Representation Ability Research Articles

The recognition and analysis of fake images based on deep neural network

The generation of fake images and the process of technology is developing quickly, which has generated great concern about its impact on society. To effectively identify the fake image, this article introduces a deep learning-based identification method. This article uses a convolutional neural network (CNN) neural network to construct a model for machine learning image recognition and lets it learn a dataset of hundreds of real and fake pictures to let it complete tasks that are difficult for humans to complete. the use of deep learning to solve this problem has the following advantages: the results can be observed after data input, which is conservative and fast, and there is no need to manually design rules as Deep learning methods can optimise the loss function to learn the rules, mining potential features of data, with strong representation ability. Using this method, the accuracy result is over 60%. This paper proves a machine can learn and recognise real and fake pictures, which is specifically inspiring that learning-based methods can also solve the challenging problem of images.

Improving paragraph segmentation using BERT with additional information from probability density function modeling of segmentation distances

Paragraphs play a key role in writing and reading texts. Therefore, studies about dividing texts into appropriate paragraphs, or paragraph segmentation have gathered academic attention for a long time. Recent advancements in pre-trained language models have achieved state-of-the-art performances in various natural language processing fields, including paragraph segmentation. However, pre-trained language model based paragraph segmentation methods had a problem in that they could not consider statistical metadata such as how far each paragraph segmentation point should be apart from each other. Therefore we focused on combining paragraph segmentation distance and pre-trained language models so that both statistical metadata and state-of-the-art representation ability could be considered at the same time. We propose a novel model by modifying BERT, a state-of-the-art pre-trained language model, by adding segmentation distance information via probability density function modeling. Our model was trained and tested on the domain of the novel, and showed improved performance compared to baseline BERT and previous study, acquiring a mean of 0.8877 F1-score and 0.8708 MCC. Furthermore, our model showed robust performance regardless of the authors of the novels.

Low-Dose CT Image Super-resolution Network with Noise Inhibition Based on Feedback Feature Distillation Mechanism.

Low-dose computed tomography (LDCT) has been widely used in medical diagnosis. In practice, doctors often zoom in on LDCT slices for clearer lesions and issues, while, a simple zooming operation fails to suppress low-dose artifacts, leading to distorted details. Therefore, numerous LDCT super-resolution (SR) methods have been proposed to promote the quality of zooming without the increase of the dose in CT scanning. However, there are still some drawbacks that need to be addressed in existing methods. First, the region of interest (ROI) is not emphasized due to the lack of guidance in the reconstruction process. Second, the convolutional blocks extracting fix-resolution features fail to concentrate on the essential multi-scale features. Third, a single SR head cannot suppress the residual artifacts. To address these issues, we propose an LDCT CT joint SR and denoising reconstruction network. Our proposed network consists of global dual-guidance attention fusion modules (GDAFMs) and multi-scale anastomosis blocks (MABs). The GDAFM directs the network to focus on ROI by fusing the extra mask guidance and average CT image guidance, while the MAB introduces hierarchical features through anastomosis connections to leverage multi-scale features and promote the feature representation ability. To suppress radial residual artifacts, we optimize our network using the feedback feature distillation mechanism (FFDM) which shares the backbone to learn features corresponding to the denoising task. We apply the proposed method to the 3D-IRCADB and PANCREAS datasets to evaluate its ability on LDCT image SR reconstruction. The experimental results compared with state-of-the-art methods illustrate the superiority of our approach with respect to peak signal-to-noise (PSNR), structural similarity (SSIM), and qualitative observations. Our proposed LDCT joint SR and denoising reconstruction network has been extensively evaluated through ablation, quantitative, and qualitative experiments. The results demonstrate that our method can recover noise-free and detail-sharp images, resulting in better reconstruction results. Code is available at https://github.com/neu-szy/ldct_sr_dn_w_ffdm .

LM-DeeplabV3+: A Lightweight Image Segmentation Algorithm Based on Multi-Scale Feature Interaction

Street-view images can help us to better understand the city environment and its potential characteristics. With the development of computer vision and deep learning, the technology of semantic segmentation algorithms has become more mature. However, DeeplabV3+, which is commonly used in semantic segmentation, has shortcomings such as a large number of parameters, high requirements for computing resources, and easy loss of detailed information. Therefore, this paper proposes LM-DeeplabV3+, which aims to greatly reduce the parameters and computations of the model while ensuring segmentation accuracy. Firstly, the lightweight network MobileNetV2 is selected as the backbone network, and the ECA attention mechanism is introduced after MobileNetV2 extracts shallow features to improve the ability of feature representation; secondly, the ASPP module is improved, and on this basis, the EPSA attention mechanism is introduced to achieve cross-dimensional channel attention and important feature interaction; thirdly, a loss function named CL loss is designed to balance the training offset of multiple categories and better indicate the segmentation quality. This paper conducted experimental verification on the Cityspaces dataset, and the results showed that the mIoU reached 74.9%, which was an improvement of 3.56% compared to DeeplabV3+; and the mPA reached 83.01%, which was an improvement of 2.53% compared to DeeplabV3+.

