Claim Missing Document
Check
Articles

Found 6 Documents
Search

ALGORITHMIC INTELLIGENCE IN ENGINEERING DESIGN: INTEGRATING MACHINE LEARNING WITH PHYSICAL MODELING Fauzi Erwis; Miku Fujita; I Putu Dody Suarnatha; Amanda Wilson
Journal of Moeslim Research Technik Vol. 3 No. 2 (2026)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/technik.v3i2.3467

Abstract

Increasing complexity in engineering systems demands design methodologies that balance computational efficiency, predictive accuracy, and physical reliability. Traditional physics-based simulations ensure mechanistic consistency but are computationally expensive, while purely data-driven machine learning models offer speed yet often lack interpretability and physical compliance. Integrating algorithmic intelligence with physical modeling has therefore emerged as a promising paradigm in advanced engineering design. This study aims to develop and evaluate a hybrid framework that integrates machine learning algorithms with governing physical equations to enhance design performance, robustness, and computational efficiency. A mixed-methods computational design was employed using 15,000 high-fidelity simulation datasets across structural, aerodynamic, and thermal engineering cases. Three modeling configurations—physics-based models, data-driven models, and hybrid physics-informed machine learning models—were comparatively analyzed using performance metrics including mean squared error, R², runtime efficiency, robustness testing, and constraint violation indices. Statistical analyses were conducted to determine significance of performance differences. Hybrid models achieved superior balance, reaching R² = 0.97 with significantly reduced runtime compared to physics-based simulations (p < 0.001), while maintaining substantially lower physical constraint violations than purely data-driven models. Sensitivity and uncertainty analyses confirmed enhanced robustness under parameter perturbation. Algorithmic intelligence integrated with physical modeling represents an epistemologically coherent and practically effective approach, advancing engineering design toward trustworthy, efficient, and physically consistent computational frameworks.
A combination of hill cipher and RC4 methods for text security Azanuddin Azanuddin; Rikie Kartadie; Fauzi Erwis; Ahmad Fitri Boy; Asyahri Hadi Nasyuha
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 2: April 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i2.25628

Abstract

To hide confidential messages from people who are not responsible or who can access the messages, a way is needed to hide the messages. One way to hide messages in transmission is to change the data into something unintelligible by encoding and embedding it using cryptography and steganography techniques. This application was built using the hill cipher algorithm and the Rivest Cipher 4 (RC4) method. This algorithm is a symmetric key algorithm which has several advantages in data encryption. The hill chiper algorithm uses a mxm matrix as the encryption and decryption key. Meanwhile, the RC4 symmetric key is in the form of a stream cipher which can process input data as well as messages or information. Input data is generally in the form of bytes or even bits. The results of this research show that hill cipher and RC4 have their respective advantages and disadvantages. However, currently, RC4 is generally considered less safe for use in security-critical scenarios due to its vulnerability to attack. It is highly recommended to use an encryption algorithm such as advanced encryption standard (AES) which is modern and strong and has been tested and proven to be more resilient.
PENGUATAN LITERASI REFERENSI DIGITAL MAHASISWA UNIVERSITAS ROKANIA MELALUI PELATIHAN APLIKASI MENDELEY Sri Wahyudi; Detri Amelia Chandra; Agung Setiawan; Fauzi Erwis; Jufri Jufri; Safrudin Safrudin
Jurnal Pemberdayaan Sosial dan Teknologi Masyarakat Vol. 5 No. 2 (2025): Desember 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jpstm.v5i2.5393

Abstract

Abstract: Enhancing digital reference literacy has become an urgent necessity in the modern academic era. This study aims to analyze the effectiveness of Mendeley application training in improving the ability of Rokania University students to manage digital references and produce scientific citations. A descriptive qualitative approach was employed through observation, interviews, and documentation. The results show that the training improved students’ competencies in importing references, managing metadata, using the Web Importer, and automating bibliographies. The implementation of the Mendeley application increased the efficiency of scientific writing and minimized citation errors commonly found in student academic work. This study affirms that digital reference literacy must become an integral component of academic competency development in higher education. Keyword: digital literacy, mendeley, citation, scientific references, students. Abstrak: Peningkatan literasi referensi digital merupakan kebutuhan mendesak pada era akademik modern. Penelitian ini bertujuan menganalisis efektivitas pelatihan aplikasi Mendeley dalam meningkatkan kemampuan mahasiswa Universitas Rokania dalam mengelola referensi digital dan menyusun sitasi ilmiah. Pendekatan deskriptif kualitatif digunakan melalui observasi, wawancara, dan dokumentasi. Hasil menunjukkan bahwa pelatihan ini meningkatkan kompetensi mahasiswa dalam impor referensi, pengelolaan metadata, penggunaan Web Importer, hingga otomatisasi daftar pustaka. Penerapan aplikasi Mendeley meningkatkan efisiensi penulisan ilmiah dan meminimalisasi kesalahan sitasi yang sering terjadi dalam karya ilmiah mahasiswa. Penelitian ini menegaskan bahwa literasi referensi digital perlu menjadi bagian integral dari pengembangan kompetensi akademik di perguruan tinggi. Kata kunci: literasi digital, mendeley, sitasi, referensi ilmiah, mahasiswa
BEYOND IMMERSION: THE EFFICACY OF VIRTUAL REALITY (VR) SIMULATIONS IN DEVELOPING TECHNICAL SKILLS FOR VOCATIONAL EDUCATION Fauzi Erwis; Yang Xiang; Jari Koskinen
Journal of Social Entrepreneurship and Creative Technology Vol. 2 No. 4 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jseact.v2i4.2677

