Representation Ability Research Articles

Bibliometric Analysis on the Research of Geoscience Knowledge Graph (GeoKG) from 2012 to 2023

The geoscience knowledge graph (GeoKG) has gained worldwide attention due to its ability in the formal representation of spatiotemporal features and relationships of geoscience knowledge. Currently, a quantitative review of the state and trends in GeoKG is still scarce. Thus, a bibliometric analysis was performed in this study to fill the gap. Specifically, based on 294 research articles published from 2012 to 2023, we conducted analyses in terms of the (1) trends in publications and citations; (2) identification of the major papers, sources, researchers, institutions, and countries; (3) scientific collaboration analysis; and (4) detection of major research topics and tendencies. The results revealed that the interest in GeoKG research has rapidly increased after 2019 and is continually expanding. China is the most productive country in this field. Co-authorship analysis shows that inter-national and inter-institutional collaboration should be reinforced. Keyword analysis indicated that geoscience knowledge representation, information extraction, GeoKG construction, and GeoKG-based multi-source data integration were current hotspots. In addition, several important but currently neglected issues, such as the integration of Large Language Models, are highlighted. The findings of this review provide a systematic overview of the development of GeoKG and provide a valuable reference for future research.

TCKGCN: Graph convolutional network for aspect-based sentiment analysis with three-channel knowledge fusion

At present, most aspect-based sentiment analysis studies addresses the syntactic dependency problem of review statements by building syntactic dependency graphs. However, this approach is insensitive to syntactic structural information and susceptible to noise interference. Existing fusion methods are unable to effectively capture the complementary relationships between information, leading to large and less efficient model structures. To tackle these issues, we introduce a unique and original scheme that fuses semantic information, ConceptNet conceptual knowledge, and SenticNet affective knowledge, intending to improve the capability of the model to capture sentence features. Specifically, the process involves four steps: first, a semantic attention mechanism is constructed as the first channel to parse the semantic relationship within the context; second, the expressive meaning of the aspects is enhanced with concept mapping as the second channel, with concepts injected into aspectual words; third, the representation ability of sentence dependency graphs is strengthened through adding the affective knowledge of SenticNet as a third channel. Subsequently, the sensitivity of the model to affective information is increased, and finally, the optimization of aspect and context coordination is strengthened by integrating an interactive attention mechanism. The overall findings underscore the efficacy of the model, showing accuracy improvements of 1.05 % and 2.80 % on the Twitter and Lap14 datasets, respectively, compared to state-of-the-art models. Moreover the macro-F1 scores showed significant improvements of 1.99 % and 1.61 %, respectively, enabling more effective capturing of aspect-specific sentiment expressions.

A2GCN: Graph Convolutional Networks with Adaptive Frequency and Arbitrary Order

Graph Neural Networks (GNNs) gain remarkable success in various graph learning tasks under homophily graph assumption. This assumption is extremely fragile since real-world graphs with heterophily are ubiquitous. Under this circumstance, existing GNNs attempt to design or learn graph spectral filters for observed graphs. The representation ability of them, however, is limited due to: (1) Constant frequency response is incapable of simulating complicated filters that real-world applications require. (2) Fixed polynomial order fails to effectively uncover the node label patterns concealing different order neighborhoods. To this end, we propose a novel Graph Convolutional Networks with Adaptive Frequency and Arbitrary Order (A2GCN) to learn various graph spectral filters suitable for distinct networks. Specifically, a simple but elegant filter with adaptive frequency response is designed to span across multiple layers for capturing different frequency components hiding in varying orders, producing A2GCN filter bases. Afterward, the coefficients of the A2GCN basis for each node are learned to achieve A2GCN filters with arbitrary polynomial order. The resulting A2GCN filters possess flexible frequency response that can automatically adapt to the node label pattern, as such, it empowers A2GCN with stronger expressiveness and naturally alleviates the over-smoothing problem. Theoretical analysis is provided to show the superiority of the proposed A2GCN. Additionally, extensive experiments on both node-level and graph-level tasks validate that the proposed A2GCN accomplishes highly competitive performance and improves classification accuracy. Codes are available at https://github.com/AIG22/A2GCN.

