Representation Ability Research Articles

MLHI-Net: multi-level hybrid lightweight water body segmentation network for urban shoreline detection

The capacity to detect shorelines is critical for the autonomous navigation of Unmanned Surface Vehicles (USVs). The majority of extant methods are unable to adapt to the discrimination of high similarity features between the shore and reflections in complex and diverse environments. Moreover, they are also incapable of accurately extracting fuzzy boundaries caused by different scenes and climatic conditions. To address these challenges, this paper proposes a multi-level hybrid lightweight water segmentation network, MLHI-Net. First, we design a convolutional module (ORRD) compatible with over-parameterized and redundancy removal techniques based on lightweight design. The over-parameterized convolutional layers enhance the interactive ability of feature representation and context information. The removal of spatial and channel redundancy, in conjunction with interactive reconstruction, serves to simulate attention and enhance the learning ability of waterscape. Then, we design a multi-branch two-layer attention fusion module (MDA), which achieves diverse attention and global optimisation of edge details by connecting spatial attention, channel attention and pixel attention in parallel. thereby guiding feature fusion and solving the problem of receptive field mismatch. This module guides feature fusion and solves the problem of receptive field mismatch. To validate the proposed methodology, a dataset, CityWater, was constructed, with multiple fields and climatic conditions, and a substantial number of experiments were conducted on this and other public datasets. Experimental results show that MLHI-Net outperforms other advanced segmentation networks in Mean Intersection over Union (MIoU) and Pixel Accuracy (PA) on the CityWater and USVInland datasets, with MIoU of 97.86% and PA of 98.92% on the CityWater dataset, and MIoU of 98.12% and PA of 99.10% on the USVInland dataset. Additionally, the network’s computational GLOPS is 13.45 G, and the number of parameters is 46.92 M, which can meet the requirements for real-time detection. The MLHI-Net has been shown to perform well in a range of environments. In addition, it has good generalisation capabilities, providing reliable support to the autonomous system.

A multi-scale feature fusion network based on semi-channel attention for seismic phase picking

A multi-scale feature fusion network based on semi-channel attention for seismic phase picking

Kemampuan Representasi Matematis Ditinjau dari Perbedaan Gender Siswa Kelas IV SD pada Materi Pecahan Campuran

This research is motivated by the importance of mathematical representation ability in mixed fraction material. This study aims to describe the mathematical representation ability of fourth grade students in mixed fraction material based on gender. The research used quantitative method. The sample in this study were fourth grade students with a total of 34 students consisting of 16 male students and 18 female students. Selection of research subjects based on purposive sampling. Data were obtained through tests conducted twice, namely pretest then given treatment (treatment) and posttest with validated test instruments to see students' mathematical representation skills which were then processed and analyzed to draw conclusions and teacher questionnaires to see teacher perceptions about this research. The results showed that the average value of students' mathematical representation ability in visual representation reached 65.2%, representation of mathematical equations or expressions reached 43.5% and representation of words or written text reached 41.2%. Based on gender, male students reached an average of 0.61 and female students reached 0.44. The results of this study indicate that the mathematical representation ability of mixed fractions of male students is faster to accept the material because male students pay more attention to the material when learning so that they understand more quickly while female students play more.

Gesture recognition from surface electromyography signals based on the SE-DenseNet network.

In recent years, significant progress has been made in the research of gesture recognition using surface electromyography (sEMG) signals based on machine learning and deep learning techniques. The main motivation for sEMG gesture recognition research is to provide more natural, convenient, and personalized human-computer interaction, which makes research in this field have considerable application prospects in rehabilitation technology. However, the existing gesture recognition algorithms still need to be further improved in terms of global feature capture, model computational complexity, and generalizability. This paper proposes a fusion model of Squeeze-and-Excitation Networks (SE) and DenseNet, inserting attention mechanism between DenseBlock and Transition to focus on the most important information, improving feature representation ability, and effectively solving the problem of gradient vanishing. This proposed method was tested on the electromyographic gesture datasets NinaPro DB2 and DB4, achieving accuracies of 85.93 and 82.39 % respectively. Through ablation experiments, it was found that the method based on DenseNet-101 as the backbone model produced the best results. Compared with existing models, this proposed method has better robustness and generalizability in gesture recognition, providing new ideas for the development of sEMG signal gesture recognition applications in the future.

