Garuda - Garba Rujukan Digital

Rekomendasi Pemilihan Jenis Tanaman Menggunakan Algoritma Random Forest dan XGBoost Regressor Rahman, Abdul; Udjulawa, Daniel; Mulyati, Mulyati
Computer Science (CO-SCIENCE) Vol. 4 No. 2 (2024): Juli 2024
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/coscience.v4i2.2987

Recommendations for plants that suit a particular planting location's environmental conditions and soil nutrients can lead to optimal harvest outcomes. Machine learning applications in agriculture have been widely explored, particularly in enhancing crop yields. In this study, two machine learning algorithms, Random Forest and XGBoost Regressor, were implemented to recommend plants based on environmental conditions and soil nutrient levels. The implementation of both algorithms was compared in terms of accuracy using three accuracy metrics: Mean Absolute Error (MAE), Mean Square Error (MSE), and R2. The results indicated that both algorithms exhibited comparable accuracy levels. The Random Forest algorithm demonstrated superior accuracy in terms of MAE and MSE, with values of 36.73681574 and 1.848396760, respectively. Meanwhile, the XGBoost Regressor algorithm displayed good accuracy, mainly when measured using the R2 accuracy metric, achieving a high accuracy level of 0.98542963509705.. Keywords : Crop Recommendation, Machine Learning, Random Forest, XGBoost

Identifikasi Tingkat Kesegaran Daging Ayam Kampung Menggunakan Metode KNN Berdasarkan Warna Daging Kasanova, Sinyo; Udjulawa, Daniel
Jurnal Algoritme Vol 4 No 2 (2024): April 2024 || 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.v4i2.7872

Free-range chicken is a type of poultry that is still natural in the sense that it has not received genetic improvement treatment. The economically advantageous characteristics of free-range chickens are relatively few compared to purebred chickens, even in terms of egg production and the ability to produce meat. Determining the level of freshness of free-range chicken meat is an important factor in determining the quality of the meat to be consumed, so that people as consumers can avoid the worst risks if they consume free-range chicken meat that is not fresh. For this reason, research was carried out to determine the level of freshness of free-range chicken meat using the KNN and HSV methods. The level of freshness is divided into 3 levels, namely rotten, fresh and not fresh. Based on the results of tests carried out using the KNN method with models k=1, k=3, k=5, k=7, k=9, and k=11, it was found that in the testing process the value of the highest accuracy was obtained by the value k=5 namely 80% and k=7, namely 80%, meanwhile the lowest result was obtained by the value k=1, namely 80%.

Klasifikasi Kanker Kulit Pada Citra Dermatoskopi Menggunakan CNN Martin, Nicolas; Udjulawa, Daniel
Jurnal Algoritme Vol 5 No 1 (2024): Oktober 2024 || 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.v5i1.9034

Skin health is an important aspect of human well-being that is often overlooked because it is considered trivial. There are various types of skin diseases, ranging from allergies, fungal infections, to skin cancer which causes high mortality rates according to WHO. Early diagnosis is essential to improve skin cancer recovery, but often requires sophisticated medical devices and biopsies, where doctors remove a patient's skin lesion through minor surgery to detect cancer cells. This study uses the Convolutional Neural Network (CNN) method with the AlexNet architecture to classify skin cancer types. Convolutional Neural Network was chosen because of its ability to extract complex features from images for accurate classification. The dataset used came from Kaggle, consisting of 24,839 images, with testing using all data and 3,000 data, 500 images each for 6 types of skin cancer. The data is divided into 80% for training and 20% for testing. The best results were achieved using 24.839 data, a learning rate of 0.0001, Adamax Optimizer, batch size 16, and epoch 40, resulting in an accuracy value of 72%, a recall value of 72%, a precision value of 70%, and an F1 score of 69%.

Klasifikasi Penyakit Mata pada Citra Fundus Menggunakan VGG-16 Sutanto, Steven Yesua; Udjulawa, Daniel
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 11 No 4 (2024): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v11i4.9165

