Claim Missing Document
Check
Articles

Found 39 Documents
Search

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.
BERT Model Implementation for Dynamic Sentiment Analysis of Pertamina on Social Media X Purba, Ronsen; Lubis, Rivaldi; Sikana, Nadya; Situmorang, Gilbert Fernando
Engineering Science Letter Vol. 4 No. 02 (2025): Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.001139

Abstract

This study aims to investigate the dynamics of public sentiment on platform X in response to the Pertamina corruption scandal, exploring how trust and perception shifted before and after the incident. Utilizing BERT-based sentiment classification model trained on real-world social media posts, the model achieved a validation loss of 0.5078 and an F1-score of 82.12%, demonstrating strong predictive performance for large-scale sentiment analysis. Results revealed a significant rise in negative sentiment and a decline in positive sentiment following the public disclosure of the scandal on February 25, 2025, reflecting a deep erosion of public trust in Pertamina. Qualitative thematic analysis further identified a shift from neutral or positive discussions focused on service quality and innovation to emotionally charged critiques emphasizing betrayal, distrust and institutional failure. These findings highlight the value of integrating deep learning classification with qualitative insights to monitor real-time public opinion and institutional reputation. The study underscores the critical need for transparency and effective communication strategies during reputational crises to rebuild public confidence. Limitations include the focus on a single social media platform, suggesting future research should incorporate cross-platform and multilingual analyses. Practically, this research offers actionable insights for corporate crisis management and contributes to understanding social media’s role in shaping public trust and accountability in the digital age.
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.
Peningkatan Kemampuan Berpikir Logis Melalui Pelatihan Python pada SMAS Tri Ratna Sibolga: Evaluasi Pre-Post Test Felix, Felix; Purba, Ronsen; Kurniawan, Heru; Tanti; Manurung, Juliana Damayanti
Dedikasi Sains dan Teknologi (DST) Vol. 5 No. 2 (2025): Artikel Pengabdian Nopember 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/dst.v5i2.7018

Abstract

Kemampuan berpikir logis merupakan keterampilan penting dalam mendukung proses pemecahan masalah, pengambilan keputusan, dan pemahaman konsep mata pelajaran. Namun, sistem pembelajaran di sekolah masih banyak menekankan metode hafalan, yang menyebabkan siswa kurang terlatih dalam berpikir kritis dan analitis. Oleh karena itu, kegiatan Pengabdian kepada Masyarakat ini dilakukan dengan tujuan untuk memperkuat kemampuan berpikir logis siswa melalui pelatihan dasar pemrograman Python. Kegiatan ini dilaksanakan di SMAS Tri Ratna Sibolga dan melibatkan siswa kelas XII IPA 33 orang dan XII IPS 29 orang sebagai peserta. Materi pelatihan mencakup pengenalan logika pemrograman, struktur algoritma sederhana, serta latihan menyusun solusi dari studi kasus menggunakan pendekatan logis. Kegiatan berlangsung selama dua hari dan disampaikan melalui metode ceramah, diskusi, dan latihan berbasis konsep pemrograman. Pelaksanaan dimulai dengan pre-test untuk mengukur pemahaman awal siswa, kemudian dilanjutkan dengan penyampaian materi, praktik, dan post-test untuk mengevaluasi hasil. Hasil kegiatan menunjukkan adanya peningkatan skor rata-rata peserta baik dalam aspek pemahaman logika pemrograman sebesar 5,83% dan kemampuan logika dasar sebesar 28,37%. Selain itu, siswa menunjukkan minat yang tinggi dalam mengikuti pelatihan dan berpartisipasi aktif selama kegiatan berlangsung berupa pengisian post test dan test yang lengkap mencapai 74,19%. Kegiatan ini tidak hanya memberikan manfaat bagi siswa, tetapi juga mempererat kerja sama antara universitas dan sekolah mitra. Secara keseluruhan, kegiatan ini berhasil mencapai tujuannya dan memberikan kontribusi positif dalam pengembangan keterampilan berpikir logis siswa di era digital.
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.
New Approach: Customer Segmentation using RFM Model and Demand Classification Fewie Rusly; Ronsen Purba; Muhammad Fermi Pasha
Jurnal Teknologi dan Manajemen Informatika Vol. 11 No. 2 (2025): Desember 2025
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v11i2.16208

Abstract

This research introduces an integrated data mining framework that combines RFM (Recency, Frequency, Monetary) analysis with demand pattern classification—encompassing Smooth, Erratic, Intermittent, and Lumpy categories—to refine customer segmentation strategies. While RFM effectively captures transactional behavior, its scope remains insufficient as it overlooks demand variability and intermittency, which critically influence purchasing dynamics and inventory planning. By incorporating demand classification, this model addresses behavioral dimensions beyond conventional transactional metrics, thereby enhancing segmentation precision and strategic relevance. Customer clustering employs the K-Means algorithm, with cluster optimization validated through Elbow Method and Silhouette Index analyses, yielding five distinct segments: Ideal, Interest, Improve, Inconsistent, and Inactive. Subsequently, Customer Lifetime Value (CLV) is computed by weighting RFM and demand parameters via Analytic Hierarchy Process (AHP), with Consistency Index and Consistency Ratio assessments ensuring methodological rigor. Results are synthesized within an interactive dashboard, facilitating data-driven decision-making in retention strategies, inventory optimization, profitability enhancement, and sustainable business development.
Implementation of the CNN-LSTM Hybrid Model in Predicting Bitcoin Price Fluctuations Candra Wibowo; Ronsen Purba; Muhammad Fermi Pasha
Jurnal Teknologi dan Manajemen Informatika Vol. 11 No. 2 (2025): Desember 2025
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v11i2.16239

Abstract

Digital financial systems of today face formidable obstacles from the extreme price volatility and unpredictability of Bitcoin. Data cleaning, Min-Max normalization, and sequence creation with a sliding window were performed on the daily BTC-USD historical data received from Yahoo Finance from 2020 to 2024 before implementing a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model in this study. The CNN layers are responsible for extracting local patterns with a limited time horizon, whereas the LSTM layers are responsible for capturing the time series' long-term relationships. The experimental findings show that the CNN-LSTM model outperforms the CNN and LSTM in terms of predictive ability, with an RMSE of 2,202.717, an MAE of 1,553.202, and a MAPE of 2.244%, which translates to an accuracy of about 97.756%. These results provide useful information for adaptive trading techniques and digital asset risk management based on artificial intelligence, and they prove that the hybrid method is successful in dealing with complicated, non-linear, and unpredictable trends in the cryptocurrency market.