Knowledge-Based Systems最新文献

{"title":"FactorVQVAE: Discrete latent factor model via Vector Quantized Variational Autoencoder","authors":"Namhyoung Kim,&nbsp;Seung Eun Ock,&nbsp;Jae Wook Song","doi":"10.1016/j.knosys.2025.113460","DOIUrl":"10.1016/j.knosys.2025.113460","url":null,"abstract":"<div><div>This study introduces FactorVQVAE, the first integration of the Vector Quantized Variational Autoencoder (VQVAE) into factor modeling, providing a novel framework for predicting cross-sectional stock returns and constructing systematic investment portfolios. The model employs a two-stage architecture to improve the extraction and utilization of latent financial factors. In the first stage, an encoder–decoder-quantizer compresses high-dimensional input data into discrete latent factors through vector quantization, addressing posterior collapse and ensuring distinct representations. In the second stage, an autoregressive Transformer captures sequential dependencies among these latent factors, enabling precise return predictions. Empirical results in the CSI300 and S&amp;P500 markets demonstrate FactorVQVAE’s superior performance. The model achieves the best Rank IC and Rank ICIR scores, surpassing the state-of-the-art latent factor models in varying market conditions. In portfolio evaluations, FactorVQVAE consistently excels in both Top-<span><math><mi>k</mi></math></span> Drop-<span><math><mi>n</mi></math></span> and Long–Short strategies, translating predictive accuracy into robust investment performance. In particular, it delivers the highest risk-adjusted returns, highlighting its ability to balance returns and risks effectively. These findings position FactorVQVAE as a significant advancement in integrating modern deep learning methodologies with financial factor modeling. Its adaptability, robustness, and exceptional performance in portfolio investment establish it as a promising tool for systematic investing and financial analytics.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113460"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835326","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":"Temporal knowledge graph fusion with neural ordinary differential equations for the predictive maintenance of electromechanical equipment","authors":"Jiawei Lu ,&nbsp;Hanyuan Chen ,&nbsp;Jianwei Chen ,&nbsp;Zhongcheng Xiao ,&nbsp;Ren Li ,&nbsp;Gang Xiao ,&nbsp;Qibing Wang","doi":"10.1016/j.knosys.2025.113450","DOIUrl":"10.1016/j.knosys.2025.113450","url":null,"abstract":"<div><div>Predictive Maintenance is the primary strategy for optimizing operational efficiency and reducing the maintenance costs of electromechanical equipment. However, existing Predictive Maintenance approaches suffer from significant shortcomings, such as the inability to learn the dynamic evolution of fault and maintenance events within massive, heterogeneous datasets and the lack of effective models to handle this complex data. To address these issues, we propose a temporal knowledge graph (TKG) reasoning method. First, we construct a TKG based on an ontology defined by the heterogeneous data features of electromechanical equipment. Second, we propose a Dynamic Graph Embedding model, which captures the dynamic evolution of the non-equal-interval events in the TKG by combining neural ordinary differential equations with a graph convolutional neural network. Furthermore, we design a Dynamic Hawkes Transformer to identify the evolutionary process and predicting future events based on historical fault and maintenance data. Finally, we use elevators as a case study to compare the proposed method with other advanced methods and demonstrate its effectiveness in TKG reasoning. Our proposed method excels in fault and maintenance event prediction, as well as time prediction, for electromechanical equipment.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113450"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821291","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":"Textual semantics enhancement adversarial hashing for cross-modal retrieval","authors":"Lei Zhu ,&nbsp;Runbing Wu ,&nbsp;Deyin Liu ,&nbsp;Chengyuan Zhang ,&nbsp;Lin Wu ,&nbsp;Ying Zhang ,&nbsp;Shichao Zhang","doi":"10.1016/j.knosys.2025.113303","DOIUrl":"10.1016/j.knosys.2025.113303","url":null,"abstract":"<div><div>Supervised cross-modal hashing seeks to embed rich semantic information into binary hash codes, thereby enhancing semantic discrimination. Despite substantial advancements in cross-modal semantic learning, two critical challenges remain: (1) the fine-grained semantic information inherent in individual words within text contents is underutilized; and (2) more efficient constraints are required to mitigate the distributional heterogeneity across modalities. To overcome these issues, we introduce a <u><strong>T</strong></u>extual <u><strong>S</strong></u>emantics <u><strong>E</strong></u>nhancement <u><strong>A</strong></u>dersarial <u><strong>H</strong></u>ashing method, abbreviated as <strong>TSEAH</strong>, aimed at further improving hashing retrieval performance. Our approach introduces an effective textual semantics enhancement strategy involving a Bag-of-Words Self-Attention (BWSA) mechanism, which accentuates fine-grained semantics from textual content. This mechanism facilitates the transfer of fine-grained semantic knowledge from texts to images. Furthermore, we incorporate an adversarial hashing strategy within the cross-modal hashing learning process to ensure semantic distribution consistency across different modalities. Importantly, our solution achieves impressive results without the need for complex visual-language pre-training models. Comparative evaluations across three commonly used datasets demonstrate that our method achieves outstanding average accuracy: 