Applied Intelligence最新文献

Multi-source medical knowledge adaptive fusion network for combinatorial medication recommendation 多源医学知识自适应融合网络的组合用药推荐

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-23 DOI: 10.1007/s10489-025-06619-7

Yiming Zhou, Jiedong Wei, Xiaodi Hou, Meiyu Duan, Yijia Zhang

{"title":"Multi-source medical knowledge adaptive fusion network for combinatorial medication recommendation","authors":"Yiming Zhou, Jiedong Wei, Xiaodi Hou, Meiyu Duan, Yijia Zhang","doi":"10.1007/s10489-025-06619-7","DOIUrl":"10.1007/s10489-025-06619-7","url":null,"abstract":"<div><p>Combinatorial medication recommendation has emerged as a significant research direction in artificial intelligence healthcare, demonstrating transformative potential for both pharmaceutical development and clinical decision-making. While promising, its practical implementation faces multifaceted engineering challenges spanning robust data integration, scalable model deployment, and regulatory compliance. Current drug recommendation methodologies predominantly rely on modeling electronic health records (EHRs) to generate patient representations, yet critically fail to incorporate external medical knowledge to enhance recommendation decisions. This limitation results in suboptimal integration between patient-specific data and domain-specific pharmacological knowledge. To address this critical gap in clinical decision support systems, our work pioneers the synergistic fusion of structured EHR patterns with curated medical knowledge bases, thereby enhancing recommendation accuracy and clinical relevance. In this paper, we propose a medication recommendation framework based on a Multi-source medical Knowledge Adaptive Fusion (MKAF) network. The proposed framework leverages patients’ health records and diverse medical knowledge to adaptively model their intrinsic relationships, enhancing recommendation accuracy. Specifically, we first mine patients’ health records to extract patient features. Subsequently, we design a multi-source medical knowledge module that adaptively fuses patients’ health features with various medication knowledge to capture the relationship between clinical symptoms and medications, balancing the contributions of different knowledge sources for better medication recommendations. Extensive experiments conducted on two public datasets MIMIC-III and MIMIC-IV, especially compared to the previous SOTA model, F1, PRAUC, and Jaccard have improved by 1.14%, 1.45%, 1.04% and 0.51%, 1.49%, 0.74% respectively on the two datasets.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144117620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Consensus guided incomplete multi-view clustering via geometric consistency learning 基于几何一致性学习的共识引导不完全多视图聚类

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-21 DOI: 10.1007/s10489-025-06618-8

Huibing Wang, Wei Wang, Mingze Yao, Yawei Chen, Jinjia Peng, Guangqi Jiang, Xianping Fu

{"title":"Consensus guided incomplete multi-view clustering via geometric consistency learning","authors":"Huibing Wang, Wei Wang, Mingze Yao, Yawei Chen, Jinjia Peng, Guangqi Jiang, Xianping Fu","doi":"10.1007/s10489-025-06618-8","DOIUrl":"10.1007/s10489-025-06618-8","url":null,"abstract":"<div><p>Incomplete multi-view clustering (IMC) aims to uncover meaningful cluster structures by leveraging the similarity information within datasets containing multiple, but partially missing, views. While most existing approaches emphasize learning consensus representations to integrate information across views, they often neglect the inherent geometric structure of the data and overlook inter-view correlations among missing samples. Furthermore, such consensus representations may diverge from the true latent structure of the original data. To address these limitations, this study proposes a novel framework known as consensus guided incomplete multi-view clustering via geometric consistency learning (CGIMC). CGIMC seamlessly integrates consensus representation learning and geometric consistency learning into a unified model through connectivity constraints. Specifically, it leverages consensus learning to capture latent data representations, while geometric consistency learning uncovers intrinsic local structures within the high-dimensional data space across views. Additionally, CGIMC adopts a one-step clustering strategy to yield final cluster assignments directly, thereby avoiding suboptimal post-processing steps. Extensive experiments conducted on multiple benchmark datasets demonstrate the superior clustering performance and robustness of the proposed CGIMC method. The source codes and datasets are available at https://github.com/whbdmu/CGIMC.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 8","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144100256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An intelligent MIMO run-to-run controller for semiconductor manufacturing processes based on an enhanced twin-delayed deep deterministic policy gradient algorithm 基于增强型双延迟深度确定性策略梯度算法的半导体制造过程智能MIMO运行控制器

