Garuda - Garba Rujukan Digital

Analysis of the Complexity of Heuristic Algorithms for Permutation Optimization in Large-Scale Computing Fitriasih, Sri Hariyati; Cynthia, Eka Pandu; Cynthia, Maulidania Mediawati; Cynthia, Dessy Nia; Remawati, Dwi
Jurnal Ilmu Komputer dan Teknik Informatika Vol. 2 No. 1 (2026): Januari 2026
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/juikti.v2i1.79

Permutation optimization is a fundamental problem in large-scale computing that arises in various applications such as scheduling, resource allocation, and combinatorial decision-making. As the size of the solution space grows exponentially, conventional optimization methods often struggle to achieve acceptable performance within reasonable computational time. Heuristic and metaheuristic algorithms have therefore become widely adopted due to their flexibility and ability to provide near-optimal solutions for NP-hard problems. However, increasing data scale significantly impacts their computational complexity, making efficiency and scalability critical concerns.This study aims to analyze the computational complexity and performance characteristics of several heuristic algorithms applied to permutation optimization in large-scale computing environments. The research employs a quantitative experimental approach combined with theoretical complexity analysis. Greedy heuristic, simulated annealing, genetic algorithm, and adaptive heuristic methods are evaluated using synthetic permutation datasets with varying sizes. Performance is assessed based on execution time, memory usage, scalability, and solution quality. The results indicate that greedy heuristics offer the fastest execution and lowest memory consumption but tend to produce suboptimal solutions due to their local search strategy. Simulated annealing improves solution quality through probabilistic exploration, while genetic algorithms achieve the highest-quality solutions at the cost of substantial computational and memory overhead. Adaptive heuristic algorithms demonstrate a balanced performance by dynamically adjusting parameters during execution, achieving near-optimal solutions with reduced computational complexity. Overall, this research highlights the trade-offs between efficiency and solution quality among heuristic algorithms and emphasizes the potential of adaptive heuristic approaches for large-scale permutation optimization. The findings provide valuable insights for designing efficient and scalable optimization algorithms suitable for real-world large-scale computing applications.

Pembandingan Arsitektur Transformer dan CNN untuk Pengolahan Data Non-Visual Rahmawati, Lailia; Atmojo, Wahyu Tisno; Cynthia, Eka Pandu; Cynthia, Maulidania Mediawati; Cynthia, Dessy Nia
Jurnal Ilmu Komputer dan Teknik Informatika Vol. 2 No. 1 (2026): Januari 2026
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/juikti.v2i1.80

Perkembangan pesat kecerdasan buatan dan pembelajaran mendalam telah mendorong eksplorasi berbagai arsitektur jaringan saraf untuk pengolahan data non-visual, seperti data numerik, sekuensial, dan tekstual. Dua arsitektur yang paling banyak digunakan dan berkembang adalah Convolutional Neural Network (CNN) dan Transformer. Meskipun CNN telah lama digunakan secara luas karena efisiensinya dalam mengekstraksi fitur lokal, arsitektur Transformer dengan mekanisme self-attention menawarkan kemampuan unggul dalam menangkap hubungan global dan dependensi kompleks antar elemen data. Penelitian ini bertujuan untuk membandingkan kinerja dan efisiensi arsitektur CNN dan Transformer dalam pengolahan data non-visual melalui pendekatan eksperimental kuantitatif. Dataset non-visual digunakan dan melalui tahapan pra-pemrosesan sebelum dilakukan pelatihan dan pengujian model. Evaluasi performa dilakukan menggunakan metrik akurasi, precision, recall, dan F1-score, serta analisis efisiensi komputasi berdasarkan waktu pelatihan dan kompleksitas model. Hasil penelitian menunjukkan bahwa Transformer secara konsisten mencapai performa yang lebih tinggi dibandingkan CNN pada seluruh metrik evaluasi, khususnya dalam menangani pola kompleks dan hubungan jangka panjang pada data non-visual. Namun, CNN menunjukkan keunggulan dalam efisiensi komputasi dan kestabilan pelatihan dengan kebutuhan sumber daya yang lebih rendah. Temuan ini mengindikasikan bahwa tidak terdapat satu arsitektur yang sepenuhnya unggul dalam semua aspek, melainkan pemilihan model harus disesuaikan dengan karakteristik data dan kebutuhan aplikasi. Selain itu, penelitian ini menyoroti potensi pendekatan hibrida yang mengombinasikan CNN dan Transformer untuk meningkatkan performa dan generalisasi model. Penelitian ini diharapkan dapat menjadi referensi empiris bagi pengembangan sistem cerdas berbasis pembelajaran mendalam dalam pengolahan data non-visual.