A tool wear monitoring method driven by workpiece surface quality inversion and EfficientNet

Abstract Tool wear status monitoring plays an important role in the safety of machine and the efficiency of production. Due to the limitation of sensor installation and complex operation conditions, traditional machine vision methods are difficult to directly act on the tool itself to obtain corresponding wear status information. Meanwhile, the surface quality of the machined workpiece can provide indirect insights into the wear status of the tool to a significant degree. Therefore, an indirect tool wear status monitoring method is proposed in this paper by workpiece surface quality inversion and EfficientNet. Firstly, the surface texture data of workpiece are obtained in the form of image by an industrial camera, and the representative features that indirectly reflect tool wear status are further highlighted by using the weighted average image grayscale and the Laplacian operator. Secondly, to monitor tool wear effectively, we have optimized three key settings, width, model depth, and input image resolution, of the EfficientNet backbone network. This optimization boosts its ability to understand and generalize, ensuring it can handle various surface textures and extract crucial information accurately. This, in turn, enhances the accuracy of our tool wear monitoring system. Finally, the improved EfficientNet network is further utilized as a pre-trained network to achieve tool wear state monitoring. Utilizing the powerful representation ability of the pre-trained model and the surface texture features of workpiece, the model can accurately identify and judge the wear degree of the tool. The tool experiment results show that the proposed tool wear monitoring method has achieved remarkable results with recognition accuracy of 97.77%. While other popular methods such as VGG19, ResNet50, and ResNet152, whose training accuracies are 95.66%, 96.37%, and 91.27%, respectively. The comparative results highlight the excellent performance of the proposed method in recognition rate, training time and generalization performance.

Alzheimer's disease image classification based on enhanced residual attention network.

With the increasing number of patients with Alzheimer's Disease (AD), the demand for early diagnosis and intervention is becoming increasingly urgent. The traditional detection methods for Alzheimer's disease mainly rely on clinical symptoms, biomarkers, and imaging examinations. However, these methods have limitations in the early detection of Alzheimer's disease, such as strong subjectivity in diagnostic criteria, high detection costs, and high misdiagnosis rates. To address these issues, this study proposes a deep learning model to detect Alzheimer's disease; it is called Enhanced Residual Attention Network (ERAN) that can classify medical images. By combining residual learning, attention mechanism, and soft thresholding, the feature representation ability and classification accuracy of the model have been improved. The accuracy of the model in detecting Alzheimer's disease has reached 99.36%, with a loss rate of only 0.0264. The experimental results indicate that the Enhanced Residual Attention Network has achieved excellent performance on the Alzheimer's disease test dataset, providing strong support for the early diagnosis and treatment of Alzheimer's disease.

An EfficientNetv2-based method for coal conveyor belt foreign object detection

The detection and recognition of foreign objects on coal conveyor belts play a crucial role in coal production. This article proposes a foreign object detection method for coal conveyor belts based on EfficientNetv2. Since MBConv and Fused-MBConv structures in EfficientNetv2 employ information compression and fusion strategies, which may lead to the loss of important information and affect the integrity of feature extraction, a hard shuffle attention (Hard-SA) mechanism is utilized to enhance the focus on important features and improve the representation ability of coal conveyor belts image features. To address the potential gradient disappearance issue during the backpropagation process of the network, an elastic exponential linear unit (EELU) activation function is introduced. Additionally, since the cross-entropy loss function may not be flexible enough to handle complex data distributions and may fail to fit the non-linear relationships between data well, a Polyloss function is adopted. Polyloss can better adapt to the complex data distribution and task requirements of coal mine images. The experimental results show that the proposed method achieves an accuracy of 93.02%, which is 2.39% higher than that of EfficientNetv2. It also outperforms some other state-of-the-art (SOTA) models and can effectively complete the detection of foreign objects on coal conveyor belts.

PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement

Light scattering and attenuation in water degrade underwater images with low visibility and color distortion, which often interfere with the high-level visual tasks of underwater autonomous robots. Most existing deep learning methods for underwater image enhancement only supervise the final output of network and ignore the promotion effect of the intermediate results on the final feature representation. These supervision methods affect the feature representation ability, network efficiency, and ability. In this paper, we present a novel idea of multiple-stage supervision to guide the network to learn useful features correctly and progressively. With this idea, we propose a pixel-wise Progressive Guided Network (PGN) for underwater image enhancement to take advantage of the network’s intermediate results and promote the final enhancement effect. The Pixel-Wise Attention Module is designed by introducing supervision in each stage to progressively promote the representation ability of the features and the recovered image quality. The experimental results on several datasets demonstrate that our method outperforms recent state-of-the-art underwater image enhancement methods.

