Strong Representation Research Articles

Komunikasi Perempuan dalam Dakwah (Menciptakan Ruang untuk Representasi dan Kepemimpinan)

This study explores the leadership role of women in da'wah with a focus on representation and transformational leadership. This study uses desk research methods to analyse relevant literature, with the aim of understanding how the representation of women in various forms of da'wah communication-such as lectures, writings, and social media-can influence people's perceptions of women's leadership capabilities. The research findings show that strong and positive representations of women in da'wah can change people's perceptions and open up opportunities for women to take on leadership roles. Key challenges faced in creating space for women's representation and leadership include persisting patriarchal norms, resistance from conservative parties, and limited access and resources. This analysis highlights that women's transformational leadership, characterised by a clear vision, attention to the individual, intellectual stimulation, and idealised influence, has great potential to bring about positive change in religious communities. The impact of this transformational leadership includes changing gender perceptions and stereotypes, increasing community participation, empowering individuals, and enhancing innovation and creativity. By addressing these challenges and supporting women's transformational leadership, religious communities can become more inclusive, just and dynamic. This research confirms the importance of strong representation and support for women in da'wah leadership to achieve significant social and cultural change.

Fog-based deep learning framework for real-time pandemic screening in smart cities from multi-site tomographies

The quick proliferation of pandemic diseases has been imposing many concerns on the international health infrastructure. To combat pandemic diseases in smart cities, Artificial Intelligence of Things (AIoT) technology, based on the integration of artificial intelligence (AI) with the Internet of Things (IoT), is commonly used to promote efficient control and diagnosis during the outbreak, thereby minimizing possible losses. However, the presence of multi-source institutional data remains one of the major challenges hindering the practical usage of AIoT solutions for pandemic disease diagnosis. This paper presents a novel framework that utilizes multi-site data fusion to boost the accurateness of pandemic disease diagnosis. In particular, we focus on a case study of COVID-19 lesion segmentation, a crucial task for understanding disease progression and optimizing treatment strategies. In this study, we propose a novel multi-decoder segmentation network for efficient segmentation of infections from cross-domain CT scans in smart cities. The multi-decoder segmentation network leverages data from heterogeneous domains and utilizes strong learning representations to accurately segment infections. Performance evaluation of the multi-decoder segmentation network was conducted on three publicly accessible datasets, demonstrating robust results with an average dice score of 89.9% and an average surface dice of 86.87%. To address scalability and latency issues associated with centralized cloud systems, fog computing (FC) emerges as a viable solution. FC brings resources closer to the operator, offering low latency and energy-efficient data management and processing. In this context, we propose a unique FC technique called PANDFOG to deploy the multi-decoder segmentation network on edge nodes for practical and clinical applications of automated COVID-19 pneumonia analysis. The results of this study highlight the efficacy of the multi-decoder segmentation network in accurately segmenting infections from cross-domain CT scans. Moreover, the proposed PANDFOG system demonstrates the practical deployment of the multi-decoder segmentation network on edge nodes, providing real-time access to COVID-19 segmentation findings for improved patient monitoring and clinical decision-making.

Pushing the Limits of Learning from Limited Data

What is the mechanism behind people's remarkable ability to learn from very little data, and what are its limits? Preliminary evidence suggests people can infer categories from extremely sparse data, even when they have fewer labeled examples than categories. However, the mechanisms behind this learning process are unclear. In our experiment, people learned 8 categories defined over a 2D manifold from just 4 labeled examples. Our results suggest that people are forming rich representations of the underlying categories despite this limited information. These results push the limits of how little information people need to build strong and systematic category representations.

