Garuda - Garba Rujukan Digital

From Tradition to Innovation: Mind Map Generation in Higher Education Mitra, Aditya Rama; Samosir, Feliks Victor Parningotan; Hudi, Robertus; Tarigan, Riswan Effendi
ULTIMA InfoSys Vol 14 No 2 (2023): Ultima Infosys : Jurnal Ilmu Sistem Informasi
Publisher : Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/si.v14i2.3432

In higher education, effectively delivering complex topics to students with diverse learning preferences remains a pressing challenge. This comprehensive survey delves into the utilization of mind maps as an innovative instructional tool to navigate this challenge. From 2003 to 2022, we review the implementation of mind maps in higher education, highlighting aspects such as the year of the paper, the techniques employed for mind mapping, target audiences, objectives, and outcomes. Mind maps, centralized and radial visual techniques, have been recognized for their capacity to enhance memory retention, comprehension, and active student engagement. We identify two primary scenarios: Learner-Driven and Lecturer-Driven Development. While students employ mind maps for revision and understanding, lecturers utilize them as visual aids to structure content and elucidate intricate relationships. The paper underscores the need for inclusivity, accommodating varied learning styles, and integrating mind maps into a broader educational toolkit. Through this study, we uncover research gaps and propose future avenues to further amplify the potential of mind maps in academia.

Sentiment Analysis in E-Commerce: Beauty Product Reviews Tumanggor, Gavrila Louise; Samosir, Feliks Victor Parningotan
Ultimatics : Jurnal Teknik Informatika Vol 16 No 2 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i2.3708

The increasing popularity of online shopping platforms is fueling the need for automated sentiment analysis for product reviews. This research aims to build an automatic sentiment analysis model in Indonesian for e-commerce product reviews. This model is expected to help consumers make purchasing decisions more quickly. We utilize the IndoBERT model, which has shown to be quite effective for general sentiment analysis, achieving an evaluation accuracy of 66.2% despite a high evaluation loss of 0.8006. The approach used combines Natural Language Processing (NLP) and Machine Learning (ML) techniques. It is hoped that this research will be useful for consumers, shop owners, and researchers in efficiently understanding the sentiment of e-commerce product reviews.

Exploratory Data Analysis terhadap Kepadatan Penumpang Kereta Rel Listrik Feliks Victor Parningotan Samosir; Loudry Palmarums Mustamu; Erik Dwi Anggara; Albertus Indarko Wiyogo; Andreas Widjaja
Jurnal Teknik Informatika dan Sistem Informasi Vol 7 No 2 (2021): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v7i2.3700

The existence of the Kereta Rel Listrik Commuter Line as the backbone of transportation in the Jakarta - Bogor - Depok - Tangerang - Bekasi - Banten area has a very important role for commuter mobility around Daerah Khusus Ibukota Jakarta. With an average number of 1.1 million passengers per day, Kereta Rel Listrik is one of the factors supporting Indonesia's economy and growth in various sectors. On the other hand, the Covid-19 pandemic that hit the world caused restrictions on human movement which resulted in a decline in all economic sectors. The purpose of this research is to obtain optimal train schedule recommendations for the operation of the Kereta Rel Listrik Commuter Line in the Rangkasbitung - Tanah Abang service to carry passengers optimally while adhering to the physical distancing protocol set by the Minister of Transportation to prevent the wider spread of Covid-19. With such a large amount of data that must be processed, Exploratory Data Analysis is one of the choices we take to process the above data to get satisfactory results.

BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper Feliks Victor Parningotan Samosir; Hapnes Toba; Mewati Ayub
Jurnal Teknik Informatika dan Sistem Informasi Vol 8 No 1 (2022): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v8i1.4474

This study aims to propose methods and models for extractive text summarization with contextual embedding. To build this model, a combination of traditional machine learning algorithms such as K-Means Clustering and the latest BERT-based architectures such as Sentence-BERT (SBERT) is carried out. The contextual embedding process will be carried out at the sentence level by SBERT. Embedded sentences will be clustered and the distance calculated from the centroid. The top sentences from each cluster will be used as summary candidates. The dataset used in this study is a collection of scientific journals from NeurIPS. Performance evaluation carried out with ROUGE-L gave a result of 15.52% and a BERTScore of 85.55%. This result surpasses several previous models such as PyTextRank and BERT Extractive Summarizer. The results of these measurements prove that the use of contextual embedding is very good if applied to extractive text summarization which is generally done at the sentence level.

