Representation Ability Research Articles

Enhancing mathematical representation ability: Innovative DMR learning model with question box media integration

This study aimed to scrutinize the effectiveness of the DMR (Diskursus Multy Reprecentacy) model with Question Box media in bolstering the mathematical representation abilities of eighth-grade students. A quasi-experimental design was employed, engaging 96 students selected via Cluster Random Sampling technique. The effectiveness was evaluated by comparing the DMR model against the conventional expository teaching method using a t-test with a 5% significance level. In this research, data testing uses the SPSS application. Findings revealed that the DMR teaching model assisted by the Question Box media was significantly more effective in enhancing students' mathematical representation skills than the traditional expository model. These findings suggest that the integration of the DMR teaching model with Question Box media could serve as an alternative pedagogical strategy in mathematics education to facilitate a deeper understanding of mathematical concepts among students.

Active and Authentic Learning in Remote Laboratory: Means of Improving Prospective Physics Teachers’ Multiple Representation Ability

Remote laboratories are a new domain that allows students and teachers to conduct experiments in hands-on exploration remotely. We studied how constructing an active and authentic learning in a remote laboratory affects prospective physics teachers' multiple representation ability. The research method used is based on the development procedures of the ADDIE research and development model. We have designed and validated a learning design with a remote laboratory environment with 2 physics experiment apparatuses, active and authentic learning stages, multi-representation ability assessment, and remote laboratory application evaluation tools. This study implemented design-based research with a one-group pre-test and post-test design. The research was conducted on 28 prospective physics teacher students. In terms of effectiveness, this learning design was able to improve significantly [t (28) = 7.480, p.05] in verbal, visual, and mathematics representation ability. Therefore, it can be used by lecturers and those in other science fields to improve the quality of learning and developing prospective physics teachers’ multiple representation Skills.

Multimodal Transformer Model Using Time-Series Data to Classify Winter Road Surface Conditions.

This paper proposes a multimodal Transformer model that uses time-series data to detect and predict winter road surface conditions. For detecting or predicting road surface conditions, the previous approach focuses on the cooperative use of multiple modalities as inputs, e.g., images captured by fixed-point cameras (road surface images) and auxiliary data related to road surface conditions under simple modality integration. Although such an approach achieves performance improvement compared to the method using only images or auxiliary data, there is a demand for further consideration of the way to integrate heterogeneous modalities. The proposed method realizes a more effective modality integration using a cross-attention mechanism and time-series processing. Concretely, when integrating multiple modalities, feature compensation through mutual complementation between modalities is realized through a feature integration technique based on a cross-attention mechanism, and the representational ability of the integrated features is enhanced. In addition, by introducing time-series processing for the input data across several timesteps, it is possible to consider the temporal changes in the road surface conditions. Experiments are conducted for both detection and prediction tasks using data corresponding to the current winter condition and data corresponding to a few hours after the current winter condition, respectively. The experimental results verify the effectiveness of the proposed method for both tasks. In addition to the construction of the classification model for winter road surface conditions, we first attempt to visualize the classification results, especially the prediction results, through the image style transfer model as supplemental extended experiments on image generation at the end of the paper.

Anticipating Trends and Innovations for A Sustainable Automotive Industrial Revolution

Graph classification aims to predict the label associated with a graph and is an important graph analytic task with widespread applications. Recently, graph neural networks (GNNs) have achieved state-of-the-art results on purely supervised graph classification by virtue of the powerful representation ability of neural networks. However, almost all of them ignore the fact that graph classification usually lacks reasonably sufficient labelled data in practical scenarios due to the inherent labelling difficulty caused by the high complexity of graph data. The existing semi-supervised GNNs typically focus on the task of node classification and are incapable of dealing with graph classification. To tackle the challenging but practically useful scenario, we propose a novel and general semi-supervised GNN framework for graph classification, which takes full advantage of a slight amount of labelled graphs and abundant unlabelled graph data. In our framework, we train two GNNs as complementary views for collaboratively learning high-quality classifiers using both labelled and unlabelled graphs. To further exploit the view itself, we constantly select pseudo-labelled graph examples with high confidence from its own view for enlarging the labelled graph dataset and enhancing predictions on graphs. Furthermore, the proposed framework is investigated on two specific implementation regimes with a few labelled graphs and the extremely few labelled graphs, respectively. Extensive experimental results demonstrate the effectiveness of our proposed semi-supervised GNN framework for graph classification on several benchmark datasets

