Garuda - Garba Rujukan Digital

The Systematic Literature Review of the spiral development model: Topics, trends, and application areas Risna Sari; Anggi Muhammad Rifa’i; Muhammad Salimy Ahsan; Mohammad Rezza Pahlevi; M. Ilham Arief
International Journal of Research and Applied Technology (INJURATECH) Vol 2 No 2 (2022): International Journal of Research and Applied Technology (INJURATECH)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v2i2.8372

The spiral model is one of the methods used to perform software engineering development and can also be used for development in other fields. This spiral model is the result of a modification from the combination of the waterfall model and prototyping model so that it has many advantages including in each result an evaluation will be carried out, carried out sequentially or systematically, and is more focused in carrying out risk analysis from each stage. Has a function in development to make changes, additions and developments by determining accuracy and speed based on needs. In its implementation the spiral model has been carried out in various fields, but the results of the implementation are not yet known in what scope and how many implementations each year. This study aims to identify the results of the implementation of the spiral model development with data obtained from related papers in the 2012-2022 range. The method used in this study is the Systematic Literature Review (SLR) with the aim of identifying, reviewing, evaluating, and concluding all research on each relevant paper. The results showed that the spiral model development was mostly implemented in software development with a total of 19 papers and in the education sector as many as 17 papers, while the peak of the spiral model development was mostly implemented in 2016 and then increased again in 2021

Comparison of LSTM and GRU Models for Forex Prediction Pahlevi, Mohammad Rezza; Kusrini, Kusrini; Hidayat, Tonny
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 4 (2023): Article Research Volume 7 Issue 4, October 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.12709

Trading foreign currencies worth trillions of dollars takes place daily in the forex market, characterized by highly volatile movements. The forex market operates on bid and ask prices, with exchange rates determined by the principles of supply and demand. Trading involves currency pairs like EUR/USD, where the value of the Euro is compared to the US Dollar, serving as a basis for analyzing price fluctuations. Due to the volatile nature of forex, market participants must make informed decisions when buying and selling, as improper choices can result in financial losses. One approach to mitigating risk in forex trading decisions is through the use of forecasting techniques. This research study employs LSTM and GRU methods to predict forex trends, which are evaluated using various dataset divisions. The most accurate results are obtained using a dataset of 4979, split into three equal parts: 80% for training, 10% for validation, and 10% for testing. This approach yields an RMSE value of 0.054, MAPE of 0.037, and R-square of 97%

Understanding of Requirements Engineering using The Three Dimensions of Requirements Engineering Method in Platform Development Sari, Risna; Anggi Muhammad Rifa'i; Muhammad Salimy Ahsan; M Ilham Arief; Mohammad Rezza Pahlevi
Jurnal Internasional Teknik, Teknologi dan Ilmu Pengetahuan Alam Vol 5 No 2 (2023): International Journal of Engineering, Technology and Natural Sciences
Publisher : Universitas Teknologi Yogyakarta, Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46923/ijets.v5i2.218

Requirements engineering is a critical activity in a development system project, the increasing need for complexity of software development and the heterogeneity of stakeholders in motivating the development of methods and the need to evaluate the engineering requirements needed and aim to lead to a large scale. This study presents a paper in an empirical form that aims to identify and understand the characteristics of the advantages and limitations of the developed platform so that we can know the challenges that will be faced, such as expectations and input from experts for the development of the platform that we develop so that it can be in accordance with what users expect. We conducted this research with the aim of understanding the engineering requirements in the research we developed by utilizing the three dimensions of the requirements engineering method, which consists of requirement elicitation, requirement specification, and requirement validation and verification. The research we conducted managed to understand the stages of needs engineering by producing many documents that help the platform development process. We get the most important UI value from attractiveness, clarity, efficiency, accuracy, stimulation, and novelty, which is 63.2% with a very interest rating, 55.6 with a very interest rating, 57.9% with a very interest rating, 44.4% with a balanced rating between interesting and very interest, 52.6% with an interesting rating, 42.1% with a very interesting rating. We get product values consisting of attractiveness, clarity, efficiency, accuracy, stimulation, and novelty, namely 68.4% with a very interest rating, 52.6% with an interest ng rating, 52.6% with a very interest rating, 47.4% with a balanced rating between interesting and very interest, 47.4% with a balanced rating between interesting and very interest, 47.4% with a balanced rating between interesting and very interest

