Search results

The aerodynamic differences between the head car (HC) and tail car (TC) of a high-speed maglev train are significant, resulting in control difficulties and safety challenges in operation. The arch structure has a significant effect on the improvement of the aerodynamic lift of the HC and TC of the maglev train. Therefore, this study aims to investigate the effect of a streamlined arch structure on the aerodynamic performance of a 600 km/h maglev train.

Three typical streamlined arch structures for maglev trains are selected, i.e. single-arch, double-arch and triple-arch maglev trains. The vortex structure, pressure of train surface, boundary layer, slipstream and aerodynamic forces of the maglev trains with different arch structures are compared by adopting improved delayed detached eddy simulation numerical calculation method. The effects of the arch structures on the aerodynamic performance of the maglev train are analyzed.

The dynamic topological structure of the wake flow shows that a change in arch structure can reduce the vortex size in the wake region; the vortex size with double-arch and triple-arch maglev trains is reduced by 15.9% and 23%, respectively, compared with a single-arch maglev train. The peak slipstream decreases with an increase in arch structures; double-arch and triple-arch maglev trains reduce it by 8.89% and 16.67%, respectively, compared with a single-arch maglev train. The aerodynamic force indicates that arch structures improve the lift imbalance between the HC and TC of a maglev train; double-arch and triple-arch maglev trains improve it by 22.4% and 36.8%, respectively, compared to a single-arch maglev train.

This study compares the effects of a streamlined arch structure on a maglev train and its surrounding flow field. The results of the study provide data support for the design and safe operation of high-speed maglev trains.

With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its training process requires a large amount of data to improve model performance. However, labeled data is expensive and not readily available.

To address the above problem, researchers have integrated semi-supervised and deep learning, using a limited number of labeled data and many unlabeled data to train models. In this paper, Generative Adversarial Networks (GANs) are analyzed as an entry point. Firstly, we discuss the current research on GANs in image super-resolution applications, including supervised, unsupervised, and semi-supervised learning approaches. Secondly, based on semi-supervised learning, different optimization methods are introduced as an example of image classification. Eventually, experimental comparisons and analyses of existing semi-supervised optimization methods based on GANs will be performed.

Following the analysis of the selected studies, we summarize the problems that existed during the research process and propose future research directions.

This paper reviews and analyzes research on generative adversarial networks for image super-resolution and classification from various learning approaches. The comparative analysis of experimental results on current semi-supervised GAN optimizations is performed to provide a reference for further research.

To predict the price of battery-grade lithium carbonate accurately and provide proper guidance to investors, a method called MFTBGAM is proposed in this study. This method integrates textual and numerical information using TCN-BiGRU–Attention.

The Word2Vec model is initially employed to process the gathered textual data concerning battery-grade lithium carbonate. Subsequently, a dual-channel text-numerical extraction model, integrating TCN and BiGRU, is constructed to extract textual and numerical features separately. Following this, the attention mechanism is applied to extract fusion features from the textual and numerical data. Finally, the market price prediction results for battery-grade lithium carbonate are calculated and outputted using the fully connected layer.

Experiments in this study are carried out using datasets consisting of news and investor commentary. The findings reveal that the MFTBGAM model exhibits superior performance compared to alternative models, showing its efficacy in precisely forecasting the future market price of battery-grade lithium carbonate.

The dataset analyzed in this study spans from 2020 to 2023, and thus, the forecast results are specifically relevant to this timeframe. Altering the sample data would necessitate repetition of the experimental process, resulting in different outcomes. Furthermore, recognizing that raw data might include noise and irrelevant information, future endeavors will explore efficient data preprocessing techniques to mitigate such issues, thereby enhancing the model’s predictive capabilities in long-term forecasting tasks.

The price prediction model serves as a valuable tool for investors in the battery-grade lithium carbonate industry, facilitating informed investment decisions. By using the results of price prediction, investors can discern opportune moments for investment. Moreover, this study utilizes two distinct types of text information – news and investor comments – as independent sources of textual data input. This approach provides investors with a more precise and comprehensive understanding of market dynamics.

