Applied Intelligence最新文献_第5页

Interpretable multi-agent reinforcement learning via multi-head variational autoencoders

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-26 DOI: 10.1007/s10489-025-06473-7

Peizhang Li, Qing Fei, Zhen Chen

{"title":"Interpretable multi-agent reinforcement learning via multi-head variational autoencoders","authors":"Peizhang Li, Qing Fei, Zhen Chen","doi":"10.1007/s10489-025-06473-7","DOIUrl":"10.1007/s10489-025-06473-7","url":null,"abstract":"<div><p>Multi-agent deep reinforcement learning (RL) is increasingly proficient at making collective decisions in complex systems. However, the black-box nature of DRL decision networks often renders agent behaviors difficult to interpret, thereby undermining human trust. Although several reinforcement learning explanation methods have been proposed, most mainly identify factors influencing decisions without elucidating the underlying causal mechanisms based on physical models. Moreover, these methods do not address the generalizability of interpretability within multi-agent system settings. To overcome these challenges, we propose a multi-agent RL network based on multi-head variational autoencoders (MVAE), which generates decisions with interpretable physical semantics for unmanned systems. The MVAE directly encodes multiple types of semantically meaningful features with physical interpretations from the latent space and generates decisions by integrating these semantics according to physical models. Furthermore, considering the different latent variable distributions in continuous and discrete action scenarios, we design two distinct MVAE models based on Gaussian and Dirichlet distributions, respectively, and design training frameworks using deterministic policy gradient networks and proximal policy optimization networks in a multi-agent environment. Additionally, we develop a visualization method to intuitively convey interpretability in both continuous and discrete action scenarios. Simulation experiments comparing our method with existing baselines demonstrate that our approach achieves superior decision-making performance under interpretability conditions, and further validate its performance in large-scale scenarios.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698477","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

Effective selection of public IoT services by learning uncertain environmental factors using fingerprint attention

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-26 DOI: 10.1007/s10489-025-06472-8

KyeongDeok Baek, In-Young Ko

{"title":"Effective selection of public IoT services by learning uncertain environmental factors using fingerprint attention","authors":"KyeongDeok Baek, In-Young Ko","doi":"10.1007/s10489-025-06472-8","DOIUrl":"10.1007/s10489-025-06472-8","url":null,"abstract":"<div><p>The scope of the Internet of Things (IoT) environment has been expanding from private to public spaces, where selecting the most appropriate service by predicting the service quality has become a timely problem. However, IoT services can be physically affected by (1) uncertain environmental factors such as obstacles and (2) interference among services in the same environment while interacting with users. Using the traditional modeling-based approach, analyzing the influence of such factors on the service quality requires modeling efforts and lacks generalizability. In this study, we propose <i>Learning Physical Environment factors based on the Attention mechanism to Select Services for UsERs (PLEASSURE)</i>, a novel framework that selects IoT services by learning the uncertain influence and predicting the long-term quality from the users’ feedback without additional modeling. Furthermore, we propose <i>fingerprint attention</i> that extends the attention mechanism to capture the physical interference among services. We evaluate PLEASSURE by simulating various IoT environments with mobile users and IoT services. The results show that PLEASSURE outperforms the baseline algorithms in rewards consisting of users’ feedback on satisfaction and interference.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06472-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

WMFusion: a W-shaped dual encoder and single decoder network for multimodal medical image fusion

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-26 DOI: 10.1007/s10489-025-06477-3