Prediksi Harga Forex Menggunakan Algoritma Long Short-Term Memory Pahlevi, Mohammad Rezza Pahlevi; Pahlevi, Mohammad Rezza
JNANALOKA Vol. 04 No. 02 September Tahun 2023
Publisher : Lentera Dua Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36802/jnanaloka.2022.v3-no2-69-76

Trillions of dollars per day of foreign currency trading activity occur in the forex market, which has very volatile movements in foreign currency trading. Trade based on bid and ask prices. The market determines foreign exchange rates based on supply and demand rules. Currency trading in pairs such as EUR/USD is a comparison of the value of the Euro against the Dollar as a basis for research, rising and falling currency prices in forex move fluctuatingly, so a market participant must be able to decide on buying and selling positions. Because wrong decisions can lead to losses. One of the ways to reduce risk in making decisions in buying and selling in forex can be using forecasting. This study uses the LSTM method in predicting forex prices which will be tested on several scales of dataset distribution. The smallest error results using a total dataset of 2631 with a dataset division of 70:15:15, which is divided into 70% data for training, 15% data for validation and 15% data for testing produces an RMSE value of 0.038, MAPE 2.5%. In measuring how well the regression model used with Rsquare on the data distribution is 70:15:15 and the total dataset used is 4979 to get the best results, namely 97%.

Prediksi Harga Forex Menggunakan Algoritma Long Short-Term Memory Pahlevi, Mohammad Rezza Pahlevi; Pahlevi, Mohammad Rezza
JNANALOKA Vol. 04 No. 02 September Tahun 2023
Publisher : Lentera Dua Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36802/jnanaloka.2022.v3-no2-69-76

Trillions of dollars per day of foreign currency trading activity occur in the forex market, which has very volatile movements in foreign currency trading. Trade based on bid and ask prices. The market determines foreign exchange rates based on supply and demand rules. Currency trading in pairs such as EUR/USD is a comparison of the value of the Euro against the Dollar as a basis for research, rising and falling currency prices in forex move fluctuatingly, so a market participant must be able to decide on buying and selling positions. Because wrong decisions can lead to losses. One of the ways to reduce risk in making decisions in buying and selling in forex can be using forecasting. This study uses the LSTM method in predicting forex prices which will be tested on several scales of dataset distribution. The smallest error results using a total dataset of 2631 with a dataset division of 70:15:15, which is divided into 70% data for training, 15% data for validation and 15% data for testing produces an RMSE value of 0.038, MAPE 2.5%. In measuring how well the regression model used with Rsquare on the data distribution is 70:15:15 and the total dataset used is 4979 to get the best results, namely 97%.

Pengembangan Sistem Prediksi Harga Emas Real-Time Berbasis LSTM Untuk Optimalisasi Waktu Investasi Bisnis Wahyu Nugraha, Diki; Rezza Pahlevi, Mohammad; Hardiansyah
Business Journal : Jurnal Bisnis Dan Sosial Vol 11 No 1 (2025): Mei
Publisher : Business Administration Department, School of Economics and Business, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jbs.v11i1.10777

Penelitian ini bertujuan mengembangkan sistem prediksi harga emas real-time berbasis Long Short-Term Memory (LSTM) untuk optimalisasi waktu investasi bisnis di tengah tingginya volatilitas pasar global. Emas sebagai aset safe haven memerlukan instrumen prediksi yang mampu menangani data deret waktu non-linear dan fluktuatif, mengatasi keterbatasan metode konvensional seperti ARIMA dalam menyimpan informasi jangka panjang. Penelitian kuantitatif eksperimental ini menggunakan data historis harga harian emas periode 3 Maret 2021 hingga 2 Maret 2026 yang diperoleh dari Yahoo Finance, dengan total 1.257 entri data. Model LSTM dirancang dengan arsitektur dua lapis (masing-masing 100 unit), fungsi aktivasi ReLU, optimasi Adaptive Moment Estimation (Adam), dan pembagian data 80% pelatihan serta 20% pengujian. Hasil evaluasi menunjukkan kinerja sangat baik dengan nilai R² Score Training 0,9908, R² Score Testing 0,9725, Mean Percentage Error (MPE) 1,74%, dan kemampuan menjelaskan variabilitas data mencapai 91%. Prediksi 30 hari ke depan (2-31 Maret 2026) mengindikasikan fase konsolidasi jangka pendek pasca tren kenaikan sejak Januari 2026, dengan rentang harga stabil di $5.203 hingga $5.217. Model mampu memprediksi arah perubahan harga harian dengan akurasi 50,67% menggunakan periode lookback 30 hari. Meskipun memiliki performa statistik kuat, prediksi bersifat probabilistik dan tidak mengantisipasi kejadian tak terduga seperti perubahan kebijakan bank sentral atau krisis geopolitik. Sistem ini direkomendasikan sebagai alat bantu analisis yang terintegrasi dengan pendekatan fundamental dan teknikal lainnya untuk mendukung pengambilan keputusan investasi yang lebih komprehensif.