90.41<span><math><mtext>%</mtext></math></span> on MIRFLICKR-25K, 82.86<span><math><mtext>%</mtext></math></span> on NUW-SIDE, and 83.53<span><math><mtext>%</mtext></math></span> on MS COCO, outperforming the state-of-the-art baselines by a significant margin ranging from 1.97<span><math><mtext>%</mtext></math></span> to 2.51<span><math><mtext>%</mtext></math></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113303"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143824293","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":"PRADA: Prompt-guided Representation Alignment and Dynamic Adaption for time series forecasting","authors":"Yinhao Liu ,&nbsp;Zhenyu Kuang ,&nbsp;Hongyang Zhang ,&nbsp;Chen Li ,&nbsp;Feifei Li ,&nbsp;Xinghao Ding","doi":"10.1016/j.knosys.2025.113478","DOIUrl":"10.1016/j.knosys.2025.113478","url":null,"abstract":"<div><div>Time series forecasting endeavors to construct models capable of predicting future values and trends grounded in historical observations. However, current LLM-based approaches migrate the inference power of LLM to the time series forecasting through prompt guidance, but ignore the modality gap between time series and natural language. This gap arises from the fact that time series have periodic and non-periodic patterns that are not present in natural language, hindering the capabilities of LLM-based models. In addition, the potential statistical property drift in time series makes the model rely on spurious correlation features, limiting the capture of spatio-temporal dependencies. To tackle the unique problems, we introduce the Prompt-guided Representation Alignment and Dynamic Adaption (PRADA) method, which harnesses multi-view Text-Series Adaptive Alignment (TSAA) guided by learnable prompts to capture the representations of different patterns. Specifically, we first decompose the input time series into different components and align orthogonal prompts consisting of learnable context vectors with time series embeddings independently for LLM’s input adaption. Furthermore, the time-frequency dual constraint is introduced to empower the model to capture the overlooked label autocorrelation from both the time and frequency domains. Through multi-view adaptive alignment guided by learnable prompts, PRADA is able to dynamically model spatio-temporal dependencies and adapt to the semantic gap between time series and natural language, which enables LLM-based models to obtain more robust times series representations in real scenarios. Experiments on multiple public datasets demonstrate the state-of-the-art (SOTA) performance of PRADA in time series forecasting. The code will be available at <span><span>https://github.com/HowardLiu28/PRADA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113478"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851970","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":"Balance recovery and collaborative adaptation approach for federated fault diagnosis of inconsistent machine groups","authors":"Bin Yang ,&nbsp;Yaguo Lei ,&nbsp;Naipeng Li ,&nbsp;Xiang Li ,&nbsp;Xiaosheng Si ,&nbsp;Chuanhai Chen","doi":"10.1016/j.knosys.2025.113480","DOIUrl":"10.1016/j.knosys.2025.113480","url":null,"abstract":"<div><div>Due to data privacy concerns and long-distance communication overhead, federated learning-based intelligent diagnosis offers a promising solution for ensuring the efficiency and reliability of machine groups in data decentralization. However, the data information from different machine nodes in a group are often inconsistent, leading to two key challenges in current federated intelligent diagnosis research: (1) data imbalance especially with respect to unseen faults, which causes the diagnosis model to become skewed, and (2) label space shifts across machine nodes, resulting in significant misalignment between the local and global distributions. As a consequence, the global diagnosis model struggles to effectively recognize unseen and under-represented fault states, and is often under-generalized to other machine nodes, especially when only a limited number of labeled samples are available. To address these challenges, this article presents a balance recovery and collaborative adaptation (BRCA) framework for federated intelligent diagnosis. The BRCA framework utilizes a central server to capture the inconsistent distribution information from each machine node, and further solves the Wasserstein barycenter to create a global distribution that carries complementary information. This barycenter is then broadcast to the client side to guide local model updates. At each client, convolutional autoencoders are constrained to supplement synthetic data for unseen and under-represented fault states, helping to restore a balanced decision boundary. Moreover, local distributions are aligned with the global barycenter through the designed adaptation trajectory that directionally ties subcategories with the same label. This is expected to correct discrepancies caused by label space shifts. The proposed BRCA is demonstrated in two federated intelligent diagnosis cases: one involving diverse machine-used bearings and the other involving different planetary gearboxes. The results show that BRCA can mitigate the performance degradation caused by data inconsistency, and achieve higher diagnosis accuracy than existing federated methods on other machine nodes even when there are very few labeled samples available.