Article
Engineering, Ocean
Bharat Kumar Saxena, Sanjeev Mishra, Komaragiri Venkata Subba Rao
Summary: This paper compares six different variants of deep learning models for offshore wind speed forecasting, and finds that EEMD can reduce forecasting error, while the superiority of deep learning models is site specific.
APPLIED OCEAN RESEARCH
(2021)
Article
Energy & Fuels
Xueyi Ai, Shijia Li, Haoxuan Xu
Summary: This paper proposes a novel hybrid wind speed forecasting model based on EEMD, LSSVM, and LSTM to improve the accuracy of wind speed prediction. The original data series is processed by EEMD and SE to obtain components with different frequencies, and a combined mechanism of LSSVM and LSTM is used to train and predict high-frequency and low-frequency sequences respectively. The predicted values of all data sequences are then superimposed to obtain the final wind speed forecasting results. Experimental results show that the EEMD-LSTM-LSSVM model achieves higher accuracy in wind speed prediction according to four performance metrics.
FRONTIERS IN ENERGY RESEARCH
(2023)
Article
Business, Finance
Kunliang Xu, Weiqing Wang
Summary: A reliable crude oil price forecast is crucial for market pricing. This study incorporates a rolling window into two prevalent EEMD-based modeling paradigms to improve accuracy. The results show that EEMD plays a weak role in improving crude oil price forecasts when only the in-sample set is preprocessed, but the rolling EEMD-denoising model has an advantage for long-term forecasting.
INTERNATIONAL REVIEW OF FINANCIAL ANALYSIS
(2023)
Article
Environmental Sciences
Ting Zhu, Wenbo Wang, Min Yu
Summary: Wind power generation is a rapidly growing renewable energy source, but its volatility and instability pose challenges to power system operation. Accurate wind speed prediction is crucial for grid management and the stability of the power system. This paper presents a novel method that decomposes, merges, and predicts wind speed sub-components, resulting in accurate short-term wind speed prediction.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Chemistry, Analytical
Shuqi Shi, Zongze Liu, Xiaofei Deng, Sifan Chen, Dongran Song
Summary: Conventional wind speed sensors face difficulties in measuring wind speeds at multiple points, and related research on predicting rotor effective wind speed (REWS) is lacking. This study proposes a data-driven prediction framework using lidar measurements and empirical mode decomposition (EMD) and gated recurrent unit (GRU) techniques to predict REWS. The results show that the proposed method achieves more accurate REWS prediction compared to the mechanism model.
Article
Computer Science, Artificial Intelligence
Zhihao Shang, Yao Chen, Yanhua Chen, Zhiyu Guo, Yi Yang
Summary: With the increase in global energy demand, the proportion of installed wind capacity continues to rise. However, accurately forecasting wind speed is challenging due to the nonlinearity, fluctuation, and intermittence of wind speed time series data. This paper proposes a novel wind speed forecasting model that can capture all implicit information of wind speed data and achieve accurate prediction results.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Yu-xing Li, Shang-bin Jiao, Xiang Gao
Summary: The article introduces a novel signal feature extraction technology based on EWT and RDE, which effectively extracts complex features of signals and improves signal separability and stability.
DEFENCE TECHNOLOGY
(2021)
Article
Energy & Fuels
Ye Zhang, Wenyu Zhang, Zhenhai Guo, Shuwen Zhang
Summary: The hybrid multistep wind speed prediction model EWP-CS-RELM outperforms seven other prediction models with the smallest statistical errors, by using ensemble empirical mode decomposition and wavelet packet transform for adaptive processing.
Article
Acoustics
Jiang Lingli, Tan Hongchuang, Li Xuejun, Yang Dalian
Summary: In this study, a method for fault diagnosis of spiral bevel gears was proposed using MPE values, LPP methods, and ELMs classifiers, demonstrating effective identification of four types of fault state spiral bevel gears with high accuracy and efficiency. The results confirmed the accuracy and superiority of the proposed method in comparison with traditional methods.
