Garuda - Garba Rujukan Digital

LSTM Network Application for Forecasting Ethereum Price Changes and Trends Pradhana, Anak Agung Surya; Batubulan, Kadek Suarjuna
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 7 No 2 (2024): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.196

Forecasting Ethereum price changes presents challenges due to the cryptocurrency market’s volatility and rapid fluctuations. This study applies Long Short-Term Memory (LSTM) networks to predict Ethereum price trends using hourly historical data. The LSTM model captures temporal dependencies effectively, achieving moderate accuracy with a Root Mean Squared Error (RMSE) of 11.42. It performs well in stable market conditions, with predicted prices closely aligning with actual values, validating its potential for identifying long-term trends. However, the model struggles during high-volatility periods, failing to predict abrupt price spikes and market crashes accurately. Overfitting is also observed, indicated by disparities between training and test errors, limiting the model’s generalizability to unseen data. To address these issues, this research suggests incorporating features such as trading volumes, market sentiment, macroeconomic indicators, and blockchain metrics to enhance predictive accuracy. Additionally, employing advanced architectures like attention mechanisms, hybrid models, and real-time learning frameworks is recommended to improve adaptability and robustness in dynamic market environments. These enhancements aim to create a more comprehensive and reliable predictive tool. This study contributes to the advancement of predictive analytics in cryptocurrency markets, offering valuable insights for traders, investors, and policymakers navigating the complexities of digital finance.

Support Vector Machine for Accurate Classification of Diabetes Risk Levels Sugiartawan, Putu; Wardani, Ni Wayan; Pradhana, Anak Agung Surya; Batubulan, Kadek Suarjuna; Kotama, I Nyoman Darma
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 3 (2025): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.107740

This research explores the application of Support Vector Machines (SVM) for accurately classifying diabetes risk levels based on a publicly available dataset containing 768 instances and 9 attributes, including glucose levels, BMI, blood pressure, and insulin levels. The model's systematic development process involved data preprocessing, feature selection, and hyperparameter optimization to ensure robust performance. Results indicate an overall accuracy of 76%, with high precision and recall for the non-diabetic risk class, but relatively lower performance for the diabetic risk class, highlighting the challenges posed by class imbalance and overlapping data features. To address these issues, future research should incorporate advanced resampling techniques, refined feature engineering, and alternative machine learning models like Random Forest or XGBoost. This research underscores the potential of SVM as a valuable tool for early diabetes detection, offering healthcare professionals a reliable means to identify at-risk individuals and personalize intervention strategies. By bridging theoretical advancements and practical applications, the research contributes to enhancing predictive analytics in medical diagnostics, paving the way for improved patient outcomes and efficient public health management

Binary Classification of Exchange Rate Trends Using Logistic Regression Wardani, Ni Wayan; Pradhana, Anak Agung Surya; Kotama, I Nyoman Darma
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 7 No 4 (2025): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.218

This study explores the use of logistic regression for binary classification of exchange rate trends, focusing on predicting upward and downward currency movements. Logistic regression, valued for its simplicity and interpretability, models the relationship between historical exchange rate data and macroeconomic indicators like interest rates, inflation, GDP growth, and trade balances. The methodology involves data collection, preprocessing, feature engineering, and model evaluation. Historical data is processed to address missing values, outliers, and noise, ensuring a robust dataset. Feature selection techniques, including mutual information scores and principal component analysis (PCA), identify key predictors, while L1 and L2 regularization enhance generalization. The model, implemented using Python's scikit-learn library, is optimized through grid search for hyperparameter tuning. Performance metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, indicate strong predictive capability, achieving 99% accuracy in forecasting upward and downward trends. Logistic regression's interpretability aids decision-making, making it a valuable tool for financial forecasting. However, the study notes limitations, such as challenges posed by market volatility and geopolitical factors. Future research suggests incorporating sentiment analysis from financial news and social media, and exploring hybrid models combining logistic regression with ensemble methods or deep learning to improve performance under real-world conditions.