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113480"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816271","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":"CTSE-Net: Resource-efficient convolutional and TF-transformer network for speech enhancement","authors":"Nasir Saleem ,&nbsp;Sami Bourouis ,&nbsp;Hela Elmannai ,&nbsp;Abeer D. Algarni","doi":"10.1016/j.knosys.2025.113452","DOIUrl":"10.1016/j.knosys.2025.113452","url":null,"abstract":"<div><div>Deep Neural Networks (DNNs) are powerful tools in real-time speech enhancement (SE) since they automatically learn high-level feature representations from raw audio, resulting in significant advancements. Therefore, demand for resource-efficient DNNs for speech enhancement is increasing, mainly using embedded systems. Still, a lightweight and resource-efficient DNN with optimal speech enhancement performance is a challenging task. Dual-path attention-driven architectures have shown notable performance in SE, primarily because of their ability to capture time and frequency dependencies. This paper proposes a resource-efficient SE using a codec-based dual-path time–frequency transformer (CTSE-Net) to improve noisy speech and apply it to speech recognition tasks. The proposed SE employs a codec (coder–decoder) architecture with feature calibration in skip connections to obtain fine-grained frequency components. The codec is interconnected using a dual-path time–frequency transformer incorporating time and frequency attentions. The encoder encodes a time–frequency (T–F) representation derived from the distorted compressed speech spectrum, whereas the decoder estimates the compressed magnitude spectrum of enhanced speech. Further, dedicated speech activity detection (SAD) is employed to identify speech segments in the input signals. By distinguishing speech from background noise or silence, the SAD block provides important information to the decoder for target speech enhancement. The proposed resource-efficient approach ensures attention across time–frequency and distinguishes speech from background noise, leading to more effective denoising and enhancement. Experiments indicate that CTSE-Net shows robust noise reduction and contributes to accurate speech recognition. On the benchmark VCTK+DEMAND dataset, the proposed CTSE-Net demonstrates better SE performance, achieving notable improvements in ESTOI (33.69%), PESQ (1.05), and SDR (11.36 dB) over the noisy mixture.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113452"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820499","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":"Temporal Motion and Spatial Enhanced Appearance with Transformer for video-based person ReID","authors":"Haifei Ma ,&nbsp;Canlong Zhang ,&nbsp;Enhao Ning ,&nbsp;Chai Wen Chuah","doi":"10.1016/j.knosys.2025.113461","DOIUrl":"10.1016/j.knosys.2025.113461","url":null,"abstract":"<div><div>For video-based person Re-Identification (Re-ID), how to efficiently extract temporal motion features and spatial appearance features from video sequences is a key issue. Conventional approaches focus on modelling the entire video spatio-temporal features, ignoring the inherent differences between temporal motion features (e.g., gait) that change over time and spatial appearance features (e.g., clothing) that are stable over time in terms of attributes. Because of their different sensitivities in real-world scenarios, conventional approaches often lose critical fine-grained features. To address these issues, we propose a <strong>T</strong>emporal <strong>M</strong>otion and spatial <strong>E</strong>nhanced <strong>A</strong>ppearance with <strong>T</strong>ransformer-based (T<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>MEA) framework for modelling spatial–temporal video discriminative representations. Specifically, (1) Dual-Branch Architecture: The content branch emphasises extracting the overall structure of the video using the spatial–temporal aggregation (STA) module from a global view, whereas the fovea branch focuses on gaining local fine-grained spatio-temporal features. (2) Zero-Parameter Design: the [CLS] Token Channel Shift Interaction (TCSI) module captures the dynamic features and static features between adjacent frames without additional parameters; the Spatial Patches Shift Enhancing (SPSE) module is introduced to enhance appearance features within frame to address occlusion and illumination changes without additional parameters. (3) Spatial–Temporal Interaction: The Cross-Attention Aggregation (CAA) module is proposed to interact between temporal and spatial features and further enrich the spatial–temporal feature representation for video sequences. Extensive experiments on three public Re-ID benchmarks (MARS, iLIDS-VID, and PRID-2011) demonstrate that the proposed framework outperforms several state-of-the-art methods.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113461"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820500","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":"Leveraging evolutionary algorithms with a dynamic weighted search space approach for fraud detection in healthcare insurance claims","authors":"Mohammad Tubishat ,&nbsp;Dina Tbaishat ,&nbsp;Ala’ M. Al-Zoubi ,&nbsp;Abed-Elalim Hraiz ,&nbsp;Maria Habib","doi":"10.1016/j.knosys.2025.113436","DOIUrl":"10.1016/j.knosys.2025.113436","url":null,"abstract":"<div><div>The healthcare industry has been suffering from fraud in many facets for decades, resulting in millions of dollars lost to fictitious claims at the expense of other patients who cannot afford appropriate care. As such, accurately identifying fraudulent claims is one of the most important factors in a well-functioning healthcare system. However, over time, fraud has become harder to detect because of increasingly complex and sophisticated fraud scheme development, data unpreparedness, as well as data privacy concerns. Moreover, traditional methods are proving increasingly inadequate in addressing this issue. To solve this issue a novel evolutionary dynamic weighted search space approach (DW-WOA-SVM) is presented in the current study. The approach has different levels that work simultaneously, where the optimization algorithm is responsible for tuning the Support Vector Machine (SVM) parameters, applying the weighting procedure for the features, and using a dynamic search space to adjust the range values. Tuning the parameters benefits the performance of SVM, and the weighting technique makes it updated with importance and lets the algorithm focus on data structure in addition to optimization objectives. The dynamic search space enhances the search range during the process. Furthermore, large language models have been applied to generate the dataset to improve the quality of the data and address the lack of good dimensionality, helping to enhance the richness of the data. The experiments highlighted the superior performance of this proposed approach than other algorithms.