Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Informasi Faktor Exacta Cyberspace: Jurnal Pendidikan Teknologi Informasi Eduvest - Journal of Universal Studies Telematika MKOM
Denni Kurniawan
Universitas Budi Luhur
Aerospace Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Health Professions Industrial & Manufacturing Engineering Library & Information Science Neuroscience Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
SISTEM PENDUKUNG KEPUTUSAN DALAM PENILAIAN PRESTASI KERJA MENGGUNAKAN FUZZY-AHP DAN SAW Denni Kurniawan; Catur Nugroho
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 3, No 2 (2019)
Publisher : UIN Ar-Raniry

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (879.469 KB) | DOI: 10.22373/cj.v3i2.5359

Abstract

Employee appraisal is one of the company's efforts to evaluate employee performance and productivity. As the result, the company can also give awards to employees who are considered gives high contribution to company.  However, it is not easy to measure employee performance, because most them only based on the leaders valuation which is subjective and do not based on standards. The objective of this study is to develop a system to assess employee performance by using a combination of Fuzzy Logic, Analytic Hierarchy Process (AHP) and Simple Additive Weighting (SAW) methods. The AHP is a method of weighting in based on multi-criteria decisions. This method uses a pairwise comparison matrix to  calculate the weight value. The Fuzzy logic is used to overcome the problem, where the AHP method is indicated still have subjectivity in criteria evaluation. After calculation based on combination of Fuzzy-AHP methods, the final result of employee performance will determined by using SAW method. The employee with the highest weight value will considered as the most productive employee and also gives the best performance in the company.
Optimization Sentimen Analysis using CRISP-DM and Naive Bayes Methods Implemented on Social Media Denni Kurniawan; Muhammad Yasir
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 6, No 2 (2022)
Publisher : UIN Ar-Raniry

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/cj.v6i2.12793

Abstract

Freedom of expression on social media Twitter not always give positive value, because sometimes can contains negative things such as fake news, spreads hate speech, and racism, where these kinds of tweet can be categorized as an act of Cyberbullying. Where this cyberbullying tends to increase every time. The aim of this study is to use the Naïve Bayes method in classifying types of sentiment on Twitter. The keyword used is Saipul Jamil, and the tweet was taken in September 2021. A total of 18,067 tweets were collected and then they will be labelled with a positive or negative value. This study also uses the CRIPS-DM method which is consist of Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment stages. The results of this study obtained the value of Accuracy (85.6%), Negative Recall (82.1%), Positive Recall (90.23%), and Negative Precision (91.76%) Positive Precision (79.18%).
PENGAMANAN DATA BERBASIS MOBILE ANDROID DENGAN PENGGABUNGAN LINEAR FEEDBACK SHIFT REGISTER (LFSR) DAN MODIFIKASI MATRIKS KUNCI ALGORITMA KRIPTOGRAFI PLAYFAIR CIPHER Denni Kurniawan; Bayu Priyatna
Telematika MKOM Vol 10, No 1 (2018): Jurnal Telematika MKOM Vol. 10 No. 1 Maret 2018
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (554.688 KB)

Abstract

Playfair cipher merupakan metode enkripsi klasik yang sulit untuk dikriptanalisis secara manual namun selain dari kelebihan yang terdapat pada plyafair cipher terdapat juga banyak kekurangan diantaranya, dapat dipecahkan dengan menggunakan informasi frekuensi kemunculan bigram, tidak dapat memasukkan huruf kecil, angka dan karakter khusus pada saat melakukan enkripsi.. Penelitian ini melakukan modifikasi pada matriks kunci algoritma kriptografi playfair dan menggabungkan dengan algoritma Linear Feedback Shift Register (LFSR), dengan merubah ukuran matriks kunci 13x13 maka playfair cipher mampu menyisipkan karakter sebanyak 196 karakter terdiri dari huruf kapital, huruf kecil. Hasil perhitungan dengan metode avalanche effect didapatkan nilai rata-rata 43,59% pada playfair cipher yang dilakukan modifikasi kunci matriks 13x13 dan digabung dengan generator LFSR, 2,15% pada playfair cipher kunci matriks 10x10 tanpa digabung dengan LFSR dan 34,41% pada playfair klasik 5x5. Bahwa playfair cipher yang telah dimodifikasi dan digabung dengan generator LFSR ini lebih kuat dari playfair cipher sebelumnya. Hasil pengujian kompleksitas waktu memiliki enkripsi dan dekripsi yang cepat.
Komparasi Pengaruh Model Klasifikasi Naive Bayes dan Support Vector Machine Pada Analisis Data Sentimen Di Bidang Pendidikan Fajriah, Riri; Kurniawan, Denni
Faktor Exacta Vol 17, No 2 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i2.22342

