Background: To offer a transparent decision support system able of classifying tweets’ sentiment into positive, neutral, and negative explains the prediction result by XAI techniques Methods: We started data preprocessing phase. For representation, we used TF-IDF, applied four machine-learning algorithms including Naive Bayes, random forest, logistic regression, vector machine, as well deep lea...

Signal frequency estimation is a fundamental problem in signal processing. Deep learning method to solve this problem. This paper used five deep methods and three datasets including different singles Single Tone (ST), Linear- Frequency-Modulated (LFM), Quadratic-Frequency-Modulated (QFM). affected by Additive White Gaussian (AWG) noise Symmetric alpha Stable (SαS) noise. Geometric SNR (GSNR) de...

Wind power is an essential component of renewable energy. It enables the conservation conventional energy sources such as coal and oil while reducing greenhouse gas emissions. To address stochastic intermittent nature ultra-short-term wind power, a combined prediction model based on variational mode decomposition (VMD) gradient boosting regression tree (GBRT) proposed. Firstly, VMD utilized to ...

To improve the accuracy of short-term wind speed forecasting, we proposed a Gated Recurrent Unit network forecasting method, based on ensemble empirical mode decomposition and Grid Search Cross Validation parameter optimization algorithm. In this study, first, in process decomposing, set was introduced to divide time series into high-frequency modal, low-frequency trend using Pearson correlatio...

Nonintrusive load monitoring (NILM) is a process that disaggregates individual energy consumption based on the total consumption. In this study, an disaggregation model was developed and verified using algorithm recurrent neural network (RNN). It also aimed to evaluate utility of occupant location information, which nonelectrical information. This study models with RNN-based long short-term mem...

In the previous research on traffic flow prediction models, most of models mainly studied time series flow, and spatial correlation was not fully considered. To solve this problem, paper proposes a method to predict spatio-temporal characteristics short-term by combining k-nearest neighbor algorithm bidirectional long memory network model. By selecting real-time data observed high-speed roads i...

Effective wind power prediction will facilitate the world’s long-term goal in sustainable development. However, a drawback of as an energy source lies its high variability, resulting challenging study forecasting. To solve this issue, novel data-driven approach is proposed for forecasting by integrating data pre-processing & re-sampling, anomalies detection treatment, feature engineering, and h...

Physically based cloth simulation requires a model that represents as collection of nodes connected by different types constraints. In this paper, we present coefficient prediction framework using Deep Learning (DL) technique to enhance video summarization for such simulations. Our proposed virtual interconnected are subject various To ensure temporal consistency, train the Gated Recurrent Unit...

Traditional reactive approach of blacklisting botnets fails to adapt the rapidly evolving landscape cyberattacks. An automated and proactive detect block botnet hosts will immensely benefit industry. Behavioral analysis attackers is shown be effective against a wide variety attack types. Previous works, however, focus solely on anomalies in network traffic bots botnet. In this work we take more...

Phishing is a type of cyber-attack that aims to deceive users, usually using fraudulent web pages appear legitimate. Currently, one the most-common ways detect these phishing according their content by entering words non-sequentially into Deep Learning (DL) algorithms, i.e., regardless order in which they have entered algorithms. However, this approach causes intrinsic richness relationship bet...