Article Per Year (5 Year)
p-Index From 2021 - 2026
2.928
P-Index
This Author published in this journals
All Journal JSM (Jurnal SIFO Mikroskil) Jurnal TIMES Jurnal Teknologi Informasi dan Ilmu Komputer InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan JURNAL MEDIA INFORMATIKA BUDIDARMA Syntax Literate: Jurnal Ilmiah Indonesia Indonesian Journal of Artificial Intelligence and Data Mining METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Martabe : Jurnal Pengabdian Kepada Masyarakat METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Data Science: Journal of Computing and Applied Informatics Jambura Journal of Mathematics Building of Informatics, Technology and Science Jurnal Mantik INFOKUM Journal of Computer Networks, Architecture and High Performance Computing Journal La Multiapp Journal of Novel Engineering Science and Technology
Ronsen Purba
Magister Komputer, STMIK Mikroskil
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Social Sciences Other

Published : 36 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 36 Documents
Search

 1   2   3   4 
Optimizing Brain Tumor Classification with Freeze-5 VGG16 and Dataset Fusion Vicky; Ronsen Purba
Journal of Novel Engineering Science and Technology Vol. 4 No. 02 (2025): Journal of Novel Engineering Science and Technology
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/jnest.v4i02.999

Abstract

Magnetic resonance imaging (MRI)-based brain tumor classification is pivotal for early diagnosis and treatment planning. This study enhances the VGG16 pretrained model through freeze-5 fine-tuning (i.e., freezing the first five convolutional layers) and dataset fusion of two public repositories, yielding 5,023 training and 1,311 testing images. Preprocessing includes normalization and grayscale-to-RGB conversion, followed by moderate augmentation (rotation ≤ 15°, shift ≤ 0.1, zoom ≤ 0.1, brightness [0.9–1.1]). The base VGG16 (without top layers) is extended with GlobalAveragePooling2D, Dense (1024, ReLU), Dropout (0.5), and Dense (4, softmax) layers. The model is compiled with the Adam optimizer (lr=1e-4), EarlyStopping, and ReduceLROnPlateau callbacks. On the test set, the proposed configuration achieves peak accuracy of 99.16 % and macro-F1 of 0.99, outperforming prior hybrid approaches. An ablation study confirms that the freeze-5 strategy combined with data augmentation significantly boosts generalization without overfitting. These results underscore the critical role of optimal layer-freezing and dataset fusion in brain tumor classification. Future work will explore ensemble architecture and real-time clinical deployment.
Combination of Regression and ARIMA Methods ( Reg – ARIMA ) Stock Price Prediction Model Br. Sinulingga, Wita Oktaviana; Purba, Ronsen; Fermi Pasha, Muhammad
Journal of Computer Networks, Architecture and High Performance Computing Vol. 7 No. 1 (2025): Article Research January 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v7i1.5474

Abstract

This research is motivated by the limitations of the ARIMA method, which is only suitable for short-term forecasting and specific periods. Therefore, a combination of Regression and ARIMA methods (Reg- ARIMA) is introduced to predict stock prices over a longer period. The purpose of this study is to implement a combination of Regression and ARIMA methods to build a stock price prediction model. The research methodology involves using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) to measure the accuracy of the generated prediction model. The study results indicate significant variations in MAPE and RMSE values among different stocks, reflecting the performance and liquidity of those stock markets. For example, stocks such as ITMG and UNTR show strong performance, while stocks with low closing values may carry higher risks or slower growth. In conclusion, the Reg-ARIMA combination method is effective in extending the range of stock price forecasting, providing a more accurate alternative compared to using only the ARIMA method. This suggests that this hybrid approach can be used to enhance investment decision-making strategies in the stock market.
Pemanfaatan Analisis Sentimen dari Ulasan Produk di Youtube untuk Pengembangan Produk Baru Limbong, Ricky Paian; Ronsen Purba; Muhammad Fermi Pasha
Syntax Literate Jurnal Ilmiah Indonesia
Publisher : Syntax Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36418/syntax-literate.v9i7.13568

