In recent years, the utilization of deep models has significantly enhanced the performance of neural machine translation (NMT). Nevertheless, the uneven distribution of data leads to critical challenges. Specifically, low-frequency words severely …

Multi-objective optimization problems characterized by a substantial number of decision variables, which are also called large-scale multi-objective optimization problems (LSMOPs), are becoming increasingly prevalent. Traditional evolutionary …

The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting “lossless” to “loss” and “less”). This will bring inconvenience in following situations: (1) what is the best way to obtain …

The rapid rise in volume and feature dimensions is negatively impacting machine learning and many other areas, leading to worse classification accuracy and higher computational costs. Feature Selection (FS) methods are crucial to lessen feature …

This paper proposes an advanced self-evolving regressive neural (ASE-GRNN) algorithm developed to control of the highly nonlinear uncertain plants regarding to unknown dynamics and undetermined perturbations. The suggested ASE-GRNN architecture is …

Fraudsters engage in diverse patterns and deceptive interactions, allowing them to move effortlessly within online networks. However, current fraud detection methods heavily rely on correlated experiences and often face challenges in adapting to …

In order to solve the problems of low prediction accuracy and inability to achieve long-term prediction in traditional coal mine gas concentration prediction, this paper proposes a new gas concentration prediction framework based on the problem of …

In recent years, semi-supervised learning (SSL) methods based on pseudo-labeling algorithms have been widely applied and achieved significant success. However, most existing deep semi-supervised learning methods suffer from the problem of …

In the field of attribute network anomaly detection, current research methodologies, such as reconstruction and contrastive learning, frequently face challenges including the minimal differentiation in embedding representations of normal and …

This paper studies the design of non-fragile dissipative filters for discrete-time interval type-2 fuzzy Markov jump systems (IT-2FMJSs). The novel mode-dependent dynamic event-triggered strategy (DETS) is used to lower the frequency of filter …

In the Internet of Things (IoT) system, sensors generate a vast amount of multivariate time series data and transmit it to the data center for aggregation and analysis. However, due to equipment failure or attacks, the collected data may contain …

ABSA aims to extract aspect terms and corresponding sentiment from unstructured texts. Supervised approaches are widely used in existing ABSA models because of their model maturity, and most of them usually need large-scale training data to deal …

Metaheuristic algorithms offer numerous advantages, such as their ability to address a wide range of problems without the need for specific problem formulations or gradient information. They have demonstrated effectiveness in solving complex …

In order to better handle the dynamic task allocation of UAV swarms, this paper first models the task allocation problem of UAV swarms. Then, improvements were made to the previous auction-based methods in terms of two aspects—the auction function …

In recent years, graph neural network (GNN) has become the main stream for most of recent researches due to its powers in dealing with complex graph data learning problems. However, as most of the recent GNN-based architectures have been mainly …

This study introduced a multi-criteria decision-making methodology leveraging text mining and analytic hierarchy process (AHP) for online course quality evaluation based on students’ feedback texts. First, a hierarchical structure of online course …

Formal concept analysis (FCA) is an important analytical tool for cognitive science. The generalized one-sided concept lattice extends the classical concept lattice, which considers the order between the attributes values. The structure of …

Data Augmentation is an essential technology for improving the performance of deep learning models. However, the semantic information change in current data augmentation methods may impair the model performance, especially in randomly …

Due to its ability to effectively address the cold start and sparsity problems in collaborative filtering, knowledge graph is commonly used as auxiliary information in recommendation systems. However, the existing recommendation algorithms based …

Precise and reliable traffic predictions play a vital role in contemporary traffic management, particularly within complex traffic networks. Currently, the approach which utilizes static graph convolution with recurrent neural networks for traffic …