Garuda - Garba Rujukan Digital

PERANCANGAN APLIKASI PERHITUNGAN BEBAN KERJA DOSEN TERINTEGRASI DENGAN PENDEKATAN WATERFALL Ratmana, Danny Oka; Syaifur Rohman, Muhammad; Firdausillah, Fahri; Wilujeng Saraswati, Galuh
Jurnal Teknoif Teknik Informatika Institut Teknologi Padang Vol 12 No 2 (2024): TEKNOIF OKTOBER 2024
Publisher : ITP Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21063/jtif.2024.V12.2.139-148

Digital transformation in higher education emphasizes the importance of information technology in enhancing management efficiency, including the management of lecturers' workloads. This study aims to design a Full-Time Equivalent Teaching Load (EWMP) calculation system integrated with the Integrated Resource Information System (SISTER), implemented by the Ministry of Education, Culture, Research, and Technology (KEMDIKBUDRISTEK). The application was developed using the Waterfall methodology and leverages the SISTER Application Programming Interface (API) to automate the collection of lecturer activity data at Universitas Dian Nuswantoro Semarang (UDINUS). By integrating the workload calculation application into the internal management system, this solution streamlines data recording, reduces manual errors, and enhances accuracy in the evaluation of lecturer performance. The test results indicate that the application successfully synchronizes data with SISTER in an accurate and real-time manner, supporting more effective workload management for lecturers. Additionally, the system provides reports and analyses of lecturer workloads, facilitating resource planning and allocation. This application is expected to contribute to a more transparent, accurate, and quality-driven human resource management process in higher education.

Comparison of IndoNanoT5 and IndoGPT for Advancing Indonesian Text Formalization in Low-Resource Settings Firdausillah, Fahri; Luthfiarta, Ardytha; Nugraha, Adhitya; Dewi, Ika Novita; Hafiizhudin, Lutfi Azis; Mumtaz, Najma Amira; Syarifah, Ulima Muna
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.4935

The rapid growth of digital communication in Indonesia has led to a distinct informal linguistic style that poses significant challenges for Natural Language Processing (NLP) systems trained on formal text. This discrepancy often degrades the performance of downstream tasks like machine translation and sentiment analysis. This study aims to provide the first systematic comparison of IndoNanoT5 (encoder-decoder) and IndoGPT (decoder-only) architectures for Indonesian informal-to-formal text style transfer. We conduct comprehensive experiments using the STIF-INDONESIA dataset through rigorous hyperparameter optimization, multiple evaluation metrics, and statistical significance testing. The results demonstrate clear superiority of the encoder-decoder architecture, with IndoNanoT5-base achieving a peak BLEU score of 55.99, significantly outperforming IndoGPT's highest score of 51.13 by 4.86 points—a statistically significant improvement (p<0.001) with large effect size (Cohen's d = 0.847). This establishes new performance benchmarks with 28.49 BLEU points improvement over previous methods, representing a 103.6% relative gain. Architectural analysis reveals that bidirectional context processing, explicit input-output separation, and cross-attention mechanisms provide critical advantages for handling Indonesian morphological complexity. Computational efficiency analysis shows important trade-offs between inference speed and output quality. This research advances Indonesian text normalization capabilities and provides empirical evidence for architectural selection in sequence-to-sequence tasks for morphologically rich, low-resource languages.

PERANCANGAN APLIKASI PERHITUNGAN BEBAN KERJA DOSEN TERINTEGRASI DENGAN PENDEKATAN WATERFALL Ratmana, Danny Oka; Syaifur Rohman, Muhammad; Firdausillah, Fahri; Wilujeng Saraswati, Galuh
Jurnal Teknoif Teknik Informatika Institut Teknologi Padang Vol 12 No 2 (2024): TEKNOIF OKTOBER 2024
Publisher : ITP Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21063/jtif.2024.V12.2.139-148

Digital transformation in higher education emphasizes the importance of information technology in enhancing management efficiency, including the management of lecturers' workloads. This study aims to design a Full-Time Equivalent Teaching Load (EWMP) calculation system integrated with the Integrated Resource Information System (SISTER), implemented by the Ministry of Education, Culture, Research, and Technology (KEMDIKBUDRISTEK). The application was developed using the Waterfall methodology and leverages the SISTER Application Programming Interface (API) to automate the collection of lecturer activity data at Universitas Dian Nuswantoro Semarang (UDINUS). By integrating the workload calculation application into the internal management system, this solution streamlines data recording, reduces manual errors, and enhances accuracy in the evaluation of lecturer performance. The test results indicate that the application successfully synchronizes data with SISTER in an accurate and real-time manner, supporting more effective workload management for lecturers. Additionally, the system provides reports and analyses of lecturer workloads, facilitating resource planning and allocation. This application is expected to contribute to a more transparent, accurate, and quality-driven human resource management process in higher education.