Abstract

Pengembangan produk yang sukses memerlukan pemahaman tentang kebutuhan dan preferensi pelanggan. Analisis sentimen telah muncul sebagai alat yang dapat mengumpulkan pendapat dari pelanggan dalam mengembangkan yang lebih baik. Penelitian ini bertujuan untuk mengeksplorasi pemanfaatan analisis sentimen dari ulasan produk di YouTube dalam rangka pengembangan produk baru. Dengan menganalisis konten yang dibuat oleh pengguna, penelitian ini bertujuan untuk menghasilkan informasi berupa prioritas fitur produk. Metode penelitian meliputi pengumpulan dan prapemrosesan data ulasan produk dari platform YouTube, dengan menerapkan teknik pemrosesan teks seperti case folding, penghilangan kata yang tidak relevan, tokenisasi, dan stemming. Analisis sentimen dilakukan menggunakan metode Support Vector Machine (SVM) untuk mengklasifikasikan sentimen yang diekspresikan dalam ulasan tersebut. model yang telah dilatih kemudian digunakan untuk memprediksi dan memberi label sentimen pada ulasan produk baru. Temuan penelitian ini menunjukkan bahwa analisis sentimen dapat membantu proses pengembangan produk baru dengan memperhatikan prioritas fitur produk yang memiliki kekurangan. Pendekatan ini memungkinkan perusahaan untuk memahami kebutuhan pelanggan, membuat keputusan yang tepat dalam memberikan fokus untuk peningkatan fitur produk untuk perilisan selanjutnya. Integrasi analisis sentimen dalam proses pengembangan produk baru dapat memanfaatkan opini konsumen untuk merilis produk yang lebih baik.
PENINGKATAN KREATIVITAS DAN PROPOSISI NILAI STARTUP DIGITAL: TAHAP IDEATION PADA SMA SWASTA PRIMBANA MEDAN Caroline Barus, Andreani; Agustina, Agustina; Halim, Fandi; Purba, Ronsen
Martabe : Jurnal Pengabdian Kepada Masyarakat Vol 7, No 7 (2024): MARTABE : JURNAL PENGABDIAN MASYARAKAT
Publisher : Universitas Muhammadiyah Tapanuli Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31604/jpm.v7i7.2480-2488

Abstract

Kewirausahaan saat ini terus berkembang dan telah menjadi bagian dari struktur kurikulum dari sekolah-sekolah yang menerapkan Kurikulum Merdeka Belajar untuk SMA. Saat ini kegiatan kewirausahaan sering dikaitkan dengan teknologi digital. Adanya pengetahuan akan ilmu komputer kemudian dikombinasikan dengan pengetahuan mengenai inovasi kewirausahaan digital startup, diharapkan dapat meningkatkan pengetahuan siswa-siswa terhadap startup digital. Kegiatan pengabdian dilakukan pada SMA Swasta Primbana Medan dengan tujuan meningkatkan kreativitas dan pengenalan proposisi nilai terutama untuk gagasan startup digital. Topik kegiatan meliputi identifikasi ide startup, konsep proposisi nilai dalam tahap ideation, dan pemodelan dengan value proposition canvas. di akhir kegiatan peserta diberi ketrampilan untuk menggunakan tools renderforest sebagai bagian dari presentasi gagasan (idea pitching). Kegiatan pengabdian dilaksanakan di lab komputer SMA Swasta Primbana Medan selama dua hari, dengan peserta merupakan siswa kelas 1. Hasil evaluasi kegiatan menunjukkan adanya peningkatan pemahaman dan kemampuan para peserta secara signifikan pada SMA Swasta Primbana Medan.
Integration of ECDHE Curve25519, RSASSA-PSS, and AES-256 for Enhanced PrivateDH Key Exchange Protocol in End-to-End Communication Ardi Saputra; Ronsen Purba
Journal of Novel Engineering Science and Technology Vol. 4 No. 03 (2025): Journal of Novel Engineering Science and Technology
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/jnest.v4i03.1275

