look Once (YOLO). The test results obtained by calculating f-measure with the highest accuracy of 0.59 and the lowest of 0.19 using CCTV video that are taken with 70 cm distance. In the second test using video that are recorded with more than 90 cm the program obtained it’s result of 0.
Implementasi Algoritma K-Nearest Neighbor untuk Klasifikasi Cuaca Dandy, Dandy; Udjulawa, Daniel; Yohannes, Yohannes
Jurnal Algoritme Vol 4 No 1 (2023): Oktober 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v4i1.4932

Abstract

Weather is a brief natural event concerning the atmospheric conditions that take place on Earth which are determined by pressure, wind speed, temperature, and air phenomena. This study classifies 3 weather classes, namely sunny, cloudy, and rainy using the K-Nearest Neighbor algorithm as a weather classification algorithm with K value parameters of 3, 5, 7, and 9. Weather dataset 96.453 data to be examined is data taken from the Kaggle website. The dataset is divided into training data and test data with a ratio of 80:20. The implementation of the K-Nearest Neighbor algorithm produces a confusion matrix and classification report where in the confusion matrix, the largest number of correctly predicted data is at the value K = 9, namely 13.132 correctly predicted data with the largest number of correctly predicted data in the cloudy class, namely 10.865 data. As for the classification report, the highest accuracy value for both the cloudy, rainy, and sunny weather classes is at K = 9, which is 68.073%, and the highest precision, recall, and f1-score values are found in the cloudy class at K = 9, respectively contributed 72.095%, 89.288%, and 79.775%.
Workshop Pembuatan Feed Instagram Taruna Siaga Bencana Di Dinas Sosial Provinsi Sumatera Selatan Rahman, Abdul; Udjulawa, Daniel; Mulyati, Mulyati
FORDICATE Vol 1 No 1 (2021): November 2021
Publisher : Universitas Multi Data Palembang, Fakultas Ilmu Komputer dan Rekayasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (507.156 KB) | DOI: 10.35957/fordicate.v1i1.1625

Abstract

The purpose of the implementation of this workshop can provideinsight to the TAGANA South Sumatra team in the creation of content that willbe uploaded on sosial media, one of which is Instagram. The use of Instagram,the majority of which is to use videos and pictures is an interesting thing to beable to convey and even promote activities from TAGANA South Sumatera. Theapplication used is Adobe Photoshop. In this activity using discussion methods,by applying this discussion method can provide training and mentoring. So thatthe participants can be closer and feel interested so that it is easily accepted bythe participants. The final result of this workshop the participants can movetheir creativity in creating an Instagram feed so that it attracts the attention ofthe public.