We propose a novel price prediction method based on TCN-BiGRU Attention for “text-numerical” information fusion. We separately use two types of textual information, news and investor comments, for prediction to enhance the model's effectiveness and generalization ability. Additionally, we utilize news datasets including both titles and content to improve the accuracy of battery-grade lithium carbonate market price predictions.

Information is presented in various modalities such as text and images, and it can quickly and widely spread on social networks and among the general public through key communication nodes involved in public opinion events. Therefore, by tracking and identifying key nodes of public opinion, we can determine the direction of public opinion evolution and timely and effectively control public opinion events or curb the spread of false information.

This paper introduces a novel multimodal semantic enhanced representation based on multianchor mapping semantic community (MAMSC) for identifying key nodes in public opinion. MAMSC consists of four core components: multimodal data feature extraction module, feature vector dimensionality reduction module, semantic enhanced representation module and semantic community (SC) recognition module. On this basis, we combine the method of community discovery in complex networks to analyze the aggregation characteristics of different semantic anchors and construct a three-layer network module for public opinion node recognition in the SC with strong, medium and weak associations.

The experimental results show that compared with its variants and the baseline models, the MAMSC model has better recognition accuracy. This study also provides more systematic, forward-looking and scientific decision-making support for controlling public opinion and curbing the spread of false information.

We creatively combine the construction of variant autoencoder with multianchor mapping to enhance semantic representation and construct a three-layer network module for public opinion node recognition in the SC with strong, medium and weak associations. On this basis, our constructed MAMSC model achieved the best results compared to the baseline models and ablation evaluation models, with a precision of 91.21%.

As intelligent technology advances, practical applications often involve data with multiple labels. Therefore, multi-label feature selection methods have attracted much attention to extract valuable information. However, current methods tend to lack interpretability when evaluating the relationship between different types of variables without considering the potential causal relationship.

To address the above problems, we propose an ensemble causal feature selection method based on mutual information and group fusion strategy (CMIFS) for multi-label data. First, the causal relationship between labels and features is analyzed by local causal structure learning, respectively, to obtain a causal feature set. Second, we eliminate false positive features from the obtained feature set using mutual information to improve the feature subset reliability. Eventually, we employ a group fusion strategy to fuse the obtained feature subsets from multiple data sub-space to enhance the stability of the results.

Experimental comparisons are performed on six datasets to validate that our proposal can enhance the interpretation and robustness of the model compared with other methods in different metrics. Furthermore, the statistical analyses further validate the effectiveness of our approach.

The present study makes a noteworthy contribution to proposing a causal feature selection approach based on mutual information to obtain an approximate optimal feature subset for multi-label data. Additionally, our proposal adopts the group fusion strategy to guarantee the robustness of the obtained feature subset.

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

This study aims to enhance the classification and processing of online appeals by employing a deep-learning-based method. This method is designed to meet the requirements for precise information categorization and decision support across various management departments.

This study leverages the ALBERT–TextCNN algorithm to determine the appropriate department for managing online appeals. ALBERT is selected for its advanced dynamic word representation capabilities, rooted in a multi-layer bidirectional transformer architecture and enriched text vector representation. TextCNN is integrated to facilitate the development of multi-label classification models.

Comparative experiments demonstrate the effectiveness of the proposed approach and its significant superiority over traditional classification methods in terms of accuracy.

The original contribution of this study lies in its utilization of the ALBERT–TextCNN algorithm for the classification of online appeals, resulting in a substantial improvement in accuracy. This research offers valuable insights for management departments, enabling enhanced understanding of public appeals and fostering more scientifically grounded and effective decision-making processes.