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113436"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816276","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":"Adversarial decoupling domain generalization network for cross-scene hyperspectral image classification","authors":"Hanqing Zhao ,&nbsp;Lianlei Lin ,&nbsp;Junkai Wang ,&nbsp;Sheng Gao ,&nbsp;Zongwei Zhang","doi":"10.1016/j.knosys.2025.113432","DOIUrl":"10.1016/j.knosys.2025.113432","url":null,"abstract":"<div><div>Cross-scene hyperspectral image classification tasks have widely applied domain adaptation (DA) methods. However, DA typically adapts to the specific target scene during training and requires retraining for new scenes. In contrast, recent domain generalization (DG) methods aim to transfer directly to unseen domains, eliminating the requirement for target data during training. Popular DG methods achieve reliable generalization performance by expanding the source distribution. However, since hyperspectral images contain implicit non-causal components, such as label-independent environmental features, the extended samples generated by the source inevitably introduce undesirable inductive biases, which cause the learning of spurious correlations. To address these issues, we design a novel DG network with adversarial decoupling and unbiased semantic extension. Specifically, we first develop a homogeneous dual-branch encoder based on latent adversarial disentanglement, which helps to separate label-dependent causal components and weakly related components and is also applied to simulate domain gaps. Secondly, to decrease the preference of generated samples on category-irrelevant components, we adopt domain-specific instance shuffling to synthesize extension domains so that the new domain can preserve intrinsic causal information while expanding semantic coverage. Furthermore, to augment domain-invariant features to combat spurious correlations, we propose a multi-attribute representation strategy that learns diverse heterogeneous features through inter-domain unsupervised reconstruction and intra-domain supervised aggregation. Extensive experiments were conducted on four datasets, the ablation study shows the effectiveness of the proposed modules, and the comparative analysis with the advanced DG algorithms shows our superiority in the face of various spectral and category shifts. The codes is available from the website: <span><span>https://github.com/HUOWUMO/ADNet_KBS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113432"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860514","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":"Optimizing IoT data collection through federated learning and periodic scheduling","authors":"Darya AzharShokoufeh ,&nbsp;Nahideh DerakhshanFard ,&nbsp;Fahimeh RashidJafari ,&nbsp;Ali Ghaffari","doi":"10.1016/j.knosys.2025.113526","DOIUrl":"10.1016/j.knosys.2025.113526","url":null,"abstract":"<div><div>The Internet of Things (IoT) describes a system of interlinked devices, sensors, and intelligent systems that facilitate intricate management in smart homes, industries, and cities. The devices constantly gather basic information like temperature, humidity, geographical location, and energy consumption to facilitate analytics and decision-making. However, traditional data collection methods, such as direct information transfer to a central server, face significant challenges regarding bandwidth use, energy efficiency, data security, reliability, and overall performance. These methods require robust communication infrastructures, often leading to network resource overexploitation due to raw data transmission. Although edge computing, fog computing, fedHGL, and centralized learning methods are considered modern techniques offering some advantages, they still require complex infrastructures and have the same difficulties processing heterogeneous or big datasets. Periodic scheduling is a new paradigm for federated learning, where the data will be processed locally, and only the updated model weights will be transferred to the central server. This approach significantly reduces bandwidth and energy consumption and facilitates faster model updates, enhancing the overall performance of IoT networks. Simulation results demonstrate that our proposed federated learning approach outperforms the other considered approaches on both MNIST and RT-IoT2022 datasets. It achieves on MNIST an accuracy improvement of 12 %, a reduction in convergence time of 22 %, and a bandwidth usage reduction of 21 %; and on RT-IoT2022, an accuracy enhancement of 9 %, a convergence time reduction of 18 %, and a bandwidth usage reduction of 25 %, confirming its overall superiority for IoT systems.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"317 ","pages":"Article 113526"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830200","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}