Knowledge-Based Systems最新文献

{"title":"Numerical treatment of fractional order Buruli ulcer and cholera model by using neural network approach","authors":"Zulqurnain Sabir ,&nbsp;M A Abdelkawy ,&nbsp;Muhammad Asif Zahoor Raja ,&nbsp;M․ R. Ali","doi":"10.1016/j.knosys.2025.113713","DOIUrl":"10.1016/j.knosys.2025.113713","url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of these investigations is to design a neuro computing solver based on the Levenberg-Marquardt backpropagation neural network for the fractional order confection Buruli ulcer and cholera model, which is divided into ten different categories.</div></div><div><h3>Method</h3><div>The numerical solutions of the Buruli ulcer and cholera model are obtained through the reliable stochastic approach. A dataset based Adam scheme is designed that implemented to decrease the mean square error by splitting the data 12%, 12% for both endorsement and testing, while 76% is applied for training. Three cases based on the fractional order values 0.5, 0.7 and 0.9 are used to present the numerical performances of the model. The structure of neural network contains twelve neurons, single layer, and log-sigmoid transfer function for the Buruli ulcer and cholera model.</div></div><div><h3>Results</h3><div>The precision of the proposed scheme is checked using the comparison of the outputs, best validation performances around 10^–06 to 10^–07, and small absolute error as 10^–04 to 10^–06. Moreover, the some test performances based on taking different proportional indices are programmatic to validate the dependability of the solver.</div></div><div><h3>Novelty</h3><div>The proposed Levenberg-Marquardt backpropagation neural network approach together with twelve neurons, single layer, and log-sigmoid transfer function is applied first time for the fractional order Buruli ulcer and cholera model.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113713"},"PeriodicalIF":7.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"“Are the current topic modeling evaluation metrics enough?” Mitigating the limitations of topic modeling evaluation metrics using a multi-perspective game theoretic approach","authors":"Antônio Pereira ,&nbsp;Felipe Viegas ,&nbsp;Diego Roberto Colombo Dias ,&nbsp;Elisa Tuler ,&nbsp;Ana Cláudia Machado ,&nbsp;Guilherme Fonseca ,&nbsp;Marcos André Gonçalves ,&nbsp;Leonardo Rocha","doi":"10.1016/j.knosys.2025.113634","DOIUrl":"10.1016/j.knosys.2025.113634","url":null,"abstract":"<div><div>Topic Modeling (TM) helps extract and organize information from large amounts of textual data by discovering semantic topics from documents. In this article, we delve into issues of <em>topic quality evaluation</em>, responsible for driving the advances in the TM field by assessing the overall quality of the topic generation process. Traditional TM metrics capture the quality of topics by strictly evaluating the words that make up the topics, either syntactically (e.g., NPMI, TF-IDF Coherence) or semantically (e.g., WEP). Here, we investigate whether we are approaching the limits of what the current evaluation metrics can assess regarding TM quality. For this, we perform a comprehensive experimental evaluation, considering three widely used datasets (ACM, 20News, WOS and Books) for which a natural organization of the collection’s documents into semantic classes (topics) does exist. We contrast the quality of topics generated by four traditional and state-of-the-art TM techniques (i.e., LDA, NMF, CluWords, BERTopic and TopicGPT) with each collection’s “natural topic structure”. Our results show that, despite the importance of the current metrics, they could not capture some important idiosyncratic aspects of the TM task, in the case, the capability of the topics to induce a structural organization of the document space into distinct semantic groups, indicating the need for new metrics that consider such aspects. In this sense, we propose incorporating metrics commonly used to evaluate clustering algorithms into the TM evaluation process, relying on some commonalities between TM and clustering tasks. Results highlight the effectiveness of clustering metrics in distinguishing the results of TM techniques when compared to the datasets’<em>ground truth</em> (class organization). However, adopting additional evaluation metrics implies expanding the analysis space. Thus, as a third contribution, we propose consolidating the various metrics into a unified framework, using Game Theory for decision-making, specifically Multi-Attribute Utility Theory (MAUT), which evaluates options based on weighted preferences across multiple criteria, on which the closer to 1, the greater the agreement between the criteria. Our experimental results demonstrate that MAUT allows a more precise assessment of TM quality. The CluWords achieved the best MAUT values for 20News, ACM and WOS collections (i.e., 0.9913, 0.9571 and 0.8684, respectively). While there is a high level of agreement between the metrics in the ACM collection, indicating CluWords as the best solution, there is a low divergence between the metrics in the WOS collection. In this case, evaluating each metric individually would lead to different conclusions, but MAUT shows us that CluWords is the most consistent as a whole, highlighting the benefits of exploring word embeddings for text representations and matrix factorization strategies to induce topics.