Claim Missing Document
Check
Articles

Found 6 Documents
Search

Analisis Peminjaman Ruangan di Gedung Creative Center Sumedang Menggunakan Metode PIECES Dipa Arya Pangestu; Asep Saeppani
Jurnal Penelitian Teknologi Informasi dan Sains Vol. 3 No. 1 (2025): JURNAL PENELITIAN TEKNOLOGI INFORMASI DAN SAINS
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jptis.v3i1.2998

Abstract

The utilization of information technology can provide benefits that are faster, more accurate, and more transparent. One application is in a room loan system that can avoid schedule clashes, increase user productivity, and make the administration process faster and more efficient. This research was conducted at the Sumedang Regency Tourism, Culture, Youth and Sports Office in the creative economy sector, which manages room loans at the Creative Center Sumedang Building. The current room loan system at the Creative Center Sumedang Building uses Google Form which experiences various obstacles, such as conflicting schedules and inefficient administrative processes. This study aims to evaluate and provide recommendations for a website-based system that is more structured and user-friendly to support room loan management. This research uses the PIECES (Performance, Information, Economy, Control, Efficiency, and Service) analysis method to evaluate the weaknesses of the current system and provide recommendations for website-based improvements with UI/UX design integration. Data was collected through observations and interviews with managers and users of room lending services. The results of the analysis show that a website-based system can improve the efficiency of room loan management, ensure a more organized schedule, and facilitate automatic data management. The proposed solution includes automatic room checking and a simpler interface design. With the implementation of an integrated and user-friendly system, room loan management is expected to become more effective and support optimal service.
OPTIMIZE TEXTILE BOOK RECOMMENDATION SYSTEM USING DEEP LEARNING ALGORITHMS Sitti Nur Alam; Asep Saeppani; Iwan Setiawan
Indonesian Journal of Education (INJOE) Vol. 4 No. 1 (2024): APRIL
Publisher : CV. ADIBA AISHA AMIRA

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

Abstract

The research aims to optimize the recommendation system for textile books by applying deep learning algorithms. The textile industry, rich in content and material variation, requires a system of recommendations that can accurately accommodate the diverse needs of its users. Deep learning, with its sophistication in processing large and complex data, offers solutions in improving the quality of recommendations. The study explores the use of deep learning models in interpreting user preferences and book characteristics, with the hope of producing more relevant and personal predictions. Research methods that literature conducts systematically through the collection of data from scientific sources such as journals, conferences, and related articles published in the last decade. The results show that deep learning algorithms such as Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN) have been successfully applied in improving the accuracy of book recommendation systems, including in textile contexts. These models are able to understand and process textile information and user preferences more deeply than traditional algorithms. The research also revealed important factors that influence model performance, such as data quantity and quality, model architecture, and parameter setting. Although there are limitations associated with resource use and the need for large datasets, the use of deep learning algorithms in recommendation systems for textile books shows significant potential in improving personalization and user satisfaction.
Analisis Sentimen Publik Program Makan Bergizi Gratis Menggunakan Support Vector Machine M.Arif Firmansyah; Asep Saeppani; Irfan Fadil
JPNM Jurnal Pustaka Nusantara Multidisiplin Vol. 3 No. 4 (2025): December : Jurnal Pustaka Nusantara Multidisiplin (ACCEPTED)
Publisher : SM Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59945/jpnm.v3i4.805

Abstract

Ketersediaan gizi merupakan faktor utama yang menunjang pertumbuhan anak dan kualitas sumber daya manusia. Pemerintah Indonesia memperkenalkan Program Makan Bergizi Gratis (MBG) sebagai langkah strategis untuk mengatasi masalah gizi buruk dan stunting pada anak sekolah. Penelitian ini berfokus pada analisis sentimen masyarakat terhadap program MBG dengan memanfaatkan algoritma Support Vector Machine (SVM) berbasis pengolahan Bahasa Alami (NLP). Data berasal dari 1.574 komentar di media sosial X (Twitter) yang diproses melalui tahapan pembersihan data, tokenisasi, penghapusan stopword, stemming, dan pembobotan TF-IDF. Hasil pengujian menunjukkan bahwa model SVM meraih akurasi 78%, sedangkan Logistic Regression mencapai 82%, dengan sebagian besar sentimen publik cenderung positif. Temuan ini mengindikasikan bahwa masyarakat menerima MBG dengan baik. Penelitian ini turut memperlihatkan manfaat penerapan machine learning untuk menganalisis kebijakan publik dan dapat digunakan pemerintah sebagai acuan menyusun strategi komunikasi dan meningkatkan efektivitas program gizi nasional
Analisi Perbandingan Kinerja Algoritma AES-128 GCM dan AES-256 GCM Pada Protokol TLS 1.2 Di Server Ngnix Muhammad Arifin Ilham; Dody Herdiana; M.Agreindra Helmiawan; Asep Saeppani
Router : Jurnal Teknik Informatika dan Terapan Vol. 3 No. 4 (2025): Desember : Router : Jurnal Teknik Informatika dan Terapan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/router.v3i4.743

