Claim Missing Document
Check
Articles

Found 16 Documents
Search

ANALISIS INTEGRITAS DATA PADA KRIPTOGRAFI CITRA DIGITAL MENGGUNAKAN PENGGABUNGAN ARNOLD’S CAT MAP DAN BERNOULLI MAP Ruddy J Suhatril; Rama Dian Syah
Jurnal Ilmiah KOMPUTASI Vol 19, No 1 (2020): Maret
Publisher : STMIK JAKARTA STI&K

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

Abstract

Kriptografi merupakan teknik untuk keamanan data. Perubahan data terenkripsi mungkin terjadi pada saat pengiriman data melalui internet oleh pihak lain. Integritas data diperlukan untuk menghindari hal tersebut. Analisis integritas data diterapkan pada kriptografi citra digital untuk menguji keamanan suatu algoritma kritptografi. Metode kriptografi pada penelitian ini yaitu mengimplementasikan penggabungan algoritma Arnold?s Cat Map dan Bernoulli Map. Pengujian integritas data dilakukan dengan melihat hasil proses dekripsi dari sebuah citra terenkripsi yang sebelumnya sudah mengalami perubahan data. Hasil dari penelitian ini adalah algoritma tidak menjamin integritas data.Keywords: Integritas Data, Kriptografi, Arnold?s Cat Map, Bernoulli Map.
METODE DECISION TREE UNTUK KLASIFIKASI HASIL SELEKSI KOMPETENSI DASAR PADA CPNS 2019 DI ARSIP NASIONAL REPUBLIK INDONESIA Syah, Rama Dian
Jurnal Ilmiah Informatika Komputer Vol 25, No 2 (2020)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2020.v25i2.2750

Abstract

Pelaksanaan seleksi Calon Pegawai Negeri Sipil (CPNS) dilakukan berdasarkan peraturan Badan Kepegawaian Negara di lingkungan instansi pemerintah. Seleksi tes cpns dilakukan dengan beberapa tahapan. Seleksi Kompetensi Dasar (SKD) merupakan tahapan yang diuji berdasarkan parameter penilaian Tes Wawasan Kewarganegaraan (TWK), Tes Intelegensi Umum (TIU), dan Tes Karakter Kepribadian (TKP). Hasil dari SKD dianalisis menggunakan Data Mining. Metode Data Mining yang digunakan yaitu Decision Tree.  Berdasarkan penelitian yang dilakukan pada 344 peserta SKD di Arsip Nasional Republik Indonesia adalah nilai Accuracy = 92.23%, Classification Error = 7.77%, Kappa = 0.879, Recall = 94.84%, dan Precision = 95.79%.
Arsitektur Keamanan Siber Dengan Protokol Denning-Sacco Rama Dian Syah
Jurnal Informatika Universitas Pamulang Vol 5, No 2 (2020): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (157.1 KB) | DOI: 10.32493/informatika.v5i2.5675

Abstract

Currently messages can be transmitted using information and communication technology. The message that is transmitted can contain data and information that is privacy or confidential. Messages that are confidential and privacy are only intended for parties that have been determined. Attacks by unauthorized parties may occur during the process of sending the message. Security in a private or confidential message exchange system is very much needed. The message exchange system is regulated by protocol to avoid certain party attacks. The method used in this research is the Denning-Sacco Protocol which is implemented in the exchange of messages from the sender to the recipient. This protocol uses a security key generated by the Key Distribution Center (KDC). The Denning-Sacco Protocol was developed from the Needham-Schroeder Protocol. This study produces an overview of the architecture of the Denning-Sacco Protocol to overcome the weaknesses of the Needham-Schroeder Protocol called the relpy attack. The steps of exchanging messages using the Denning-Sacco Protocol are explained in detail.
Performa Algoritma User K-Nearest Neighbors pada Sistem Rekomendasi di Tokopedia Rama Dian Syah
Jurnal Informatika Universitas Pamulang Vol 5, No 3 (2020): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v5i3.6312

