cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Febri Dristyan
Contact Email
fdristyan@gmail.com
Phone
+6282273841417
Journal Mail Official
fusionjretas@gmail.com
Editorial Address
Jl. Nusa Indah No.47 Lorong Sehat Kota Jambi
Location
Kota jambi,
Jambi
INDONESIA
Fusion : Journal of Research in Engineering, Technology and Applied Sciences
Published by PT. Faaslib Serambi Media
ISSN : -     EISSN : 30478278     DOI : -
Core Subject : Science, Engineering,
Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Materials Science & Nanotechnology
Fusion : Journal of Research in Engineering, Technology and Applied Sciences adalah jurnal interdisipliner yang menampilkan riset terkini dalam bidang rekayasa, teknologi, dan ilmu terapan. Jurnal ini memuat artikel-artikel yang mencakup berbagai topik, mulai dari inovasi teknologi terbaru hingga penerapan ilmu pengetahuan dalam berbagai bidang kehidupan. Melalui penelitian yang ditampilkan, "Fusion" bertujuan untuk memfasilitasi pertukaran informasi antara akademisi, peneliti, dan praktisi di seluruh dunia, serta mendorong kolaborasi lintas disiplin ilmu. Dengan fokus pada integrasi antara teori dan praktik, jurnal ini menjadi wadah penting untuk memajukan pengetahuan dan teknologi dalam mendukung perkembangan masyarakat secara global.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 30 Documents
 1   2   3 
Analisis Penentuan Harga Pokok Produksi  dan Harga Jual Udang Menggunakan Metode Full Costing dan Cost Plus Pricing di Tambak Udang Fiqri Ragustu Ilma Permata Linda; Mufrida Meri; Irmayani Irmayani; Desriyenti Desriyenti
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 2 No. 2 (2025): Fusion - Oktober
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v2i2.280

Abstract

Penelitian ini bertujuan untuk menganalisis penentuan harga pokok produksi (HPP) dan harga jual udang vaname pada Tambak Fiqri Ragustu yang berlokasi di Desa Kantarok. Penelitian dilakukan dengan menggunakan metode Full Costing untuk menghitung seluruh komponen biaya produksi, meliputi biaya tenaga kerja, biaya bahan baku, dan biaya overhead. Selain itu, metode Cost Plus Pricing digunakan untuk menentukan harga jual berdasarkan HPP ditambah dengan tingkat keuntungan yang diharapkan. Berdasarkan hasil analisis, diperoleh total biaya produksi sebesar Rp1.539.140.000 dengan harga jual minimal Rp102.000/kg untuk mencapai titik impas (break-even point). Sementara itu, dengan penerapan metode Cost Plus Pricing dan target keuntungan sebesar 50%, harga jual yang ideal ditetapkan sebesar Rp155.000/kg. Hasil penelitian ini menunjukkan bahwa penggunaan kedua metode tersebut memberikan gambaran yang komprehensif terhadap struktur biaya dan strategi penetapan harga yang efektif dalam usaha budidaya udang vaname. Dengan demikian, hasil kajian ini dapat menjadi acuan bagi pelaku usaha perikanan dalam menentukan harga jual yang kompetitif dan berkelanjutan, serta menjadi referensi bagi penelitian selanjutnya terkait analisis biaya produksi di sektor perikanan.
Optimalisasi Pencarian Data Produksi Kelapa Sawit Menggunakan Algoritma Binary Search Pada Struktur Data Terurut Muhammad Hadi Saputra; Febri Dristyan; Syifa Andini Aulia Putri
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 2 No. 2 (2025): Fusion - Oktober
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v2i2.291