Yu Shao, Lei Yu, Haozhe Tang

{"title":"WMFusion: a W-shaped dual encoder and single decoder network for multimodal medical image fusion","authors":"Yu Shao, Lei Yu, Haozhe Tang","doi":"10.1007/s10489-025-06477-3","DOIUrl":"10.1007/s10489-025-06477-3","url":null,"abstract":"<div><p>The current deep learning-based multimodal medical image fusion algorithms usually use a single feature extractor to extract features from images of different modalities. However, these approaches tend to overlook the distinctive features of different modality medical images, resulting in feature loss. In addition, applying complex network structures to low-level image-processing tasks would waste computational power. Therefore, we innovatively design an end-to-end multimodal fusion network with a dual encoder and single decoder structure, which resembles the letter ‘W’, and we have termed WMFusion. Specifically, we first develop a multi-scale context dynamic feature extractor (MCDFE) that employs context-gated convolution to extract multiscale features from different modalities effectively. Subsequently, we propose a local-global feature fusion module (LGFM) for fusing features of different scales, and we design a cross-modality bidirectional interaction structure in the local branch. Finally, feature redundancy is suppressed and the fusion image is reconstructed by a spatial channel reconstruction module (SCRM) with a spatial and channel reconstruction unit. A large number of experimental results demonstrate that our proposed WMFusion method is superior to some state-of-the-art algorithms in terms of both subjective and objective evaluation metrics, and has satisfactory computation efficiency.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698478","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

IAMTrack: interframe appearance and modality tokens propagation with temporal modeling for RGBT tracking

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-26 DOI: 10.1007/s10489-025-06438-w

Huiwei Shi, Xiaodong Mu, Hao He, Chengliang Zhong, Bo Zhang, Peng Zhao

{"title":"IAMTrack: interframe appearance and modality tokens propagation with temporal modeling for RGBT tracking","authors":"Huiwei Shi, Xiaodong Mu, Hao He, Chengliang Zhong, Bo Zhang, Peng Zhao","doi":"10.1007/s10489-025-06438-w","DOIUrl":"10.1007/s10489-025-06438-w","url":null,"abstract":"<div><p>RGBT tracking has emerged as a robust solution for various applications, including surveillance, autonomous driving, and robotics, owing to its resilience in challenging environments. However, existing RGBT tracking approaches often overlook target appearance changes, location shifts, and the dynamic significance of modality features, limiting long-term tracking accuracy. To address these limitations, we propose IAMTrack, a novel transformer-based framework that achieves sequential tracking by propagating modality and appearance tokens across frames. The method compresses the discriminative features of each modality into modality tokens to transmit modality quality and target location information in real time, allowing the model to focus more on features with high modality quality and features with high target probability, while suppressing noise and redundant information. It also compresses the appearance features of objects similar in appearance across frames into appearance tokens to convey changes in appearance. To further enhance the token learning capability, we design a temporal generalized relation modelling approach that guides future predictions based on past information. The experimental results show that IAMTrack outperforms existing methods in various RGBT tracking scenarios, especially in UAV tracking tasks. Compared with those of previous methods, the MPRs and MSRs of the VTUAV short-term and long-term subdatasets are improved by <span>(1.7%/2.1%)</span> and <span>(2.5%/2.2%)</span>, respectively.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06438-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143707040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Probabilistic linguistic hesitant fuzzy multi-attribute decision making for rural revitalization project selection of China

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-25 DOI: 10.1007/s10489-025-06305-8

Jiu-Ying Dong, Si-Hang Gong, Shu-Ping Wan

{"title":"Probabilistic linguistic hesitant fuzzy multi-attribute decision making for rural revitalization project selection of China","authors":"Jiu-Ying Dong, Si-Hang Gong, Shu-Ping Wan","doi":"10.1007/s10489-025-06305-8","DOIUrl":"10.1007/s10489-025-06305-8","url":null,"abstract":"<div><p>Rural revitalization strategy has pointed out the right direction for solving Chinese \"three rural\" problems. Selecting the most suitable rural revitalization project can be regarded as a multi-attribute decision making (MADM) problem. This paper utilizes the probabilistic linguistic (PL) hesitant fuzzy sets (PLHFSs) to characterize the uncertain information of evaluating rural revitalization projects. PLHFS introduces the characteristics of linguistic hesitant fuzzy set (LHFS) into probabilistic linguistic term set (PLTS), which can represent the membership degrees of linguistic terms (LTs) and the associated probabilities to the set, simultaneously. The normalized and ordered PLHFS is proposed. Some new operation laws for PLHFSs are defined by using Archimedean T-norm and T-conorm (ATT) functions. By employing the Maclaurin symmetric mean (MSM) operator and power average (PA) operator, this paper develops a probabilistic linguistic hesitant fuzzy Archimedean power Maclaurin symmetric mean (PLHFAPMSM) operator and a probabilistic linguistic hesitant fuzzy Archimedean power weighted Maclaurin symmetric mean (PLHFAPWMSM) operator. Some desirable properties of the PLHFAPMSM and PLHFAPWMSM operators are discussed deeply. For MADM with PLHFSs, the individual attribute weight vector for each alternative is derived by data envelopment analysis (DEA). Further, the comprehensive attribute weight vector is determined by a linear goal programming model. Thereby, using the PLHFAPWMSM operator, a new method for MADM with PLHFSs is proposed. Finally, a practical example of rural revitalization project selection is analyzed to illustrate the effectiveness and feasibility of the proposed method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698485","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