SHOCK AND VIBRATION
(2021)
Article
Green & Sustainable Science & Technology
Yuanzhuo Du, Kun Zhang, Qianzhi Shao, Zhe Chen
Summary: This study proposes a novel hybrid prediction method for improving the prediction accuracy of wind power generation. The method includes data correlation analyses, power decomposition and reconstruction, and a new prediction model.
Article
Thermodynamics
Binrong Wu, Lin Wang, Yu-Rong Zeng
Summary: This study proposes a new approach for wind speed forecasting that combines decomposition techniques, interpretable forecasting models, and optimization algorithms to achieve satisfactory performance. The results show that the proposed model outperforms other comparable models in terms of performance metrics and provides interpretable outputs, which are important for wind speed prediction and decision-making.
Article
Engineering, Electrical & Electronic
Lian Lian, Zhongda Tian
Summary: A novel prediction model based on ensemble empirical mode decomposition and multiple models is proposed to improve the prediction accuracy of network traffic. The complexity of each component is judged by introducing approximate entropy, and different prediction models are used to predict components with different complexities. An improved whale optimization algorithm is utilized to optimize model parameters for enhancing prediction accuracy. Experimental results demonstrate that the proposed model outperforms other models in terms of prediction accuracy and statistical performance indicators.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2021)
Article
Engineering, Multidisciplinary
Zhenjie Liu, Haizhong Liu
Summary: This study proposes a hybrid model integrating GA-VMD, SE, and BiLSTM for wind speed prediction. The method decomposes and reconstructs the modal components of the wind speed sequence and achieves lower errors and a higher R2 value through BiLSTM.
Article
Engineering, Electrical & Electronic
Wanming Ying, Jinde Zheng, Haiyang Pan, Qingyun Liu
Summary: PEUPEMD method improves the decomposition effect of UPEMD by adding uniform phase sinusoidal signals as masking signals, addressing issues such as noise residue and incomplete decomposition. Experimental results demonstrate that PEUPEMD outperforms other comparative methods in terms of decomposition accuracy and mode mixing suppression.
DIGITAL SIGNAL PROCESSING
(2021)
Article
Instruments & Instrumentation
Xiaoming Liu, Ling Shu
Summary: This paper proposes a fault feature extraction method for rotating machinery based on optimized resonance-based sparse signal decomposition and refined composite multiscale fluctuation dispersion entropy, which has been validated through experiments to exhibit superior performance in terms of classification accuracy and stability.
REVIEW OF SCIENTIFIC INSTRUMENTS
(2022)
Article
Mathematics, Applied
Hector Quintian, Esteban Jove, Jose-Luis Casteleiro-Roca, Daniel Urda, Angel Arroyo, Jose Luis Calvo-Rolle, Alvaro Herrero, Emilio Corchado
Summary: This paper introduces a visualization-based method for detecting intrusions in traffic flows, and validates its effectiveness on eight traffic segments.
LOGIC JOURNAL OF THE IGPL
(2022)
Article
Mathematics, Applied
Jose Antonio Moscoso-Lopez, Javier Gonzalez-Enrique, Daniel Urda, Juan Jesus Ruiz-Aguilar, Ignacio J. Turias
Summary: This study aims to forecast the Air Quality Index (AQI) by predicting pollutant concentrations using artificial neural networks and long short-term memory networks. Two input approaches were evaluated, and the results showed that the method of adding exogenous variables improved the performance of the prediction models. The newly proposed method LSTMNA provided the best performances in most cases evaluated.
