Stock price series forecasting using multi-scale modeling with boruta feature selection and adaptive denoising

J Li, Y Liu, H Gong, X Huang - Applied Soft Computing, 2024 - Elsevier
In recent times, predicting stock prices has garnered attention from both regulators and
academic circles. However, the intricate nature of financial time-series data, with its …

RSTC: Residual Swin Transformer Cascade to approximate Taylor expansion for image denoising

J Liu, Y Yang, B Xu, H Yu, Y Zhang, Q Li… - Computer Vision and …, 2024 - Elsevier
Traditional denoising methods establish mathematical models by employing different priors,
which can achieve preferable results but they are usually time-consuming and their outputs …

Analysis of transient pressure of pump-turbine during load rejection based on a multi-step extraction method

T Zhou, X Yu, J Zhang, H Xu - Energy, 2024 - Elsevier
During the load rejection condition of the pump-turbines, the S-shaped characteristic would
lead to intense pressure pulsations, thus threatening the safe operation of the pumped …

A new denoising approach based on mode decomposition applied to the stock market time series: 2LE-CEEMDAN

ZD Akşehir, E Kılıç - PeerJ Computer Science, 2024 - peerj.com
Time series, including noise, non-linearity, and non-stationary properties, are frequently
used in prediction problems. Due to these inherent characteristics of time series data …

Can Clean Energy Stocks Predict Crude Oil Markets Using Hybrid and Advanced Machine Learning Models?

A Jarboui, E Mnif - Asia-Pacific Financial Markets, 2024 - Springer
The volatility of crude oil markets and the pressing need for sustainable energy solutions
have sparked significant interest in forecasting methodologies that can better capture market …

The multi-strategy hybrid forecasting base on SSA-VMD-WST for complex system

H Su, S Ma, X Xu - Plos one, 2024 - journals.plos.org
In view of the strong randomness and non-stationarity of complex system, this study
suggests a hybrid multi-strategy prediction technique based on optimized hybrid denoising …

The Importance of Labeling and Noise on The Trading Strategy

ZD Akşehir, E Kılıç - 2023 8th International Conference on …, 2023 - ieeexplore.ieee.org
This study proposed an indirectly developed trading strategy based on the labeling methods
used in the literature on noiseless financial time series using the C EEMDAN method. This …

Obtaining quantitative information from time series patterns: Insights from SAX, MDL and the Matrix Profile

E Cartwright - 2024 - doras.dcu.ie
In the contemporary trading environment any competitive advantage is of core interest to
technical traders and financial analysts. Motifs (ie time series patterns corresponding to …

An ensemble learning approach for webshell detection

B Shi, K Xu, M Li, Z Li - Third International Conference on …, 2024 - spiedigitallibrary.org
Webshell is a type of malicious script that is written by network attackers based on the
characteristics of web programming languages. It usually exists in the form of web files such …