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-09 DOI: 10.1007/s10489-025-06615-x

Zhu Ma, Yonglin Chen, Tianhong Pan

{"title":"An intelligent MIMO run-to-run controller for semiconductor manufacturing processes based on an enhanced twin-delayed deep deterministic policy gradient algorithm","authors":"Zhu Ma, Yonglin Chen, Tianhong Pan","doi":"10.1007/s10489-025-06615-x","DOIUrl":"10.1007/s10489-025-06615-x","url":null,"abstract":"<div><p>Achieving accurate target tracking in semiconductor manufacturing processes with complex nonlinearities, strong coupling, and uncertain disturbance environments poses a formidable challenge to run-to-run (RtR) control. In this study, we propose an innovative approach for the online refinement of multi-input multi-output double exponentially weighted moving average (dEWMA) controllers by applying deep reinforcement learning (DRL) techniques. This method harnesses the dynamic interaction capabilities of DRL with the operational environment, facilitating the adaptive tuning of dEWMA parameters to improve the control performance. To further enhance the learning efficiency of the DRL agent, a lightweight DRL model is proposed by combining the structural control network (SCN) with the twin-delayed deep deterministic policy gradient (TD3) algorithm. The SCN component improves the control efficiency by partitioning the policy network into linear and nonlinear modules, enabling the extraction of both local and global features for more effective control. Accordingly, a composite control strategy that synergizes SCN-TD3 with dEWMA is developed. The effectiveness and superiority of the proposed method are rigorously validated through comprehensive comparisons over various disturbance scenarios in both linear and nonlinear chemical mechanical polishing processes. These findings highlight the potential of the proposed DRL-based approach for intelligent RtR control and contribute to yield improvement in semiconductor manufacturing.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DMC-Watermark: A backdoor richer watermark for dual identity verification by dynamic mask covering DMC-Watermark：通过动态掩码覆盖实现双重身份验证的后门丰富水印

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-09 DOI: 10.1007/s10489-025-06608-w

Yujia Zhu, Ruoxi Wang, Daoxun Xia

{"title":"DMC-Watermark: A backdoor richer watermark for dual identity verification by dynamic mask covering","authors":"Yujia Zhu, Ruoxi Wang, Daoxun Xia","doi":"10.1007/s10489-025-06608-w","DOIUrl":"10.1007/s10489-025-06608-w","url":null,"abstract":"<div><p>With the increasing use of neural networks, the importance of copyright protection for these models has gained significant attention. Backdoor watermarking is one of the key methods for protecting copyright. However, on the one hand, most existing backdoor watermarks are triggered by visual images, making them easily detectable, and therefore vulnerable to various attacks. On the other hand, it is difficult for these methods to carry information related to the creator’s identity which can easily lead to fraudulent claims of ownership. These factors contribute to the vulnerability and limitations of backdoor watermarking. In this paper, we propose DMC-Watermark, a backdoor richer watermarking method that uses dynamic mask-covered image structures as triggers. Leveraging the semantic preservation of image structure in transformation attacks, we select image structure as triggers. Furthermore, we convert the author-related information into an array of color information and apply it as a mask to the extracted image structures, allowing it to serve as a second layer of verification during the validation phase to resist fraudulent claims of ownership. The final trigger pattern, embedded with author-related image structures, is applied to the selected images in the trigger set, generating a final trigger set that is trained together with clean samples to produce a protected model. The experiments show that the proposed DMC-Watermark performs well in terms of fidelity, invisibility, undetectability, functionality, dual verification and robustness on three different datasets and four representative DNNs, and it has wide applicability and excellent results in high-resolution images.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AEP: An adaptive ensemble P300-BCI classifier based on user-feedback and knowledge-transfer 基于用户反馈和知识转移的自适应集成P300-BCI分类器

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-09 DOI: 10.1007/s10489-025-06612-0

Zhihua Huang, Qingzhi Chen, Xuewei Chen, Wenming Zheng, Zhixiong Lin, Tian-jian Luo

