Article Per Year (5 Year)
p-Index From 2021 - 2026
1.235
P-Index
This Author published in this journals
All Journal International Journal of Recent Technology and Applied Science (IJORTAS) JUKI : Jurnal Komputer dan Informatika Jurnal Indonesia : Manajemen Informatika dan Komunikasi Jurnal Ilmu Komputer dan Teknik Informatika Journal of Electrical Engineering Research
Eka Pandu Cynthia, Eka Pandu
UIN Sultan Syarif Kasim Riau
Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Social Sciences

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

Found 7 Documents
Search

 1 
Klasifikasi Sentimen Masyarakat di Twitter terhadap Puan Maharani dengan Metode Modified K-Nearest Neighbor Putra, Wahyu Eka; Fikry, Muhammad; Yusra; Yanto, Febi; Cynthia, Eka Pandu
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 1 (2025): Januari
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v6i1.1211

Abstract

This study aims to address the challenges in classifying sentiment on Twitter regarding Puan Maharani by implementing the Modified K-Nearest Neighbor (MK-NN) method, supplemented with feature weighting and feature selection techniques. This method is designed to improve accuracy by assigning higher weights to important features and reducing data dimensions to avoid overfitting. Data is collected using a crawling technique on Indonesian-language tweets, which are then manually labeled and processed through a preprocessing stage. The testing results using the modified K-Nearest Neighbor (MK-NN) method with confusion matrices show the model's performance at three different values of K (3, 5, and 7) and data ratios of 90:10, 80:20, and 70:30. With a 90:10 data ratio and K=3, the method achieved the highest accuracy of 89.0%. These results indicate that the combination of MK-NN and related techniques is highly effective in sentiment classification, offering an innovative solution to the limitations of conventional methods. These findings have potential applications in public opinion analysis, particularly for supporting data-driven strategic decision-making.
Penerapan Naïve Bayes Classifier dalam Klasifikasi Sentimen Publik di Twitter terhadap Puan Maharani Hidayat, Rizki; Fikry, Muhammad; Yusra, Yusra; Yanto, Febi; Cynthia, Eka Pandu
JUKI : Jurnal Komputer dan Informatika Vol. 6 No. 1 (2024): JUKI : Jurnal Komputer dan Informatika, Edisi Mei 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53842/juki.v6i1.479

Abstract

Twitter adalah salah satu jejaring sosial terpopuler di Indonesia, dengan 18,45 juta pengguna aktif pada tahun 2022. Politisi berpengaruh Puan Maharani menjadi topik hangat di pesta ulang tahunnya di tengah protes harga bahan bakar. Analisis sentimen dapat membantu memahami keseluruhan sentimen yang diungkapkan di Twitter tentang Puan Maharani. Dua jenis dataset yang digunakan dalam penelitian ini, yaitu dataset tidak seimbang (9000 tweet: 7800 positif, 1200 negatif) dan dataset seimbang (2400 tweet: 1200 positif, 1200 negatif). Metode Naive Bayes classifier digunakan untuk klasifikasi sentimen, meliputi pengumpulan data, pelabelan, preprocessing, pembobotan TF-IDF, seleksi fitur, pembagian data, klasifikasi Naive Bayes, dan evaluasi dengan confusion matrix. Data dibagi dengan rasio 70:30, 80:20 dan 90:10 untuk data latih serta data uji. Feature selection menggunakan threshold 0,001. Merujuk hasil penelitian yang dilaksanakan, bisa disimpulkan bahwsanya analisis sentimen dapat menjadi alat yang efektif untuk memahami pendapat masyarakat khususnya netizen di platform Twitter terkait dengan persepsi terhadap Puan Maharani. Nilai akurasi tertinggi dari dataset tidak seimbang didapatkan yaitu sebesar 88.89% pada rasio pembagian data latih dan data uji 90:10 serta akurasi tertinggi dari dataset seimbang sebesar 81.0% pada rasio pembagian data 90:10.
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

Abstract

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.
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

Abstract

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

Abstract

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

Abstract

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.
Explaining Cholesterol-Related Coronary Artery Disease Risk Using Machine Learning and SHAP Cynthia, Eka Pandu; Mohamad Samuri, Suzani; Shir Li, Wang; Saeed, Alabbas Hussein; Permana, Inggih; Yanto, Febi
International Journal of Recent Technology and Applied Science (IJORTAS) Vol 8 No 1: March 2026
Publisher : Lamintang Education and Training Centre, in collaboration with the International Association of Educators, Scientists, Technologists, and Engineers (IA-ESTE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36079/lamintang.ijortas-0801.920

Abstract

Coronary Artery Disease (CAD) remains a leading cause of global mortality, with dyslipidemia recognized as a major modifiable risk factor. This study investigates the relationship between serum lipid parameters and CAD using the Z-Alizadeh Sani clinical dataset comprising 303 patients with 55 clinical, biochemical, and electrocardiographic attributes. Logistic Regression (LR) and Random Forest (RF) models were developed to predict CAD status, supported by a standardized preprocessing pipeline, multi-split train–test evaluation (70/30, 80/20, 90/10), and performance assessment using Accuracy, Precision, Recall, F1-Score, and AUC-ROC. SHapley Additive exPlanations (SHAP) were employed to enhance model interpretability and quantify the contribution of lipid-related and clinical features to individual predictions. The RF model consistently outperformed LR across all split configurations, achieving a maximum AUC of 0.96, while LR attained an AUC of 0.90. SHAP analysis revealed that total cholesterol (CHOL) and low-density lipoprotein (LDL) were strong positive predictors of CAD, whereas high-density lipoprotein (HDL) exhibited a protective effect, in line with established cardiovascular pathophysiology. These findings demonstrate that integrating explainable machine learning with routine clinical lipid profiles can provide accurate and transparent decision support for early CAD risk stratification.
Co-Authors Cynthia, Dessy Nia Cynthia, Maulidania Mediawati Febi Yanto Hidayat, Rizki Inggih Permana mohamad samuri, suzani Muhammad Fikry Putra, Wahyu Eka Saeed, Alabbas Hussein Shir Li, Wang Yusra Yusra, Yusra