PEMBERDAYAAN KETERAMPILAN DIGITAL DAN KREATIF DI SEKOLAH NON-PROFIT UNTUK MENDUKUNG INOVASI BERKELANJUTAN Calandra Alencia Haryani; Hery; Andree E. Widjaja; Feliks V.P. Samosir
Proceeding National Conference Business, Management, and Accounting (NCBMA) 8th National Conference Business, Management, and Accounting
Publisher : Faculty of Economics and Business Universitas Pelita Harapan

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

Transformasi industri berbasis digital menuntut penguatan literasi digital dan keterampilan kreatif di seluruh sektor pendidikan. Keterampilan dalam pembuatan website dan desain konten digital menjadi esensial untuk mendukung pembangunan industri yang inovatif dan berkelanjutan. Penelitian ini berbasis pada kegiatan Pengabdian kepada Masyarakat yang dilaksanakan di Sekolah Pendidikan Integral untuk Semua (PINUS), dengan tujuan meningkatkan keterampilan digital peserta didik melalui pelatihan berbasis WordPress dan Canva. Metode pelaksanaan melibatkan pelatihan berbasis proyek serta evaluasi melalui survei kepuasan peserta. Hasil penelitian menunjukkan adanya peningkatan kemampuan peserta dalam membangun situs web sederhana dan menghasilkan desain visual kreatif. Tingkat kepuasan peserta terhadap program tercatat sangat tinggi, dengan rata-rata skor 5 pada skala 1–5. Selain itu, peserta menunjukkan antusiasme dalam mengembangkan portofolio digital pribadi sebagai sarana personal branding untuk memperluas peluang ekonomi. Temuan ini mengindikasikan bahwa pendekatan praktis dalam literasi digital dapat menjadi strategi efektif dalam mendukung tujuan Sustainable Development Goal (SDG) 9, khususnya dalam memperkuat kapasitas inovasi dan keberlanjutan industri di masa depan.

Convolutional Kolmogorov-Arnold Network for Pneumonia Detection in Medical Image Analysis Riechie, Riechie; Jessica, Vira; Kurniawan, Matthew; Samosir, Feliks Victor Parningotan
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 7 No. 3 (2025): August
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v7i3.106

Pneumonia is a serious respiratory infection that poses a significant global health burden, particularly in regions with limited access to medical personnel and diagnostic resources. Chest X-ray imaging remains the most common method for pneumonia diagnosis, however, manual interpretation is prone to error and often requires experienced radiologists. To address this challenge, automated diagnostic systems based on deep learning have gained increasing attention. This study aims to evaluate the effectiveness of the Convolutional Kolmogorov-Arnold Network (CKAN) in detecting pneumonia from chest X-ray images and compare its performance against a baseline Convolutional Neural Network (CNN) model. The study involved three variations of CKAN architecture that combined convolutional layers with Kolmogorov-Arnold-based layers. Both CKAN and CNN models were trained on balanced and imbalanced datasets using data augmentation techniques to improve model robustness. Additional experiments were conducted with and without the application of early stopping mechanisms. Performance evaluation was conducted using five metrics: accuracy, precision, recall, specificity, and balanced accuracy. Loss history and confusion matrices were also analyzed to assess learning stability and classification behavior. The best-performing CKAN model achieved an accuracy of 83.49%, precision of 79.96%, recall of 98.21%, specificity of 78.59%, and balanced accuracy of 78.59%. In comparison, the best-performing CNN model reached 81%, 77.98%, 97.18%, 75.73%, and 75.73%, respectively. These results demonstrate CKAN’s superior generalization capability and its effectiveness in handling class imbalance. In conclusion, CKAN shows promising potential for improving pneumonia detection from chest X-rays using a more compact and interpretable model structure. Future studies can explore hyperparameter optimization and extend the method to other medical imaging tasks. This work contributes to the development of more accurate and accessible automated diagnostic systems.

Sentiment Analysis in E-Commerce: Beauty Product Reviews Tumanggor, Gavrila Louise; Samosir, Feliks Victor Parningotan
ULTIMATICS Vol 16 No 2 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i2.3708

The increasing popularity of online shopping platforms is fueling the need for automated sentiment analysis for product reviews. This research aims to build an automatic sentiment analysis model in Indonesian for e-commerce product reviews. This model is expected to help consumers make purchasing decisions more quickly. We utilize the IndoBERT model, which has shown to be quite effective for general sentiment analysis, achieving an evaluation accuracy of 66.2% despite a high evaluation loss of 0.8006. The approach used combines Natural Language Processing (NLP) and Machine Learning (ML) techniques. It is hoped that this research will be useful for consumers, shop owners, and researchers in efficiently understanding the sentiment of e-commerce product reviews.

Analisis Histori Pembelian Laptop untuk Menentukan Faktor Utama Pembelian Menggunakan Regresi Logistik Samosir, Feliks Victor Parningotan; Hery, Hery
Jurnal Teknik Informatika dan Sistem Informasi Vol 10 No 2 (2024): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v10i2.8897

E-Commerce is a new concept commonly described as the process of buying and selling goods or services over the World Wide Web or the exchange of products, services, and information through information networks, including the internet. Tokopedia, one of the largest e-commerce platforms in Indonesia, markets many products, including electronics. This study analyzes laptop data from Tokopedia. The vast history of purchase data and customer data in Tokopedia's database offers various ways to process it. One approach is using logistic regression models. The logistic regression results on the three features (price_cat, memory_size, and merk_cat) indicate that all three can be used to create logistic regression equations to determine laptop purchase probability. However, the regression calculations show that the r^2 value for price_cat is the highest at 0.82, indicating that price_cat significantly influences the probability of purchasing a laptop.

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