Principal space approximation ensemble discriminative marginalized least-squares regression for hyperspectral image classification

Discriminative marginalized least-squares regression (DMLSR) is unable to extract the spectral-spatial joint features, the proportion of learned interfering pixels is high. To solve this problem, a novel principal space approximation ensemble discriminant edge least-squares regression, namely PSAE-DMLSR is proposed for hyperspectral image classification. In the PSAE-DMLSR, a marginal principal component method (MP) is employed to search the optimal spectral subspace, and a principal space local marginal principal component (PSLMP) method is proposed to search the optimal representation space (ORS). In the PSLMP, a principal space representation (PSR) is designed to integrate the global spectral-spatial joint features information of the ORS, and the PSR is used to impose approximate averaging constraints and stochastic cascade fusion on the ORS, which can further improve the representation ability of the ORS. The ORS can effectively reduce the proportion of interfering pixels in DMLSR learning. It conducted comparative experiments with some more advanced classification methods on the three commonly used hyperspectral datasets. The experiment results show that the PSAE-DMLSR classification model can still obtain high classification accuracy under low hardware conditions, and the execution efficiency also has advantages.

A novel hierarchical feature selection with local shuffling and models reweighting for stock price forecasting

Stock price forecasting is a challenging task due to the complexity of financial markets and the high volatility of stocks. Because of the strong nonlinear representation ability of neural network models, such as long-short memory network (LSTM) and deep learning, they are used extensively in recent years for stock price forecasting. However, due to the volatility of financial data, neural network models often suffer from overfitting or instability problems. In addition, quantitative trading with feature mining tools can generate a growing number of features for financial data. Therefore, selecting effective features for financial data is an urgent problem. To address these problems, we propose a novel hierarchical feature selection with local shuffling (HFSLS) and models reweighting (MR) based on LSTM, named HFSLSMR-LSTM, for stock price forecasting. Specifically, for each layer, local shuffling perturbs each feature to re-predict, and its predicted value is compared with the true value to calculate the feature importance, and the important features are selected and returned to the next layer. Besides, a proximity reweighting scheme is presented to adjust the weight for each layer model that learns from hierarchical features. The HFSLSMR-LSTM model is still effective for financial data with multiple features and frequent fluctuations. Experimental results on stock index dataset and Dow Jones Industrial Average dataset demonstrate that the HFSLSMR-LSTM outperforms Informer, DoubleEnsemble, LSTM, GRU, BI-GRU and BI-LSTM on the metrics MSE, RMSE, MAE, MAPE and R2.

A Deep Learning Method for Building Extraction from Remote Sensing Images by Fuzing Local and Global Features

As important disaster-bearing bodies, buildings are the focus of attention in seismic disaster risk assessment and emergency rescue. It is of great practical significance to extract buildings quickly and accurately with complex textures and variable scales and shapes from high-resolution remote sensing images. We proposed an improved TransUnet model based on multiscale grouped convolution and attention named MATUnet to retain more local detail features and enhance the representation ability of global features, while reducing the network parameters. We designed the multiscale grouped convolutional feature extraction module with attention (GAM) to enhance the representation of detailed features. The convolutional positional encoding module (PEG) was added to redetermine the number of transformer, it solved the problem of local feature information loss and the difficulty of convergence of the network. The channel attention module (CAM) of the decoder enhanced the salient information of the features and solved the problem of information redundancy after feature fusion. We experimented through MATUnet on the WHU building dataset and Massachusetts dataset. MATUnet achieved the best IOU results of 92.14% and 83.22%, respectively, and achieved better than the other generalized and state-of-the-art networks under the same conditions. We also have achieved good segmentation results on the GF2 Xichang building dataset.

