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

The fiscal position of governments in rentier economies depends heavily on oil revenues. The relationship between oil prices and the budget surplus or deficit is often nonlinear and characterized by complex temporal dependencies, which may limit the predictive capability of conventional econometric models. Accordingly, this study aims to forecast the Iraqi budget surplus and deficit and compare the predictive performance of the ARDL, NARDL, LSTM, 1D-CNN, and hybrid 1D-CNN-LSTM models using oil prices as the primary predictive variable. The hybrid model integrates the feature-extraction capability of One-Dimensional Convolutional Neural Networks (1D-CNN) with the ability of Long Short-Term Memory (LSTM) networks to capture long-term

This paper introduces a novel nonparametric hybrid cyber-intelligence-based statistical process control and anomaly detection framework in time series data. It is developed to overcome the shortcomings of the classical control schemes in dealing with complex, abnormal, and noisy input data, especially when it is autocorrelated. The proposed methodology combines three technical pillars: First, it utilizes a bidirectional long-short-term memory architecture (Bi-LSTM) to capture long-term time dependency and learn nonlinear patterns, leaving only true deviations as residuals that remove trends and noises from the market. Second, it adopts the Golden Eagle Optimizer (GEO) algorithm for optimal parameter selection. This intelligent algor

Data centric techniques, like data aggregation via modified algorithm based on fuzzy clustering algorithm with voronoi diagram which is called modified Voronoi Fuzzy Clustering Algorithm (VFCA) is presented in this paper. In the modified algorithm, the sensed area divided into number of voronoi cells by applying voronoi diagram, these cells are clustered by a fuzzy C-means method (FCM) to reduce the transmission distance. Then an appropriate cluster head (CH) for each cluster is elected. Three parameters are used for this election process, the energy, distance between CH and its neighbor sensors and packet loss values. Furthermore, data aggregation is employed in each CH to reduce the amount of data transmission which le

Often phenomena suffer from disturbances in their data as well as the difficulty of formulation, especially with a lack of clarity in the response, or the large number of essential differences plaguing the experimental units that have been taking this data from them. Thus emerged the need to include an estimation method implicit rating of these experimental units using the method of discrimination or create blocks for each item of these experimental units in the hope of controlling their responses and make it more homogeneous. Because of the development in the field of computers and taking the principle of the integration of sciences it has been found that modern algorithms used in the field of Computer Science genetic algorithm or ant colo

Extended utilization of adaptive algorithms, Evaluative Algorithms (EAs), to address these issues offers a way to handle massive multi-objective optimization, even if the algorithmic method for handling combinations of objectives (CO) has been accessible for quite some time. Combining the idea of superiority with the Hypervolume (HV) tag approach, the GSA algorithm utilizes various target effects to explain several algorithms depending on the Hypervolume (HV) spacing. The Multi-objective Gravitational Search Algorithm with Hypervolume (MOGSA/HV). Since rapid convergence could result from GSA foundation work, Hypervolume rewrites the multi-objective problem (MOP) as a sequence of Tchebycheff solutions, improving it. Since the one in charge h

Many industrial systems involve multiple criteria and objectives, and they are very complex problems in computational science, such as task scheduling. We propose bi-criteria and bi-objective scheduling problems, which are solved by two nature-inspired evolutionary algorithms, such as Simulated Annealing (SA) and Bee Algorithm (BA). This problem is characterized by scheduling a batch of tasks on multiple machines, and it is fundamental because the solution should focus on the simultaneous optimization of two conflicting objectives: the makespan minimization and the total tardiness minimization. This problem is NP-Hard, and therefore, two evolutionary methods were used to search for solutions intelligently in this huge, very complex

Digital image manipulation has become increasingly prevalent due to the widespread availability of sophisticated image editing tools. In copy-move forgery, a portion of an image is copied and pasted into another area within the same image. The proposed methodology begins with extracting the image's Local Binary Pattern (LBP) algorithm features. Two main statistical functions, Stander Deviation (STD) and Angler Second Moment (ASM), are computed for each LBP feature, capturing additional statistical information about the local textures. Next, a multi-level LBP feature selection is applied to select the most relevant features. This process involves performing LBP computation at multiple scales or levels, capturing textures at different