LOGIC JOURNAL OF THE IGPL
(2023)
Article
Environmental Sciences
M. Rodriguez-Garcia, J. Gonzalez-Enrique, J. A. Moscoso-Lopez, J. J. Ruiz-Aguilar, I. J. Turias
Summary: The aim of this study is to conduct an in-depth analysis of air pollution in the two main cities of Bay of Algeciras, Spain. Data from 2010-2015 on air pollutant concentrations and weather measurements were collected, revealing higher levels of nitrogen dioxide, sulphur dioxide, and particulate matter in Algeciras and La Linea. Equivalent stations were identified through trends analysis, allowing for substitution of data in case of failure.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Daniel Urda, Patricia Ruiz, El Ghazali Talbi, Pascal Bouvry, Jamal Toutouh
APPLIED SOFT COMPUTING
(2023)
Article
Green & Sustainable Science & Technology
Maria Inmaculada Rodriguez-Garcia, Maria Gema Carrasco-Garcia, Javier Gonzalez-Enrique, Juan Jesus Ruiz-Aguilar, Ignacio J. Turias
Summary: Predicting air quality is crucial for health. This study uses long short-term memory models to forecast SO2 and NO2 pollutants in the Bay of Algeciras, Spain. The results show that SO2 is better predicted using autoregressive information, while NO2 is closely related to combustion engines and can be better predicted using ship and wind autoregressive time series. This study is important as it provides valuable information for decision-making by authorities, companies, and citizens.
Article
Engineering, Environmental
M. I. Rodriguez-Garcia, M. C. Ribeiro Rodrigues, J. Gonzalez-Enrique, J. J. Ruiz-Aguilar, I. J. Turias
Summary: The main aim of this research is to accurately predict pollutant concentrations associated with maritime traffic in the Bay of Algeciras in southern Spain. The study analyzes different scenarios and uses databases of air pollution, meteorological measurements, and maritime traffic to develop prediction models. These models have been compared using various classification indexes and the best models have been selected based on their performance. The results demonstrate the potential of the models to forecast air pollution and support decision-making regarding air quality.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Daniel Urda, Nuno Basurto, Meelis Kull, Alvaro Herrero
Summary: Websites are attractive targets for attackers due to the high number of users and information exchange. Computational Intelligence-based techniques, including feature selection methods, are used to detect undesired events. This paper evaluates feature selection methods and classifiers on the CSIC2010 v2 dataset and explores the dataset's features to improve web attack detection.
INTERNATIONAL JOINT CONFERENCE 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN SECURITY FOR INFORMATION SYSTEMS (CISIS 2022) 13TH INTERNATIONAL CONFERENCE ON EUROPEAN TRANSNATIONAL EDUCATION (ICEUTE 2022)
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Nuno Basurto, Alvaro Michelena, Daniel Urda, Hector Quintian, Jose Luis Calvo-Rolle, Alvaro Herrero
Summary: Websites are common targets for attackers, and protecting them is crucial. However, there has been limited research on using unsupervised machine learning to analyze web traffic and detect attacks. This paper proposes the use of dimensionality reduction methods to generate intuitive visualizations for analyzing web traffic. Several methods have been benchmarked with promising results on the CSIC2010 v2 dataset, suggesting the need for further research.
INTERNATIONAL JOINT CONFERENCE 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN SECURITY FOR INFORMATION SYSTEMS (CISIS 2022) 13TH INTERNATIONAL CONFERENCE ON EUROPEAN TRANSNATIONAL EDUCATION (ICEUTE 2022)
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Nuno Basurto, Hector Quintian, Daniel Urda, Jose Luis Calvo-Rolle, Alvaro Herrero, Emilio Corchado
Summary: This paper proposes a new technique called Hybrid Unsupervised Exploratory Plots (HUEPs) for visualizing the structure of an Android malware dataset through advanced 3D visualization, providing an overview of the malware families and supporting the analysis of their internal organization.
14TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN SECURITY FOR INFORMATION SYSTEMS AND 12TH INTERNATIONAL CONFERENCE ON EUROPEAN TRANSNATIONAL EDUCATIONAL (CISIS 2021 AND ICEUTE 2021)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Roberto Magan-Carrion, Daniel Urda, Ignacio Diaz-Cano, Bernabe Dorronsoro
Summary: This article discusses the importance of feature engineering in intrusion detection systems, introduces a feature as a counter approach, and proposes a batch-based aggregation technique to overcome the issue of timestamp-less datasets.
14TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN SECURITY FOR INFORMATION SYSTEMS AND 12TH INTERNATIONAL CONFERENCE ON EUROPEAN TRANSNATIONAL EDUCATIONAL (CISIS 2021 AND ICEUTE 2021)
(2022)