Complex & Intelligent Systems最新文献_第7页

A multi-channel modal fusion hypergraph convolutional neural network for Tibetan medicinal material classification 基于多通道模态融合超图卷积神经网络的藏药材分类

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-17 DOI: 10.1007/s40747-026-02388-z

JianFu Chen,Jingru Ma,Zhaohui Zhang,Yan Sun,Jiuchang Pei

引用次数: 0

Anomaly detection in smart agricultural control systems using semi-supervised bidirectional encoding 基于半监督双向编码的智能农业控制系统异常检测

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-16 DOI: 10.1007/s40747-026-02512-z

Jun Zhu,Yiyuan Wang,Zhiqing Tao,Qikun Xu,Yuan Rao,Ke Li

引用次数: 0

Micro-video recommendation based on multi-dimensional sequence features in content e-commerce platform 基于多维序列特征的内容电商平台微视频推荐

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-13 DOI: 10.1007/s40747-026-02489-9

Feipeng Guo,Qi Li,Wei Zhou,Bei Wu

引用次数: 0

Causality mining by candidate events extension and multi-level background knowledge 基于候选事件扩展和多层次背景知识的因果关系挖掘

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-10 DOI: 10.1007/s40747-026-02502-1

Wajid Ali,Wanli Zuo,Wang Ying,Gohar Rahman,Inam Ullah

引用次数: 0

3D visual grounding based on active perception 基于主动感知的三维视觉基础

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-10 DOI: 10.1007/s40747-026-02514-x

Liang Geng

引用次数: 0

A double-layer consensus framework for group decision-making with multi-scale fuzzy information and behavioral preferences 具有多尺度模糊信息和行为偏好的群体决策双层共识框架

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-10 DOI: 10.1007/s40747-026-02492-0

Mingxuan Chai,Jianping Fan,Jintao Lu,Meiqin Wu,Rui Cheng,Ruixin Chen

引用次数: 0

Dynamic multi-priority admission scheduling for multimorbid patients: an MDP approach incorporating balking penalties 多病种患者的动态多优先入院安排：一种包含犹豫处罚的MDP方法

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-10 DOI: 10.1007/s40747-026-02476-0

Zhi Li,Feitong Zhou,Xiantao Huang,Yixin Tong,Haixin Li

引用次数: 0

Unsupervised cross-lingual part-of-speech tagging with monolingual corpora only 仅使用单语语料库的无监督跨语言词性标注

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-09 DOI: 10.1007/s40747-026-02498-8

Jianyu Zheng

引用次数: 0

Enhancing TimeXer with TCN and differential attention for multivariate stock forecasting 基于TCN和差分注意力的TimeXer多元股票预测

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-09 DOI: 10.1007/s40747-026-02500-3

Sixing Liu,Quanxiang Lan,Jing Zhang,Wei Feng

{"title":"Enhancing TimeXer with TCN and differential attention for multivariate stock forecasting","authors":"Sixing Liu,Quanxiang Lan,Jing Zhang,Wei Feng","doi":"10.1007/s40747-026-02500-3","DOIUrl":"https://doi.org/10.1007/s40747-026-02500-3","url":null,"abstract":"Abstract Multivariate stock forecasting requires models that can preserve short-lived price dynamics while using auxiliary market variables without amplifying unstable cross-variable relations. TimeXer provides an Endo/Exo dual-branch architecture that separates target-sequence modeling from auxiliary-variable interaction, but its patch-level tokenization may underrepresent fine-grained local transitions, while standard Exo-branch attention may be sensitive to redundant or weakly informative variables. This paper proposes DAT-TimeXer, a structure-aware adaptation of TimeXer for closing-price forecasting. The model introduces a temporal convolutional network before tokenization to encode causal and dilated local temporal patterns at the original resolution, and applies multi-head differential attention exclusively to the Exo branch. By contrasting two independently learned attention maps, the Exo-side module refines auxiliary-variable dependencies before Endo–Exo interaction while preserving target-sequence dynamics in the Endo branch. Experiments are conducted on three Chinese A-share series and nine U.S.-listed stocks using chronological splits, training-only feature screening, and one-step and multi-step forecasting settings. DAT-TimeXer achieves the lowest mean forecasting errors among the compared models in the one-step evaluations and maintains lower errors at horizons of 1, 3, 5, and 10 in the evaluated multi-step tasks. Cross-asset ablation, chronological subperiod, statistical, and attention analyses provide further evidence for the complementary contributions of pre-tokenization TCN enhancement and Exo-specific differential attention. The added components introduce moderate computational overhead relative to TimeXer.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"68 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932514","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