An efficient customer behavior prediction model is designed using deep learning techniques. The necessary data used for the implementation are taken from standard datasets and presented to perform subsequent tasks. Here, deep restricted Boltzmann machines (RBM) features are retrieved from the input images. Further, the extracted deep RBM features are presented to the customer behavior prediction phase. Here, the attention-based hybrid deep learning (A-HDL) technique is designed based on the incorporation of a dilated deep temporal convolutional network (dilated-DTCN) and a weighted recurrent neural network (weighted RNN). Moreover, the weights in RNN are tuned using a modernized random parameter-based cheetah optimizer (MRPCO). Further, various experiments were performed on the implemented framework, and it secured an enhanced customer behavior prediction rate than the conventional models.

A novel hybrid deep network-based customer behavior prediction model was developed to predict the behavior of the customer so the companies yield more income by advertising their products based on the predicted results.

When considering the first dataset, the designed customer behavior prediction mechanism produced 94% accuracy, which is higher than the conventional techniques such as long short-term memory (LSTM), DTCN, RNN and A-HDL with 88%, 87%, 89% and 93%.

The precision and the accuracy of the developed MRPCO-A-HDL-based customer behavior prediction model progressed than the conventional techniques and algorithms.

Three-way decision (3WD) and probabilistic rough sets (PRSs) are theoretical tools capable of simulating humans' multi-level and multi-perspective thinking modes in the field of decision-making. They are proposed to assist decision-makers in better managing incomplete or imprecise information under conditions of uncertainty or fuzziness. However, it is easy to cause decision losses and the personal thresholds of decision-makers cannot be taken into account. To solve this problem, this paper combines picture fuzzy (PF) multi-granularity (MG) with 3WD and establishes the notion of PF MG 3WD.

An effective incomplete model based on PF MG 3WD is designed in this paper. First, the form of PF MG incomplete information systems (IISs) is established to reasonably record the uncertain information. On this basis, the PF conditional probability is established by using PF similarity relations, and the concept of adjustable PF MG PRSs is proposed by using the PF conditional probability to fuse data. Then, a comprehensive PF multi-attribute group decision-making (MAGDM) scheme is formed by the adjustable PF MG PRSs and the VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method. Finally, an actual breast cancer data set is used to reveal the validity of the constructed method.

The experimental results confirm the effectiveness of PF MG 3WD in predicting breast cancer. Compared with existing models, PF MG 3WD has better robustness and generalization performance. This is mainly due to the incomplete PF MG 3WD proposed in this paper, which effectively reduces the influence of unreasonable outliers and threshold settings.

The model employs the VIKOR method for optimal granularity selections, which takes into account both group utility maximization and individual regret minimization, while incorporating decision-makers' subjective preferences as well. This ensures that the experiment maintains higher exclusion stability and reliability, enhancing the robustness of the decision results.

This study proposes an integrated Machine Learning and simulated framework for a personalized learning system. This framework aims to improve the integrity of the provided tasks, adapt to each student individually and ultimately enhance students' academic performance.

This methodology comprises two components. (1) A simulation-based system that utilizes reinforcement algorithms to assign additional questions to students who do not reach pass grade thresholds. (2) A Machine Learning system that uses the data from the system to identify the drivers of passing or failing and predict the likelihood of each student passing or failing based on their engagement with the simulated system.

The results of this study offer preliminary evidence of the effectiveness of the proposed simulation system and indicate that such a system has the potential to foster improvements in learning outcomes.

As with all empirical studies, this research has limitations. A simulation study is an abstraction of reality and may not be completely accurate. Student performance in real-world environments may be higher than estimated in this simulation, reducing the required teacher support.

The developed personalized learning (PL) system demonstrates a strong foundation for improving students' performance, particularly within a blended learning context. The findings indicate that simulated performance using the system exhibited improvement when individual students experienced higher learning benefits tailored to their needs.

The research offers evidence of the effectiveness of personalized learning systems and highlights their capacity to drive improvements in education. The proposed system holds the potential to enhance learning outcomes by tailoring tasks to meet the unique needs of each student.

This study contributes to the growing literature on personalized learning, emphasizing the importance of leveraging machine learning in educational technologies to enable precise predictions of student performance.