Abstract

Pencarian data merupakan proses krusial dalam pengelolaan informasi. Penelitian ini bertujuan mengoptimalisasi algoritma binary search pada struktur data terurut untuk meningkatkan efisiensi waktu pencarian dan penggunaan memori, khususnya pada data produksi kelapa sawit. Metodologi penelitian meliputi studi literatur, perancangan dan simulasi algoritma menggunakan Python, eksperimen pengukuran performa (waktu eksekusi dan efisiensi memori), serta validasi hasil. Diharapkan penelitian ini menghasilkan model algoritma pencarian optimal yang mampu memberikan peningkatan kinerja signifikan dibandingkan metode binary search konvensional pada berbagai ukuran dan kondisi data. Simpulan dari penelitian ini akan membahas efektivitas model yang diusulkan dalam mengoptimalkan pencarian data pada sistem nyata.
Systematic Literature Review Metode Data Science dalam Prediksi Kinerja dan Keamanan Jaringan Cloud Aliyah Aliyah; M. Adhit Dwi Yuda; Iwan Iwan
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 2 No. 2 (2025): Fusion - Oktober
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v2i2.307

Abstract

Transformasi menuju cloud computing meningkatkan kompleksitas pengelolaan kinerja jaringan dan risiko ancaman keamanan siber, sehingga diperlukan pendekatan prediktif yang akurat dan adaptif. Penelitian ini menyajikan Systematic Literature Review (SLR) mengenai penerapan metode data science dalam prediksi kinerja jaringan dan deteksi ancaman keamanan siber pada lingkungan cloud. Tinjauan dilakukan mengikuti pedoman PRISMA terhadap publikasi periode 2015–2025 yang diindeks pada Scopus, IEEE Xplore, ACM Digital Library, dan ScienceDirect. Hasil kajian menunjukkan bahwa metode machine learning seperti Support Vector Machine dan Random Forest, serta deep learning seperti Convolutional Neural Network dan Long Short-Term Memory, mendominasi penelitian terkait. Teknik anomaly detection dan hybrid learning terbukti efektif dalam mengidentifikasi pola serangan kompleks pada infrastruktur cloud berskala besar. Namun, tantangan utama masih mencakup ketidakseimbangan data, keterbatasan generalisasi model, dan minimnya dataset terbuka. Studi ini memberikan pemetaan tren metodologis dan celah penelitian sebagai dasar pengembangan model prediktif yang lebih robust dan skalabel pada infrastruktur cloud.
Penerapan Design Thinking untuk Meningkatkan Kinerja Pengiriman dan Efisiensi Operasional Gudang JNE Jambi Ines Ramadani; Siti Masruroh; Bella Suryani
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 2 No. 2 (2025): Fusion - Oktober
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v2i2.312

Abstract

Keterlambatan pengiriman barang merupakan permasalahan utama dalam industri jasa logistik yang berdampak pada kepuasan pelanggan dan kinerja operasional. Penelitian ini bertujuan untuk meningkatkan kinerja pengiriman barang melalui penerapan pendekatan Design Thinking pada operasional Gudang JNE Jambi. Metode penelitian menggunakan lima tahapan Design Thinking, yaitu empathize, define, ideate, prototype, dan test. Data dikumpulkan melalui observasi operasional gudang, wawancara dengan staf, serta analisis keluhan pelanggan. Hasil penelitian menunjukkan bahwa keterlambatan pengiriman disebabkan oleh proses sortir yang tidak efisien, keterbatasan sistem pelacakan, dan lemahnya koordinasi internal. Solusi yang diimplementasikan meliputi perbaikan alur sortir, optimalisasi sistem pelacakan pengiriman, dan peningkatan koordinasi antarunit. Evaluasi kinerja menunjukkan penurunan tingkat keterlambatan pengiriman dari 20% menjadi 14%, sehingga terjadi peningkatan kinerja sebesar 6%. Temuan ini membuktikan bahwa Design Thinking efektif dalam meningkatkan efisiensi operasional pengiriman barang.
Analisis Tingkat Kemiskinan di Indonesia Dengan Metode DBSCAN Maria M Mitan; I Wayan Sudiarsa; Andrianus Koda; Stanisilia D. Wero Koda; Moh M. Azmi Koda
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 2 No. 2 (2025): Fusion - Oktober
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v2i2.314

