cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Hafiz Irsyad
Contact Email
hafizirsyad@mdp.ac.id
Phone
+6281373740969
Journal Mail Official
hafizirsyad@mdp.ac.id
Editorial Address
Universitas Multi Data Palembang, Kampus Rajawali. Jl. Rajawali no 14 Palembang
Location
Kota palembang,
Sumatera selatan
INDONESIA
Algoritme Jurnal Mahasiswa Teknik Informatika
Published by Universitas Multi Data Palembang
ISSN : -     EISSN : 27758796     DOI : https://doi.org/10.35957/algoritme.v2i2
Core Subject : Science,
Computer Science & IT
Jurnal Algoritme menjadi sarana publikasi artikel hasil temuan Penelitian orisinal atau artikel analisis. Bahasa yang digunakan jurnal adalah bahasa Inggris atau bahasa Indonesia. Ruang lingkup tulisan harus relevan dengan disiplin ilmu seperti: - Machine Learning - Computer Vision, - Artificial Inteledence, - Internet Of Things, - Natural Language Processing, - Image Processing, - Cyber Security, - Data Mining, - Game Development, - Digital Forensic, - Pattern Recognization, - Virtual & AUmented Reality,. - Cloud Computing, - Game Development, - Mobile Application, dan - Topik kajian lainnya yang relevan dengan ilmu teknik informatika.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 13 Documents
 1   2 
Search results for , issue "Vol 3 No 1 (2022): Jurnal Algoritme" : 13 Documents clear
IDENTIFIKASI CACAT PADA KAYU MENGGUNAKAN FITUR GLCM DENGAN METODE SVM Muhammad Azwar Tsar Siregar; Gasim Gasim
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.2970

Abstract

Wood is the part of the stem or twig of a plant that hardens as a result of the natural lignification process. Wood has properties that cannot be imitated by other materials. The properties of wood are durable, strong and non-corrosive. Weaknesses of wood, namely natural deficiencies contained in it such as knot defects, heart brittle defects, and borer hole defects. This study uses the SVM (Support Vector Machine) method to obtain accuracy against defects in wood by using GLCM (Gray Level Co-occurence Matrix) extraction. The dataset used contains 160 images and then separated into 112 train data and 48 test data. The identification carried out on the Gaussian kernel got the highest accuracy of 27.08% compared to using the Linear kernel with a smaller accuracy of 16.67%.
Klasifikasi Penyakit Daun Sawit Menggunakan Metode Jaringan Saraf Tiruan Dengan Fitur Local Binary Pattern Andreas Jeremy Obet Simanjuntak; Daniel Udjulawa
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
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
Penerapan Algoritma C4.5 Untuk Kepuasan Pelanggan Toko Online Parfume Chantik Caesar Rizky Aditya Nugroho; Titin Kristiana
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3169

Abstract

Currently, there are many online stores or marketplaces either owned by individuals / companies that are specifically eduated by buyers or costumers who want to see and buy products. In some countries in the world, the marketplace functioned as electronic commerce is often interpreted as e-commerce in several locations in Indonesia. The difference between marketplace and e-commerce is in a concept similar to the traditional market / store. In this study used the C4.5 Algorithm method to analyze the quality of service satisfaction and products from online stores perfume chantik. Using the C4.5 algorithm method, it is necessary to know the accuracy of predictions, namely the ability of models to be able to predict class labels against new data or previously unknown data well. In this study, experiments were conducted using the C4.5 algorithm's data mining deceision tree classification method against customer satisfaction kuisoner data after buying from an online store parfume chantik.
Implementasi Algoritma C4.5 Untuk Memprediksi Capaian Pembelajaran Daring (Studi Kasus Siswa MAN 3 Blitar) Muchamad Azis Hidayatuloh; Kurnia Paranita Kartika; Dimas Fanny Hebrasianto Permadi
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3292

