The complexity and variety of language included in policy and academic documents make the automatic classification of research papers based on the United Nations Sustainable Development Goals (SDGs) somewhat difficult. Using both pre-trained and contextual word embeddings to increase semantic understanding, this study presents a complete deep learning pipeline combining Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) architectures which aims primarily to improve the comprehensibility and accuracy of SDG text classification, thereby enabling more effective policy monitoring and research evaluation. Successful document representation via Global Vector (GloVe), Bidirectional Encoder Representations from Tra

To obtain the approximate solution to Riccati matrix differential equations, a new variational iteration approach was ‎proposed, which is suggested to improve the accuracy and increase the convergence rate of the approximate solutons to the ‎exact solution. This technique was found to give very accurate results in a few number of iterations. In this paper, the ‎modified approaches were derived to give modified solutions of proposed and used and the convergence analysis to the exact ‎solution of the derived sequence of approximate solutions is also stated and proved. Two examples were also solved, which ‎shows the reliability and applicability of the proposed approach. ‎

A substantial portion of today’s multimedia data exists in the form of unstructured text. However, the unstructured nature of text poses a significant task in meeting users’ information requirements. Text classification (TC) has been extensively employed in text mining to facilitate multimedia data processing. However, accurately categorizing texts becomes challenging due to the increasing presence of non-informative features within the corpus. Several reviews on TC, encompassing various feature selection (FS) approaches to eliminate non-informative features, have been previously published. However, these reviews do not adequately cover the recently explored approaches to TC problem-solving utilizing FS, such as optimization techniques.

This study was aimed to investigate the response surface methodology (RSM) to evaluate the effects of various experimental conditions on the removal of levofloxacin (LVX) from the aqueous solution by means of electrocoagulation (EC) technique with stainless steel electrodes. The EC process was achieved successfully with the efficiency of LVX removal of 90%. The results obtained from the regression analysis, showed that the data of experiential are better fitted to the polynomial model of second-order with the predicted correlation coefficient (pred. R2) of 0.723, adjusted correlation coefficient (Adj. R2) of 0.907 and correlation coefficient values (R2) of 0.952. This shows that the predicted models and experimental values are in go

Abstract  

  In this work, two algorithms of Metaheuristic algorithms were hybridized. The first is Invasive Weed Optimization algorithm (IWO) it is a numerical stochastic optimization algorithm and the second is Whale Optimization Algorithm (WOA) it is an algorithm based on the intelligence of swarms and community intelligence. Invasive Weed Optimization Algorithm (IWO) is an algorithm inspired by nature and specifically from the colonizing weeds behavior of weeds, first proposed in 2006 by Mehrabian and Lucas. Due to their strength and adaptability, weeds pose a serious threat to cultivated plants, making them a threat to the cultivation process. The behavior of these weeds has been simulated and used in Invas

The multi-focus image fusion method can fuse more than one focused image to generate a single image with more accurate description. The purpose of image fusion is to generate one image by combining information from many source images of the same scene. In this paper, a multi-focus image fusion method is proposed with a hybrid pixel level obtained in the spatial and transform domains. The proposed method is implemented on multi-focus source images in YCbCr color space. As the first step two-level stationary wavelet transform was applied on the Y channel of two source images. The fused Y channel is implemented by using many fusion rule techniques. The Cb and Cr channels of the source images are fused using principal component analysis (PCA).

In high-dimensional semiparametric regression, balancing accuracy and interpretability often requires combining dimension reduction with variable selection. This study intro- duces two novel methods for dimension reduction in additive partial linear models: (i) minimum average variance estimation (MAVE) combined with the adaptive least abso- lute shrinkage and selection operator (MAVE-ALASSO) and (ii) MAVE with smoothly clipped absolute deviation (MAVE-SCAD). These methods leverage the flexibility of MAVE for sufficient dimension reduction while incorporating adaptive penalties to en- sure sparse and interpretable models. The performance of both methods is evaluated through simulations using the mean squared error and variable selection cri

Geographic Information Systems (GIS) are obtaining a significant role in handling strategic applications in which data are organized as records of multiple layers in a database. Furthermore, GIS provide multi-functions like data collection, analysis, and presentation. Geographic information systems have assured their competence in diverse fields of study via handling various problems for numerous applications. However, handling a large volume of data in the GIS remains an important issue. The biggest obstacle is designing a spatial decision-making framework focused on GIS that manages a broad range of specific data to achieve the right performance. It is very useful to support decision-makers by providing GIS-based decision support syste