COVID-19 Suspects Monitoring System Based on Symptom recognition using Deep Neural Network Udayanti, Erika Devi; Kartikadharma, Etika; Firdausillah, Fahri; Ikhsan, Nur
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 2 No. 1 (2023): March 2023
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v2i1.2073

The outbreak of the Corona virus or COVID-19 was still a global concern even though it has been declared an endemic in several countries in the world, including Indonesia. However, with the emergence of new variants of this virus, preventive efforts continue to be made to prevent its spread. To prevent the spread of this virus, early detection was important, especially in knowing prospective clients who are positive and reactive to this virus, thus enabling early isolation measures for prospective patients who are taking action. This identification can be carried out in public areas that are the center of community activities. In this study, an intelligent system will be developed that can detect people suspected of COVID-19 through fever and breathing problem symptoms that can provide solutions to prevent the spread of this virus. Identify these symptoms through thermography-based image processing sourced from thermal camera sensors and then look for the possibility of suspected and reactive COVID19. Furthermore, the AI model was used by the early detection system of people suspected of being positive and reactive for COVID-19 using the Deep Neural Network method. This study aims to identify symptoms of fever and respiratory infection through image processing sourced from thermal camera sensors and further diagnose prospective patients who are suspected of being positive and reactive for COVID19 using the CNN method as an intelligent system for early detection of suspected positive and reactive COVID19 patientsIn the process of testing the classification training model, the performance results in the CNN classification process have an accuracy value of more than 88%. Furthermore, a comparison was made between the CNN classification and other classifications, such as SVM, Naive Bayes and Multi-Layer Perceptron (MLP). The results obtained from this comparison have an average percentage of accuracy above 80%. MLP has the lowest accuracy among its classification methods of 83.56%. CNN has the highest accuracy value compared to other methods of 88.68%. Therefore, CNN can be chosen to be the right one for use in the COVID-19 suspect detection system through the recognition of symptoms and respiratory disorders. Based on these performance measurements, the process of detecting COVID19 suspects indicated by health symptoms can be applied to real data.

N-Beats Optimization With K-Fold Cross-Validation For Stock Market Price Prediction In Indonesia Santoso, Natanael James; Firdausillah, Fahri
Eduvest - Journal of Universal Studies Vol. 5 No. 11 (2025): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i11.52367

In the era of capital market digitalization, stock price prediction poses a significant challenge, particularly in developing countries like Indonesia, where high market volatility is driven by political dynamics and exchange rate fluctuations. This study aims to address these challenges by developing a stock price prediction model using the N-BEATS architecture, which is designed to overcome the limitations of traditional methods such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). The dataset includes open, high, low, close, and volume from five leading Indonesian banks between 2004 and 2024. The N-BEATS model is optimized using K-Fold cross-validation to enhance accuracy and reduce overfitting risks. Evaluation results demonstrate that the N-BEATS model gave better accuracy compared to CNN and RNN models, with a 30% improvement over CNN and 25% over RNN. Analysis of performance variability across stock symbols reveals that the intrinsic data characteristics of each stock influence prediction accuracy. The N-BEATS model exhibits significant potential for stock price prediction in the Indonesian market, excelling in capturing long-term dependencies and offering better interpretability.

Design and Implementation of a Hierarchically Interoperable Tag-Based File System using FUSE (PreTFS) Lie Steven Staria Nugraha; Fahri Firdausillah
Journal of Information System and Informatics Vol 8 No 1 (2026): February
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i1.1416

Traditional hierarchical file systems make semantic organization awkward: a file that naturally belongs to multiple contexts must be forced into a single directory, leaving users to choose an arbitrary location or rely on duplication, linking, or search. This paper presents the design, prototype, and evaluation of a file system that preserves conventional hierarchical standards while adding an opt-in, tag-based semantic layer for multi-context categorization. We describe (i) a design in which tags are represented as directories with reserved, prefixed names and tag intersections are expressed through ordinary path nesting, and (ii) a proof-of-concept implementation that validates feasibility in practice. The implementation, PreTFS, is built as a FUSE (Filesystem in User Space) file system and uses SQLite to store file metadata and content. Results show that the design is realizable and remains compatible with conventional applications and workflows without external tools or specialized APIs. Benchmarking against a native kernel file system (btrfs) reveals expected overheads from user-space indirection and metadata management, measuring approximately ~2–73 ms for metadata-oriented operations and ~1–160 ms for file-content operations. These costs indicate the approach is practical for small-scale environments such as personal information management, where semantic flexibility and interoperability can outweigh peak performance. The novelty lies in a simple, hierarchically interoperable tagging design that enables semantic categorization through standard directory navigation.

Comparative Performance of Fine-Tuned IndoBERT BASE and LARGE Variants for Emotion Detection in Indonesian Tweets Winarno, Sri; Novita Dewi, Ika; Nugraha, Adhitya; Firdausillah, Fahri; Fitri, Maulatus Shaffira; Ramadhani, Talitha Olga; Widhiyanti, Erna Amalia; Rizqi, Ainur Rahma Miftakhul
JOIN (Jurnal Online Informatika) Vol 11 No 1 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i1.1704

In the digital era, where emotions play a crucial role in shaping human behavior, communication, and decision-making, their expressions are often conveyed through short and informal texts on platforms such as Twitter. This research aims to improve the accuracy of emotion detection in Indonesian text using the IndoBERT-BASE-P2 and IndoBERT-LARGE-P2 transformer models. The dataset consists of 7,080 tweets annotated with six basic emotion categories (anger, fear, joy, love, neutral, and sad). The research methodology included text preprocessing, class balancing using SMOTE, and fine-tuning with optimized training parameters. Evaluation results show that IndoBERT-BASE-P2 achieved an accuracy of 84.43% and a macro F1-score of 84.33%, surpassing previous studies, while the larger IndoBERT-LARGE-P2 model tended to overfit and offered no meaningful improvement. Error analysis showed the neutral class was the most difficult to classify. These findings demonstrate that with effective preprocessing and parameter optimization, a smaller model can be a highly efficient solution for emotion classification in Indonesian text, especially in resource-constrained conditions.

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search