Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Applied Data Sciences Journal of Current Research in Blockchain
Jing Sun
Faculty of Liberal Arts, Shinawatra University, Thailand
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
A Hybrid Ensemble Framework Combining Transformer Networks, CNN-LSTM, and Prophet for Multi-Horizon Bitcoin Price Prediction Using 1-Minute Time Series Data Siti Sarah Maidin; M. Hemalatha; Jing Sun
Journal of Current Research in Blockchain Vol. 3 No. 1 (2026): Regular Issue March 2026
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jcrb.v3i1.57

Abstract

Bitcoin price forecasting at one-minute frequency presents significant challenges due to rapid volatility and noise in high-frequency markets. This study proposes a hybrid ensemble framework integrating a CNN-LSTM model, a Transformer architecture, and a Prophet-based component to perform multi-horizon prediction using 500,000 one-minute BTC/USD observations. The model is evaluated across 5-minute, 15-minute, and 30-minute horizons. The results show that the ensemble achieves the best performance for the 5-minute horizon with MAE = 41.565 USD, RMSE = 60.722 USD, and MAPE = 0.156. This outperforms the CNN-LSTM model (MAE = 47.838 USD) and the Transformer model (MAE = 53.733 USD). Performance decreases at the 15-minute horizon due to Transformer instability, where the ensemble reaches MAE = 269.347 USD and the Transformer reaches MAE = 530.429 USD. At the 30-minute horizon, performance stabilizes, with the ensemble producing MAE = 84.481 USD, close to the CNN-LSTM result (MAE = 84.186 USD) and better than the Transformer (MAE = 153.887 USD). These findings indicate that the hybrid ensemble is highly effective for ultra-short-term forecasting but requires horizon-specific tuning to remain stable for medium-range intervals.
An Effective Investigation of Genetic Disorder Disease Using Deep Learning Methodology B. Vidhya; B. L. Shivakumar; Siti Sarah Maidin; Jing Sun
Journal of Applied Data Sciences Vol 5, No 3: SEPTEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i3.370

Abstract

This study evaluates the performance of four neural network models—Artificial Neural Network (ANN), ANN optimized with Artificial Bee Colony (ANN-ABC), Multilayer Feedforward Neural Network (MLFNN), and Forest Deep Neural Network (FDNN)—across different iteration levels to assess their effectiveness in predictive tasks. The evaluation metrics include accuracy, precision, Area Under the Curve (AUC) values, and error rates. Results indicate that FDNN consistently outperforms the other models, achieving the highest accuracy of 99%, precision of 98%, and AUC of 99 after 250 iterations, while maintaining the lowest error rate of 2.8%. MLFNN also shows strong performance, particularly at higher iterations, with notable improvements in accuracy and precision, but does not surpass FDNN. ANN-ABC offers some improvements over the standard ANN, yet falls short compared to FDNN and MLFNN. The standard ANN model, though improving with iterations, ranks lowest in all metrics. These findings highlight FDNN's robustness and reliability, making it the most effective model for high-precision predictive tasks, while MLFNN remains a strong alternative. The study underscores the importance of model selection based on performance metrics to achieve optimal predictive accuracy and reliability. 
Co-Authors B. L. Shivakumar B. Vidhya M. Hemalatha Siti Sarah Maidin