Abstract

While TLS 1.3 is the latest standard, TLS 1.2 remains widely implemented in many cloud infrastructures. The selection of cipher suites in TLS 1.2, particularly between AES-128-GCM and AES-256-GCM, presents a trade-off between cryptographic strength and system performance. This research aims to analyze the performance comparison of these two algorithms on an Nginx server to determine the optimal configuration for cloud storage services. The study uses a quantitative experimental method by benchmarking two scenarios: (A) Strict (AES-256-GCM), and (B) Balanced (AES-128-GCM). Performance metrics measured include Requests Per Second (RPS), Latency, and Throughput. The results show that handshake performance (RPS and Latency) is nearly identical across all scenarios. However, in large file transfer tests, the AES-128-GCM algorithm (Scenario B) achieved a throughput of 32.4 MB/s, which is 12.5% faster than AES-256-GCM (28.8 MB/s). This study concludes that AES-128-GCM provides the best balance of security and efficiency for data-intensive environments.
Analisi Perbandingan Kinerja Algoritma AES-128 GCM dan AES-256 GCM Pada Protokol TLS 1.2 Di Server Ngnix Muhammad Arifin Ilham; Dody Herdiana; M.Agreindra Helmiawan; Asep Saeppani
Router : Jurnal Teknik Informatika dan Terapan Vol. 3 No. 4 (2025): Desember : Router : Jurnal Teknik Informatika dan Terapan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/router.v3i4.743

Abstract

While TLS 1.3 is the latest standard, TLS 1.2 remains widely implemented in many cloud infrastructures. The selection of cipher suites in TLS 1.2, particularly between AES-128-GCM and AES-256-GCM, presents a trade-off between cryptographic strength and system performance. This research aims to analyze the performance comparison of these two algorithms on an Nginx server to determine the optimal configuration for cloud storage services. The study uses a quantitative experimental method by benchmarking two scenarios: (A) Strict (AES-256-GCM), and (B) Balanced (AES-128-GCM). Performance metrics measured include Requests Per Second (RPS), Latency, and Throughput. The results show that handshake performance (RPS and Latency) is nearly identical across all scenarios. However, in large file transfer tests, the AES-128-GCM algorithm (Scenario B) achieved a throughput of 32.4 MB/s, which is 12.5% faster than AES-256-GCM (28.8 MB/s). This study concludes that AES-128-GCM provides the best balance of security and efficiency for data-intensive environments.
Analisis Perbandingan Algoritma Regresi Linear dan Decision Tree untuk Prediksi Dropout Mahasiswa Abdah Syakiroh Gustian; Asep Saeppani
Merkurius : Jurnal Riset Sistem Informasi dan Teknik Informatika Vol. 4 No. 1 (2026): Januari : Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/merkurius.v4i1.1362

Abstract

This study aims to develop an effective predictive model for identifying students at risk of academic dropout using the Decision Tree and Linear Regression algorithms. The data used are sourced from the public Kaggle dataset Students Dropout and Academic Success, which includes demographic, socioeconomic, and academic performance variables for each semester. The research method includes data preprocessing stages, such as data cleaning, label encoding for categorical variables, numeric feature normalization, and target class adjustment to focus on binary classification, namely Dropout and Graduate. The modeling process is carried out by comparing the performance of the two algorithms using evaluation metrics of accuracy, precision, and recall. The results show that the Decision Tree algorithm has superior performance compared to Linear Regression in mapping non-linear patterns in student data. Feature importance analysis revealed that the number of curricular units in the second semester and tuition payment status are the main predictors of dropout risk. These findings are expected to assist educational institutions in implementing early interventions to improve student academic success.