{"title":"AEP: An adaptive ensemble P300-BCI classifier based on user-feedback and knowledge-transfer","authors":"Zhihua Huang, Qingzhi Chen, Xuewei Chen, Wenming Zheng, Zhixiong Lin, Tian-jian Luo","doi":"10.1007/s10489-025-06612-0","DOIUrl":"10.1007/s10489-025-06612-0","url":null,"abstract":"<div><p>As a stable and reliable paradigm, P300-based brain-computer interface (P300-BCI) is expected to play an important role in efforts to replace, restore, enhance, supplement, or improve the natural output of the brain. However, the costly calibration of P300-BCI limits its development. The calibration-free approaches for P300-BCI have become a research focus in the field. In this work, we forwarded our previous study, transferred P300 linear upper confidence bound (TPLUCB), to propose an adaptive ensemble P300-BCI classifier (AEP). This renovation mainly includes a simplified calculation method and a dynamical update strategy. The competitive calculation model in TPLUCB was simplified as a linear calculation model. Based on this, a dynamical update strategy was proposed to facilitate the growth of target domain model and optimize the weights, by which the source domain models and the target domain model are combined as a P300-BCI classifier, <i>i.e.</i> AEP. We conducted the performance evaluation by observing the classifier’s dynamical development and overall performance. The comparison in the two aspects between AEP and TPLUCB demonstrates AEP’s clear advantage over TPLUCB. Without prior calibration, AEP achieved an average ITR exceeding 40 bit/min on electroencephalogram (EEG) data of 20 subjects. This work has provided a better calibration-free approach for P300-BCI and is an important step towards promoting the research on calibration-free BCIs.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MSR-GAN: multi-scales decomposition representations for unsupervised anomaly detection 无监督异常检测的多尺度分解表示

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-08 DOI: 10.1007/s10489-025-06606-y

Dongwei Xu, Tianhao Xia, Jiaye Hou, Yun Xiang, Qi Xuan

{"title":"MSR-GAN: multi-scales decomposition representations for unsupervised anomaly detection","authors":"Dongwei Xu, Tianhao Xia, Jiaye Hou, Yun Xiang, Qi Xuan","doi":"10.1007/s10489-025-06606-y","DOIUrl":"10.1007/s10489-025-06606-y","url":null,"abstract":"<div><p>Time series anomaly detection is crucial in many fields due to the unique combinations and complex multi-scale time-varying features of time series data, which require accurate analysis. However, previous research has failed to adequately address these complexities, lacking effective decomposition and multi-scale modeling to comprehensively capture differences between normal and abnormal time points at various scales. To address this, our study aims to propose an innovative approach, the Multi-Scale Reconstruction Network (MSR-GAN). It features a Multi-Scale Decoupling Module (MTD) to separate input time series into different-scale components and models the reconstruction as parallel full-scale time series recovery. Furthermore, a Reconstructed Residual Collaborative Learning Module (RRCL) is constructed to perform inter-scale interactions by adaptively calculating importance scores for generator weight control. Extensive experiments demonstrate MSR-GAN’s state-of-the-art performance on multiple benchmark datasets for time series anomaly detection, thus providing a more effective solution, enhancing monitoring and handling of abnormal situations in related fields, and promoting the further development of time series analysis techniques.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DFPN: a dynamic fusion prototypical network for few-shot learning DFPN：一种基于少次学习的动态融合原型网络

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-08 DOI: 10.1007/s10489-025-06581-4

Mengping Dong, Fei Li, Zhenbo Li, Xue Liu

{"title":"DFPN: a dynamic fusion prototypical network for few-shot learning","authors":"Mengping Dong, Fei Li, Zhenbo Li, Xue Liu","doi":"10.1007/s10489-025-06581-4","DOIUrl":"10.1007/s10489-025-06581-4","url":null,"abstract":"<div><p>Prototypical networks have been widely adopted for few-shot image classification. However, due to data scarcity, these methods often suffer from bias and struggle to capture discriminative features effectively. To address the problem, we propose a novel <i>dynamic fusion</i> prototypical network (DFPN) that learns more representative prototypes from limited training samples. In particular, we present a dynamic prototypical network that leverages dynamic routing within a meta-learning framework, effectively mapping sample representations to prototype representations. To further enhance prototype estimate, we design a distribution-based fusion strategy that mitigates biased distributions by integrating mean-based prototypes with adaptively generated dynamic prototypes. Moreover, we employ the <i>Yeo-Johnson transformation</i> to make the feature distribution more Gaussian-like, thereby improving representation quality. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our method. Notably, our DFPN achieves state-of-the-art performance on the <i>mini</i>ImageNet dataset, reaching 74.34% accuracy in the 5-way 1-shot setting and 86.56% in the 5-way 5-shot setting. These results demonstrate DFPN can learn more expressive prototypes, significantly advancing few-shot image classification performance.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Structural decomposition-based learning of large bayesian networks for detecting conditionally independent overlapping superstructure communities 基于结构分解的大型贝叶斯网络检测条件独立重叠上层建筑群体