Analisis kemampuan representasi matematis peserta didik sekolah dasar ditinjau dari resiliensi matematis

<p class="Abstract">This research aims to describe the mathematical representation abilities of students with high, medium and low mathematical resilience. This research is a descriptive qualitative research. The data collection techniques used were questionnaires, tests, and interviews. The data analysis technique in this research used the Miles and Huberman model which consists of data reduction, data presentation, and drawing conclusions. The results of the research concluded that: 1) Students with high mathematical resilience fulfill all indicators of mathematical representation ability in both linguistic, visual and symbolic aspects; 2) Students with moderate mathematical representation abilities meet both indicators in visual representation and do not meet indicators in language and symbolic aspects; 3) Students with low mathematical resilience, one of whom does not meet the indicators for language, visual or verbal. One of the students met one indicator, namely the verbal indicator aspect.</p>

Interpretable domain adaptation transformer: a transfer learning method for fault diagnosis of rotating machinery

Domain adaptation-based transfer learning methods have been widely investigated in fault diagnosis of rotating machinery, but their basic convolution or recurrent structure is subject to poor global feature representation ability, which hinders the learning of domain-irrelevant modulation information. In addition, the “black box” nature of deep learning models limits their applications in high risk-sensitive scenarios. In this paper, an interpretable domain adaptation transformer (IDAT) is proposed for the transferable fault diagnosis of rotating machinery. First, a multi-layer domain adaptation transformer framework is proposed, which can capture the global information that is crucial for learning the modulation information of different domains, and meanwhile reduce the feature distribution discrepancy. Second, an ensemble attention weight is applied to enable the transfer learning framework to be interpretable, which is implemented by averaging the integral values of the multi-head attention maps along the key direction. In addition, the raw vibration signals are embedded as the input of the model, which provides an end-to-end fault diagnosis. The proposed IDAT is tested by various cross-condition and cross-machine bearing fault diagnosis tasks, and results confirm the advantages of the method.

HCA-DAN: hierarchical class-aware domain adaptive network for gastric tumor segmentation in 3D CT images

BackgroundAccurate segmentation of gastric tumors from CT scans provides useful image information for guiding the diagnosis and treatment of gastric cancer. However, automated gastric tumor segmentation from 3D CT images faces several challenges. The large variation of anisotropic spatial resolution limits the ability of 3D convolutional neural networks (CNNs) to learn features from different views. The background texture of gastric tumor is complex, and its size, shape and intensity distribution are highly variable, which makes it more difficult for deep learning methods to capture the boundary. In particular, while multi-center datasets increase sample size and representation ability, they suffer from inter-center heterogeneity.MethodsIn this study, we propose a new cross-center 3D tumor segmentation method named Hierarchical Class-Aware Domain Adaptive Network (HCA-DAN), which includes a new 3D neural network that efficiently bridges an Anisotropic neural network and a Transformer (AsTr) for extracting multi-scale context features from the CT images with anisotropic resolution, and a hierarchical class-aware domain alignment (HCADA) module for adaptively aligning multi-scale context features across two domains by integrating a class attention map with class-specific information. We evaluate the proposed method on an in-house CT image dataset collected from four medical centers and validate its segmentation performance in both in-center and cross-center test scenarios.ResultsOur baseline segmentation network (i.e., AsTr) achieves best results compared to other 3D segmentation models, with a mean dice similarity coefficient (DSC) of 59.26%, 55.97%, 48.83% and 67.28% in four in-center test tasks, and with a DSC of 56.42%, 55.94%, 46.54% and 60.62% in four cross-center test tasks. In addition, the proposed cross-center segmentation network (i.e., HCA-DAN) obtains excellent results compared to other unsupervised domain adaptation methods, with a DSC of 58.36%, 56.72%, 49.25%, and 62.20% in four cross-center test tasks.ConclusionsComprehensive experimental results demonstrate that the proposed method outperforms compared methods on this multi-center database and is promising for routine clinical workflows.