Abstract

Traditional vocational education (VET) for complex psychomotor skills is costly, risky, and difficult to scale. While Virtual Reality (VR) is a potential solution, research has focused on “immersion,” not empirical “efficacy.” The critical gap is the unverified “transfer-of-training” from virtual simulations to real-world, physical tasks. This study aimed to empirically evaluate the efficacy of VR-only training versus traditional hands-on methods. It specifically sought to measure (1) “virtual-to-real” skill transfer, (2) long-term skill retention, and (3) training efficiency. An experimental pre-test/post-test/retention-test design was used. 80 (N=80) novice welding trainees were randomized to a VR-Only (n=40) or Traditional (n=40) group. Psychomotor skill was measured on physical equipment at baseline (T1), post-intervention (T2), and 4-week retention (T3) using an expert-validated rubric (PAR), analyzed with ANCOVA. The VR-Only group demonstrated statistically superior skill transfer on the physical post-test (T2) (p < .001, \eta_p^2 = .710). This superiority was durable, with significantly higher skill retention at the T3 follow-up (p < .001). The VR group also achieved competency 27% faster (6.4 vs 8.8 hours) and at zero consumable material cost. -fidelity VR, driven by instantaneous data-driven feedback, is a more effective, efficient, and cost-effective training modality than the traditional “gold standard” for novice psychomotor skill acquisition. This study provides robust validation for the “virtual-to-real” transfer-of-training.
Penguatan Literasi Referensi Digital Mahasiswa Universitas Rokania Melalui Pelatihan Aplikasi Mendeley Sri Wahyudi; Firman Santosa; Jufri; Safrudin; Agung Setiawan; Fauzi Erwis
Journal Of Indonesian Social Society (JISS) Vol. 3 No. 3 (2025): JISS - Oktober
Publisher : PT. Padang Tekno Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59435/jiss.v3i3.614

Abstract

Peningkatan literasi referensi digital merupakan kebutuhan mendesak pada era akademik modern. Penelitian ini bertujuan menganalisis efektivitas pelatihan aplikasi Mendeley dalam meningkatkan kemampuan mahasiswa Universitas Rokania dalam mengelola referensi digital dan menyusun sitasi ilmiah. Pendekatan deskriptif kualitatif digunakan melalui observasi, wawancara, dan dokumentasi. Hasil menunjukkan bahwa pelatihan ini meningkatkan kompetensi mahasiswa dalam impor referensi, pengelolaan metadata, penggunaan Web Importer, hingga otomatisasi daftar pustaka. Penerapan aplikasi Mendeley meningkatkan efisiensi penulisan ilmiah dan meminimalisasi kesalahan sitasi yang sering terjadi dalam karya ilmiah mahasiswa. Penelitian ini menegaskan bahwa literasi referensi digital perlu menjadi bagian integral dari pengembangan kompetensi akademik di perguruan tinggi.
Use of Augmented Reality (AR) in Mobile Learning for Natural Science Lessons Fauzi Erwis; Cai Jixiong; Novi Rahayu; Agung Rachmat Raharja; Rony Sandra Yofa Zebua
Journal of Social Science Utilizing Technology Vol. 2 No. 1 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jssut.v2i1.784

Abstract

Background. The development of information technology continues to change from time to time, especially Augmented Reality (AR), which has opened up new opportunities in education by introducing more interactive and interesting learning concepts. In the context of Natural Science (Science) lessons, the use of Augmented Reality in Mobile Learning offers the potential to increase students’ understanding of complex concepts through visual and practical-based learning experiences. Purpose. This research aims to determine the use of Augmented Reality in Mobile Learning for learning Natural Sciences. The focus is to assess the impact of using Augmented Reality on understanding Natural Science concepts, learning motivation, and student engagement. Method. The research method used in this research is a quantitative method using a random control experiment where two groups of students are divided randomly, one group uses conventional learning methods while the other group uses the Mobile Learning application with Augmented Reality features. Data was collected through a learning motivation questionnaire. Results. The research results showed that the group that used Augmented Reality in Mobile Learning showed an increase in understanding of Natural Science concepts compared to the control group that used conventional methods. In addition, they also show higher levels of learning motivation and more active involvement in the learning process.   Conclusion. The conclusion of this research is that the use of Augmented Reality in Mobile Learning for learning Natural Sciences has the potential to increase learning effectiveness by providing a more interactive, visual and practical learning experience. The results of this research show that Augmented Reality can be a valuable tool in increasing students’ understanding of Natural Science concepts, as well as motivating them to learn better. Therefore, the integration of Augmented Reality in Mobile Learning can be an effective strategy in improving the quality of Natural Sciences education in this digital era.