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113634"},"PeriodicalIF":7.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UV Gaussians: Joint learning of mesh deformation and Gaussian textures for human avatar modeling","authors":"Yujiao Jiang ,&nbsp;Qingmin Liao ,&nbsp;Xiaoyu Li ,&nbsp;Li Ma ,&nbsp;Qi Zhang ,&nbsp;Chaopeng Zhang ,&nbsp;Zongqing Lu ,&nbsp;Ying Shan","doi":"10.1016/j.knosys.2025.113470","DOIUrl":"10.1016/j.knosys.2025.113470","url":null,"abstract":"<div><div>Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While existing NeRF-based methods can achieve high-quality novel view rendering of human models, both training and inference processes are time-consuming. Recent approaches have utilized 3D Gaussians to represent the human body, enabling faster training and rendering. However, they undermine the importance of the mesh guidance and directly predict Gaussians in 3D space with coarse mesh guidance. This hinders the learning procedure of the Gaussians and tends to produce blurry textures. Therefore, this paper proposes UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures. The method utilizes the embedding of UV map to learn Gaussian textures in 2D space, leveraging the capabilities of powerful 2D networks to extract features. Additionally, through an independent Mesh network, the approach optimizes pose-dependent geometric deformations, thereby guiding Gaussian rendering and significantly enhancing rendering quality. A new dataset of human motion has been collected and processed, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that the proposed method achieves state-of-the-art synthesis of novel view and novel pose. The code and data will be made available as open-source.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113470"},"PeriodicalIF":7.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semi-supervised multi-label feature selection via partial label correlation and feature self-representation","authors":"Yao Zhang,&nbsp;Jun Tang,&nbsp;Ziqiang Cao","doi":"10.1016/j.knosys.2025.113632","DOIUrl":"10.1016/j.knosys.2025.113632","url":null,"abstract":"<div><div>In the field of multi-label feature selection (MLFS), semi-supervised learning can effectively reduce the labeling cost and alleviate the negative impacts caused by labeling noise. However, there are complex inherent correlations among labels in multi-label data. Existing semi-supervised MLFS methods fail to fully exploit the limited label information to assist the learning process of pseudo-labels, limiting the accuracy and reliability of pseudo-labels during model training. To address this issue, we design a manifold regularization term based on partial label correlations and integrate it with the instance manifold to jointly guide the learning process of pseudo-labels. In addition, we develop a sparse formulation for feature self-representation to capture dynamic feature correlations. Moreover, we introduce latent representation learning to explore the latent supervisory information within these dynamic feature correlations. Combining all these ingredients, we propose a novel semi-supervised MLFS method named PLCFS (Semi-supervised MLFS via partial label correlation and feature self-representation). Moreover, we theoretically demonstrate the convergence of PLCFS. Finally, extensive experimental results on multiple datasets show that, when 20% of the training samples are labeled, compared with existing advanced methods, PLCFS has achieved an overall performance improvement of 1.06%–4.15% in terms of the average precision metric.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113632"},"PeriodicalIF":7.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intuition meets analytics: Reasoning implicit aspect-based sentiment quadruplets with a dual-system framework","authors":"Zewen Bai ,&nbsp;Yuanyuan Sun ,&nbsp;Changrong Min ,&nbsp;Junyu Lu ,&nbsp;Haohao Zhu ,&nbsp;Liang Yang ,&nbsp;Hongfei Lin","doi":"10.1016/j.knosys.2025.113534","DOIUrl":"10.1016/j.knosys.2025.113534","url":null,"abstract":"<div><div>The implicit sentiments pose a challenge to aspect sentiment quad prediction (ASQP), and replicating human cognitive processes is essential for understanding them. However, existing methods fail to model from a human cognitive perspective, leading to limited performance. Inspired by the dual-process theory in psychology, which identifies two distinct but synergistic modes of reasoning–intuitive and analytic, we