Abstract

Kemiskinan merupakan permasalahan multidimensional yang masih menjadi fokus utama pembangunan di Indonesia. Penelitian ini bertujuan untuk menganalisis tingkat kemiskinan kabupaten/kota di Indonesia menggunakan metode Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Data dianalisis menggunakan Google Colaboratory dengan parameter DBSCAN berupa nilai epsilon (ε) sebesar 0,5 dan minimum points (MinPts) sebesar 5.Hasil pengujian menunjukkan bahwa metode DBSCAN menghasilkan 2 klaster utama dan 7 data teridentifikasi sebagai noise (cluster −1). Klaster pertama mencakup 68 kabupaten/kota dengan karakteristik tingkat kemiskinan relatif sedang, sedangkan klaster kedua terdiri dari 34 kabupaten/kota dengan tingkat kemiskinan tinggi. Keberadaan data noise menunjukkan wilayah dengan karakteristik kemiskinan yang bersifat ekstrem dan berbeda dari pola umum.Hasil ini membuktikan bahwa DBSCAN mampu mengelompokkan wilayah berdasarkan kepadatan karakteristik kemiskinan serta mengidentifikasi wilayah outlier yang memerlukan perhatian kebijakan khusus.
Artificial Intelligence and Machine Learning in Education: A Systematic Literature Review of Transformative Trends and Future Directions Aliyah Aliyah
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 3 No. 1 (2026): Fusion - April
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v3i1.282

Abstract

The transformation of education in the digital era has been significantly accelerated by the integration of Artificial Intelligence (AI) and Machine Learning (ML), fundamentally reshaping how learning is designed, delivered, and assessed. This study aims to systematically identify emerging trends, key benefits, prevailing challenges, and future directions of AI and ML applications in education through a Systematic Literature Review (SLR) approach. The reviewed literature was sourced from leading academic databases, including Scopus, IEEE Xplore, and ScienceDirect, covering publications from 2015 to 2025.  The findings reveal that AI and ML technologies have been widely implemented in various educational domains, particularly in adaptive learning systems, automated assessment mechanisms, and intelligent virtual assistants that facilitate personalized learning experiences. Despite these advancements, several critical challenges persist, notably digital inequality, data privacy concerns, and the limited technological literacy among educators, which hinder the effective adoption of these technologies. Furthermore, the study highlights that the future of education will increasingly rely on the integration of intelligent systems that enable data-driven, flexible, and learner-centered environments. The insights derived from this SLR are expected to provide valuable guidance for policymakers, educators, and technology developers in formulating adaptive and sustainable educational strategies in the era of artificial intelligence.
Detection of Rupiah Nominal Values Based on Computer Vision and OCR for Low Vision Accessibility Doucoure Mohammed Hakeem; Trisna Almuti; Syahbil Afriza Baharaji; Muhammad Iqbal; Albert Riyandi
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 3 No. 1 (2026): Fusion - April
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v3i1.338

Abstract

The ability to recognize banknotes' nominal value is a fundamental skill in daily economic transactions. However, for low-vision individuals, this simple task poses a major challenge, risking transaction errors and fraud. This study aims to build a web-based application capable of detecting Rupiah currency nominals in real-time by integrating computer vision and Optical Character Recognition (OCR) as an independent accessibility feature. The method combines a custom object detection model based on the YOLO architecture via the Roboflow platform and Tesseract OCR for nominal text verification, which is then integrated with the Web Speech API for voice-based output (Text-to-Speech). The system test results indicate that the combined "Roboflow + OCR" approach significantly improves detection reliability compared to using the object model alone. The system achieved a classification accuracy rate of 94.5% under optimal lighting conditions, with an average Text-to-Speech response latency of 1.8 seconds. This implementation proves that the synergy of image processing and OCR can provide an effective and inclusive assistive technology solution for visually impaired groups in Indonesia.
A Comparative Analysis of Naïve Bayes and Random Forest Algorithms for Sentiment Classification of Akulaku User Reviews Nur Ferdiansyah; Ariel Mutia Salsabila; Putri Wiji Lestari
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 3 No. 1 (2026): Fusion - April
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v3i1.342