The Role of Interactive e-Modules Based on Realistic Mathematics Education to Improve Mathematical Representation Ability

Excellent mathematical representation ability is needed by students to develop and deepen understanding and relationships between mathematical concepts. Therefore, the teacher has the responsibility to create learning that encourages mathematical representation ability. The existence of interactive e-modules with a realistic mathematic education approach makes it easy for students to learn interactively and adapt to different students' mathematical abilities. This study aims to determine the improvement of mathematical representation ability from the use of interactive e-modules with realistic mathematics education approach. This research is a quantitative research conducted on seventh grade students of SMPN 18 Banda Aceh which is divided into experimental and control classes. The data analysis technique used was analysis of variance (ANOVA) followed by t-test. The results showed that students' mathematical representation ability in the experimental class was better than the control class. The interaction between the use of E-modules and students' initial mathematical ability on mathematical representation ability showed that the use of E-modules and early mathematical ability together had a significant effect on improving mathematical representation ability. Students who have high early math ability have a great influence if given treatment in the form of using RME-based e-modules. Students with low early mathematical ability did not experience significant improvement. Interactive e-modules with the RME approach can be used to improve mathematical representation skills by considering students' early mathematical abilities.

Systematic Literature Review: The Influence of Discovery Learning Model on Students' Mathematical Representation Ability

The purpose of this Systematic Literature Review (SLR) is to highlight the effectiveness of the Discovery Learning model in improving students' mathematical representation ability. The research process involves the following stages: formulating research objectives, article collection using Publish or Perish 8, article sreening with the inclusion criteria used, and data evaluation where the article that selected were reviewed in depth. The review encompassed studies from various educational settings and consistently demonstrated the positive impact of Discovery Learning on students' ability to represent mathematical concepts and solve problems. The findings underscore the potential of the discovery learning model as a valuable approach to enhance students' mathematical representation ability and pave the way for further research and implementation in educational settings

EDANet: Efficient Dynamic Alignment of Small Target Detection Algorithm

Unmanned aerial vehicles (UAVs) integrated with computer vision technology have emerged as an effective method for information acquisition in various applications. However, due to the small proportion of target pixels and susceptibility to background interference in multi-angle UAV imaging, missed detections and false results frequently occur. To address this issue, a small target detection algorithm, EDANet, is proposed based on YOLOv8. First, the backbone network is replaced by EfficientNet, which can dynamically explore the network size and the image resolution using a scaling factor. Second, the EC2f feature extraction module is designed to achieve unique coding in different directions through parallel branches. The position information is effectively embedded in the channel attention to enhance the spatial representation ability of features. To mitigate the low utilization of small target pixels, we introduce the DTADH detection module, which facilitates feature fusion via a feature-sharing interactive network. Simultaneously, a task alignment predictor assigns classification and localization tasks. In this way, not only is feature utilization optimized, but also the number of parameters is reduced. Finally, leveraging logic and feature knowledge distillation, we employ binary probability mapping of soft labels and a soft label weighting strategy to enhance the algorithm’s learning capabilities in target classification and localization. Experimental validation on the UAV aerial dataset VisDrone2019 demonstrates that EDANet outperforms existing methods, reducing GFLOPs by 39.3% and improving Map by 4.6%.

Mathematics Learning Problem Based Learning Model in Improving Students' Mathematical Representation Ability: A Meta-Analysis

This research aims to examine the effect size of studies that discuss the application of the Problem Based Learning model as an effort to improve students' mathematical representation skills. The statistical procedures used in this study were based on the meta-analysis procedures namely: (a) calculating the effect size of each primary study; (b) conducting heterogeneity tests and selecting estimation models; (c) check for publication bias; (d) calculate the p-value to test the research hypothesis. The primary studies used were 10 studies obtained from the Google Scholar search engine with publication years between 2018 and 2024. The results of statistical calculations showed that the overall effect size of the studies used was 0.600, which is included in the moderate effect size category with a standard deviation of 0.171. This finding means that the application of the Problem Based Learning model in mathematics learning has a moderate influence on students' mathematical representation skills.

I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network

The key to building a 3D point cloud map is to ensure the consistency and accuracy of point cloud data. However, the hardware limitations of LiDAR lead to a sparse and uneven distribution of point cloud data in the edge region, which brings many challenges to 3D map construction, such as low registration accuracy and high construction errors in the sparse regions. To solve these problems, this paper proposes the I-PAttnGAN network to generate point clouds with image-assisted approaches, which aims to improve the density and uniformity of sparse regions and enhance the representation ability of point cloud data in sparse edge regions for distant objects. I-PAttnGAN uses the normalized flow model to extract the point cloud attention weights dynamically and then integrates the point cloud weights into image features to learn the transformation relationship between the weighted image features and the point cloud distribution, so as to realize the adaptive generation of the point cloud density and resolution. Extensive experiments are conducted on ShapeNet and nuScenes datasets. The results show that I-PAttnGAN significantly improves the performance of generating high-quality, dense point clouds in low-density regions compared with existing methods: the Chamfer distance value is reduced by about 2 times, the Earth Mover’s distance value is increased by 1.3 times, and the F1 value is increased by about 1.5 times. In addition, the effectiveness of the newly added modules is verified by ablation experiments, and the experimental results show that these modules play a key role in the generation process. Overall, the proposed model shows significant advantages in terms of accuracy and efficiency, especially in generating complete spatial point clouds.