Abstract

The biggest marketplace in Indonesia such as Tokopedia has data on e-commerce activities that always increase with time. Large data growth in Marketplace can cause problems for users. Buyers who have difficulty in finding the best product that suits their needs and sellers who have difficulty in promoting products that are often visited by buyers can be overcome. The recommendation system can overcome these problems by providing specific product recommendations to be promoted and offered to buyers. This research implements the Recommendation System using the Item Rating Prediction Method by applying the User K-Nearest Neighbors Algorithm. The Recommendation System provides recommendations based on ratings on products given by the buyer. Algorithm performance in Recommendation System is measured by the parameters of Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Normalized Mean Absolute Error (NMAE). The performance values obtained are RMSE = 0.713, MAE = 0.488 and NMAE = 0.122. Perfomance values below 1 proves that the User K-Nearest Neighbors Algorithm is suitable as a rating prediction model on recommendation system.
Tinjauan Literatur terhadap Metode Sistem Rekomendasi pada Pasar Online Rama Dian Syah; Ahmad Hidayat
Jurnal Informatika Universitas Pamulang Vol 8, No 1 (2023): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v8i1.20114

Abstract

Product Recommendations for e-commerce activities in online market are important in product promotion to buyers. The Recommendation System in e-commerce can take advantage of growing data to inform the best product recommendations for buyers. Recommendation systems provide great opportunities for businesses so that research on the development of Recommendation System methods is increasing nowadays. This study examines the development of the Recommendation System of e-commerce activities in online market. The purpose of this research is to see a comparison and summary of several studies that have been done. Comparisons and summaries of previous research produce an analysis of research progress and find out problems with the Recommendation System of ecommerce activities in online market. The results of this study provide insight for researchers about the development of research on Recommendation Systems of ecommerce activities in online market.
ENKRIPSI CITRA DIGITAL MENGGUNAKAN KOMPOSISI TRANSPOSISI CAT MAP DAN SUBTITUSI KEY STREAM LOGISTIC MAP Rama Dian Syah; Sarifuddin Madenda; Ruddy J. Suhatril; Suryadi Harmanto
Jurnal Ilmiah Teknologi dan Rekayasa Vol 28, No 3 (2023)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2023.v28i3.7951

Abstract

Transmisi pertukaran data digital melalui jaringan internat menjadi hal penting pada kemajuan teknologi. Risiko pembajakan oleh pihak yang tidak bertanggung jawab mungkin terjadi karena kemudahan dalam pertukaran data. Pengembangan metode enkripsi data yang andal dan kuat adalah solusi untuk risiko ini. Penelitian ini mengusulkan algoritma enkripsi data baru melalui komposisi enkripsi transposisi Cat Map dan enkripsi substitusi Logistic Map. Algoritma yang diusulkan secara bersamaan mengubah posisi data dan mengubah nilai data secara acak. Penelitian telah dilakukan dengan menggunakan beberapa citra dengan berbagai fitur dan ukuran yang berbeda. Analisis keacakan citra hasil enkripsi menunjukkan bahwa histogram intensitas warna piksel memiliki distribusi yang seragam dengan nilai korelasi rendah mendekati 0. Hasil analisis peak signal to noise ratio (PSNR) menunjukkan citra hasil dekripsi sama dengan citra asli . Algoritma yang diusulkan memiliki ruang kunci 3.24 × 1068. Hasil NPCR, UACI dan Entropi menunjukkan algoritma yang diusulkan tahan terhadap serangan diferensial dan serangan entropi.
ANALISIS SENTIMEN TERHADAP APLIKASI GOJEK PADA PLAY STORE MENGGUNAKAN METODE RANDOM FOREST CLASSIFIER Naura Zainaty Rania; Rama Dian Syah
Jurnal Ilmiah Informatika Komputer Vol 29, No 2 (2024)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2024.v29i2.11877

Abstract

Ulasan pengguna aplikasi memiliki peran yang sangat penting dalam menentukan kesuksesan sebuah layanan aplikasi. Analisis sentiment. Teknologi Natural Language Processing (NLP) memungkinkan pengembang untuk mengkategorikan emosi dalam ulasan secara otomatis. Penelitian ini bertujuan untuk melakukan analisis sentimen pada ulasan aplikasi Gojek yang tersedia di Google Playstore menggunakan metode Random Forest Classifier. Dataset yang digunakan sebanyak 50000 ulasan. Model yang dibangun berhasil melakukan prediksi sentiment dengan baik yang dibuktikan dengan nilai akurasi mencapai 89%. Model yang dibangun mampu mengidentifikasi sampel negatif sebanyak 3231 data diprediksi dengan benar (True Negative). Sampel negative sebanyak 298 data diprediksi dengan salah prediksi sebagai positif (False Positive). Sampel negative sebanyak 722 data diprediksi dengan salah sebagai negative (False Negative). Sampel positif sebanyak 5376 data diprediksi dengan benar (True Positive). Penelitian ini menunjukkan sentimen pengguna Gojek cenderung negative sehingga peningkatan layanan Gojek dapat ditingkatkan agar loyalitas pengguna semakin bertambah.
Evaluation of Machine Learning Models for Predicting Cardiovascular Disease Based on Framingham Heart Study Data Suhatril, Ruddy J; Syah, Rama Dian; Hermita, Matrissya; Gunawan, Bhakti; Silfianti, Widya
ILKOM Jurnal Ilmiah Vol 16, No 1 (2024)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v16i1.1952.68-75