Exploring Feature Pruning Techniques on High-Relevance Datasets for Predictive Analysis Cynthia, Eka Pandu; Cynthia, Maulidania Mediawati; Cynthia, Dessy Nia
Jurnal Ilmu Komputer dan Teknik Informatika Vol. 2 No. 1 (2026): Januari 2026
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/juikti.v2i1.86

In the era of big data, predictive analytics has become a vital approach for extracting actionable insights from high-relevance datasets across various domains, including healthcare, finance, and environmental science. However, the increasing dimensionality of modern datasets poses significant challenges, such as overfitting, high computational costs, and reduced model interpretability, which can negatively impact predictive performance. Feature pruning has emerged as an effective strategy to address these challenges by eliminating irrelevant or redundant features while preserving the most informative attributes for model learning. This study aims to explore and systematically evaluate the effectiveness of multiple feature pruning techniques when applied to high-relevance datasets for predictive analysis. The research adopts an experimental comparative approach by analyzing filter-based, wrapper-based, embedded, and adaptive pruning methods in conjunction with several widely used predictive models, including Random Forest, Support Vector Machine, and Neural Networks. Performance evaluation is conducted using standard metrics such as accuracy, precision, recall, F1-score, and computational training time to assess both predictive quality and efficiency. The experimental results demonstrate that feature pruning significantly enhances model performance and generalization while reducing computational complexity. Among the evaluated techniques, adaptive pruning methods consistently outperform traditional approaches by dynamically capturing complex feature interactions and minimizing information loss. Moreover, the cross-domain analysis reveals that adaptive and embedded pruning techniques exhibit strong scalability and robustness across different dataset characteristics. These findings highlight the critical role of feature pruning as an integral component of predictive modeling pipelines rather than a mere preprocessing step. Overall, this study contributes to a deeper understanding of feature pruning dynamics and provides practical insights for selecting appropriate pruning strategies to improve predictive accuracy, efficiency, and interpretability in high-dimensional data environments.

Perbandingan Algoritma Kriptografi Modern dalam Melindungi Data Transmisi Cynthia, Maulidania Mediawati; Cynthia, Eka Pandu; Cynthia, Dessy Nia
Jurnal Ilmu Komputer dan Teknik Informatika Vol. 2 No. 1 (2026): Januari 2026
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/juikti.v2i1.87

Keamanan data transmisi merupakan aspek penting dalam sistem informasi modern seiring meningkatnya pertukaran data melalui jaringan terbuka. Berbagai ancaman seperti penyadapan, manipulasi data, dan serangan siber menuntut penerapan algoritma kriptografi yang andal dan efisien. Penelitian ini bertujuan untuk membandingkan algoritma kriptografi modern dalam melindungi data transmisi berdasarkan parameter keamanan, kecepatan enkripsi dan dekripsi, ukuran kunci, serta efisiensi penggunaan sumber daya sistem. Metode penelitian yang digunakan adalah pendekatan komparatif eksperimental dengan tahapan meliputi studi literatur, penentuan algoritma dan parameter pengujian, implementasi simulasi, pengumpulan data, serta analisis hasil. Algoritma yang dianalisis meliputi AES, ChaCha20, RSA, dan ECC. Hasil penelitian menunjukkan bahwa algoritma kriptografi simetris, khususnya ChaCha20 dan AES, memiliki performa yang lebih unggul dalam hal kecepatan dan efisiensi sumber daya dibandingkan algoritma asimetris. Sementara itu, algoritma ECC menunjukkan keunggulan signifikan dibandingkan RSA dengan tingkat keamanan tinggi dan ukuran kunci yang lebih kecil. Penelitian ini menyimpulkan bahwa tidak terdapat satu algoritma yang unggul pada semua aspek, sehingga pemilihan algoritma kriptografi harus disesuaikan dengan kebutuhan sistem. Kombinasi algoritma simetris dan asimetris merupakan pendekatan paling efektif dalam melindungi data transmisi pada sistem informasi modern.