Difficult Airway Assessment Based on Multi-View Metric Learning.

The preoperative assessment of difficult airways is of great significance in the practice of anesthesia intubation. In recent years, although a large number of difficult airway recognition algorithms have been investigated, defects such as low recognition accuracy and poor recognition reliability still exist. In this paper, we propose a Dual-Path Multi-View Fusion Network (DMF-Net) based on multi-view metric learning, which aims to predict difficult airways through multi-view facial images of patients. DMF-Net adopts a dual-path structure to extract features by grouping the frontal and lateral images of the patients. Meanwhile, a Multi-Scale Feature Fusion Module and a Hybrid Co-Attention Module are designed to improve the feature representation ability of the model. Consistency loss and complementarity loss are utilized fully for the complementarity and consistency of information between multi-view data. Combined with Focal Loss, information bias is effectively avoided. Experimental validation illustrates the effectiveness of the proposed method, with the accuracy, specificity, sensitivity, and F1 score reaching 77.92%, 75.62%, 82.50%, and 71.35%, respectively. Compared with methods such as clinical bedside screening tests and existing artificial intelligence-based methods, our method is more accurate and reliable and can provide a reliable auxiliary tool for clinical healthcare personnel to effectively improve the accuracy and reliability of preoperative difficult airway assessments. The proposed network can help to identify and assess the risk of difficult airways in patients before surgery and reduce the incidence of postoperative complications.

Optimized dispersion Higuchi fractal dimension and its refined composite multi-scale version for signal analysis

Higuchi fractal dimension (HFD), as a classic nonlinear dynamic metric, which is commonly used to detect signal dynamic changes. However, it is difficult for HFD to process signal outliers. To address this issue, dispersion HFD (DHFD) is proposed, which improves the signal complexity representation ability of HFD by introducing the normal cumulative distribution function and round function in dispersion entropy. Nevertheless, the parameter selection of DHFD can affect the complexity value. Therefore, an optimized dispersion HFD (ODHFD) is proposed, which solves the threshold selection problem of DHFD and can more effectively reflect the complexity of the signal. In addition, an optimized refined composite DHFD (ORCMDHFD) has been proposed, which can more comprehensively reflect the complexity information for the signal at multiple scales. The simulation experiment results show that DHFD has a smaller standard deviation than HFD when calculating white noise signal complexity, and DHFD have the least dependence on signal length compared to other metrics, as well as RCMDHFD has the best separability for simulated noise signals. Actual experiments have shown that ODHFD and ORCMDHFD is superior to other entropy and fractal dimension metrics in distinguishing ship radiated noise and mechanical fault signals, and has broad application prospects in the field of signal analysis.

Multiple Contrastive Experts for long-tailed image classification

Real-world image classification data usually exhibits a challenging long-tailed distribution, attributed to the inherent difficulty in data collection. Existing ensemble approaches predominantly prioritize the empirical diversification of the ensemble model, sidelining its critical aspects of representation ability. A noticeable gap also exists in theoretical analysis elucidating the intricate relationship between ensemble model diversity and its generalization efficacy. This paper introduces a loosely coupled ensemble framework, Multiple Contrastive Experts (MCE) tailored for long-tailed image classification, aiming to bolster image representation while ensuring diversity within the proposed MCE. Leveraging skill-diverse classification losses, the experts in the ensemble model are able to specialize in different kinds of classes in the long-tailed distribution. An adapted supervised contrastive learning (SCL) loss is introduced to guide training for each feature learning branch to enhance the representation ability of MCE. Through the effective integration of the different losses from all experts, each expert model can be optimized coordinately. Moreover, the relationship between the generalization ability of MCE and its diversity is theoretically revealed against a single classification model. At last, extensive experiments were made over five widely used long-tailed image classification datasets. The results show that our proposed MCE is very competitive against the state-of-the-art methods, while maintaining a relatively lower computational cost. Besides, MCE has also exhibited superior performance with an increasing number of experts.

