Complex & Intelligent Systems最新文献_第6页

Compound task-class noise in task-agnostic inference for multi-task binary classification: an intuitionistic fuzzy approach 多任务二元分类中任务不可知推理中的复合任务类噪声：一种直觉模糊方法

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-24 DOI: 10.1007/s40747-026-02493-z

Hong Son Nguyen,Khac Trung Nguyen,Ngoc Linh Pham,Ngoc Thang Tran,Ngoc Chi Lê

{"title":"Compound task-class noise in task-agnostic inference for multi-task binary classification: an intuitionistic fuzzy approach","authors":"Hong Son Nguyen,Khac Trung Nguyen,Ngoc Linh Pham,Ngoc Thang Tran,Ngoc Chi Lê","doi":"10.1007/s40747-026-02493-z","DOIUrl":"https://doi.org/10.1007/s40747-026-02493-z","url":null,"abstract":"Abstract Multi-task learning often trains one shared representation across tasks, where each example is annotated with both a task identity and a class label whose meaning depends on that task. In real annotation pipelines, however, wrong task assignment can make the attached class label answer the wrong question, which makes it unreliable. We formalize this setting as compound task-class noise , where errors in the observed task identity can change the interpretation of the observed class label and can couple with ordinary class-label noise, rather than as two independent errors. This is especially problematic for task-agnostic inference, where no task name is supplied and the model must infer which task should interpret the class label. We propose IFS-Hesitant , which uses a hesitation score derived from Intuitionistic Fuzzy Sets as a structured task-fit uncertainty signal that down-weights suspicious task-class pairs during training. By separating task fit from class evidence, the hesitation score can down-weight suspicious supervision during training and can also route the input at inference without an external task classifier. Experiments on different multi-task classification datasets show that the method is competitive with top baselines when the task is given and substantially more robust when the task must be inferred without external task labels. The same hesitation score supports accurate routing and post-hoc corruption detection, suggesting that structured hesitation is a useful primitive for robust binary multi-task learning under coupled task and class noise.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"17 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149049240","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

REF-VMUNetUp: a position-aware mamba network with dynamic upsampling for medical image segmentation REF-VMUNetUp：一个位置感知曼巴网络与动态上采样医学图像分割

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-23 DOI: 10.1007/s40747-026-02515-w

Chuanghua Yang,Hang Yang,Huiying Yuan,Wen Gao,Weijia Li,Zixuan Pan,Yuxiang Li,Xinrui Bai

引用次数: 0

Federated hybrid quantum convolutional neural network for Alzheimer’s disease classification using magnetic resonance imaging 基于磁共振成像的联邦混合量子卷积神经网络阿尔茨海默病分类

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-23 DOI: 10.1007/s40747-026-02499-7

Jahnabi Medhi,Amitava Nag,Anup Kumar Barman,Sukumar Nandi

引用次数: 0

Mitigating client heterogeneity in federated learning: a reinforcement learning approach for efficient client selection 减轻联邦学习中的客户端异质性：一种用于高效客户端选择的强化学习方法

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-23 DOI: 10.1007/s40747-026-02519-6

Haiming Luo,Fu Yan,Yuling Chen,Changgen Peng

引用次数: 0

AffectMoE: continuous valence–arousal soft routing of mixture of experts for emotion-consistent 3D dance generation AffectMoE：连续的价值唤醒软路由的混合专家情绪一致的3D舞蹈生成

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-22 DOI: 10.1007/s40747-026-02490-2

Rui Zhang

引用次数: 0

RViTCANet: a multimodal network for UAV recognition based on millimeter wave radar RCS data RViTCANet：基于毫米波雷达RCS数据的多模态无人机识别网络

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-22 DOI: 10.1007/s40747-026-02526-7

Hongyu Gao,Yujie Huo,Ahmad Najmi Bin Amerhaider Nuar,Junkun Hong

引用次数: 0

Multi-objective evidence construction in retrieval-enhanced question answering: from ranking to subset optimization 检索增强问答中的多目标证据构建：从排序到子集优化

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-21 DOI: 10.1007/s40747-026-02520-z

Qilei Ye,Yan Wang,Chi Chen

引用次数: 0

An aspect-centric, noise-resilient cross-modal dynamic fusion framework for fine-grained sentiment analysis 一个面向细粒度情感分析的以方面为中心、抗噪声的跨模态动态融合框架

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-20 DOI: 10.1007/s40747-026-02521-y

Shuwan Yang,Junjun Guo,Zhengtao Yu,Ran Song

引用次数: 0

Mamba-OrthoNet: unified global–local feature fusion and angular encoding for accurate ship orientation detection Mamba-OrthoNet：统一的全局-局部特征融合和角度编码，用于精确的船舶方向检测

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-19 DOI: 10.1007/s40747-026-02518-7

Jiandan Zhong,Lingfeng Liu,Tao Yu,Zhipeng Yang,Yingxiang Li,Yajuan Xue,Fei Song

{"title":"Mamba-OrthoNet: unified global–local feature fusion and angular encoding for accurate ship orientation detection","authors":"Jiandan Zhong,Lingfeng Liu,Tao Yu,Zhipeng Yang,Yingxiang Li,Yajuan Xue,Fei Song","doi":"10.1007/s40747-026-02518-7","DOIUrl":"https://doi.org/10.1007/s40747-026-02518-7","url":null,"abstract":"Abstract Accurate ship orientation detection in high-resolution remote-sensing imagery is vital for maritime monitoring, traffic management, and search-and-rescue. Yet port scenes are crowded and ships vary in scale: global context separates adjacent ships, while fine local cues identify bow and stern, so either alone is insufficient. Angle regression also suffers from periodicity and the $$0^circ /360^circ $$ 0 ∘ / 360 ∘ discontinuity, causing training instability. We propose Mamba-OrthoNet, integrating a CNN branch with a Mamba state-space branch and gradually fusing them from representation alignment to residual refinement. Orthogonal Feature Fusion (OFF) maps both streams into a shared space and decomposes CNN features to extract detail, reducing redundancy for compatible fusion. Progressive residual enhancement (PRE) aggregates residuals layer by layer to iteratively refine fused features. We adopt FPBiFusion and introduce ConvNorm with CSPRep for stronger multi-scale representations. For angle modeling, dual-granularity ring encoding (DGRE) combines coarse cyclic bins with fine smoothed sub-bins for stable full-range 0 $$^circ $$ ∘ –360 $$^circ $$ ∘ prediction. On DOTA-ORShip, Mamba-OrthoNet achieves 96.3% mAP $$_{50}$$ 50 and 94.8% orientation accuracy, with ablation studies confirming the contributions of OFF, PRE, and DGRE under this benchmark setting.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"102 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149021339","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

Hybrid deep learning framework for AI-generated text detection 用于人工智能生成文本检测的混合深度学习框架

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-18 DOI: 10.1007/s40747-026-02501-2

Muhammad Sohail,Zan Hongying,Niu Guiling,Javed Rashid,Muhammad Abdullah,Ghulam Ali,Muhammad Irfan,AbdulGuddoos S. A. Gaid

引用次数: 0