Article Per Year (5 Year)
p-Index From 2020 - 2025
0.659
P-Index
This Author published in this journals
All Journal HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Natzir, Sadam Muhammad
Unknown Affiliation
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
PREDIKSI HARGA CRYPTOCURRENCY XLM MENGGUNAKAN METODE DEEP LEARNING LSTM DAN GRU: PREDICTING XLM CRYPTOCURRENCY PRICES USING LSTM AND GRU DEEP LEARNING MODELS Natzir, Sadam Muhammad; Jatiprasetya, Harumawan
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 16 No. 1 (2025): Jurnal HOAQ - Teknologi Informasi
Publisher : STIKOM Uyelindo Kupang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol16no1.p49-58

Abstract

Volatilitas pasar yang tinggi serta potensi keuntungan besar dari cryptocurrency menjadikan prediksi harga sebagai topik penelitian yang menarik. Penelitian ini bertujuan untuk memprediksi harga cryptocurrency Stellar (XLM) dengan menerapkan metode Deep Learning, yaitu Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU). Data yang digunakan mencakup harga harian XLM selama beberapa tahun terakhir, serta indikator teknikal dan aktivitas perdagangan. Model LSTM dan GRU dievaluasi berdasarkan akurasi dalam memprediksi harga XLM menggunakan metrik MAPE, RMSE, dan MSE. Hasil menunjukkan bahwa meskipun keduanya mampu menangkap pola tren jangka pendek, model GRU memberikan hasil yang lebih unggul. GRU mencatat MAPE sebesar 3.6164%, RMSE sebesar 0.0206, dan MSE sebesar 0.0004. Sementara itu, LSTM mencatat MAPE sebesar 4.5638%, RMSE sebesar 0.0244, dan MSE sebesar 0.0005. Temuan ini menunjukkan bahwa GRU lebih efektif dalam memodelkan kompleksitas dan non-linearitas data harga XLM dibandingkan LSTM. Dengan demikian, GRU dapat dipertimbangkan sebagai metode yang lebih unggul dalam prediksi harga cryptocurrency. Hasil penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan model prediksi yang lebih akurat serta membantu pengambilan keputusan investasi yang lebih bijak.   The high market volatility and significant profit potential of cryptocurrencies have made price prediction a compelling area of research. This study aims to predict the price of Stellar (XLM), a widely recognized cryptocurrency, by applying deep learning methods, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The dataset includes daily XLM prices over the past few years, along with technical indicators and trading activity data. The LSTM and GRU models are evaluated based on their accuracy in predicting XLM prices using metrics such as MAPE, RMSE, and MSE. The results show that while both models are capable of capturing short-term trends, the GRU model outperforms LSTM. GRU achieved a MAPE of 3.6164%, RMSE of 0.0206, and MSE of 0.0004, whereas LSTM recorded a MAPE of 4.5638%, RMSE of 0.0244, and MSE of 0.0005. These findings indicate that GRU is more effective in modeling the complexity and non-linearity of XLM price data compared to LSTM. Therefore, GRU can be considered a superior approach for cryptocurrency price prediction. This study is expected to contribute to the development of more accurate forecasting models and to support better investment decision-making.
PERBANDINGAN KINERJA MODEL PEMBELAJARAN MESIN DALAM PREDIKSI BANJIR MENGGUNAKAN KNN, NAIVE BAYES, DAN RANDOM FOREST Natzir, Sadam Muhammad
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 14 No. 2 (2023): Jurnal HOAQ - Teknologi Informasi
Publisher : STIKOM Uyelindo Kupang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol14no2.p59-64

Abstract

Penelitian ini menyajikan analisis komparatif model pembelajaran mesin untuk prediksi banjir menggunakan data historis curah hujan. Tiga model, yaitu K-Nearest Neighbors (KNN), Naive Bayes, dan Random Forest, dievaluasi berdasarkan metrik kinerja mereka. Evaluasi mencakup akurasi, presisi, recall, skor F1, dan ROC AUC. Hasilnya menunjukkan bahwa model Random Forest mengungguli yang lain, mencapai skor sempurna dalam semua metrik. Namun, KNN dan Naive Bayes juga menunjukkan kinerja yang kompetitif, meskipun dengan beberapa trade-off antara presisi dan recall. Temuan ini memberikan wawasan berharga tentang efektivitas berbagai pendekatan pembelajaran mesin untuk prediksi banjir, yang berkontribusi pada pengembangan sistem prediksi banjir yang lebih andal.   This study presents a comparative analysis of machine learning models for flood prediction using historical rainfall data. Three models, namely K-Nearest Neighbors (KNN), Naive Bayes, and Random Forest, are evaluated based on their performance metrics, including accuracy, precision, recall, F1 score, and ROC AUC. The evaluation results show that the Random Forest model consistently outperforms KNN and Naive Bayes. Random Forest achieves a perfect score (100%) on all measured indicators. Meanwhile, KNN and Naive Bayes also demonstrate competitive performance, albeit with some trade-offs between precision and recall. Specifically, for accuracy, precision, recall, F1 score, and ROC AUC, the Random Forest model scores 100%, whereas KNN and Naive Bayes are in the range of 90-95%. Nevertheless, KNN and Naive Bayes still show competitive performance and are worth considering as alternative flood prediction models. These findings provide valuable insights into the effectiveness of various machine learning approaches for flood prediction. The Random Forest model proves to be the superior approach, yet KNN and Naive Bayes also show significant potential. The results of this study contribute to the development of more reliable and accurate flood prediction systems, with important implications for disaster management and flood risk reduction..
Prototype Alat Pemberitahuan Kecelakaan Menggunakan Microcontroller Node MCU dan Sensor Crash Natzir, Sadam Muhammad; Malahina, Edwin Ariesto Umbu
Jurnal Teknik Informatika dan Sistem Informasi Vol 10 No 1 (2024): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v10i1.6961

Abstract

This research has successfully developed a prototype for an automatic accident notification device using the Node MCU Microcontroller and Crash Sensor. The device is designed to detect accident incidents and provide a quick response by sending notifications containing the location of the accident through Short Messages (SMS/Telegram) to the relevant units in real-time. The Crash Sensor and Node MCU work together to detect and track incidents, while the GPS marking system and cellular communication module are used to track and send the coordinates of the accident location. The prototype was tested in various accident scenarios to test the accuracy and responsiveness of the system. The results showed that this prototype is capable of detecting and sending notifications about incidents with high speed and accuracy. The SIM800l module used in this prototype has a message delivery success rate of 90%. The implementation of this technology has the potential to increase the efficiency and effectiveness of emergency response to accidents, reducing handling time and potential further losses. Furthermore, this research indicates potential for further integration with traffic control systems or emergency services, which will form a more coordinated and effective response to accident incidents.
Co-Authors Edwin Ariesto Umbu Malahina Jatiprasetya, Harumawan