A New Ecological Contract

A New Ecological Contract is a pedagogical framework for design studios that focus on sites of socioenvironmental conflict. Through ecocritical video game design, students engage with situated impacts of large-scale climate issues by working through images of environmental impact assessment reports and baseline studies as archives of landscape transformation. This framework pursued two objectives: first, to awaken a critical and spatial political imagination in the context of a four-year constitutional referendum process that challenged the basis of the Chilean economy and its relationship to the environment from which it derives its riches, and second, to present students with a case for using their representational abilities to engage with situated impacts of large scale climate issues by going through environmental impact assessment reports’ images and baselines studies approaching a design brief otherwise.

Robust and Effective: A Deep Matrix Factorization Framework for Classification.

For complex data, high dimension and high noise are challenging problems, and deep matrix factorization shows great potential in data dimensionality reduction. In this article, a novel robust and effective deep matrix factorization framework is proposed. This method constructs a dual-angle feature for single-modal gene data to improve the effectiveness and robustness, which can solve the problem of high-dimensional tumor classification. The proposed framework consists of three parts, deep matrix factorization, double-angle decomposition, and feature purification. First, a robust deep matrix factorization (RDMF) model is proposed in the feature learning, to enhance the classification stability and obtain better feature when faced with noisy data. Second, a double-angle feature (RDMF-DA) is designed by cascading the RDMF features with sparse features, which contains the more comprehensive information in gene data. Third, to avoid the influence of redundant genes on the representation ability, a gene selection method is proposed to purify the features by RDMF-DA, based on the principle of sparse representation (SR) and gene coexpression. Finally, the proposed algorithm is applied to the gene expression profiling datasets, and the performance of the algorithm is fully verified.

Multi-Modal Modality-Masked Diffusion Network for Brain MRI Synthesis With Random Modality Missing.

Synthesis of unavailable imaging modalities from available ones can generate modality-specific complementary information and enable multi-modality based medical images diagnosis or treatment. Existing generative methods for medical image synthesis are usually based on cross-modal translation between acquired and missing modalities. These methods are usually dedicated to specific missing modality and perform synthesis in one shot, which cannot deal with varying number of missing modalities flexibly and construct the mapping across modalities effectively. To address the above issues, in this paper, we propose a unified Multi-modal Modality-masked Diffusion Network (M2DN), tackling multi-modal synthesis from the perspective of "progressive whole-modality inpainting", instead of "cross-modal translation". Specifically, our M2DN considers the missing modalities as random noise and takes all the modalities as a unity in each reverse diffusion step. The proposed joint synthesis scheme performs synthesis for the missing modalities and self-reconstruction for the available ones, which not only enables synthesis for arbitrary missing scenarios, but also facilitates the construction of common latent space and enhances the model representation ability. Besides, we introduce a modality-mask scheme to encode availability status of each incoming modality explicitly in a binary mask, which is adopted as condition for the diffusion model to further enhance the synthesis performance of our M2DN for arbitrary missing scenarios. We carry out experiments on two public brain MRI datasets for synthesis and downstream segmentation tasks. Experimental results demonstrate that our M2DN outperforms the state-of-the-art models significantly and shows great generalizability for arbitrary missing modalities.

Learning Lightweight Dynamic Kernels With Attention Inside via Local-Global Context Fusion.

Traditional convolutional neural networks (CNNs) share their kernels among all positions of the input, which may constrain the representation ability in feature extraction. Dynamic convolution proposes to generate different kernels for different inputs to improve the model capacity. However, the total parameters of the dynamic network can be significantly huge. In this article, we propose a lightweight dynamic convolution method to strengthen traditional CNNs with an affordable increase of total parameters and multiply-adds. Instead of generating the whole kernels directly or combining several static kernels, we choose to "look inside," learning the attention within convolutional kernels. An extra network is used to adjust the weights of kernels for every feature aggregation operation. By combining local and global contexts, the proposed approach can capture the variance among different samples, the variance in different positions of the feature maps, and the variance in different positions inside sliding windows. With a minor increase in the number of model parameters, remarkable improvements in image classification on CIFAR and ImageNet with multiple backbones have been obtained. Experiments on object detection also verify the effectiveness of the proposed method.