Abstract

Optimalisasi Model Klasifikasi Naive Bayes dan Support Vector Machine Dengan Fast Text dan Chi Square Pada Analisis Sentimen Penyelenggaraan Pembelajaran Pemrograman di Fasilkom Universitas Mercu Buana Fajriah, Riri; Kurniawan, Denni
Faktor Exacta Vol 17, No 4 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i4.24751

Abstract

The implementation of effective programming learning at the Faculty of Computer Science, Universitas Mercu Buana is one of important strategy. This expectation is constrained because the results of the evaluation of the competency achievements of many graduates have not mastered programming skills well. Therefore, the research conducted is related to analyzing the sentiments of all stakeholders who have been involved with the implementation of programming learning. The data source based on the results of an online questionnaire. The sentiment data analysis process uses the Cross Industry Standard Process for Data Mining method with the Naive Bayes and Support Vector Machine classification models. The result of the research is an increase in the accuracy of sentiment analysis data processing which previously only used the Naive Bayes Algorithm only achieving an accuracy of 65.56% and by optimizing with Feature Extraction Fast Text, the accuracy achievement increased to 90.49%. While optimizing the algorithm using Feature Selection Chi Square can make the Support Vector Machine classification model optimized to achieve an accuracy value of 99.58% from the previous accuracy achievement was 90.72%. This research can prove that optimizing the application classification model algorithms can use using Fast Text and Chi Square techniques.
Appropriateness of Student Major Selection Using Naive Bayes and K-Nearest Neighbor Algorithms at SMK Plus Al Musyarrofah Kamaluddin Mustofa; Tyan Tasa; Denni Kurniawan
Eduvest - Journal of Universal Studies Vol. 4 No. 6 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i6.1483

Abstract

The process of selecting a major is a critical stage for students because it can influence their motivation and learning outcomes while attending school, especially at Vocational High Schools (SMK). This challenge is becoming more significant with the emergence of many new schools in various cities and districts in Indonesia, especially in DKI Jakarta Province. Prospective students often choose majors not based on personal interests, which can then result in lower grades, especially in productive subjects or certain competencies. To overcome this problem, a major suitability system is needed that can provide recommendations based on student abilities through certain attributes. In this research, a department suitability classification process was carried out using the Naive Bayes and k-Nearest Neighbor methods using data from 238 tenth grade (X) students for the 2023/2024 academic year, which included 9 relevant attributes. The testing process was carried out with a composition of training data and test data in five comparisons, namely 90:10, 80:20, 70:30, 60:40, and 50:50. The research results show that the 80:20 composition provides the best results, with k-Nearest Neighbor achieving recall, accuracy and precision levels of 100%. On the other hand, the Naive Bayes Classifier produces a recall rate of 61%, with an accuracy of 73%. These results indicate that k-Nearest Neighbor is superior in predicting major suitability compared to Naive Bayes under these conditions.
Optimizing Online Gambling Site Detection via XLM-RoBERTa and ResNet34-Based Early Fusion Rahmat Nugroho; Denni Kurniawan
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

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

Abstract

The illegal online gambling ecosystem in Indonesia has evolved into a persistent cyber threat, driven by the adaptability of threat actors in manipulating content and network infrastructure. Conventional detection methods relying on domain reputation-based blocking (blacklists) and keyword matching now face systemic failure due to sophisticated evasion techniques such as domain hopping, SEO manipulation, and content cloaking. This study proposes an automated detection framework based on Multimodal Deep Learning that simultaneously integrates semantic, visual, and infrastructure metadata analysis. We employ an Early Fusion strategy by constructing a 1,284-dimensional combined feature vector, consisting of 768 dimensions of text embeddings from the XLM-RoBERTa model, 512 dimensions of global visual features from the ResNet34 architecture, and 4 hybrid technical metadata features. To ensure high-quality ground truth and address previous transparency concerns, this approach is evaluated using a balanced dataset of 3,546 sites constructed via active crawling using the Playwright framework. The data was rigorously verified by a panel of five security experts using a majority voting scheme, achieving a Fleiss’ Kappa agreement score of 0.87, which indicates almost perfect consensus. Experimental results demonstrate that the Early Fusion model with Random Forest classification achieved an F1-Score of 95.52%, significantly outperforming the Late Fusion strategy (91.62%) and other unimodal approaches. Furthermore, this study empirically confirms the phenomenon of adversarial adaptation, revealing that traditional metadata features contribute only 0.62% to the classification decision. These findings underscore the urgency of a paradigm shift towards Deep Content Inspection to modernize national cybersecurity filtering infrastructure.
Co-Authors Bayu Priyatna Catur Nugroho Fajriah, Riri Kamaluddin Mustofa Muhammad Yasir Rahmat Nugroho Tyan Tasa