H3C-BEACON: hierarchical hybrid heterogeneous control with Bayesian-elite adaptive coalition network for multi-agent reinforcement learning H3C-BEACON：用于多智能体强化学习的贝叶斯精英自适应联盟网络分层混合异构控制

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-09-08 DOI: 10.1007/s40747-026-02494-y

Basile Bete Mbezele,Ghislain Alo’o Abessolo

{"title":"H3C-BEACON: hierarchical hybrid heterogeneous control with Bayesian-elite adaptive coalition network for multi-agent reinforcement learning","authors":"Basile Bete Mbezele,Ghislain Alo’o Abessolo","doi":"10.1007/s40747-026-02494-y","DOIUrl":"https://doi.org/10.1007/s40747-026-02494-y","url":null,"abstract":"Abstract Multi-agent reinforcement learning (MARL) in partially observable and non-stationary environments requires agents to simultaneously infer hidden states, coordinate under limited communication, and learn stable cooperative policies. While existing approaches typically address these challenges through independent mechanisms, their interactions remain insufficiently exploited. We present H3C-BEACON ( Hierarchical Hybrid Heterogeneous Control with Bayesian-Elite Adaptive Coalition Network ), a unified hierarchical framework for coordination and control in cooperative MARL that jointly integrates communication, probabilistic belief inference, adaptive coalition formation, and policy stabilisation. The framework combines six complementary components: (i) Dynamic Graph Attention Networks (DGAT) for distance-aware communication, (ii) Bayesian belief fusion for hidden-state estimation under partial observability, (iii) spectral coalition formation for adaptive role specialisation, (iv) a dual-critic architecture that separates global coordination from local decision making, (v) RTD++ elite-trajectory anchoring to improve policy optimisation stability, and (vi) bounded entropy control to balance exploration and exploitation. We evaluate H3C-BEACON on three widely used cooperative MARL benchmarks spanning communication-intensive, coordination, and imperfect-information settings. On the Multi-Agent Particle Environments, H3C-BEACON consistently improves coordination quality over MAPPO, achieving a perfect win rate across all five independent random seeds on while improving the best episode reward from $$-6.06pm 0.70$$ - 6.06 ± 0.70 to $$-2.35pm 0.62$$ - 2.35 ± 0.62 . On , the framework substantially reduces performance variability, producing a $$95%$$ 95 % confidence interval approximately $$28times $$ 28 × narrower than MAPPO ( $$pm 0.57$$ ± 0.57 versus $$pm 15.90$$ ± 15.90 ), indicating significantly improved reproducibility across random initialisations. Ablation experiments indicate that each architectural component contributes to overall performance, with win-rate reductions ranging from $$28%$$ 28 % (−DGAT) to $$70%$$ 70 % (−RTD++ or −Coalitions) when individual modules are removed. Under partial observability in Hanabi-full, H3C-BEACON increases the mean score from $$2.29pm 0.23$$ 2.29 ± 0.23 to $$3.96pm 0.82$$ 3.96 ± 0.82 ( $$+73%$$ + 73 % ) while avoiding policy collapse across all runs, suggesting that RTD++ provides effective stabilisation during cooperative learning. Although MAPPO remains superior on StarCraft combat scenarios, a result consistent with the structural characteristics of that environment (homogeneous units, dense global state, and no explicit communication channel that would benefit from DGAT or coalition formation), the overall results indicate that jointly modelling communication, belief estimation, adaptive coalition formation, and stable optimisation provides a robust and effective framework for cooperative MARL in en","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"6 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148932516","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