Ensemble-based Disease Prediction in Medical Image Data

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 622 - 632

Published: Jan. 1, 2025

Language: Английский

---

Assessment of sediment yield and surface runoff using the SWAT hydrological model: a case study of the Khazir River basin, northern Iraq

Euro-Mediterranean Journal for Environmental Integration, Journal Year: 2024, Volume and Issue: 9(2), P. 809 - 825

Published: March 31, 2024

Language: Английский

---

Long Short-Term Memory Autoencoder and Extreme Gradient Boosting-Based Factory Energy Management Framework for Power Consumption Forecasting

Energies, Journal Year: 2024, Volume and Issue: 17(15), P. 3666 - 3666

Published: July 25, 2024

Electricity consumption prediction is crucial for the operation, strategic planning, and maintenance of power grid infrastructure. The effective management systems depends on accurately predicting electricity usage patterns intensity. This study aims to enhance operational efficiency minimize environmental impact by mid long-term in industrial facilities, particularly forging processes, detecting anomalies energy consumption. We propose an ensemble model combining Extreme Gradient Boosting (XGBoost) a Long Short-Term Memory Autoencoder (LSTM-AE) forecast approach leverages strengths both models improve accuracy responsiveness. dataset includes data from processes manufacturing plants, as well system load System Marginal Price data. During preprocessing, Expectation Maximization Principal Component Analysis was applied address missing values select significant features, optimizing model. proposed method achieved Mean Absolute Error 0.020, Squared 0.021, Coefficient Determination 0.99, Symmetric Percentage 4.24, highlighting its superior predictive performance low relative error. These findings underscore model’s reliability integration into Energy Management Systems real-time processing facilitating sustainable use informed decision making settings.

Language: Английский

---

A Review on Deep Anomaly Detection in Blockchain

Blockchain Research and Applications, Journal Year: 2024, Volume and Issue: unknown, P. 100227 - 100227

Published: Aug. 1, 2024

The last few years have witnessed the widespread use of blockchain technology in several works, due to its effectiveness terms privacy, security, and trustworthiness. However, Cyber-attacks challenges represent a real threat systems based on this technology. resort anomaly detection focused deep learning, also called detection, is an appropriate efficient means tackle cyber-attacks blockchain. This paper provides overview concept, characteristics, limitations, taxonomy. Numerous are discussed such as 51% attacks, selfish mining double spending Sybil etc. Furthermore, we surveyed with their unresolved issues. In addition, article gives glimpse various learning approaches implemented for environment, presenting methods that enhance security features systems. Finally, benefits drawbacks these recent advanced light three categories, which discriminative, generative, hybrid other graphs highlighting ability proposed perform real-time detection.

Language: Английский

---

Enhancing spatial resolution of satellite soil moisture data through stacking ensemble learning techniques

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 26, 2024

Language: Английский

---