Abstract

The Framingham Heart Study Community is a research community that produces data related to Cardiovascular Disease (CVD). This research applies technology to predict CVD using machine learning based on data from the Framingham Heart Study. The eight machine learning algorithms are deployed in this study, they are decision tree, naïve bayes, k-nearest neighbors, support vector machine, random forest, logistic regression, neural network, and gradient boosting.This research uses several stages of research such as load dataset, preprocessing data, data modeling, evaluation of various data modelling, and input new data.  The best performance was produced by the random forest model with an accuracy value of 0.84, a precision value of 0.84, a recall value of 0.85, an f1-score value of 0.79 and an AUC value of 0.72. The prediction generated by the proposed machine learning model is high risk or low risk of CVD.
COMPARATIVE STUDY OF MULTI CRITERIA DECISION MAKING METHODS IN A CASE STUDY OF THE BEST EMPLOYEE DECISION SUPPORT SYSTEMS Istini, Syalis Ibnih Melati; Ahmad Apandi; Rama Dian Syah
International Journal Science and Technology Vol. 3 No. 2 (2024): July: International Journal Science and Technology
Publisher : Asosiasi Dosen Muda Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56127/ijst.v3i2.1581

Abstract

Selecting the best employees is an alternative for companies to maintain and improve the quality of employee work. Being best employee is a matter of pride for every employee, so this good thing will also have an impact on the company. Having employees with good quality will certainly improve the quality of the company itself. Making decisions for the best employees is a challenge for companies because its subjective nature makes the selection inaccurate, so an objective decision-making system is needed according to the criteria. The purpose of this study is to compare three multi-criteria decision-making methods (MCDM) namely AHP (Analysis Hierarchy Process), SAW (Simple Additive Weighting Model) and TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution). Based on comparative studies from several journals, the results of the accuracy levels obtained from different methods show that there are different results from several cases discussed in reference journals, this is due to differences in the number of criteria and alternatives used for analysis.
MODEL MACHINE LEARNING UNTUK DETEKSI TINGKAT KEMATANGAN TANDAN BUAH SEGAR KELAPA SAWIT MENGGUNAKAN METODE YOLOV8 Genoveva, Zahwa; Syah, Rama Dian
Jurnal Pertanian Presisi (Journal of Precision Agriculture) Vol 8, No 2 (2024)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/jpp.2024.v8i2.11848

Abstract

Kemajuan teknologi informasi membawa banyak perubahan dibidang pertanian. Pemanfaatan teknologi dapat dilakukan pada kelapa sawit untuk mendukung pertaniandi Indonesia. Penelitian ini bertujuan untuk membuat model machine learning untuk deteksi tingkat kematangan Tandan Buah Segar (TBS) kelapa sawit menggunakan model YOLOv8. Model machine learning ini dirancang untuk meningkatkan akurasi dan efisiensi penentuan kematangan buah kelapa sawit, yang sangat penting bagi industri kelapa sawit. Dataset yang digunakan dalam penelitian ini terdiri dari 6592 citra yang dikumpulkan dari platform Roboflow, yang mencakup berbagai tingkat kematangan buah kelapa sawit. Metodologi penelitian yang diterapkan adalah Cross Industry Standard Process for Data Mining (CRISP-DM), yang meliputi tahap pemahaman bisnis, pemahaman data, persiapan data, pemodelan, dan evaluasi. Proses pelatihan model machine learning berlangsung selama 3107 jam dengan nilai precision mencapai 0.945, nilai recall mencapai 0.947, dan nilai mean Average Precision (mAP) mencapai 0.98. Model deteksi ini mampu mendeteksi tingkat kematangan kelapa sawit dengan baik yang dibuktikan oleh evaluasi model dengan nilai kurva f1-confidence mencapai 95% serta nilai kurva precision-recall mencapai 98%.