present a straightforward and effective strategy-level approach: <strong>Du</strong>al <strong>S</strong>ystem-based <strong>R</strong>easoning framework with Intuitive <strong>R</strong>eactions (D<span>uSR²</span>). This framework includes the <em>Intuitive System</em> based on intuitive reactions and the <em>Analytic System</em> based on complex reasoning. Specifically, we first employ commonsense reasoning tools to estimate human intuitive reactions to enhance the original text, enriching semantic information. Then we integrate the enhanced text with analytic instruction, conducting complex reasoning to capture implicit sentiments. Experimental results show that D<span>uSR²</span> significantly advances the state-of-the-art performance on four datasets of ASQP task. Detailed evaluation confirms the effectiveness, universality, and robustness of D<span>uSR²</span> in handling various scenarios.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113534"},"PeriodicalIF":7.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainability-based graph augmentation for out-of-distribution robustness in digital pathology","authors":"Saba Heidari Gheshlaghi ,&nbsp;Milan Aryal ,&nbsp;Nasim Yahya Soltani ,&nbsp;Masoud Ganji","doi":"10.1016/j.knosys.2025.113640","DOIUrl":"10.1016/j.knosys.2025.113640","url":null,"abstract":"<div><div>Whole slide images (WSIs), which are high-resolution digital representations of tissue samples, present significant challenges for processing because of their gigapixel scale. Recent studies show that graph neural networks (GNNs), which leverage neighborhood information, can enhance cancer classification accuracy in WSIs. However, GNN performance is affected by out-of-distribution (OOD) data, which occurs when the training and testing data are from different sources. Detecting OOD samples in graph data is especially challenging due to its complexity, which makes GNNs vulnerable to performance degradation. To address this issue, we propose a novel data augmentation framework to improve GNN robustness against OOD samples. Our approach augments node features by sampling important subgraphs, simulating potential OOD scenarios during training. Experiments on three public WSI datasets demonstrate significant improvements in graph classification tasks on OOD samples. In this work, one dataset serves as the in-distribution benchmark, while the others represent OOD scenarios. These results highlight the potential of data augmentation to enhance GNN robustness against OOD samples, improving cancer classification in WSIs.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113640"},"PeriodicalIF":7.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CoAPT: Context Attribute words for Prompt Tuning","authors":"Gun Lee ,&nbsp;Subin An ,&nbsp;Sungyong Baik ,&nbsp;Soochahn Lee","doi":"10.1016/j.knosys.2025.113653","DOIUrl":"10.1016/j.knosys.2025.113653","url":null,"abstract":"<div><div>We propose a novel prompt tuning method called <em>CoAPT (Context Attribute words in Prompt Tuning)</em> for few/zero-shot image classification. The core motivation is that attributes are descriptive words with rich information about a given concept. Thus, we aim to enrich text queries of existing prompt tuning methods, improving alignment between text and image embeddings in CLIP embedding space. To do so, <em>CoAPT</em> integrates attribute words as additional prompts within learnable prompt tuning and can be easily incorporated into various existing prompt tuning methods. To facilitate the incorporation of attributes into text embeddings and the alignment with image embeddings, soft prompts are trained together with an additional meta-network that generates input-image-wise feature biases from the concatenated feature encodings of the image–text combined queries. Our experiments demonstrate that <em>CoAPT</em> leads to considerable improvements for existing baseline methods on several few/zero-shot image classification tasks, including base-to-novel generalization, cross-dataset transfer, and domain generalization. Our findings highlight the importance of combining hard and soft prompts and pave the way for future research on the interplay between text and image latent spaces in pre-trained models.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113653"},"PeriodicalIF":7.