Getting it Just Right: Towards Balanced Utility, Privacy, and Equity in Shared Space Sensing

Low-cost sensors have enabled a wide array of data-driven applications and insights. As a result, encountering spaces with pervasive sensing has become all but unavoidable. This creates a fundamental tension: the success of smart environments will become increasingly dependent on equity of access to data-driven insights and consideration of the privacy expectations of sensed individuals. These concerns highlight the need to bring equity to all stakeholders of smart environments, which in turn would preserve public trust in these smart spaces. In this work, we explored several approaches to identity-obscuring visual representations through a progressive series of experiments. We designed and validated a series of visual representations through stakeholder interactions and tested the ability of these visual representations to limit identification via a crowdsourced study. An evaluation across three months of data gathered within our organization also showed that the identity-obscured data could still be leveraged to accurately count group size. Our contributions lay the groundwork for sensing frameworks that bring utility to all stakeholders of shared spaces while being cognizant of their diverse privacy expectations.

Spatiotemporal Inconsistency Learning and Interactive Fusion for Deepfake Video Detection

With the rise of the metaverse, the rapid advancement of Deepfakes technology has become closely intertwined. Within the metaverse, individuals exist in digital form and engage in interactions, transactions, and communications through virtual avatars. However, the development of Deepfakes technology has led to the proliferation of forged information disseminated under the guise of users’ virtual identities, posing significant security risks to the metaverse. Hence, there is an urgent need to research and develop more robust methods for detecting deep forgeries to address these challenges. This paper explores deepfake video detection by leveraging the spatiotemporal inconsistencies generated by deepfake generation techniques, and thereby proposing the interactive spatioTemporal inconsistency learning and interactive fusion (ST-ILIF) detection method, which consists of phase-aware and sequence streams. The spatial inconsistencies exhibited in frames of deepfake videos are primarily attributed to variations in the structural information contained within the phase component of the Fourier domain. To mitigate the issue of overfitting the content information, a phase-aware stream is introduced to learn the spatial inconsistencies from the phase-based reconstructed frames. Additionally, considering that deepfake videos are generated frame-by-frame and lack temporal consistency between frames, a sequence stream is proposed to extract temporal inconsistency features from the spatiotemporal difference information between consecutive frames. Finally, through feature interaction and fusion of the two streams, the representation ability of intermediate and classification features is further enhanced. The proposed method, which was evaluated on four mainstream datasets, outperformed most existing methods, and extensive experimental results demonstrated its effectiveness in identifying deepfake videos. Our source code is available at https://github.com/qff98/Deepfake-Video-Detection

Efektivitas Penerapan Model Pembelajaran Student Facilitator and Explaining terhadap Kemampuan Representasi Matematis Siswa

This research aims to evaluate the impact of using the Student Facilitator and Explaining learning model on students' mathematical representation abilities. This research uses a quantitative approach with a Quasi-Experimental Design research design with a design form, namely a non-equivalent control group design. The sample chosen was 56 students from a population of 111 students at SMA Negeri 11 Bulukumba, using a simple random sampling technique. Data was collected using tests to assess mathematical representation abilities, observations to determine the implementation of learning scenarios and questionnaires. The data obtained were analyzed using descriptive statistical tests and inferential statistical tests. The research results show differences in the mathematical representation abilities of students who use the Student Facilitator and Explaining model with students who are taught using direct learning. The Student Facilitator and Explaining Learning Model effectively improves the mathematical representation abilities of class XI MIPA students at SMA Negeri 11 Bulukumba.