Measuring student mathematical representation abilities in physics on heat and temperature topic: Learning mode and gender

This research examined an in-depth analysis of students' MRAP: (1) the students’ MRAP score in each sub-topic (temperature, expansion, heat, heat transfer); (2) the students’ MRAP score in terms of learning mode (online and offline); (3) the students’ MRAP level based on gender. The study used the survey method as a quantitative approach. The study sample consisted of 260 grade 11 students from three public senior high schools in Yogyakarta, Indonesia, with low, medium, and high ability levels. The Mann-Whitney U test was performed to determine if there was a statistically significant difference in the pupils' test results by learning mode and gender. The study’s findings concluded that the students’ scores in each sub-topic of temperature, expansion, heat, and heat transfer are 67.66; 63.67; 56.86; and 60.43; respectively. There are significant differences in students’ mathematical representation abilities in physics between students learning modes (offline and online learning. At the same time there are no significant differences in students’ mathematical representation abilities in physics between males and females.

그림책과 연계한 신체표현활동이 유아발달에 미치는 효과

The purpose of this study was to develop body expression activities in connection with picture books and to examine the effects of these activities on children's motor skills, language skills, and drawing representation skills. For this study, exercise ability, language ability, and drawing representation ability were measured in 48 children aged 5 years old (experimental group: 24 and comparative group: 24) of kindergarten A located in K City. As the measurement tools, the infant exercise ability scale, the syntactic meaning comprehension test tool, and the drawing representation ability scale were used. A total of 12 experimental treatments were performed 3 times a week over 4 weeks. The experimental group conducted picture book-linked physical expression activities, and the comparative group conducted picture book-linked drawing activities. As a result of the study, it was found that picture book-linked physical expression activities effectively cultivate children's motor skills, language skills, and drawing representation skills.

YOLOv8-QR: An improved YOLOv8 model via attention mechanism for object detection of QR code defects

Defect detection in Quick Response (QR) codes has important implications for downstream tasks. However, QR code defects include small objects and complex backgrounds, which makes their recognition effect poor. To address the above problems, we proposed a model based on YOLOv8, called YOLOv8-QR, to detect QR code defects. Specifically, first, the non-local attention (Non-local) module is introduced into the backbone of the YOLOv8 to enhance the interactive ability of the feature. The Non-local captures the correlation information of long-distance dependencies between features by calculating the attention weight between any positions. In addition, the contextual information required for representation learning of different defective objects is different. To extract multi-scale features, a Large Selective Kernel Network (LSKNet) was introduced. LSKNet dynamically adjusts the convolution receptive field of the neck fusion network and effectively uses the receptive field to capture the background information of different objects, thereby improving the representation ability of the model. To improve the defect detection accuracy of small objects in QR codes, the Normalized Gaussian Wasserstein Distance (NGWD) is introduced to replace the Intersection over Union (IoU) optimization function that is sensitive to the position deviation of objects and is not conducive to the regression of multi-scale objects. To verify the effectiveness of the model, the QR dataset was constructed and a series of experiments were conducted based on this dataset. The results show that the mAP50 and mAP50:95 of the YOLOv8-QR reach 95.5% and 65%, which are 3.8% and 2.3% higher than YOLOv8 respectively. The proposed YOLOv8-QR can better adapt to the needs of QR code defect detection in actual industrial environments. Our code is available at https://github.com/Code-of-Liujie/YOLOv8-QR.git.