Large Scale Time-Series Representation Learning via Simultaneous Low-and High-Frequency Feature Bootstrapping.

Learning representations from unlabeled time series data is a challenging problem. Most existing self-supervised and unsupervised approaches in the time-series domain fall short in capturing low-and high-frequency features at the same time. As a result, the generalization ability of the learned representations remains limited. Furthermore, some of these methods employ large-scale models like transformers or rely on computationally expensive techniques such as contrastive learning. To tackle these problems, we propose a noncontrastive self-supervised learning (SSL) approach that efficiently captures low-and high-frequency features in a cost-effective manner. The proposed framework comprises a Siamese configuration of a deep neural network with two weight-sharing branches which are followed by low-and high-frequency feature extraction modules. The two branches of the proposed network allow bootstrapping of the latent representation by taking two different augmented views of raw time series data as input. The augmented views are created by applying random transformations sampled from a single set of augmentations. The low-and high-frequency feature extraction modules of the proposed network contain a combination of multilayer perceptron (MLP) and temporal convolutional network (TCN) heads, respectively, which capture the temporal dependencies from the raw input data at various scales due to the varying receptive fields. To demonstrate the robustness of our model, we performed extensive experiments and ablation studies on five real-world time-series datasets. Our method achieves state-of-art performance on all the considered datasets.

UMS[formula omitted]-ODNet: Unified-scale domain adaptation mechanism driven object detection network with multi-scale attention

Unsupervised domain adaptation techniques improve the generalization capability and performance of detectors, especially when the source and target domains have different distributions. Compared with two-stage detectors, one-stage detectors (especially YOLO series) provide better real-time capabilities and become primary choices in industrial fields. In this paper, to improve cross-domain object detection performance, we propose a Unified-Scale Domain Adaptation Mechanism Driven Object Detection Network with Multi-Scale Attention (UMS2-ODNet). UMS2-ODNet chooses YOLOv6 as the basic framework in terms of its balance between efficiency and accuracy. UMS2-ODNet considers the adaptation consistency across different scale feature maps, which tends to be ignored by existing methods. A unified-scale domain adaptation mechanism is designed to fully utilize and unify the discriminative information from different scales. A multi-scale attention module is constructed to further improve the multi-scale representation ability of features. A novel loss function is created to maintain the consistency of multi-scale information by considering the homology of the descriptions from the same latent feature. Multiply experiments are conducted on four widely used datasets. Our proposed method outperforms other state-of-the-art techniques, illustrating the feasibility and effectiveness of the proposed UMS2-ODNet.

DSTCNet: Deep Spectro-Temporal-Channel Attention Network for Speech Emotion Recognition.

Speech emotion recognition (SER) plays an important role in human-computer interaction, which can provide better interactivity to enhance user experiences. Existing approaches tend to directly apply deep learning networks to distinguish emotions. Among them, the convolutional neural network (CNN) is the most commonly used method to learn emotional representations from spectrograms. However, CNN does not explicitly model features' associations in the spectral-, temporal-, and channel-wise axes or their relative relevance, which will limit the representation learning. In this article, we propose a deep spectro-temporal-channel network (DSTCNet) to improve the representational ability for speech emotion. The proposed DSTCNet integrates several spectro-temporal-channel (STC) attention modules into a general CNN. Specifically, we propose the STC module that infers a 3-D attention map along the dimensions of time, frequency, and channel. The STC attention can focus more on the regions of crucial time frames, frequency ranges, and feature channels. Finally, experiments were conducted on the Berlin emotional database (EmoDB) and interactive emotional dyadic motion capture (IEMOCAP) databases. The results reveal that our DSTCNet can outperform the traditional CNN-based and several state-of-the-art methods.

Problem-Solving Based Epistemic Learning Pattern: Optimizing Mathematical Representation Ability of Prospective Teachers and Pharmacists

Problem-Solving Based Epistemic Learning Pattern: Optimizing Mathematical Representation Ability of Prospective Teachers and Pharmacists

CADS: A Self-supervised Learner via Cross-modal Alignment and Deep Self-distillation for CT Volume Segmentation.