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FedLGMatch: Federated semi-supervised learning via joint local and global pseudo labeling","authors":"Qing Zhao ,&nbsp;Jielei Chu ,&nbsp;Zhaoyu Li ,&nbsp;Wei Huang ,&nbsp;Zhipeng Luo ,&nbsp;Tianrui Li","doi":"10.1016/j.knosys.2025.113642","DOIUrl":"10.1016/j.knosys.2025.113642","url":null,"abstract":"<div><div>The bulk of existing Federated Learning (FL) algorithms pay attention to supervised setting and assume that clients have fully labeled data. However, it may be impractical for all clients to obtain plenty of labels due to high annotation costs. Hence, the Federated Semi-Supervised Learning (FSSL) as a promising paradigm has better prospect in many realistic applications (e.g. medical scenario). Under Labels-at-Server scenario, most pseudo labeling based FSSL approaches use only the global model to generate pseudo-labels for unlabeled data, while the local models are ignored. When the local data distribution is much more different from the central server (e.g., Non-IID setting), the generated pseudo-labels may contain much noise, thus, resulting in more serious confirmation bias. To tackle the crucial issue, a novel Federated Semi-Supervised Learning via Joint Local and Global Pseudo Labeling (FedLGMatch) framework is proposed in this paper. The prominent advantage of the proposed FedLGMatch is that it allows local models trained in the last communication round to assist global model in generating pseudo-labels, which successfully emphasizes more clean pseudo-label learning at each client. Experimental results also show that FedLGMatch achieves significant performance improvements than other state-of-the-art models on the standard benchmark datasets.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113642"},"PeriodicalIF":7.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143927397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"OD-DDA: Real-Time Object Detector with Dual Dynamic Adaptation in Variable Scenes","authors":"Mengmei Sang ,&nbsp;Shengwei Tian ,&nbsp;Long Yu ,&nbsp;Xin Fan ,&nbsp;Zhezhe Zhu","doi":"10.1016/j.knosys.2025.113611","DOIUrl":"10.1016/j.knosys.2025.113611","url":null,"abstract":"<div><div>Object detection becomes challenging in variable scenarios, such as when object features change and cluttered backgrounds. We propose an object detector with dual dynamic adaptation (OD-DDA) to address these issues and enhance network performance in complex environments. First, we introduce a dynamic feature adaptation (DFA) module at each stage of the network, utilizing large kernel depthwise separable convolutions to capture multiscale contextual information, thereby enhancing the feature extraction capability of the model and effectively addressing object variations across different scenarios. Next, we design a dynamic fine-grained weight adaptation (DFGWA) module, which could selectively learn the fine-grained features of an image and calculate the corresponding weights before feature aggregation, thereby reducing interference among features and enhancing the model’s responsiveness to targets. Through the synergy of these modules, OD-DDA can flexibly handle the challenges faced during the detection of objects in complex scenarios and significantly improve the inference speed. We conduct rigorous experimental comparisons on five datasets, and the results show that OD-DDA exhibits excellent performance in different scenarios. Especially on the UAVDT dataset, <span><math><mrow><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>50</mn></mrow></msub></mrow></math></span> reaches 37.9% and FPS reaches 87.5, proving its ability to balance speed and accuracy.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113611"},"PeriodicalIF":7.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigating over-smoothing in Graph Neural Networks for node classification through Adaptive Early Embedding and Biased DropEdge procedures","authors":"Fateme Hoseinnia ,&nbsp;Mehdi Ghatee ,&nbsp;Mostafa Haghir Chehreghani","doi":"10.1016/j.knosys.2025.113615","DOIUrl":"10.1016/j.knosys.2025.113615","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) are widely used for tasks involving graph-structured data across various fields, including computer vision, biology, social media, and traffic prediction. Despite their substantial success, increasing the depth of GNNs can impair the discriminability of node representations, leading to a decline in performance for node classification tasks. This challenge is partly attributed to a phenomenon known as over-smoothing. This paper introduces an Adaptive Early Embedding (AEE) procedure between Graph Convolutional Network (GCN) layers. This method adaptively halts the aggregation of neighboring nodes before the final layer of the main network. By reducing the over-smoothing of node embeddings, we enhance the distinguishability of the data. Another important contribution of this work is using the inter-class Biased DropEdge (BDE) procedure, which effectively propagates beneficial information. The proposed model based on AEE+BDE can be integrated with baseline message-passing GNN models to mitigate over-smoothing challenges. Our experiments show that the proposed model outperforms baseline models. Additionally, we provide theoretical evidence supporting the effectiveness of the AEE and BDE procedures for node classification tasks.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"320 ","pages":"Article 113615"},"PeriodicalIF":7.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}