Exploring the Impact of Artificial Intelligence (AI-based) English Games in Enhancing English Communication Skills among Indonesian L2 Generation Z

The role of artificial intelligence (AI-based) English games in enhancing English communication skills among Indonesian Generation Z (Gen-Z) for whom English is a second language (L2), is the main focus of this study. Questionnaires to collect data consisted of both open and closed-ended questions. Seventy-eight Indonesian Gen- Z from different parts of Indonesia participated, and provides a strong representation of the country. This study is aimed to address a gap in the present literature by directly engaging with game players and examining their perspectives and experiences with actual games that they play for enjoyment rather than games designed for educational purposes. The study’s findings show that English AI-based games significantly help respondents develop their vocabulary, improve comprehension, and acquire confidence in English speaking. The findings also indicate that English AI-based game learning is favoured over traditional methods. The respondents noted gaming's immersive and interactive aspect as beneficial to language acquisition and skill development. These findings emphasise the transformative potential of English AI-based games in language learning and advocate for their integration into educational frameworks to better fulfil the needs of L2 learners, particularly Gen-Z.

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.

Evaluating Intangible Cultural Heritage Policy of Balinese Handwoven Textiles

Several key factors drive contemporary concerns about the sustainability of intangible cultural heritage. Cultural policy has given meaning and importance to the cultural diversity of society. However, the efforts to preserve intangible cultural heritage by providing a way to community welfare are facing new challenges. The article aims to present an analysis of local cultural policy from Bali Governance to sustain the intangible heritage of handwoven textiles by increasing the economy demand. Using a focus group approach, qualitative data were collected and using Nvivo12 to analyze the data from 15 interviews of weavers and practices of Balinese handwoven textiles living in Bali. This approach is used as a means to represent the complex diversity of opinions among members of the weaving group in a dynamic interaction that is provided so that a diversity of views emerges from the participants and direct clarification of the issues that influence the diversity of arguments on the reality of the impact on policy. The result found that the cultural policy is increasing the sense of identity by using Balinese handwoven textiles and significantly has the direct impact for the demand of handwoven textiles. Furthermore, the research revealed that cultural policy plays important role in shaping and reviving the traditional practices by evaluating the challenges of cultural industries such as industrialization, regeneration knowledge, environmental sustainability by reducing chemical dyes, the welfare of women weavers, market access and strong representation between communities.

SwinSOD: Salient object detection using swin-transformer

The Transformer structure has achieved excellent performance in a wide range of applications in computer vision, and Swin-Transformer also shows strong feature representation capabilities. On this basis, we proposed a fusion model SwinSOD for RGB salient object detection. This model used a Swin-Transformer as the encoder to extract hierarchical features, was driven by a multi-head attention mechanism to bridge the gap between hierarchical features, progressively fused adjacent layer feature information under the guidance of global information, and refined the boundaries of saliency objects through the feedback information. Specifically, the Swin-Transformer encoder extracted multi-level features and then recalibrated the channels to optimize intra-layer channel features. The feature fusion module realized feature fusion between each layer under the guidance of global information. In order to clarify the fuzzy boundaries, the second stage feature fusion achieved edge refinement under the guidance of feedback information. The proposed model outperforms state-of-the-art models on five popular SOD datasets, demonstrating the advanced performance of this network. Code released: https://github.com/user-wu/SwinSOD.

Optimization of financial data processing strategy based on LSTM-GCN

In the process of training LSTM-GCN mixed model with labeled data, a common practice is to divide the data set into a training set and a validation set, and cross-validation techniques are frequently used to ensure the effective partitioning of data. The training phase mainly involves the selection of optimization methods such as gradient descent to update the model parameters, so that the model can correctly identify the feature patterns in the data. In this process, we first define a loss function to quantify the difference between the model's predicted value and the actual value. For example, when dealing with classification problems, the cross-entropy loss function is often used; Whereas in regression problems, the mean square error loss function or the absolute error loss function is more common. Then, the loss gradient of each parameter is calculated by backpropagation algorithm, and optimization strategies such as gradient descent are applied to adjust the parameter values. Through repeated iterations, these algorithms aim to minimize the loss function as a core goal for training the model. In addition, the details of model training, such as setting the appropriate learning rate, taking the appropriate regularization measures, and choosing the appropriate weight initialization strategy, are also key steps that cannot be ignored. This paper conforms to the research and development trend of the industry, focusing on how to use the LSTM-GCN model to capture temporal and spatial characteristics, process multi-modal data, process nonlinear data and dynamic weight allocation, etc., providing new ideas for Internet finance companies in data processing. This model combines the advantages of LSTM and GCN, and has prominent advantages such as timeliness, strong representation learning ability, associability, and interpretability. It can process both time series data and graphic data, and can analyze and mine the correlation and regularity in large-scale time series data, so as to process financial data more accurately. It greatly reduces the risk of investment decision.