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-08 DOI: 10.1007/s10489-025-06601-3

Xiaolong Jia, Hongru Li

{"title":"Structural decomposition-based learning of large bayesian networks for detecting conditionally independent overlapping superstructure communities","authors":"Xiaolong Jia, Hongru Li","doi":"10.1007/s10489-025-06601-3","DOIUrl":"10.1007/s10489-025-06601-3","url":null,"abstract":"<div><p>Community detection is an advanced technique that is employed to facilitate the structural decomposition of large Bayesian networks and enable their learning processes. According to the nonoverlapping community characteristics of Bayesian networks, these networks are broken down into several nonoverlapping smaller subgraphs for learning. However, the learning results of this method are still poor because Bayesian networks are composed of overlapping subgraphs that share causal nodes. A unique decomposition method is introduced in this paper for learning large Bayesian network structures; this approach relies on the principles of overlapping community detection and superstructures. First, to preserve more true dependence relationships so that adjacent nodes are not separated, we present an algorithm for constructing a superstructure, which is an undirected independent graph. Second, to prevent the common parent nodes from being separated, we present a conditionally independent overlapping community detection algorithm to break the superstructure into some overlapping subgraphs. Finally, the subgraphs are individually learned and eventually combined into a whole network. To validate the effectiveness of our method, we conduct a comparative analysis against other famous methods using benchmark networks and large real-world datasets with thousands of variables. The experimental results demonstrate that our method outperforms the state-of-the-art methods.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143919168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Linear self-attention with multi-relational graph for knowledge graph completion 基于多关系图的线性自关注知识图补全

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-07 DOI: 10.1007/s10489-025-06592-1

Weida Liu, Baohua Qiang, Ruidong Chen, Yuan Xie, Lirui Chen, Zhiqin Chen

{"title":"Linear self-attention with multi-relational graph for knowledge graph completion","authors":"Weida Liu, Baohua Qiang, Ruidong Chen, Yuan Xie, Lirui Chen, Zhiqin Chen","doi":"10.1007/s10489-025-06592-1","DOIUrl":"10.1007/s10489-025-06592-1","url":null,"abstract":"<div><p>Knowledge graph completion (KGC) aims to infer missing facts based on the existing knowledge. Graph Convolutional Networks (GCNs) have gained significant traction due to their proficiency in effectively modeling graph structures, especially within the realm of Knowledge Graph Completion (KGC). In GCN-based KGC methodologies, GCNs are initially employed to generate comprehensive representations of entities, followed by the application of Knowledge Graph Embedding (KGE) models to elucidate the interactions among entities and relations. However, most GCN-based KGC models ignore the long-range pairwise relationships in the graph. To address these limitations and enhance KGC, we propose a model called Linear Self-Attention with Multi-Relational Graph Network (LTRGN). Specifically, this model merges GCN and linear self-attention to serve as the encoder. This model introduces a linear self-attention that can capture long-range node dependencies without introducing excessive computational overhead. Furthermore, we implement an attention mechanism designed to better assess the significance of various neighboring nodes relative to the source node. We demonstrate the effectiveness of the proposed LTRGN on the standard FB15k-237, WN18RR, Kinship, and UMLS datasets. On the dense graphs Kinship and UMLS, the MRR of our model improves by 1.3% and 4.1%, respectively, while Hits@1 increases by 1.7% and 6.4% compared to the best-performing model. The results show the efficacy of the model for the KGC task. The code is released at https://github.com/lixianqingliuyan/LTRGN.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NLC-block: Enhancing neural network training robustness with noisy label reweighting nlc块：用带噪声标签重加权增强神经网络训练鲁棒性

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-05-07 DOI: 10.1007/s10489-025-06594-z

Ben Liu, Qiao Hu

引用次数: 0