Applying K-Nearest Neighbors Algorithm for Wine Prediction and Classification Pradhana, Anak Agung Surya; Batubulan, Kadek Suarjuna; Kotama, I Nyoman Darma
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 3 (2024): March
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.231

This study evaluates the performance of a machine learning classification model using a confusion matrix to analyze predictions across three distinct classes. The results show the model achieving a high accuracy of 94.44%, indicating reliable classification performance. The confusion matrix highlights that most instances were classified correctly, with minimal misclassifications observed, particularly in Class 1, where some overlap with other classes was evident. The findings suggest that the model effectively distinguishes between well-separated classes while facing minor challenges with overlapping data distributions. To address these issues, potential improvements such as feature engineering, class balancing, and advanced optimization techniques are recommended. The study underscores the importance of confusion matrix analysis as a diagnostic tool for understanding classification errors and guiding model refinement. Additionally, this research emphasizes the role of high-quality datasets, proper model selection, and hyperparameter tuning in achieving optimal classification accuracy. The outcomes provide a basis for further enhancement of machine learning models in applications requiring multi-class classification. By reducing errors and improving model robustness, this approach can contribute to more accurate and reliable decision-making processes across various domains, including healthcare, finance, and natural language processing.

K-Nearest Neighbors Algorithm for Analyzing Doge Coin Market Behavior Batubulan, Kadek Suarjuna; Pradhana, Anak Agung Surya; Kotama, I Nyoman Darma
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 4 (2024): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.238

This study investigates the application of the K-Nearest Neighbors (KNN) algorithm to analyze Dogecoin's market behavior using historical trading data, including daily metrics such as Open, High, Low, Close, and Volume, spanning from November 2017. As a proximity-based machine learning algorithm, KNN effectively captures short-term market patterns, achieving a low Mean Absolute Error (MAE) of 0.0017, demonstrating its capability in identifying general trends during stable periods. However, the model faces challenges in predicting sudden price shifts caused by external factors like social media sentiment and regulatory news, highlighting its limitations in highly volatile cryptocurrency markets. Preprocessing steps, including normalization and outlier handling, improved the algorithm’s performance, yet its scalability and sensitivity to hyperparameters remain issues. Future research directions include integrating external data sources, such as social media sentiment and macroeconomic indicators, and adopting advanced models like Gradient Boosting Machines (GBMs) or Long Short-Term Memory (LSTM) networks to enhance predictive accuracy and adaptability. These improvements aim to provide more robust insights into Dogecoin's market dynamics, aiding traders and financial analysts in navigating the complexities of cryptocurrency markets.

Predicting Wine Quality Based on Features Using Naive Bayes Classifier Pradhana, Anak Agung Surya; Batubulan, Kadek Suarjuna; Kotama, I Nyoman Darma
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 7 No 1 (2024): September
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.244

This study explores the application of the Naive Bayes classifier in predicting wine quality based on physicochemical attributes. Leveraging a dataset containing features such as acidity, pH, alcohol content, and sulfur dioxide concentrations, the research aims to address the limitations of traditional sensory evaluation methods, which are often subjective and inconsistent. Data preprocessing, including normalization and feature selection, is performed to ensure the dataset is suitable for machine learning. The Naive Bayes classifier is implemented using Python's scikit-learn library, with hyperparameter tuning conducted to optimize its performance. The model is evaluated on metrics such as accuracy, precision, recall, and F1-score, achieving competitive results compared to other machine learning techniques such as Decision Trees and Support Vector Machines. The findings demonstrate the Naive Bayes classifier’s efficiency in handling high-dimensional data, its computational simplicity, and its potential for real-time quality assessment in the wine industry. This research highlights the role of machine learning in automating and enhancing quality control processes, contributing to the broader integration of data-driven approaches in the agri-food sector. The study underscores the feasibility of using physicochemical features as objective indicators of wine quality, offering a scalable and cost-effective alternative to traditional methods.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search