D-Net: A dual-encoder network for image splicing forgery detection and localization

Many detection methods based on convolutional neural networks (CNNs) have been proposed for image splicing forgery detection. Most of these methods focus on validating local patches or local objects. We regard image splicing forgery detection as a binary classification task that distinguishes tampered and non-tampered regions by forensic fingerprints rather than semantic features. As the network goes deep, its representation ability becomes strong. However, the non-semantic forensic fingerprints can hardly be retained by normal CNNs in deep layers. We proposed a novel dual-encoder network (D-Net) for image splicing forgery detection to resolve these issues, employing an unfixed and a fixed encoder. The unfixed encoder autonomously learns the image fingerprints that differentiate between the tampered and non-tampered regions, whereas the fixed encoder intentionally provides structural information that assists the learning and detection of the forgeries. This dual-encoder is followed by a spatial pyramid global-feature extraction module that expands the global insight of D-Net for classifying the tampered and non-tampered regions more accurately. In an experimental comparison study of D-Net and state-of-the-art methods, D-Net, without pre-training or training on a large number of forgery images, outperformed the other methods in pixel-level forgery detection. Moreover, it is stably robust to different anti-forensic attacks.

A method for disturbance identification in power quality based on cross-attention fusion of temporal and spatial features

The rapid growth of energy storage scale in power systems has posed higher demands on the monitoring and classification of power quality disturbances (PQDs). Therefore, a method based on cross-attention fusion of temporal and spatial features is proposed to improve the accuracy and robustness of fine classification of PQDs in this study.Firstly, utilizing the improved Sample Convolution and Interaction Model (SCINet) with its recursive downsampling-convolution-interaction architecture, and adding convolutional pooling layers to extract the temporal features of PQDs.Then, the improved VGG model is employed to extract the spatial features of PQDs. Finally, by introducing a cross-attention mechanism to capture the correlation and interaction between the temporal and spatial features, the representation ability of the features is enhanced to achieve disturbance recognition. This study is based on IEEE standards and mathematical models, and generates 25 types of PDQ data through Python simulation for training and testing.The proposed method achieves an average classification accuracy of 95.01 % in a high-noise environment of 20 dB, as well as compared with other mainstream deep learning models and verified through ablation study. Furthermore, the classification test of 10 types of PQDs sampled on a hardware platform demonstrates an average accuracy of 99.66 %, further validating the reliability of the proposed method.

The Effect of Using Edugame Wordwall on Students' Mathematical Representation Ability

The difficulty students face in comprehending problems presented through diagrams and mathematical models, coupled with the monotony experienced during mathematics lessons, has resulted in low mathematical representation skills among students. While studies indicate that Wordwall can enhance student engagement, the specific factors influencing this engagement when utilizing Wordwall remain under-explored. This study aims to assess the impact of Wordwall media on students' mathematical representation abilities and determine the extent of this influence. Adopting a quantitative research approach with experimental methods, the researchers employed a post-test-only design using cluster random sampling. Class VII-A was designated as the experimental group, while Class VII-B was the control group. Data were gathered through a post-test essay examination. Analytical techniques involved prerequisite tests (normality and homogeneity) and hypothesis testing (t-test and effect size). Results indicated a significance level of 0.008 in the t-test and an effect size of 0.685, suggesting that using Wordwall media has a moderate yet significant positive effect on students' mathematical concept representation skills. The findings reveal that incorporating Wordwall edugames in classroom instruction can enhance students' mathematical representation capabilities, foster an interactive learning environment, and improve students' self-expression. Consequently, Wordwall has been proven to elevate student engagement in learning and can effectively supplement traditional classroom instruction.

A Novel Dual-Component Radar-Signal Modulation Recognition Method Based on CNN-ST

Dual-component radar-signal modulation recognition is a challenging yet significant technique for electronic reconnaissance systems. To improve the lower recognition performance and the higher computational costs of the conventional methods, this paper presents a randomly overlapping dual-component radar-signal modulation recognition method based on a convolutional neural network–swin transformer (CNN-ST) under different signal-to-noise ratios (SNRs). To enhance the feature representation ability and decrease the loss of the detailed features of dual-component radar signals under different SNRs, the swin transformer is adopted and integrated into the designed CNN model. An inverted residual structure and lightweight depthwise convolutions are used to maintain the powerful representational ability. The results show that the dual-component radar-signal recognition accuracy of the proposed CNN-ST is up to 82.58% at −8 dB, which shows the better recognition performance of the CNN-ST over others. The dual-component radar-signal recognition accuracies under different SNRs are all more than 88%, which verified the fact that the CNN-ST achieves better recognition accuracy under different SNRs. This work offers essential guidance in enhancing dual-component radar signal recognition under different SNRs and in promoting actual applications.