DeFRCN-MAM: DeFRCN and multi-scale attention mechanism-based industrial defect detection method

ABSTRACT With the technology development, industrial defect detection based on deep learning has attracted extensive attention in the academic community. Different from general visual objects, industrial defects have the characteristics of small sample, weak visibility and irregular shape, which hinder the application of related studies. According to these problems, a few-shot object detection (FSOD) method based on Decoupled Faster R-CNN (DeFRCN) is proposed in this paper. Firstly, it includes fine-tuning processing, because of the small sample characteristics. To adapt to the invisible characteristics of defects, we introduce the Feature Pyramid Network (FPN) and Residual Attention Module (RAM) into DeFRCN, which can enhance the capture ability of multi-scale features and feature association information. Furthermore, the feature representation ability is strengthened by parallel connecting of two channels, consisting of R-CNN head, box classifier and box regression models. Finally, it is completed that the pre-training, fine-tuning and testing of the proposed network, with DAGM 2007 and NEU-DET public industrial defect datasets as the base class and flange shaft defect data collected in the laboratory as the new class. To verify the effectiveness of the proposed one, we compare them with other classical FSOD methods. The superiority of the proposed method is obvious.

Dual-path multi-scale attention residual network for fault diagnosis of rolling bearings under complex operating conditions

Rolling bearing faults inevitably occur during the long-term continuous operation of rotating machinery. Therefore, fault diagnosis is greatly important for ensuring the normal and safe operation of rolling bearings. However, the complexity and diversity of working conditions of rolling bearings present a significant challenge in extracting fault characteristics accurately, which further affects the ultimate fault diagnosis results. In this article, we propose a new model, called dual-path multi-scale attention residual network (DPMARN), for diagnosing bearing faults under complex operating conditions. DPMARN can effectively capture the feature-feature correlation information at different scales, which is more beneficial for fusing fault features at different scales to improve the model’s performance. The main contributions of this work are summarized as follows: (1) the designed dual-path network model which incorporates parallel multi-scale branches of convolutional kernels and serially connects skip-layer multi-scale branches can integrate both low-frequency and high-frequency information and enhance the multi-scale feature extraction and complex data representation abilities. (2) The squeeze-and-excitation attention mechanism is embedded into the residual blocks to improve the ability of learning feature correlations and utilizing feature information effectively, which is helpful for extracting important fault characteristics. Extensive experiments conducted on two public bearing datasets demonstrate the superior performance of the DPMARN model for addressing the complex fault diagnosis problem. These results indicate that our proposed approach provides an effective solution for fault diagnosis of rolling bearings under complex operating conditions.

Other tokens matter: Exploring global and local features of Vision Transformers for Object Re-Identification

Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However, the effects of the global–local relation have not been fully explored in Transformers for object Re-ID. In this work, we first explore the influence of global and local features of ViT and then further propose a novel Global–Local Transformer (GLTrans) for high-performance object Re-ID. We find that the features from last few layers of ViT already have a strong representational ability, and the global and local information can mutually enhance each other. Based on this fact, we propose a Global Aggregation Encoder (GAE) to utilize the class tokens of the last few Transformer layers and learn comprehensive global features effectively. Meanwhile, we propose the Local Multi-layer Fusion (LMF) which leverages both the global cues from GAE and multi-layer patch tokens to explore the discriminative local representations. Extensive experiments demonstrate that our proposed method achieves superior performance on four object Re-ID benchmarks. The code is available at https://github.com/AWangYQ/GLTrans.

Identity-Guided Collaborative Learning for Cloth-Changing Person Reidentification.

