Pendekatan Machine Learning Dengan Menggunakan Algoritma Xgboost (Extreme Gradient Boosting) Untuk Peningkatan Kinerja Klasifikasi Serangan Syn

Gunawan, Rahmad Gunawan; Handika, Erik Suanda; Ismanto, Edi

doi:10.37859/coscitech.v3i3.4356

Cited by 3 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Data Cleaning: Data cleaning atau pembersihan data, merupakan langkah yang dilakukan untuk menghapus gangguan dari data yang tidak konsisten atau tidak memiliki relevansi. Tindakan pembersihan ini akan memiliki dampak pada kinerja teknik/metode data mining karena jumlah dan kompleksitas data yang dikelola akan berkurang [12]. Pada dataset yang digunakan, terdapat data yang bernilai Not a Number (NaN) dan nol.…”

Section: A Data Preprocessingunclassified

Pendekatan Metode Ensemble Learning untuk Deteksi Serangan DDoS menggunakan Soft Voting Classifier

Joses,

Quinevera,

Mardianto

et al. 2024

JEPIN

View full text Add to dashboard Cite

Serangan Distributed Denial of Service (DDoS) adalah jenis serangan yang kompleks dan sering melibatkan berbagai pola lalu lintas jaringan yang berbeda. Model soft voting classifier dapat menggabungkan hasil dari beberapa model klasifikasi yang berbeda, sehingga meningkatkan kemampuan untuk mendeteksi dan mengatasi serangan DDoS dengan berbagai pola dan skenario yang berbeda. Dengan memanfaatkan model soft voting classifier berdasarkan fitur-fitur yang mendukung, dapat meningkatkan ketahanan sistem terhadap serangan DDoS dengan lebih efektif, mengurangi dampaknya, dan memastikan ketersediaan sumber daya jaringan dan layanan internet bagi pengguna yang mengaksesnya. Data yang digunakan dalam penelitian ini menggunakan dataset DDoS yang diperoleh dari situs kaggle.com. Dataset ini memiliki 23 atribut termasuk satu variabel output dengan jumlah data sebanyak 104.245 record. Dilakukan preprocessing pada dataset kemudian diklasifikasi menggunakan lima model machine learning dan sepuluh ensemble learning method untuk mendapatkan hasil akurasi tertinggi. Hasil pengujian menunjukkan bahwa ensemble method sangat optimal dalam mendeteksi serangan DDoS baik menggunakan fitur berdasarkan Information Gain maupun menggunakan fitur berdasarkan Gain Ratio dibandingkan dengan metode machine learning tunggal.

show abstract

Section: A Data Preprocessingunclassified

Pendekatan Metode Ensemble Learning untuk Deteksi Serangan DDoS menggunakan Soft Voting Classifier

Joses,

Quinevera,

Mardianto

et al. 2024

JEPIN

View full text Add to dashboard Cite

show abstract

“…b. Cleaning Sebelum masuk ke tahap data mining, data akan melalui tahap cleaning terlebih dahulu, tujuannya yaitu untuk menghapus data duplikat, memeriksa data yang tidak konsisten, dan memperbaiki data [12]. Jumlah data yang kosong adalah 41 data, sehingga data berubah menjadi 1133 dari 1174 data.…”

Section: Pengumpulan Dataunclassified

Pengelompokan pembagian zakat dengan menggunakan metode clustering k-means

et al. 2023

View full text Add to dashboard Cite

Zakat is a worship that involves property. Zakat is also included in the fourth pillar of Islam which has the aim of purifying the assets of every Muslim by setting aside a portion of his wealth, if it has reached the time and the amount is given to those who are entitled to receive it. The collection and distribution of zakat is usually handled by the Amil Zakat Agency (BAZ) in every region of Indonesia, one of which is in Pekanbaru. In accordance with the regulations, there are two stages in providing assistance to mustahik, namely conducting interviews and field observations, then determining the nominal amount of assistance given to the Mustahik category of recipients of zakat 1, zakat 2, and zakat 3. Problems that are often encountered in determining potential recipients assistance is a way of selecting Mustahik which still uses the manual method, so that it often causes problems such as the length of the selection process and the occurrence of miscalculations so that the results of Mustahik's selection become inaccurate. For that, it is necessary to create analysis that can process data into information. Data mining is a process for processing data into information using statistical techniques, AI, and machine learning. There are many methods in data mining. In this study using the k-means clustering and for testinguse Davies Bouldin Index. based on testing using the davies bouldin index (DBI) cluster 4 is the best cluster with a value of 0.671, where the lower the value, the better the cluster.

show abstract

“…The advantage of the Support Vector Machine algorithm is in generalization by minimizing the occurrence of prediction errors and parameter estimation to find the best hyperplane for different classes [15]. The XGBoost algorithm's advantages are speed, scalability, efficiency, and simplicity [16].…”

Section: Introductionmentioning

confidence: 99%

Hole Detection in Plastic Mulch Using Template Matching and Machine Learning Algorithms

Aziz,

Arkeman,

Kusuma

et al. 2023

j. nas. pendidik. teknik. inform.

View full text Add to dashboard Cite

Mulch is a ground cover material to maintain soil moisture and temperature stability as a plant medium. Mulch also helps prevent weed growth for better plant growth. For planting with plastic mulch, farmers need to make holes in the mulch the day before planting. Precision agriculture is needed because it can obtain savings in input financing, labor, and better yields, so this research aims to identify holes in mulch based on Unmanned Aerial Vehicle images. The advantage of this research is that it can monitor each plant based on the mulch holes, and the number of holes identified can be used as a parameter to estimate the amount of crop production. This research combines Template Matching Algorithm and Machine Learning Algorithm to improve accuracy in predicting holes in mulch. Three machine learning algorithms are used, namely the Random Forest, Support Vector Machine, and XGBoost. The data used is an orthophoto mosaic from aerial photographs. Nine areas were taken from orthophotos to be used as research samples. The results of this study obtained the highest average recall, precision, and f-measure values using the Support Vector Machine algorithm with a recall value of 87.7%, precision of 97.5%, and f-score of 92.3%. This research focuses on reducing detected commission errors. Therefore, omission errors were still detected in the damaged or leaf-covered holes.

show abstract

Pendekatan Machine Learning Dengan Menggunakan Algoritma Xgboost (Extreme Gradient Boosting) Untuk Peningkatan Kinerja Klasifikasi Serangan Syn

Cited by 3 publications

References 4 publications

Pendekatan Metode Ensemble Learning untuk Deteksi Serangan DDoS menggunakan Soft Voting Classifier

Pendekatan Metode Ensemble Learning untuk Deteksi Serangan DDoS menggunakan Soft Voting Classifier

Pengelompokan pembagian zakat dengan menggunakan metode clustering k-means

Hole Detection in Plastic Mulch Using Template Matching and Machine Learning Algorithms

Contact Info

Product

Resources

About