Abstract

Learning outcomes are focused on what students want to be able to do during or at the end of a learning process that includes the learning and teaching process. The problem when learning online is that there are network constraints and the lack of teaching hours for teachers and the limited amount of material that can be delivered. So a solution is needed to determine the level of student satisfaction in the process of achieving online learning in schools. This study applies the C4.5 algorithm for the classification of online learning outcomes at MAN 3 Blitar. This study aims to predict the achievement of online learning with the C4.5 algorithm. There are 10 attributes that affect the achievement of online learning, namely: remembering, attendance, assignments, assessment, material, conditions, application, creating, discussion, analysis. With research, it can make it easier for teachers to determine online learning methods with minimal constraints. The results of the research using the C4.5 algorithm are 27 decision trees and rules, the highest gain value is the Create attribute, which is 0.383923. The results of the validation test using the confusion matrix level of accuracy in predicting online learning achievement on average are 88%, precision is 83%, recall is 86%. With the results of the accuracy value obtained, it can be said to be included in the Good Classification.
Analisis Sentimen Analisis Sentimen Popularitas Aplikasi Moodle dan Edmodo Menggunakan Algoritma Support Vector Machine Nedya Yolanda; Indyah Hartami Santi; Dimas Fanny Hebrasianto Permadi
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3313

Abstract

Pandemic Covid-19 in Indonesia has caused face-to-face learning to be temporarily suspended, resulting in online learning. Indirectly encouraging an E-Learning application to have a high usage rate and number of downloads on the Play Store. The best application is always given to the application with highest number of downloads and ratings on the Play Store. Meanwhile comments from users need to be taken into account because many E-learning applications have the same number of downloads and ratings Moodle and Edmodo, therefore a sentiment analysis of the popularity of Moodle and Edmodo is carried out using the SVM Algorithm. User comments on Play Store are used as data source. From 250 data scraping results from user comments, the preprocessing process and TF IDF extraction were carried out. Based on results of testing using confusion matrix it can be concluded that user sentiment the Edmodo application has a better percentage compared to the Moodle application which can be shown by the emergence of a positive sentiment 67% with accuracy 84% and precision 93%, recall 82% and f1-score 87%. Moodle application has a negative sentiment percentage 67% with an accuracy 82% and a precision test of 79%, 100% recall and 88% f1-score.
Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network Dengan Arsitektur VGG-19 Dewi Marcella; Yohannes Yohannes; Siska Devella
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3331

Abstract

This study raised a topic related to the classification by using eye diseases in humans. This study uses two optimizing options, namely SGD and Adagrad. The data used are 601 images consisting of 430 training images, 50 validation images, and 121 test images with a total of 4 classes. The method used in this study is the Convolutional Neural Network (CNN) method with the VGG-19 architecture, with input in the form of images that have gone through a preprocessing process, namely resizing and the CLAHE (Contrast Limited Adaptive Histogram Equalization) method of eye disease images. The test scenario consisted of 8 scenarios with different Optimizer and ClipLimit. The highest test results were obtained in the first scenario using the Adagrad optimizer and clipLimit of 1.0 with an accuracy value of 65.29%, precision of 66.53%, recall of 65.29%, and f1-score of 65. 40%.
Klasterisasi Topik Skripsi Informatika dengan Metode DBSCAN Zicola Vladimir VIky Khan; Derry Alamsyah; Wijang Widhiarso
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3337

Abstract

This research analyzed 176 Palembang public universities’ students’ theses which were published in 2020. The data was analyzed by conducting text processing and extraction with TF-IDF feature by using two scenarios, the reduced feature value and the unreduced one, with SVD method. In each scenario, three metrics, cosine, euclidean, and, manhattan were used, which generated six scenarios in total. The result found that the best quality of cluster which was measured by silhouette coefficient comes from metric cosine and reducted by SVD with the silhouette coefficient value of 0.88382763, intracluster value of 0.08688583, and intercluster value of 0.74671096. Therefore, the cluster quality value of the reducted feature is the best among all metrics. In addition, the use of DBSCAN method showed a positive correlation between epsilon and intracluster with the value of 0.97669, and also showed a negative correlation between epsilon and silhouette with the value of 0.9789.
Sistem Pakar Sistem Pakar Diagnosis Hama Dan Penyakit Tanaman Bonsai Menggunakan Metode Forward Chaining Ismiya Nurhayati; Sri Lestanti; Saiful Nur Budiman
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3343