Cloth-changing person reidentification (ReID) is a newly emerging research topic aimed at addressing the issues of large feature variations due to cloth-changing and pedestrian view/pose changes. Although significant progress has been achieved by introducing extra information (e.g., human contour sketching information, human body keypoints, and 3D human information), cloth-changing person ReID remains challenging because pedestrian appearance representations can change at any time. Moreover, human semantic information and pedestrian identity information are not fully explored. To solve these issues, we propose a novel identity-guided collaborative learning scheme (IGCL) for cloth-changing person ReID, where the human semantic is effectively utilized and the identity is unchangeable to guide collaborative learning. First, we design a novel clothing attention degradation stream to reasonably reduce the interference caused by clothing information where clothing attention and mid-level collaborative learning are employed. Second, we propose a human semantic attention and body jigsaw stream to highlight the human semantic information and simulate different poses of the same identity. In this way, the extraction features not only focus on human semantic information that is unrelated to the background but are also suitable for pedestrian pose variations. Moreover, a pedestrian identity enhancement stream is proposed to enhance the identity importance and extract more favorable identity robust features. Most importantly, all these streams are jointly explored in an end-to-end unified framework, and the identity is utilized to guide the optimization. Extensive experiments on six public clothing person ReID datasets (LaST, LTCC, PRCC, NKUP, Celeb-reID-light, and VC-Clothes) demonstrate the superiority of the IGCL method. It outperforms existing methods on multiple datasets, and the extracted features have stronger representation and discrimination ability and are weakly correlated with clothing.

Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery.

Since higher-order tensors are naturally suitable for representing multi-dimensional data in real-world, e.g., color images and videos, low-rank tensor representation has become one of the emerging areas in machine learning and computer vision. However, classical low-rank tensor representations can solely represent multi-dimensional discrete data on meshgrid, which hinders their potential applicability in many scenarios beyond meshgrid. To break this barrier, we propose a low-rank tensor function representation (LRTFR) parameterized by multilayer perceptrons (MLPs), which can continuously represent data beyond meshgrid with powerful representation abilities. Specifically, the suggested tensor function, which maps an arbitrary coordinate to the corresponding value, can continuously represent data in an infinite real space. Parallel to discrete tensors, we develop two fundamental concepts for tensor functions, i.e., the tensor function rank and low-rank tensor function factorization, and utilize MLPs to paramterize factor functions of the tensor function factorization. We theoretically justify that both low-rank and smooth regularizations are harmoniously unified in LRTFR, which leads to high effectiveness and efficiency for data continuous representation. Extensive multi-dimensional data recovery applications arising from image processing (image inpainting and denoising), machine learning (hyperparameter optimization), and computer graphics (point cloud upsampling) substantiate the superiority and versatility of our method as compared with state-of-the-art methods. Especially, the experiments beyond the original meshgrid resolution (hyperparameter optimization) or even beyond meshgrid (point cloud upsampling) validate the favorable performances of our method for continuous representation.

MRMNet: Multi-scale residual multi-branch neural network for object detection

Neural networks in object detection methods are designed to handle the challenging task of multi-scale object detection in computer vision. However, small objects occupy small blocks of pixels, and feature information can easily be overwhelmed, which further leads to certain shortcomings and deficiencies in the network’s multi-scale representation abilities. To alleviate this problem, we propose a novel multi-scale residual multi-branch neural network (MRMNet) for object detection. Particularly, we first propose a multi-scale extension (MSE) module to structurally construct optimal solutions to enhance feature extraction and alleviate information loss, thus effectively improving multi-scale object detection performance. Furthermore, we propose a contextual feature refinement (CFR) module, which draws on the idea of residuals to introduce a multi-residual structure and the feature of partial convolution, which can effectively alleviate the problem of small objects being overwhelmed by conflicting semantic information while avoiding the degradation problem of deep feature networks in some sense. Finally, by combining our own MSE module and integrating it into the existing Modified CSP v6 backbone, we propose a new backbone network, the multi-scale residual (MSRes) network. Experimental results show that our MRMNet and MSRes backbone achieve a competitive detection performance of 43.1% AP on the MS-COCO 2017 dataset.