Dual-layer contrastive learning for aspect-aligned multimodal sentiment analysis

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-25 DOI: 10.1007/s10489-025-06483-5

Junjun Guo, Zida Yan, Guanghua Zhang

{"title":"Dual-layer contrastive learning for aspect-aligned multimodal sentiment analysis","authors":"Junjun Guo, Zida Yan, Guanghua Zhang","doi":"10.1007/s10489-025-06483-5","DOIUrl":"10.1007/s10489-025-06483-5","url":null,"abstract":"<div><p>Multi-modal Aspect-Based Sentiment Analysis (MABSA) aims to identify the sentiment polarity of aspects by incorporating visual information into text. Image and text are two types of modality information with significant modality gaps in both data form and semantic expression. Narrowing the modality gaps and feature fusion are two crucial challenges in MABSA. To address these issues, this paper introduces an aspect-enhanced alignment and fusion strategy with dual-layer contrastive learning to tackle the cross-modal fusion problem. Unlike traditional contrastive learning methods, our approach increases the number of negative samples, enabling the model to learn more discriminative features and better capture fine-grained cross-modal relationships. The proposed approach leverages overlapping aspect information as multi-modal pivots to first bridge the modality gaps and then integrate visual and text information in the multi-modal feature space, thereby improving multi-modal sentiment analysis performance. We first introduce an aspect-guided modality alignment strategy that narrows the fundamental modality gaps between image and text using modality contrastive learning. Then, we design an aspect-oriented multi-modal fusion approach to promote cross-modal feature fusion through symmetric cross-modal interaction. Extensive experiments demonstrate that the proposed approach outperforms other state-of-the-art (SOTA) MABSA methods on three MABSA benchmark datasets. In-depth analysis further validates the effectiveness of the proposed multi-modal fusion approach for MABSA.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688501","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

Multi-view clustering with filtered bipartite graph

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-25 DOI: 10.1007/s10489-025-06476-4

Jintian Ji, Hailei Peng, Songhe Feng

{"title":"Multi-view clustering with filtered bipartite graph","authors":"Jintian Ji, Hailei Peng, Songhe Feng","doi":"10.1007/s10489-025-06476-4","DOIUrl":"10.1007/s10489-025-06476-4","url":null,"abstract":"<div><p>The key challenge of graph-based multi-view clustering methods lies in how to capture a consensus clustering structure. Although existing methods have achieved good performances, they still share the following limitations: 1) The high computational complexity caused by large graph leaning. 2) The contaminated information in different views reduces the consistency of the fused graph. 3) The two-stage clustering strategy leads to sub-optimal solutions and error accumulation. To solve the above issues, we propose a novel multi-view clustering algorithm termed Multi-View Clustering with Filtered Bipartite Graph (MVC-FBG). In the graph construction stage, we select representative anchors to construct anchor graphs with less space complexity. Then we explicitly filter out the contaminated information to preserve the consistency in different views. Moreover, a low-rank constraint is imposed on the Laplacian matrix of the unified graph to obtain the clustering results directly. Furthermore, we design an efficient alternating optimization algorithm to solve our model, which enjoys a linear time complexity that can scale well with the data size. Extensive experimental results on different scale datasets demonstrate the effectiveness and efficiency of our proposed method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688522","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