The eye is a vital sensory organ crucial for vision and various aspects of daily life. Eye diseases such as diabetic retinopathy, glaucoma, cataracts, macular degeneration, hypertension, pathological myopia, and other diseases are global health issues that significantly impact quality of life. The 2022 RAAB survey by Perdami revealed that 8 million people in Indonesia suffer from visual impairments, with 1.6 million of them being blind. Diagnosing eye diseases often requires considerable time and depends on the accuracy and subjectivity of doctors analyzing fundus images. Convolutional Neural Network (CNN) methods can process images and recognize complex patterns and features, assisting in the classification of eye diseases with high accuracy and efficiency. This research aims to classify various eye diseases automatically using the CNN method, speeding up the diagnosis process, enabling faster treatment, and improving effectiveness in the medical field. The implementation of the CNN method with the VGG-16 architecture was successful, capable of classifying 8 types of eye diseases, with the best result obtained in the 10th trial, achieving an accuracy of 54.17%

Deteksi Kategori Sampah Menggunakan Metode You Only Look Once Ja'far, Ja'far; Udjulawa, Daniel
Jurnal Algoritme Vol 5 No 2 (2025): April 2025 || 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.v5i2.9047

Waste is the residue generated from human daily activities or natural processes that is no longer needed. According to data from the Ministry of Environment and Forestry, waste generation in Indonesia reaches 36 million tons per year, with unmanaged waste totaling 13 million tons annually. Inadequate waste management can lead to various issues. One significant source of unmanaged waste is found in schools, attributed to lack of awareness and low concern, resulting in student’s laziness in disposing of waste properly. This project aims to develop a system that assists students in identifying specific waste categories and incorporates a royalty points system to boost student motivation. The method employed is You Only Look Once Version 5 with the Darknet architecture, utilizing an 80% training, 10% validation, and 10% testing dataset split. The results of testing this method at the development stage showed a recall value of 92.4%, precision of 88.4%, and mAP of 96.4%. Meanwhile, at the implementation stage on smartphones, the recall value reached 89.9% with a precision of 94.2%, and an average detection speed of around 1.68 seconds.

Identify the Maturity Level of Apples Using Fuzzy Logic Mamdani Andre Zulnardi; Daniel Udjulawa
Jurnal Teknik Indonesia Vol. 2 No. 02 (2023): Jurnal Teknik Indonesia (JU-TI), Desember 2023
Publisher : SEAN Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/ju-ti.v2i02.545

Apples are one type of fruit that has properties including preventing disease, nourishing the body and being a menu when running a diet. This study aims to develop an identification system for the maturity level of apples using the mamdani fuzzy logic method. Fuzzy logic mamdani is a fairly good method of identification because the classes to be used have been predetermined. In this study, the apples used were Rome Beauty apples. The maturity level is based on the color which is divided into two, namely green raw and reddish yellow ripe. Data processing is done by preprocessing images such as resizing fruit directly. The accuracy of the dataset measured using this method results in an accuracy of 96%. In this study, an analysis of the input and output features needed by Mamdani's fuzzy logic was also carried out in classifying the maturity level of apples. The results showed that the input data could not be used effectively to classify the maturity level of apples due to the lack of input types used.

KECERDASAN BUATAN MENGGUNAKAN ALGORITMA ALPHA –BETA PRUNING PADA PERMAINAN CATUR XIANG QI Udjulawa, Daniel
SISKOMTI: Jurnal Sistem Informasi Komputer dan Teknologi Informasi Vol. 2 No. 1 (2020): Februari 2020
Publisher : Universitas Lembah Dempo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54342/8nj3xx02

Kecerdasan Buatan merupakan usaha merancang sebuah mesin agar dapat berfikir, mengambil tindakan serta menentukan tindakan melalui komputer. Layaknya manusia keputusan tersebut akan mengakibatkan sebuah keputusan yang diambil dalam sebuah permainan mengunakan komputer. Permainan komputer yang diterapkan pada penelitian ini adalah permainan strategi yakni permainan Catur Xiang qi atau sering disebut Catur Gajah ataupun Catur Cina. Ciri-ciri yang unik termasuklah pergerakan unik pao (meriam), peraturan yang melarang panglima (seperti "raja" dalam catur internasional ) bertemu dalam garisan yang sama, serta "sungai" dan "istana" yang membatasi pergerakan buah catur. Penelitian ini ditekankan pada implementasi algoritma Alpha Beta Pruning. Algoritma Alpha Beta Pruning adalah algoritma yang digunakan untuk mencegah perluasan node untuk mendapatkan hasil pencarian langkah yang lebih baik dari sebelumnya. Algoritma Alpha Beta Pruning di uji dengan proses iterasi kedalaman dan preset yang telah ditentukan. Metodologi yang digunakan adalah Iterasi. Pembuatan game ini menggunakan game engine Unity dan bahasa pemograman java dan C#. Hasil yang didapat pada penelitian ini adalah memberikan gambaran tentang penerapan algoritma Alpha Beta Pruning yang digunakan dalam membangun sebuah kecerdasan buatan yang ada pada game catur Xiang qi