Multi-scale recurrent attention gated fusion network for single image dehazing

The purpose of single image dehazing is to eliminate the bad influence of haze on images, so as to maintain more scene information of images. In recent years, the convolutional neural networks (CNN) have made significant contributions to single image dehazing. However, the visual quality of dehazed images still needs to be further improved. In view of the problems of single-scale shallow image feature extraction and the insufficient use of intermediate layer features in existing dehazing networks, we propose an end-to-end Multi-scale Recurrent Attention Gated Fusion Network (MRAGFN) to address the image dehazing task. We cascade three Dual Attention Fusion (DAF) modules to progressively form three haze-relevant features map, meanwhile, we adopt downsampling operation on the input to produce global feature map, which are used to weight the three feature maps to compensate for the missing of single-scale feature information. We present Feature Enhancement Module (FEM) to enhance the feature representation ability of these weighted feature maps. We design Recurrent Attention Gated Fusion (RAGF) module by adding attention mechanism and gating mechanism to gradually obtain more refined features based on these weighted features while eliminating redundant features. Experimental results on different hazy images demonstrate that the proposed dehazing network can restore the haze-free images and perform better than the state-of-the-art dehazing networks in terms of the objective indicators (such as PSNR, SSIM)and the subjective visual quality.

Deep M2CDL: Deep Multi-Scale Multi-Modal Convolutional Dictionary Learning Network.

For multi-modal image processing, network interpretability is essential due to the complicated dependency across modalities. Recently, a promising research direction for interpretable network is to incorporate dictionary learning into deep learning through unfolding strategy. However, the existing multi-modal dictionary learning models are both single-layer and single-scale, which restricts the representation ability. In this paper, we first introduce a multi-scale multi-modal convolutional dictionary learning ( M2CDL) model, which is performed in a multi-layer strategy, to associate different image modalities in a coarse-to-fine manner. Then, we propose a unified framework namely Deep M2CDL derived from the M2CDL model for both multi-modal image restoration (MIR) and multi-modal image fusion (MIF) tasks. The network architecture of Deep M2CDL fully matches the optimization steps of the M2CDL model, which makes each network module with good interpretability. Different from handcrafted priors, both the dictionary and sparse feature priors are learned through the network. The performance of the proposed Deep M2CDL is evaluated on a wide variety of MIR and MIF tasks, which shows the superiority of it over many state-of-the-art methods both quantitatively and qualitatively. In addition, we also visualize the multi-modal sparse features and dictionary filters learned from the network, which demonstrates the good interpretability of the Deep M2CDL network.

ANALISIS KEMAMPUAN REPRESENTASI SISWA DALAM MENYELESAIKAN SOAL MATEMATIS BERBASIS ETNOMATEMATIKA

This research aims to analyze the representational abilities of junior high school students in solving ethnomathematics-based mathematical problems. The newest thing is to see the representation of junior high school students when working on ethnomathematics-based mathematical problems, namely the engklek game. The type of research carried out in this research is qualitative research. Data collection methods use tests and interviews. The subjects in this research were MTs 1 Putri Annuqayah students whose address is Jalan Komplek PP Annuqayah Guluk-guluk Sumenep class IX Amazing, 2 students with high mathematical abilities and 2 students with low mathematical abilities. The results of the research show that students with high mathematical abilities are able to fulfill all indicators of representational abilities, namely verbal, visual and symbolic representational abilities, while students with low mathematical abilities are only able to fulfill one indicator of representational abilities, namely symbolic representational abilities.

Analisis Kemampuan Representasi Matematis Siswa dalam Menyelesaikan Soal Matematika Ditinjau dari Tipe Kepribadian Florence Littauer

This research purpose to describe students' mathematical representation abilities in solving mathematics problems in terms of Florence Littauer's personality type. This type of research is descriptive qualitative with the research subjects being class VIII students at SMPN 2 Sukodadi, totaling 8 students. This research uses technical triangulation, a Florence Littauer questionnaire to determine students' personality types and tests used to determine students' mathematical representation abilities. The results of this research show that students with a sanguine personality with high ability can complete visual and symbolic representations, students with moderate ability are less able to complete verbal representations, and students with moderate ability are less able to complete all indicators of mathematical representation ability. Choleric personality students with medium ability are less able to complete visual and symbolic representation indicators, low ability students are not able to complete verbal representations, and students with low ability are not able to complete all indicators of mathematical representation ability. Melancholic personality students with high abilities can complete all mathematical representation abilities. Phlegmatic personality students with low abilities have not been able to complete all mathematical representation skills