A Reconstruction Algorithm for Compression Perception Based on Local Learning Dictionary and Sparsity Iterative Update

The global sparse representation method based on compressed sensing fails to capture the local texture and detail structure of an image. To address this, a local dictionary learning method based on the wavelet domain is proposed. The wavelet high-frequency subband sub-block classification and local dictionary learning are implemented using the FCM clustering method and K-L method, respectively. At the reconstruction end, a compressed sampling Matching pursuit algorithm based on iterative update of sparsity is proposed. This adaptive iteration can effectively reconstruct the original image under unknown sparsity conditions. Simulation experiments show that compared to existing reconstruction methods, this approach has the advantages of simple computation, strong adaptive sparse representation ability for the original image, and superior reconstructed image performance.

A Collaborative Compression Scheme for Fast Activity Recognition on Mobile Devices via Global Compression Ratio Decision

Despite strong representation ability, deep convolutional neural networks (CNNs) are largely hindered in practical human activity recognition (HAR) deployment due to high computational cost, which is often unaffordable on resource-limited wearable devices. In this paper, to bridge the gap between on-device HAR and deep learning, we present a collaborative compression scheme to reduce the runtime of HAR with an acceptable performance degradation, which combines channel pruning and tensor decomposition to simultaneously handle sparsity and low-rankness when fully considering mutual interference in one network consisting of efficient 1-dimensional convolutional kernels. Our method includes two main stages. Concretely, given a target compression ratio, a global compression ratio decision optimization is first performed to automatically decide per-layer compression ratio by measuring compression sensitivity, without requiring labor-exhaustive human intervention. Then a multi-step collaborative compression is iteratively implemented to remove the least important compression unit based on an improved importance metric until the per-layer target compression ratio is attained. Extensive experiments on multiple HAR benchmarks show that our approach considerably outperforms previous compression strategies. For example, it can achieve around 50% FLOPs reduction with only an accuracy drop of 0.25% and 0.15% on UCI-HAR and PAMAP2, respectively. Actual implementation is evaluated on an embedded platform.

Bibliometric and visualized analysis of DME from 2012 to 2022.

Diabetic macular edema (DME) is the main cause of irreversible vision loss in patients with diabetes mellitus (DM), resulting in a certain burden to patients and society. With the increasing incidence of DME, more and more researchers are focusing on it. The papers related to DME between 2012 and 2022 from the Web of Science core Collection were searched in this study. Based on CiteSpace and VOS viewer, these publications were analyzed in terms of spatiotemporal distribution, author distribution, subject classification, topic distribution, and citations. A total of 5165 publications on DME were included. The results showed that the research on DME is on a steady growth trend. The country with the highest number of published documents was the US. Wong Tien Yin from Tsinghua University was the author with the most published articles. The journal of Retina, the Journal of Retinal and Vitreous Diseases had a large number of publications. The article "Mechanisms of macular edema: Beyond the surface" was the highly cited literature and "Aflibercept, bevacizumab, or ranibizumab for diabetic macular edema" had the highest co-citation frequency. The treatment, diagnosis, pathogenesis, as well as etiology and epidemiological investigation of DME, have been the current research direction. Deep learning has been widely used in the medical field for its strong feature representation ability. The study revealed the important authoritative literature, journals, institutions, scholars, countries, research hotspots, and development trends in in the field of DME. This indicates that communication and cooperation between disciplines, universities, and countries are crucial. It can advance research in DME and even ophthalmology.

Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders

Learning 3D representation plays a critical role in masked autoencoder (MAE) based pre-training methods for point cloud, including single-modal and cross-modal based MAE. Specifically, although cross-modal MAE methods learn strong 3D representations via the auxiliary of other modal knowledge, they often suffer from heavy computational burdens and heavily rely on massive cross-modal data pairs that are often unavailable, which hinders their applications in practice. Instead, single-modal methods with solely point clouds as input are preferred in real applications due to their simplicity and efficiency. However, such methods easily suffer from limited 3D representations with global random mask input. To learn compact 3D representations, we propose a simple yet effective Point Feature Enhancement Masked Autoencoders (Point-FEMAE), which mainly consists of a global branch and a local branch to capture latent semantic features. Specifically, to learn more compact features, a share-parameter Transformer encoder is introduced to extract point features from the global and local unmasked patches obtained by global random and local block mask strategies, followed by a specific decoder to reconstruct. Meanwhile, to further enhance features in the local branch, we propose a Local Enhancement Module with local patch convolution to perceive fine-grained local context at larger scales. Our method significantly improves the pre-training efficiency compared to cross-modal alternatives, and extensive downstream experiments underscore the state-of-the-art effectiveness, particularly outperforming our baseline (Point-MAE) by 5.16%, 5.00%, and 5.04% in three variants of ScanObjectNN, respectively. Code is available at https://github.com/zyh16143998882/AAAI24-PointFEMAE.

Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis

Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we propose Point Deformable Network (PDNet), a concise MLP-based network that can capture long-range relations with strong representation ability. Specifically, we put forward Point Deformable Aggregation Module (PDAM) to improve representation capability in both long-range dependency and adaptive aggregation among points. For each query point, PDAM aggregates information from deformable reference points rather than points in limited local areas. The deformable reference points are generated data-dependent, and we initialize them according to the input point positions. Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest. We also suggest estimating the normal vector for point clouds and applying Enhanced Normal Embedding (ENE) to the geometric extractors to improve the representation ability of single-point. Extensive experiments and ablation studies on various benchmarks demonstrate the effectiveness and superiority of our PDNet.

Orthopedic Surgery Residency Program Rankings and Gender Diversity.

Background Orthopedic surgery residency programs are some of the least gender-diverse specialty programs in medicine. Despite strong representation at the undergraduate and medical school levels and increased applications to orthopedic surgery residency programs by women, there is still a substantial gender gap at the resident level. This study explores the relationship between the gender diversity of orthopedic surgery residency programs and program rankings. Methodology Program rank, program director gender identity, and gender diversity data were collected for the top 100 programs by reputation in Doximity. Gender diversity was measured as the proportion of female residents in the program and alumni. Results The greatest percentage of women in a program was 33% and the smallest was 3%. After linear regression analysis, we found that there was a statistically significant positive correlation between program rank and the proportion of women. The higher ranked a program was, the greater the proportion of women. There was no significant correlation between program director gender, appointment year, and program rank. Conclusions These results suggest that, although there is still a long way to go before closing the gender gap in orthopedic surgery residency programs, higher-ranked programs are associated with greater gender diversity than their lower-ranked counterparts.

Switching Self-Attention Text Classification Model with Innovative Reverse Positional Encoding for Right-to-Left Languages: A Focus on Arabic Dialects

Transformer models have emerged as frontrunners in the field of natural language processing, primarily due to their adept use of self-attention mechanisms to grasp the semantic linkages between words in sequences. Despite their strengths, these models often face challenges in single-task learning scenarios, particularly when it comes to delivering top-notch performance and crafting strong latent feature representations. This challenge is more pronounced in the context of smaller datasets and is particularly acute for under-resourced languages such as Arabic. In light of these challenges, this study introduces a novel methodology for text classification of Arabic texts. This method harnesses the newly developed Reverse Positional Encoding (RPE) technique. It adopts an inductive-transfer learning (ITL) framework combined with a switching self-attention shared encoder, thereby increasing the model’s adaptability and improving its sentence representation accuracy. The integration of Mixture of Experts (MoE) and RPE techniques empowers the model to process longer sequences more effectively. This enhancement is notably beneficial for Arabic text classification, adeptly supporting both the intricate five-point and the simpler ternary classification tasks. The empirical evidence points to its outstanding performance, achieving accuracy rates of 87.20% for the HARD dataset, 72.17% for the BRAD dataset, and 86.89% for the LABR dataset, as evidenced by the assessments conducted on these datasets.