Analisis Protokol Routing Adaptif untuk Jaringan Komputer Skala Besar Cynthia, Eka Pandu; Cynthia, Maulidania Mediawati; Cynthia, Dessy Nia
Jurnal Ilmu Komputer dan Teknik Informatika Vol. 2 No. 1 (2026): Januari 2026
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/juikti.v2i1.88

Jaringan komputer skala besar memiliki tingkat kompleksitas dan dinamika yang tinggi, sehingga membutuhkan mekanisme routing yang mampu beradaptasi terhadap perubahan kondisi jaringan secara cepat dan efisien. Protokol routing adaptif dirancang untuk menyesuaikan pemilihan rute berdasarkan kondisi jaringan terkini, seperti beban trafik, kualitas link, dan perubahan topologi. Penelitian ini bertujuan untuk menganalisis kinerja protokol routing adaptif pada jaringan komputer skala besar melalui pendekatan simulasi jaringan. Metode penelitian yang digunakan meliputi perancangan model jaringan, implementasi protokol routing adaptif, serta pengujian kinerja jaringan berdasarkan beberapa parameter utama, yaitu delay, throughput, packet loss, dan waktu konvergensi. Pengujian dilakukan pada beberapa skenario, meliputi kondisi jaringan normal, peningkatan beban trafik, dan kegagalan link. Hasil penelitian menunjukkan bahwa protokol routing adaptif mampu mempertahankan kinerja jaringan yang stabil pada berbagai kondisi pengujian. Nilai delay dan packet loss tetap berada pada tingkat yang rendah, sementara throughput jaringan dapat dipertahankan secara optimal meskipun terjadi gangguan jaringan. Selain itu, protokol routing adaptif menunjukkan waktu konvergensi yang relatif cepat dalam menyesuaikan diri terhadap perubahan topologi jaringan. Berdasarkan hasil tersebut, dapat disimpulkan bahwa protokol routing adaptif efektif untuk diterapkan pada jaringan komputer skala besar yang membutuhkan keandalan, efisiensi, dan kemampuan adaptasi tinggi terhadap dinamika jaringan.

Analisis Efisiensi Sistem Kendali Otomatis pada Jaringan Distribusi Listrik Modern Cynthia, Eka Pandu; Cynthia, Maulidania Mediawati; Cynthia, Dessy Nia
Journal of Electrical Engineering Research Vol. 1 No. 3 (2025): September 2025
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/joeer.v1i3.18