A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning

Discovering tactical knowledge aims to extract tactical data derived from battlefield signal data, which is vital in information warfare. The learning and reasoning from battlefield signal information can help commanders make effective decisions. However, traditional methods are limited in capturing sequential and global representation due to their reliance on prior knowledge or feature engineering. The current models based on deep learning focus on extracting implicit behavioral characteristics from combat process data, overlooking the embedded martial knowledge within the recognition of combat intentions. In this work, we fill the above challenge by proposing a dual fusion pipeline introducing graph representation learning into sequence learning to construct tactical behavior sequence graphs expressing implicit martial knowledge, named TBGCN. Specifically, the TBGCN utilizes graph representation learning to represent prior knowledge by building a graph to induce deep learning paradigms, and sequence learning finds the hidden representation from the target’s serialized data. Then, we employ a fusion module to merge two such representations. The significance of integrating graphs with deep learning lies in using the artificial experience of implicit graph structure guiding adaptive learning, which can improve representation ability and model generalization. Extensive experimental results demonstrate that the proposed TBGCN can effectively discover tactical knowledge and significantly outperform the traditional and deep learning methods.

The task of plotting flat cross-sections of polyhedrons as a means of developing divergent and algorithmic thinking and spatial representation ability

The task of plotting flat cross-sections of polyhedrons as a means of developing divergent and algorithmic thinking and spatial representation ability

A hybrid U‐shaped and transformer network for change detection in high‐resolution remote sensing images

AbstractDeep convolutional neural networks based remote sensing change detection has recently shown significant performance improvement. However, small region changes and global‐local features in high‐resolution remote sensing images are not fully explored. This paper introduces a hybrid U‐shaped and transformer network for change detection in high‐resolution remote sensing images. Specifically, a UNet++‐based backbone to facilitate feature learning across different scales. In addition, we introduce a transformer‐based feature fusion module for extracting long‐range dependencies, which can enhance the representation ability of the network. Furthermore, the introduced efficient channel attention mechanism can efficiently calibrate the feature representation and concentrate on more important feature information. Thanks to the above designs, the proposed method enjoys a strong ability to extract local and global features for remote sensing change detection. Extensive experimental results on different remote sensing images show that our method can achieve superior performance in comparison with state‐of‐the‐art change detection methods.

AIE-YOLO: Effective object detection method in extreme driving scenarios via adaptive image enhancement.

The widespread research and implementation of visual object detection technology have significantly transformed the autonomous driving industry. Autonomous driving relies heavily on visual sensors to perceive and analyze the environment. However, under extreme weather conditions, such as heavy rain, fog, or low light, these sensors may encounter disruptions, resulting in decreased image quality and reduced detection accuracy, thereby increasing the risk for autonomous driving. To address these challenges, we propose adaptive image enhancement (AIE)-YOLO, a novel object detection method to enhance road object detection accuracy under extreme weather conditions. To tackle the issue of image quality degradation in extreme weather, we designed an improved adaptive image enhancement module. This module dynamically adjusts the pixel features of road images based on different scene conditions, thereby enhancing object visibility and suppressing irrelevant background interference. Additionally, we introduce a spatial feature extraction module to adaptively enhance the model's spatial modeling capability under complex backgrounds. Furthermore, a channel feature extraction module is designed to adaptively enhance the model's representation and generalization abilities. Due to the difficulty in acquiring real-world data for various extreme weather conditions, we constructed a novel benchmark dataset named extreme weather simulation-rare object dataset. This dataset comprises ten types of simulated extreme weather scenarios and is built upon a publicly available rare object detection dataset. Extensive experiments conducted on the extreme weather simulation-rare object dataset demonstrate that AIE-YOLO outperforms existing state-of-the-art methods, achieving excellent detection performance under extreme weather conditions.

Hybrid attention-based improved temporal convolutional BiGRU approach for short-term load forecasting

Accurate load forecasting can ensure the safe and reliable operation of power systems, reduce generation costs, and improve economic efficiency. To improve the accuracy and performance of short-term load forecasting, this paper proposes a hybrid short-term load forecasting method composed of an improved temporal convolutional network (TCNPlus) with an attention mechanism and a bidirectional gated recurrent unit (BiGRU). Firstly, the collected pre-processed training data is reconstructed using a fixed-length sliding window. Secondly, using the self-attention mechanism (SA) in the improved TCN to further enhance the weight of key features, and introducing residual connections can allow the input to propagate forward faster and improve the representation ability and efficiency of error backpropagation of the network, to eliminate the impact of interference signals. Finally, BiGRU is used to learn the forward and backward dependencies of the load sequence in both directions and predict the true load value. Based on the real load data of a national power grid in South China, through experimental comparison of multiple models, the results show that this model still has higher short-term load forecasting accuracy with fewer input features.