The role of the waste sector in the sustainable development goals and the IPCC assessment reports

The management of waste plays a pivotal role in achieving the Sustainable Development Goals (SDGs) set by the United Nations through both direct and indirect linkages. Directly, waste management issues are addressed in four SDGs (6, 11, 12, 14), while landfilling issues are only mentioned in SDG 6 reflecting water quality in connection with waste dumping. However, inadequate management and disposal of waste pose environmental, health and safety risks; thereby undermining more SDGs. Indirectly, waste management and landfilling influence various SDGs ranging from 4 to all 17 SDGs depending on the literature reference.Although not directly addressed in SDG 13 (Climate action), the waste sector contributes to climate change, with the biggest share of greenhouse gases emitted from landfills and waste dumps. According to the latest assessment report by the IPCC (Intergovernmental Panel on Climate Change), waste management—and thereby mainly landfills—are responsible for 64 Mt of CH4 per year worldwide.A waste-related assessment of the IPCC report series from 1990 to 2023 revealed a paradigm shift in the covered waste management strategies, transitioning from conventional technical disposal methods towards holistic approaches that align with the principles of sustainability encapsulated in the SDGs. The focus in the reports moves upwards the “waste management hierarchy”, fostering circular economy. Indirectly, this leads to seemingly less focus on landfills and waste dumps despite their high share of greenhouse gas emissions and particularly their strong representation in low/lower middle-income countries, which is still expected to increase during the next years.

CD-MAE: Contrastive Dual-Masked Autoencoder Pre-Training Model for PCB CT Image Element Segmentation

Element detection is an important step in the process of the non-destructive testing of printed circuit boards (PCB) based on computed tomography (CT). Compared with the traditional manual detection method, the image semantic segmentation method based on deep learning greatly improves efficiency and accuracy. However, semantic segmentation models often require a large amount of data for supervised training to generalize better model performance. Unlike natural images, the PCB CT image annotation task is more time-consuming and laborious than the semantic segmentation task. In order to reduce the cost of labeling and improve the ability of the model to utilize unlabeled data, unsupervised pre-training is a very reasonable and necessary choice. The masked image reconstruction model represented by a masked autoencoder is pre-trained on the unlabeled data, learning a strong feature representation ability by recovering the masked image, and shows a good generalization ability in various downstream tasks. In the PCB CT image element segmentation task, considering the characteristics of the image, it is necessary to use a model with strong feature robustness in the pre-training stage to realize the representation learning on a large number of unlabeled PCB CT images. Based on the above purposes, we proposed a contrastive dual-masked autoencoder (CD-MAE) pre-training model, which can learn more robust feature representation on unlabeled PCB CT images. Our experiments show that the CD-MAE outperforms the baseline model and fully supervised models in the PCB CT element segmentation task.

Few-Shot Font Generation With Weakly Supervised Localized Representations.

Automatic few-shot font generation aims to solve a well-defined, real-world problem because manual font designs are expensive and sensitive to the expertise of designers. Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style. However, this approach limits the model in representing diverse local styles because it is unsuitable for complicated letter systems. For example, Chinese characters consist of a varying number of components (often called "radical") with a highly complex structure. In this paper, we propose a novel font generation method that learns localized styles, namely component-wise style representations, instead of universal styles. The proposed style representations enable synthesizing complex local details in text designs. However, learning component-wise styles solely from a few reference glyphs is infeasible when a target script has a large number of components, for example, over 200 for Chinese. To reduce the number of required reference glyphs, we represent component-wise styles by a product of component and style factors inspired by low-rank matrix factorization. Owing to the combination of strong representation and a compact factorization strategy, our method shows remarkably better few-shot font generation results (with only eight reference glyphs) than other state-of-the-art methods. Moreover, strong locality supervision was not utilized, such as the location of each component, skeleton, or strokes. The source code is available at https://github.com/clovaai/lffont.

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

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

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

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