Abstract

This study aims to build an expert system that can help determine quickly what pests or diseases attack bonsai plants based on symptoms that appear, especially in Blitar Nursery. Not only types of pests or diseases, this system also informs how to handle plants that are attacked by pests or diseases and how to prevent them. The method used in this study is the forward chaining method, the tracking process of this method is from symptom data, then matches the data with the IF part of the IF-THEN rule, if it is in accordance with the existing rules, then the rule will be executed to get a conclusion. This expert system was built using Bootstrap and the Hypertext Preprocessor (PHP) programming language with the Sublime Text text editor. Testing this expert system using black box and beta testing to IT experts and experts. The results of black box testing are 97.22% and beta test results are 85.2%, the conclusion that the system is feasible to use and can provide a diagnosis of pests or diseases in bonsai plants based on the symptoms given.
Identifikasi Kadar Ikan Pada Pempek Menggunakan Teknik Blok Citra Dengan Fitur GLCM Dan Metode JST Nurdiana Dewi Saputri; Gasim Gasim
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

As we know today, Indonesia has many unique foods, each in each region. For example, pempek is a typical food from Palembang, South Sumatra. The ingredients for making pempek do not only use fish, but there are many different dough formulas that create different flavor compositions. Differences that occur in the dough formula when making pempek will affect the texture and taste, because there is a mixture of fish and the amount of flour. The research uses image block techniques with GLCM (Gray Level Co-Occurrence Matrix) features and artificial neural network methods. The GLCM (Gray Level Co-Occurrence Matrix) feature extraction used consists of Entropy, Standard Deviation, Contrast, Angular Second Moment (ASM)/ Homogeneity, Correlation, and Inverse Different Moment (IDM)/ Energy. The dataset used in this study is to use the best results at a portrait distance of 13 cm from previous studies. There are 4 types of comparisons used, namely 1 fish 1 flour, 1.5 fish 1 flour, 2 fish 1 flour, and 1 fish 2 flour. The recognition results obtained in this study were 360 recognized training data and 89 recognized test data and obtained an accuracy rate of 37.08%.
Identifikasi Kadar Ikan Pada Pempek Dengan Fitur LBP Dan Metode Pengenalan SVM Kevita Titany Suhanto; Gasim Gasim
Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3363

Abstract

The main ingredients commonly used by the community in making pempek are ground fish and sago flour. The people of Palembang usually make pempek into several variants such as egg pempek, pempek pistel, pempek curly, pempek submarine, pempek roasted, pempek lenggang, etc. In the previous study, the dataset was 4 types of pempek lenjer with different levels of snakehead fish and flour, where each comparison was equal to 200 grams. The comparisons are: 1 snakehead fish to 1 sago flour, 1.5 snakehead fish to 1 sago flour, 2 snakehead fish to 1 sago flour, 1 snakehead fish to 2 sago flour. In this study, the dataset used is a photo image using a 2MP camera resolution which is the best dataset from previous research (Amatullah, 2021) which obtained an accuracy rate of 23.33% and the number of test data recognition was 56 out of 240 test data. Then this research was conducted using LBP feature extraction and the introduction of the Support Vector Machine method which resulted in an accuracy rate of 22.92%.

Page 1 of 2 | Total Record : 13

 1   2 

Filter by Year

2022 2022


Reset
Filter By Issues
All Issue Vol 4 No 1 (2023): Jurnal Algoritme Vol 3 No 2 (2023): Jurnal Algoritme Vol 3 No 1 (2022): Jurnal Algoritme Vol 2 No 2 (2022): Jurnal Algoritme Vol 2 No 1 (2021): Jurnal Algoritme Vol 1 No 2 (2021): Jurnal Algoritme Vol 1 No 1 (2020): Jurnal Algoritme