Klasifikasi Lukisan Karya Van Gogh Menggunakan Convolutional Neural Network-Support Vector Machine Yohannes Yohannes; Daniel Udjulawa; Febbiola Febbiola
Jurnal Teknik Informatika dan Sistem Informasi Vol 7 No 1 (2021): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v7i1.3399

Painting is a work of art with various strokes, textures, and color gradations so that a painting that is synonymous with beauty is created. The various paintings created have characteristics, such as the paintings by Van Gogh, which have tightly arranged strokes, creating a repetitive and patterned impression. This study classifies paintings by Van Gogh or not by using the VGG-19 and ResNet-50 feature extraction methods. The SVM method is used as a classification method with two optimizations, namely random and grid optimization in the linear kernel. The data set used consisted of 124 Van Gogh paintings and 207 paintings by other painters. The use of VGG-19 feature extraction using grid optimization has the best value of 93,28% using the use of random optimization which has a value of 92,89%. The use of ResNet-50 using grid optimization with the best value of 90,28% using the use of random optimization which has a value of 90,15%. The extraction feature of VGG-19 is better than ResNet-50 in paintings by Van Gogh or not.

Rekomendasi Pemilihan Jenis Tanaman Menggunakan Algoritma Random Forest dan XGBoost Regressor Rahman, Abdul; Udjulawa, Daniel; Mulyati, Mulyati
Computer Science (CO-SCIENCE) Vol. 4 No. 2 (2024): Juli 2024
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/coscience.v4i2.2987

Recommendations for plants that suit a particular planting location's environmental conditions and soil nutrients can lead to optimal harvest outcomes. Machine learning applications in agriculture have been widely explored, particularly in enhancing crop yields. In this study, two machine learning algorithms, Random Forest and XGBoost Regressor, were implemented to recommend plants based on environmental conditions and soil nutrient levels. The implementation of both algorithms was compared in terms of accuracy using three accuracy metrics: Mean Absolute Error (MAE), Mean Square Error (MSE), and R2. The results indicated that both algorithms exhibited comparable accuracy levels. The Random Forest algorithm demonstrated superior accuracy in terms of MAE and MSE, with values of 36.73681574 and 1.848396760, respectively. Meanwhile, the XGBoost Regressor algorithm displayed good accuracy, mainly when measured using the R2 accuracy metric, achieving a high accuracy level of 0.98542963509705.. Keywords : Crop Recommendation, Machine Learning, Random Forest, XGBoost

Comparison of Dijkstra's Algorithm and A Star's Algorithm in the Pac-Man game Ramadhan, Ahmad Wildan Rizky; 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

AI (Artificial Inteligence) atau yang disebut juga dengan kecerdasan buatan merupakan salah satu cabang dari ilmu komputer untuk memberikan suatu pengetahuan pada komputer agar dapat mampu menyelesaikan tugas – tugas atau berpikir seperti manusia. Salah satu contoh kecerdasan buatan yang dapat diterapkan pada game adalah Path Finding. Path Finding adalah salah satu kecerdasan buatan yang dipakai untuk menentukan jaur terpendek antara titik awal dengan titik akhir. Logika Fuzzy merupakan ilmu yang mempelajari mengenai ketidakpastian. Logika Fuzzy juga mampu untuk memetakan suatu ruang input kedalam suatu ruang output dengan tepat. Metode yang digunakan dalam penelitian ini adalah meode prototype dimana tahap-tahap yang dilakukan adalah menganalisis kebutuhan, mendesain prototype, implementasi, dan pengujian. Tujuan utama yang ingin dicapai dari penelitian ini adalah Untuk membandingkan performa algoritma Djikstra dan algoritma A Star untuk penyelesaian game Pac-Man. Hasil yang didapatkan untuk algoritma Dijkstra adalah 2 kali gagal, dan 1 kali berhasil dalam menyelesaikan permainan dengan score 4100, 3350, 3940, sedangkan untuk algoritma A Star mendapatkan hasil 2 kali berhasil, dan 1 kali gagal dengan score 4300, 2350, 3450. Dari kedua Algoritma yang digunakan untuk menyelesaikan permaian PAC-MAN dengan mendapatkan score terbaik adalah algoritma A Star.

Title

Found 27 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 27 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 27 Documents
Search