Penelitian ini membahas analisis efisiensi sistem kendali otomatis pada jaringan distribusi listrik modern dalam menghadapi peningkatan beban dan integrasi sumber energi terdistribusi, khususnya pembangkit fotovoltaik. Seiring meningkatnya kebutuhan energi listrik, jaringan distribusi dituntut untuk beroperasi secara lebih efisien, andal, dan responsif terhadap perubahan kondisi sistem. Metode penelitian yang digunakan adalah pendekatan kuantitatif berbasis simulasi dengan memanfaatkan perangkat lunak Electrical Transient Analyzer Program (ETAP). Model jaringan distribusi dirancang untuk merepresentasikan kondisi operasi sebelum dan sesudah penerapan sistem kendali otomatis dengan beberapa skenario, termasuk variasi beban dan penetrasi energi terbarukan. Parameter kinerja yang dianalisis meliputi rugi daya, profil tegangan, stabilitas frekuensi, serta waktu pemulihan gangguan. Hasil penelitian menunjukkan bahwa penerapan sistem kendali otomatis mampu menurunkan rugi daya secara signifikan, memperbaiki profil tegangan pada seluruh bus jaringan, serta meningkatkan keandalan sistem melalui percepatan pemulihan gangguan. Selain itu, sistem kendali otomatis terbukti efektif dalam mengelola fluktuasi daya akibat integrasi pembangkit fotovoltaik sehingga stabilitas sistem tetap terjaga. Temuan ini menunjukkan bahwa sistem kendali otomatis merupakan solusi strategis dalam pengembangan jaringan distribusi listrik yang efisien, andal, dan berkelanjutan.

Evaluation of Cloud Computing Technology in Supporting Distributed Information Systems Cynthia, Eka Pandu; Cynthia, Maulidania Mediawati; Cynthia, Dessy Nia
Journal of Electrical Engineering Research Vol. 1 No. 3 (2025): September 2025
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/joeer.v1i3.21

The rapid growth of distributed information systems has increased the demand for computing infrastructures that are scalable, reliable, and cost-efficient. Cloud computing has emerged as a prominent technological solution capable of addressing these demands by providing on-demand access to configurable computing resources. This study aims to evaluate the effectiveness of cloud computing technology in supporting distributed information systems by examining its capabilities, benefits, and inherent challenges. The research adopts a qualitative descriptive approach based on a systematic review and analysis of relevant academic literature, technical reports, and authoritative industry sources. The evaluation is conducted across several key dimensions, including scalability, availability and reliability, performance efficiency, security and data management, cost effectiveness, and system integration. The results indicate that cloud computing significantly enhances the operational performance of distributed information systems through elastic resource provisioning, fault tolerance mechanisms, and flexible pricing models. Cloud-based architectures also support improved interoperability and system integration through standardized interfaces and service-oriented designs. However, the findings reveal that challenges related to network latency, data privacy, regulatory compliance, and vendor dependency remain critical issues that must be carefully managed. Overall, this study concludes that cloud computing serves as a strong technological foundation for distributed information systems, provided that appropriate architectural designs, governance strategies, and resource management practices are implemented. The results contribute to a deeper understanding of cloud computing adoption and provide practical insights for organizations and system designers seeking to optimize distributed information system performance.

Integrating Artificial Intelligence in the Development of Modern Information Systems Cynthia, Dessy Nia; Cynthia, Maulidania Mediawati; Cynthia, Eka Pandu
Journal of Electrical Engineering Research Vol. 1 No. 3 (2025): September 2025
Publisher : CV. Raskha Media Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64803/joeer.v1i3.22

The development of modern information systems requires more intelligent, adaptive, and efficient data processing capabilities due to the increasing complexity and volume of data. Artificial Intelligence (AI) has emerged as a strategic solution to enhance the ability of information systems to perform analysis, prediction, and data-driven decision support. This study aims to examine the integration of artificial intelligence in the development of modern information systems from the perspective of electrical engineering and systems engineering. The research adopts an applied research approach using a systems engineering methodology, which includes problem identification, literature review, system architecture design, simulational implementation, and performance testing and evaluation. The results indicate that modular integration of artificial intelligence significantly improves data processing efficiency, analytical accuracy, and system adaptability to changing data patterns. AI-based information systems demonstrate superior performance compared to conventional systems, particularly in supporting proactive and predictive decision-making processes. Furthermore, AI integration contributes positively to computational resource efficiency, which is a critical aspect of sustainable information system development. However, the findings also highlight that data quality and proper system architecture design are decisive factors for successful AI implementation. This research provides both conceptual and technical contributions that can serve as a reference for the development of modern AI-driven information systems and as a foundation for future studies in this field.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search