Implementasi Server Virtualisasi Menggunakan Proxmox untuk Manajemen Infrastruktur Jaringan dan Layanan Internet pada Institusi Pendidikan Rido Rido; Mohammad Rezza Pahlevi; Imam Maliki; Muhammad Iqbal
Jurnal Sistem Informasi, Sains Data, dan Informatika Vol 1 No 1 (2026): Volume 1 No. 1, Januari 2026
Publisher : Universitas Indonesia Membangun (Inaba)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56956/s6zv7r91

Modern educational institutions face challenges in managing complex information technologyinfrastructure with limited resources. This research examines the implementation of virtualizationtechnology using Proxmox Virtual Environment to optimize server management, computer networks, and internet services in higher education environments. The research method uses a case studyapproach with data collection through direct observation, interviews with 12 informants, systemdocumentation, and performance monitoring over 6 months. The results show that ProxmoxVEimplementation can increase hardware resource ef iciency by up to 70 percent with CPUutilizationincreasing from 22 percent to 50-55 percent. Physical server consolidation from 12 units to3host servers successfully reduced operational costs by 45 percent or $35,650 per year. Service availabilityincreased significantly from 96.8 percent to 99.5 percent with Mean Time To Recovery reducedfrom4 hours to 45 minutes. Cost-benefit analysis shows Return on Investment achieved in 2.9 years withprojected Total Cost of Ownership savings of $73,250 over a 5-year period. This research providespractical contributions in the form of virtualization architecture blueprints and implementationguidelines that can be adopted by other educational institutions with similar characteristics.

Perancangan Design UI/UX Aplikasi Fyostore Untuk TopUp Roblox Berbasis Android Jabbar, Muhammad Sidiq Abdul; Pahlevi, Mohammad Rezza
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 1 (2026): Februari - April
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i1.6536

Perkembangan industri game digital di Indonesia mengalami peningkatan yang signifikan seiring dengan tingginya minat masyarakat terhadap platform permainan daring, salah satunya Roblox. Popularitas tersebut turut mendorong kebutuhan akan layanan top-up Robux yang cepat, aman, dan mudah digunakan. Namun, berbagai aplikasi top-up yang tersedia saat ini masih menunjukkan keterbatasan pada aspek User Interface (UI) dan User Experience (UX), sehingga berdampak pada rendahnya kenyamanan, kemudahan penggunaan, serta tingkat kepercayaan pengguna. Berdasarkan permasalahan tersebut, penelitian ini bertujuan untuk merancang antarmuka dan pengalaman pengguna aplikasi Fyostore sebagai aplikasi top-up Roblox berbasis Android dengan pendekatan Design Thinking. Penelitian ini menggunakan metode kualitatif deskriptif yang berfokus pada eksplorasi kebutuhan, persepsi, dan pengalaman pengguna dalam proses top-up Robux. Proses perancangan dilakukan melalui lima tahapan Design Thinking, yaitu empathize untuk memahami pengguna, define untuk merumuskan permasalahan utama, ideate untuk menghasilkan solusi desain, prototype untuk membuat rancangan awal aplikasi, serta test untuk mengevaluasi hasil desain. Teknik pengumpulan data meliputi observasi terhadap penggunaan aplikasi, pengembangan prototipe UI/UX, serta pengujian desain melalui kuesioner yang diberikan kepada pengguna. Hasil penelitian menunjukkan bahwa rancangan UI/UX aplikasi Fyostore mampu menyajikan alur transaksi yang lebih sistematis, navigasi yang intuitif, serta tampilan antarmuka yang mudah dipahami. Desain yang dihasilkan juga meningkatkan tingkat kenyamanan dan kepuasan pengguna, khususnya bagi pengguna pemula. Dengan demikian, penerapan metode Design Thinking dinilai efektif dalam menghasilkan rancangan UI/UX aplikasi top-up game yang berorientasi pada kebutuhan pengguna dan sesuai dengan karakteristik perangkat Android.