Self-supervised learning (SSL) has long had great success in advancing the field of annotation-efficient learning. However, when applied to CT volume segmentation, most SSL methods suffer from two limitations, including rarely using the information acquired by different imaging modalities and providing supervision only to the bottleneck encoder layer. To address both limitations, we design a pretext task to align the information in each 3D CT volume and the corresponding 2D generated X-ray image and extend self-distillation to deep self-distillation. Thus, we propose a self-supervised learner based on Cross-modal Alignment and Deep Self-distillation (CADS) to improve the encoder's ability to characterize CT volumes. The cross-modal alignment is a more challenging pretext task that forces the encoder to learn better image representation ability. Deep self-distillation provides supervision to not only the bottleneck layer but also shallow layers, thus boosting the abilities of both. Comparative experiments show that, during pre-training, our CADS has lower computational complexity and GPU memory cost than competing SSL methods. Based on the pre-trained encoder, we construct PVT-UNet for 3D CT volume segmentation. Our results on seven downstream tasks indicate that PVT-UNet outperforms state-of-the-art SSL methods like MOCOv3 and DiRA, as well as prevalent medical image segmentation methods like nnUNet and CoTr. Code and pre-trained weight will be available at https://github.com/yeerwen/CADS.

Advanced retinal disease detection from OCT images using a hybrid squeeze and excitation enhanced model.

Retinal problems are critical because they can cause severe vision loss if not treated. Traditional methods for diagnosing retinal disorders often rely heavily on manual interpretation of optical coherence tomography (OCT) images, which can be time-consuming and dependent on the expertise of ophthalmologists. This leads to challenges in early diagnosis, especially as retinal diseases like diabetic macular edema (DME), Drusen, and Choroidal neovascularization (CNV) become more prevalent. OCT helps ophthalmologists diagnose patients more accurately by allowing for early detection. This paper offers a hybrid SE (Squeeze-and-Excitation)-Enhanced Hybrid Model for detecting retinal disorders from OCT images, including DME, Drusen, and CNV, using artificial intelligence and deep learning. The model integrates SE blocks with EfficientNetB0 and Xception architectures, which provide high success in image classification tasks. EfficientNetB0 achieves high accuracy with fewer parameters through model scaling strategies, while Xception offers powerful feature extraction using deep separable convolutions. The combination of these architectures enhances both the efficiency and classification performance of the model, enabling more accurate detection of retinal disorders from OCT images. Additionally, SE blocks increase the representational ability of the network by adaptively recalibrating per-channel feature responses. The combined features from EfficientNetB0 and Xception are processed via fully connected layers and categorized using the Softmax algorithm. The methodology was tested on UCSD and Duke's OCT datasets and produced excellent results. The proposed SE-Improved Hybrid Model outperformed the current best-known approaches, with accuracy rates of 99.58% on the UCSD dataset and 99.18% on the Duke dataset. These findings emphasize the model's ability to effectively diagnose retinal disorders using OCT images and indicate substantial promise for the development of computer-aided diagnostic tools in the field of ophthalmology.

The Effect of CPA-Based Multimedia Articulate Storyline Batik Motif on Elementary Students’ Mathematical Representation

Mathematical representation is a fundamental ability to develop students' thinking skills. But in reality, this ability is still low. The investigation aims to ascertain the impact of CPA-based articulated storyline multimedia on the Mathematical Representation Abilities (MRA) of elementary school students. The research uses CPA-based articulate storyline multimedia in learning activities. A type of experimental research with pre-experimental designs, one group pretest-posttest. 44 pupils from one of Karawang Regency's elementary schools in West Java made up the sample. Data were obtained through MRA tests in the form of descriptions, students' daily journals, interviews, and photo documentation of research activities. The MRA test questions used were valid and reliable. Based on Guilford's criteria, the results of the test validity and reliability calculation are in the high category (Retrieved from zero point eighty-four). Descriptive data analysis was conducted by finding the simple linear regression equation and the coefficient of determination. Inferential data analysis was performed with a t-test. Descriptive results showed that using CPA-based multimedia articulated storyline affected the Mathematical Representation ability (MRA) of elementary school students. Based on hypothesis testing, it is known that CPA-based articulate storyline multimedia significantly affects the mathematical representation skills of elementary school pupils. The implication from research is that multimedia articulate storylines based on CPA represent alternatives for enhancing elementary school pupils' mathematical representation ability in learning two-dimensional mathematics.