Two-stage zero-shot sparse hashing with missing labels for cross-modal retrieval

Recently, zero-shot cross-modal hashing has gained significant popularity due to its ability to effectively realize the retrieval of emerging concepts within multimedia data. Although the existing approaches have shown impressive results, the following limitations still need to be solved: (1) Labels in large-scale multimodal datasets in real scenes are usually incomplete or partially missing. (2) The existing methods ignore the influence of features-wise low-level similarity and label distribution on retrieval performance. (3) The representation ability of dense hash codes limits its discriminative potential. To solve these issues, we introduce an effective cross-modal retrieval framework called two-stage zero-shot sparse hashing with missing labels (TZSHML). Specifically, we learn a classifier through the partially known labeled samples to predict the labels of unlabeled data. Then, we use the reliable information in the correctly marked labels to recover the missing labels. The predicted and recovered labels are combined to obtain more accurate labels for the samples with missing labels. In addition, we employ sample-wise fine-grained similarity and cluster-wise similarity to learn hash codes. Therefore, TZSHML ensures that more samples with similar semantics are clustered together. Besides, we apply high-dimensional sparse hash codes to explore richer semantic information. Finally, the drift and interaction terms are introduced into the learning of the hash function to further narrow the gap between different modalities. Extensive experimental results demonstrate the competitiveness of our approach over other state-of-the-art methods in zero-shot retrieval scenarios with missing labels. The source code of this paper can be obtained from https://github.com/szq0816/TZSHML.

Analisis Kemampuan Representasi Matematis Ditinjau dari Gaya Kognitif Field Dependent dan Field Independent

This study focuses on using different cognitive styles to solve mathematical issues. Their cognitive styles can be observed when students work on mathematical problems involving mathematical representation skills. Furthermore, the analyst should assess the mathematical representation abilities of pupils at MTsN 1 Banda Aceh using the field-dependent (FD) and Field Independent (FI) cognitive styles. A descriptive, qualitative technique is used. This study employs purposive sampling procedures and focuses on two pupils from class VIII-2, one identified as FD and the other as FI. Instruments utilized include representation skill tests, interview guidelines, and GEFT questions. Analyzing the research data involves data reduction, presentation, triangulation, and conclusion formulation. The research findings point to many conclusions: (1) FI students find it easier to understand issues, can provide better conceptual explanations, solve problems faster, and explain their solutions accurately. (2) FD students have more difficulty solving issues because they rely on teacher directions. Additional concerns include their failure to analyze and comprehend information and retain concepts from challenges effectively. It is envisaged that students will understand their cognitive types to improve their mathematical representation skills in math and other courses.

Development of Predict Observe Explain Based Flat Side Building Worksheets to Improve Students' Mathematical Representation Skills

Purpose of the study: This research aims to knowing student and teacher responses to Predict Observe Explain based worksheets to develop students' mathematical representation abilities. Methodology: The type of research that will be used is research and development (R&D). In this research, the 4D device development research method (Four D Model) was used as a research and development procedure. The data collection technique in research on developing student work sheets uses a questionnaire. The data collection instrument used in this research is the product trial instrument. Data obtained through trial instruments were analyzed using qualitative descriptive statistics. Main Findings: Based on the results of questionnaire data on student responses in the small-scale and large-scale field trials, the mathematical media developed in the criteria for interpreting attractiveness, it is very interesting as a source of learning material and is suitable for use. Novelty/Originality of this study: This study found that the Predict Observe Explain -based flat-sided geometric worksheet is suitable for use in improving students' mathematical representation skills and getting a positive response from students and teachers. This research contributes to the development of innovative and effective learning tools in the context of mathematics learning.