Differences in high school students' mathematical representation ability in homogeneous classes: Which is better?

Mathematical representation is one of the higher-order thinking skills needed by students in analyzing physics cases as a form of proving the truth of understanding. Referring to the inconsistencies in the results of research on mathematical representation involving gender and the phenomenon of the high ability of female students in heterogeneous classes, it is suspected that there is a relationship between class type and mathematical representation. This study aims to analyze the increase in students' mathematical representation abilities in terms of gender differences in homogeneous classes. The research subjects consisted of class X high school students in Bantul, Indonesia, consisting of 26 boys and 27 girls. The research instrument was 5 physics questions that referred to indicators of mathematical representation. Data analysis to find out how the category of mathematical representation increases using the N-Gain index. The results of this study were (1) the improvement in the ability of the male students' mathematical representation in the medium category was superior to that of the female students, (2) the improvement in the ability to make mathematical expressions and use visual representations was better for the male students, and (3) the ability of the female students in terms of making image representations better than male students. This research implies that further research is needed to be related to the causes of students' misinterpretation in dealing with physics test.

APPLICATION OF THE CREATIVE PROBLEM-SOLVING LEARNING MODEL TOWARDS STUDENTS' MATHEMATICS REPRESENTATION ABILITY

This research aims to find out what the learning process is like using the Problem based learning model. Hypothesis testing using the t test shows that there is a significant difference, namely significant (2-tailed) 0.004 < 0.05 so it can be concluded that H0 is rejected and H1 is accepted. This means that there is an average difference in students' mathematical representation abilities between the experimental class and the control class. Thus, the results of this hypothesis test show that there is an influence of the Creative Problem-Solving learning model on students' mathematical representation abilities

Preserving node similarity adversarial learning graph representation with graph neural network

AbstractIn recent years, graph neural networks (GNNs) have showcased a strong ability to learn graph representations and have been widely used in various practical applications. However, many currently proposed GNN‐based representation learning methods do not retain neighbor‐based node similarity well, and this structural information is crucial in many cases. To address this issue, drawing inspiration from generative adversarial networks (GANs), we propose PNS‐AGNN (i.e., Preserving Node Similarity Adversarial Graph Neural Networks), a novel framework for acquiring graph representations, which can preserve neighbor‐based node similarity of the original graph and efficiently extract the nonlinear structural features of the graph. Specifically, we propose a new positive sample allocation strategy based on a node similarity index, where the generator can generate vector representations that satisfy node similarity through adversarial training. In addition, we also adopt an improved GNN as the discriminator, which utilizes the original graph structure for recursive neighborhood aggregation to maintain the local structure and feature information of nodes, thereby enhancing the graph representation's ability. Finally, we experimentally demonstrate that PNS‐AGNN significantly improves various tasks, including link prediction, node classification, and visualization.

Research on surface defect detection algorithm of pipeline weld based on YOLOv7

Aiming at the problems of low target detection accuracy and high leakage rate of the current traditional weld surface defect detection methods and existing detection models, an improved YOLOv7 pipeline weld surface defect detection model is proposed to improve detection results. In the improved model, a Le-HorBlock module is designed, and it is introduced into the back of fourth CBS module of the backbone network, which preserves the characteristics of high-order information by realizing second-order spatial interaction, thus enhancing the ability of the network to extract features in weld defect images. The coordinate attention (CoordAtt) block is introduced to enhance the representation ability of target features, suppress interference. The CIoU loss function in YOLOv7 network model is replaced by the SIoU, so as to optimize the loss function, reduce the freedom of the loss function, and accelerate convergence. And a new large-scale pipeline weld surface defect dataset containing 2000 images of pipeline welds with weld defects is used in the proposed model. In the experimental comparison, the improved YOLOv7 network model has greatly improved the missed detection rate compared with the original network. The experimental results show that the improved YOLOv7 network model mAP@80.5 can reach 78.6%, which is 15.9% higher than the original model, and the detection effect is better than the original network and other classical target detection networks.