Abstract

Abstract User reviews of the Akulaku application on Google Play Store contain important information regarding user satisfaction and complaints. This study compares the performance of Naïve Bayes and Random Forest algorithms in classifying sentiment into three classes: positive, negative, and neutral. A total of 2,000 Indonesian-language reviews were collected using web scraping techniques. Data were processed through case folding, cleaning, normalization, stopword removal, tokenizing, and stemming. Labeling was based on user ratings. After preprocessing, 1,953 data points remained with an imbalanced distribution; SMOTE was applied to balance each class to 1,114 samples. TF-IDF was used for feature weighting with an 80:20 train-test split. Results showed Random Forest achieved 83% accuracy, while Naïve Bayes reached 80%. However, Naïve Bayes outperformed in precision, recall, and F1-score with macro averages of 0.59, 0.70, and 0.60, compared to Random Forest at 0.52, 0.55, and 0.54. Based on these results, the choice of the best algorithm depends on the specific needs. If the priority is overall accuracy, Random Forest is more recommended however, if the priority is balanced performance across sentiment classes, Naïve Bayes performs better.
Sentiment Analysis of YouTube Comments on the KDM Policy in Handling Juvenile Delinquency Using Naïve Bayes Muhammad Afan Adi Saputra; Wildan Arosyid; Huda Mutamam
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 3 No. 1 (2026): Fusion - April
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v3i1.344

Abstract

The policy of West Java Governor Dedi Mulyadi (KDM) to send troubled youths to military barracks as a form of character development to address juvenile delinquency triggered diverse public opinions in YouTube comment sections, which were difficult to analyze manually due to their large volume and linguistic variation. This study aims to analyze the sentiment of YouTube comments toward the policy using the Naïve Bayes Classifier algorithm with Term Frequency-Inverse Document Frequency (TF-IDF) weighting, and to evaluate model performance based on accuracy, precision, recall, and F1-score metrics. The research data were obtained from a public Kaggle dataset comprising 7,875 comments, which after preprocessing resulted in 7,407 valid data with a proportion of 56.6% negative and 43.4% positive comments. The data were split using an 80:20 ratio with stratified sampling. Test results show that the Naïve Bayes model achieved an accuracy of 73.95%, precision of 84.64%, recall of 48.83%, and F1-score of 61.93%, with the negative class performing better (F1-score 80%) than the positive class (F1-score 62%) due to class imbalance in the dataset. Word cloud analysis revealed that negative sentiment was largely not directed at the KDM policy itself, but rather at criticism toward the Indonesian Child Protection Commission (KPAI). This study provides an objective overview of public perception that can serve as a basis for evaluating juvenile delinquency handling policies.
Integration of the MobileNetV2 Convolutional Neural Network Architecture into a Sorting System for Citrus Fruit Maturity Classification Fitri Aisah Pohan; Romy Aulia; Syukriadi Syukriadi
Fusion : Journal of Research in Engineering, Technology and Applied Sciences Vol. 3 No. 1 (2026): Fusion - April
Publisher : PT. Faaslib Serambi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66341/fusion.v3i1.359

Abstract

This research aims to develop an automated sorting system for post-harvest oranges to address subjectivity and the risk of errors caused by human fatigue. The method employed involves developing an automated sorting conveyor prototype based on an ESP32 microcontroller integrated with deep learning technology via a webcam. The continuous ripeness classification process utilizes a Convolutional Neural Network (CNN) with the MobileNetV2 architecture to categorize the fruit into ripe and half-ripe stages. The detection results are then transmitted serially to the ESP32 to drive the sorting servo in real-time. Based on testing with 50 orange samples, the MobileNetV2 CNN model achieved an accuracy of 90% with an F1-Score of 0.90. The implementation of this system is proven to significantly increase post-harvest productivity by reducing processing time by 63.3% compared to manual methods. Additionally, the data counter feature for the Ripe and Half-Ripe categories operates simultaneously to standardize production output monitoring. This study demonstrates that the integration of MobileNetV2 and ESP32 is effectively applied to a prototype-scale sorting system.

Page 3 of 3 | Total Record : 30

 1   2   3 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2026): Fusion - April Vol. 2 No. 2 (2025): Fusion - Oktober Vol. 2 No. 1 (2025): Fusion - April Vol. 1 No. 2 (2024): Fusion - Oktober Vol. 1 No. 1 (2024): Fusion - April