Abstract

The growing demand for secure digital communication calls for cryptographic protocols that are not only efficient but also capable of ensuring message confidentiality, integrity, and authenticity. PrivateDH is one such protocol that combines Diffie-Hellman, RSA, and AES; however, it still exhibits key weaknesses, including the absence of user authentication and reliance on classical Diffie-Hellman algorithms, which are computationally intensive and do not support forward secrecy. This study proposes an enhanced version of the PrivateDH protocol by integrating ECDHE Curve25519 as a replacement for classic DH, and RSASSA-PSS as a robust digital signature mechanism for user authentication. The methodology involves implementing and testing the proposed protocol within a peer-to-peer communication scenario, with performance evaluations based on handshake duration, CPU and memory usage, as well as security assessments including digital signature validation and forward secrecy. The results demonstrate that the enhanced protocol effectively accelerates key exchange, maintains resource efficiency, and provides reliable user authentication. In conclusion, this protocol contributes meaningfully to the advancement of more secure and efficient end-to-end communication systems, aligning with the demands of modern digital environments.
ANALISIS SENTIMEN MENGGUNAKAN MODEL CONCATENATION CLASSIFICATION INDOBERT UNTUK ULASAN PENGGUNA APLIKASI MYTELKOMSEL DI PLAYSTORE Tri Fitria Ningsih; Ronsen Purba; Fermi Pasha
Jurnal TIMES Vol 15 No 1 (2026): Jurnal TIMES
Publisher : STMIK TIME

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51351/jtm.15.1.2026943

Abstract

In the digital era, user reviews of mobile applications have become an important data source for evaluating and improving service quality. This study aims to analyze user sentiment toward the MyTelkomsel application on Google PlayStore using the Concatenation Classification IndoBERT approach, which combines embeddings from IndoBERT and FastText to enrich the semantic representation of text. A total of 30,000 user reviews in Indonesian from 2022 to 2024 were collected through web scraping using the google-play-scraper library. The data was processed through several preprocessing stages, including normalization, cleaning, stopword removal, and stemming, followed by sentiment labeling into five categories: very negative, negative, neutral, positive, and very positive, based on polarity scores. Modeling was performed by combining the [CLS] token vector from IndoBERT (768 dimensions) and the FastText vector (300 dimensions), resulting in a 1068-dimensional vector. The dataset was split into 80% training data, 20% testing data and 80% training data, 10% testing data and 10% validation data . Evaluation using metrics such as accuracy, precision, recall, and F1-score showed high performance, with accuracy reaching 95% in 2022–2023 and increasing to 96% in 2024. These results indicate that the IndoBERT concatenation approach significantly improves sentiment classification accuracy and is effective in handling unstructured user review texts
Co-Authors Adek Efnaldi Rambe Agustina Aldo Alex Sitorus Ali Akbar Lubis Andri Andri, Andri Anisah - Anna Agustiana Anwar Utama Apin Ridwan Ardi Saputra Aritonang, Mendarissan Arwin Arwin Arwin Halim Arwin Halim Arwin Halim Asif Rana Br Sibarani, Sabrina Adela Br. Sinulingga, Wita Oktaviana Caroline Barus, Andreani Erlina Halim Erwin Setiawan Panjaitan Fandi Halim Fandi Presly Simamora Feredy Lestari Pandia Fermi Pasha Fermi Pasha, Muhammad Frans Agus Purba Gilbert Fernando Situmorang Harry Darmawan Hendra - Indra Syahputra Irpan Pardosi Jimmy Nganta Ginting Jimmy Peranginangin Kardika Sidabariba Kelvin Chen Manurung, Juliana Damayanti Mark Dhruba Sikder Maya Silvi Lidya Megawaty Simamora Muhammad Fermi Pasha Munthe, Andreas Nadya Sikana Pasha, Muhammad Fermi Poerianto Poerianto Ricky Paian Limbong Rudy Rudy Sari Fatmawati Sastra Wandi Nduru Sibarani, Sabrina Adela Br Sinaga, Frans Mikael Sio Jurnalis Pipin Sunario Megawan Tri Fitria Ningsih Vicky Winardi, Sunaryo Wita Clarisa Ginting Wulan Sri Lestari Yudi Pratama Hasibuan Yundari, Yundari