Dual-Branch Cross-Attention Network for Micro-Expression Recognition with Transformer Variants

A micro-expression (ME), as a spontaneous facial expression, usually occurs instantaneously and is difficult to disguise after an emotion-evoking event. Numerous convolutional neural network (CNN)-based models have been widely explored to recognize MEs for their strong local feature representation ability on images. However, the main drawback of the current methods is their inability to fully extracting holistic contextual information from ME images. To achieve efficient ME learning representation from diverse perspectives, this paper uses Transformer variants as the main backbone and the dual-branch architecture as the main framework to extract meaningful multi-modal contextual features for ME recognition (MER). The first branch leverages an optical flow operator to facilitate the motion information extraction between ME sequences, and the corresponding optical flow maps are fed into the Swin Transformer to acquire motion–spatial representation. The second branch directly sends the apex frame in one ME clip to Mobile ViT (Vision Transformer), which can capture the local–global features of MEs. More importantly, to achieve the optimal feature stream fusion, a CAB (cross attention block) is designed to interact the feature extracted by each branch for adaptive learning fusion. The extensive experimental comparisons on three publicly available ME benchmarks show that the proposed method outperforms the existing MER methods and achieves an accuracy of 81.6% on the combined database.

Analisis Kemampuan Representasi Matematis Siswa dalam Menyelesaikan Masalah Luas Permukaan Bangun Ruang

Mathematical representation ability is one of the five basic abilities which is the goal of mathematics learning. Through mathematical representation, problems that initially appear difficult and complicated can be seen more easily and simply, so that they can be presented simply and can be solved more easily. But in reality, the representation ability of elementary school students is still low. The aim of this research is to describe the mathematical representation abilities of class VI students at SD Negeri Kebonsari Kulon I Probolinggo, in solving surface area problems of geometric shapes. This research is qualitative research with a descriptive approach. The population in this study were all class VI students at SD Negeri Kebonsari Kulon I Probolinggo, totaling 19 students. The data collection method in this research is the test method. Next, the data obtained was analyzed to determine students' representational abilities in solving problems on the surface area of ​​geometric figures. The results of this research show that students' visual and symbolic mathematical representation abilities in solving mathematical problems on the surface area of ​​spatial figures can be categorized as good with a percentage of 78.94% and 89.47%, while their verbal mathematical representation abilities can be categorized as very good with a percentage of 55.26. %.

EFFECT THE PROBLEM-BASED LEARNING MODEL ON ABILITY MULTIPLE REPRESENTATIONS OF XI-GRADE STUDENTS ON ACID-BASED TOPIC

It takes the ability to conceive at three different levels of representation, macroscopic, sub microscopic, and symbolic to comprehend acid-base material. Still, most students are unable to make the connection between the three levels of representation. As a result, instruction that helps students connect various representations in acid-base content is required. The PBL model is one appropriate learning paradigm that can be used. The purpose of this study is to determine whether PBL models and conventional models differ in their capacity to support numerous representations. A quantitative experiment using a quasi-experimental study design is the research methodology employed. A post-test-only control group design is used in this study. The samples of this study were XI MIPA 3 as a control group of 34 students and XI MIPA 4 as an experimental group of 33 students. Simple random sampling was used to get the research samples. A post-test consisting of multiple-choice questions was the instrument utilized. With a reliability score of 0,802 across 20 items, the empirical validation results indicate that all instruments are appropriate for use as research measures. methods for gathering data through tests. Data collection techniques in the form of tests. The data analysis technique in this study is descriptive and inferential statistics with hypothesis testing in the form of the Independent Sample t-Test. With a sig value of 0,000 < 0,05, the results demonstrated that there is a difference in the ability of multiple representations between those taught using the PBL model and those taught using the conventional model.

ANALYSIS OF MULTIPLE REPRESENTATION ABILITIES OF MALE AND FEMALE GRADE STUDENT AT SMAN 1 TANJUNGANOM IN ACID-BASE MATERIAL

The field of chemistry has become one of the abstract sciences, particularly in the context of acid-base materials, thus requiring the integration of multiple representations. Incomplete multiple representation abilities in students can lead to difficulties in understanding acid-base materials. Therefore, this research aims to analyze (1) the level of students' multiple representation abilities in acid-base materials and (2) the differences in the levels of multiple representation abilities between male and female students. The research method used is a comparative ex-post facto approach with a quantitative approach. The research instruments include test questions based on the DAC framework and interview sheets. The results of this research are as follows: (1) the average level of multiple representation abilities is 20%, categorized as very poor. The percentages of multiple representation abilities based on the DAC framework are 29% for definition, 18% for algorithmic, and 20% for conceptual. The highest percentage in the DAC framework indicators is D-R at 32%, the lowest percentage is C-O at 11%. (2) There is a difference in the levels of multiple representation abilities between male and female students, as evidenced by the results of the Mann-Whitney U test, with an Asymp. Sig. (2-tailed) value of 0.000 ≤ 0.05.