Perancangan Design UI/UX Aplikasi Tourify Berbasis Android Menggunakan Pendekatan Design Thinking Adittia Prasetia; Febriyansyah Ramadhan; Debi Irawan; Mohammad Rezza Pahlevi
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.8128

Pesatnya perkembangan aplikasi pariwisata berbasis Android menuntut perancangan User Interface (UI) dan User Experience (UX) yang optimal agar dapat memberikan pengalaman pengunaan yang mudah dan memuaskan. Namun demikian masih banyak aplikasi tour and travel yang menghadapi permasalahan, seperti navigasi yang kurang intuitif, ketidakjelasan penyajian informasi, serta alur transaksi yang kompleks dan memakan waktu. Kondisi tersebut berpotensi menurunkan tingkat usability dan kepuasan pengguna. Penelitian ini bertujuan untuk merancang desain UI/UX aplikasi Tourify berbasis Android dengan menerapkan pendekatan Design Thinking yang berorientasi pada kebutuhan pengguna. Metode penelitian dilakukan melalui lima tahapan, yaitu empathize, define, ideate, prototype, dan test. Pengumpulan data pada tahap empathize dilakukan melalui observasi dan penyebaran kuesioner Google Form terhadap 51 responden yang memiliki pengalaman menggunakan aplikasi tour and travel. Permasalahan utama pengguna dirumuskan menggunakan teknik How Might We (HMW), kemudian dikembangkan menjadi solusi desain melalui proses brainstorming. Hasil perancangan diwujudkan dalam bentuk prototype menggunakan perangkat lunak Figma dan selanjutnya diuji menggunakan metode Single Ease Question (SEQ) untuk mengukur tingkat kemudahan penggunaan. Hasil pengujian menunjukkan nilai rata-rata SEQ sebesar 6,88 pada skala 1–7, yang mengindikasikan tingkat usability yang sangat baik. Dengan demikian, penerapan metode Design Thinking menunjukkan peningkatan usability dalam meningkatkan kualitas UI/UX aplikasi tour and travel berbasis Android (Tourify).

Analisis Akurasi Dua Metode Klasifikasi: K-Nearest Neighbor vs Naïve Bayes pada Data Diabetes Fidalina Nirigi; Mochammad Triyanto; Mohammad Rezza Pahlevi; Athia Saelan; Fadhlanrashif Ibrahim Supriana
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.8671

Diabetes merupakan kondisi metabolik yang ditandai oleh tingginya kadar glukosa darah dan telah menjadi masalah kesehatan global. Apabila tidak ditangani dengan tepat, diabetes dapat menyebabkan komplikasi serius seperti penyakit kardiovaskular, stroke, kerusakan ginjal, mata, dan sistem saraf. Perkembangan teknologi machine learning memberikan peluang dalam membantu proses klasifikasi dan prediksi penyakit diabetes secara lebih cepat dan akurat. Penelitian ini bertujuan untuk menganalisis tingkat akurasi dua metode klasifikasi, yaitu K-Nearest Neighbor (KNN) dan Naïve Bayes pada data diabetes. Dataset yang digunakan adalah Pima Indians Diabetes Database dengan pembagian data sebesar 80% untuk data latih dan 20% untuk data uji. Tahapan penelitian meliputi preprocessing data, pelatihan model, dan pengujian klasifikasi. Variabel yang digunakan meliputi kadar glukosa, usia, indeks massa tubuh (BMI), tekanan darah, serta riwayat diabetes. Hasil penelitian menunjukkan bahwa kedua algoritma mampu melakukan klasifikasi data diabetes dengan baik. Namun, algoritma K-Nearest Neighbor memperoleh tingkat akurasi lebih tinggi sebesar 81%, sedangkan Naïve Bayes memperoleh akurasi sebesar 77%. Berdasarkan hasil tersebut, metode K-Nearest Neighbor dinilai lebih efektif dalam proses prediksi penyakit diabetes dibandingkan metode Naïve Bayes. Penelitian ini diharapkan dapat menjadi referensi dalam pengembangan sistem pendukung keputusan berbasis machine learning di bidang kesehatan, khususnya untuk deteksi dini penyakit diabetes.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search