Unveiling the frontiers of deep learning: Innovations shaping diverse domains

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-25 DOI: 10.1007/s10489-025-06259-x

Shams Forruque Ahmed, Md. Sakib Bin Alam, Maliha Kabir, Shaila Afrin, Sabiha Jannat Rafa, Aanushka Mehjabin, Amir H. Gandomi

{"title":"Unveiling the frontiers of deep learning: Innovations shaping diverse domains","authors":"Shams Forruque Ahmed, Md. Sakib Bin Alam, Maliha Kabir, Shaila Afrin, Sabiha Jannat Rafa, Aanushka Mehjabin, Amir H. Gandomi","doi":"10.1007/s10489-025-06259-x","DOIUrl":"10.1007/s10489-025-06259-x","url":null,"abstract":"<div><p>Deep learning (DL) allows computer models to learn, visualize, optimize, refine, and predict data. To understand its present state, examining the most recent advancements and applications of deep learning across various domains is essential. However, prior reviews focused on DL applications in only one or two domains. The current review thoroughly investigates the use of DL in four different broad fields due to the plenty of relevant research literature in these domains. This wide range of coverage provides a comprehensive and interconnected understanding of DL’s influence and opportunities, which is lacking in other reviews. The study also discusses DL frameworks and addresses the benefits and challenges of utilizing DL in each field, which is only occasionally available in other reviews. DL frameworks like TensorFlow and PyTorch make it easy to develop innovative DL applications across diverse domains by providing model development and deployment platforms. This helps bridge theoretical progress and practical implementation. Deep learning solves complex problems and advances technology in many fields, demonstrating its revolutionary potential and adaptability. CNN-LSTM models with attention mechanisms can forecast traffic with 99% accuracy. Fungal-diseased mango leaves can be classified with 97.13% accuracy by the multi-layer CNN model. However, deep learning requires rigorous data collection to analyze and process large amounts of data because it is independent of training data. Thus, large-scale medical, research, healthcare, and environmental data compilation are challenging, reducing deep learning effectiveness. Future research should address data volume, privacy, domain complexity, and data quality issues in DL datasets.</p><h3>Graphical Abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06259-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual heterogeneous graph contrastive learning for QoS prediction

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-25 DOI: 10.1007/s10489-025-06431-3

Yuting Xiu, Ding Ding, Ziteng Wu, Yuekun Zhao, Jiaqi Liu

{"title":"Dual heterogeneous graph contrastive learning for QoS prediction","authors":"Yuting Xiu, Ding Ding, Ziteng Wu, Yuekun Zhao, Jiaqi Liu","doi":"10.1007/s10489-025-06431-3","DOIUrl":"10.1007/s10489-025-06431-3","url":null,"abstract":"<div><p>The proliferation of Web Services leads to homogeneity issues, making accurate Quality of Service (QoS) prediction extremely helpful for inexperienced users to choose suitable services. However, the complex relationship between users and services in service invocation poses numerous challenges on QoS prediction. Given the capability of graph neural networks in modeling diverse relationships, a Dual Heterogeneous Graph Contrastive Learning method (DHGCL) is proposed in this paper to achieve high-accuracy QoS prediction. First, a dual heterogeneous graph is innovatively constructed, in which a global interaction graph is generated by a proposed graph learning to enable the direct interactions concerning the distant neighbors, while a local relationship graph is simultaneously constructed to enhance the close associations between users and services through spectral clustering. On this basis, the graph convolution network on the meta-paths is further designed to acquire the embedding of nodes for both of these two graphs. Finally, the global-local contrastive learning is served as a self-supervised mechanism to balance global interaction and local relationship information, and to complete the final QoS prediction. Extensive experiments have proven that our DHGCL method can achieve significantly higher accuracy than most of existing methods with the help of the dual heterogeneous graph.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688538","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

Demystifying the black box: AI-enhanced logistic regression for lead scoring

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-25 DOI: 10.1007/s10489-025-06430-4

Bingran LIU

引用次数: 0