Information Processing & Management最新文献_第8页

Evolvable psychology informed neural network for memory behavior modeling 进化心理学为神经网络记忆行为建模提供了信息

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-16 DOI: 10.1016/j.ipm.2025.104312

Xiaoxuan Shen , Zhihai Hu , Qirong Chen , Pei Wang

{"title":"Evolvable psychology informed neural network for memory behavior modeling","authors":"Xiaoxuan Shen , Zhihai Hu , Qirong Chen , Pei Wang","doi":"10.1016/j.ipm.2025.104312","DOIUrl":"10.1016/j.ipm.2025.104312","url":null,"abstract":"<div><div>Memory behavior modeling is a fundamental issue in the fields of cognitive psychology and education. Classical theoretical models of memory are characterized by insufficient accuracy and ongoing controversies, while data-driven memory modeling methods often require large amount of training data and lack interpretability, highlighting the need for new approaches to memory behavior modeling. This paper integrates classic psychological theories of memory to explore the feasibility of knowledge-driven neural networks in memory behavior modeling. It proposes the EPsyINN model, which combines temporal neural networks with sparse differential regression in a unified framework, enabling the joint optimization of neural networks and classical symbolic models. More specifically, to address the controversies in classical psychological theories and the ambiguity of descriptors, it proposes a descriptor evolution method based on differential operators to achieve precise descriptor characterization and advance the evolution of classical symbolic models. Additionally, it introduces a caching mechanism for regression coefficient matrices and an alternating iterative optimization method for multiple modules, effectively alleviating local optima in model optimization. On five large-scale real-world memory behavior datasets, the proposed method surpasses state-of-the-art memory modeling approaches in predictive accuracy, while the evolved classical symbolic models also achieve performance improvements. Ablation experiments validate the effectiveness of the proposed improvements, and application experiments demonstrate its potential to inspire psychological research. The code for the experiments is available at: <span><span>https://github.com/hellowads/PsyINN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104312"},"PeriodicalIF":6.9,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-head divide-and-conquer residual-attention mechanism with pointer network for multimodal question summarization in healthcare 基于指针网络的医疗保健多模态问题总结多头分治剩余注意机制

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-16 DOI: 10.1016/j.ipm.2025.104348

S. Priskilla Manonmani, S. Malathi

{"title":"Multi-head divide-and-conquer residual-attention mechanism with pointer network for multimodal question summarization in healthcare","authors":"S. Priskilla Manonmani, S. Malathi","doi":"10.1016/j.ipm.2025.104348","DOIUrl":"10.1016/j.ipm.2025.104348","url":null,"abstract":"<div><div>In contemporary medicine, summaries of medical questions are vital for effective and precise patient care. Current techniques handle only text-based summarization without considering the merit of incorporating visual information. To meet this, this research presents a multimodal summarization system that combines textual queries with medical images to support the extraction of meaningful details. The proposed system has three phases. In the first step, a gradual fusion decoder bidirectional encoder representation from transformers with vision transformers is utilized to produce fine-grained feature maps and diagnose diseases. The Multi-Agent Contextualized Diffusion Model (MACDM) is then utilized to contextualize knowledge using cross-modal information. Lastly, a Multi-head Divide-and-Conquer Residual-Attention mechanism with Pointer Network (MDCRAPN) is utilized to provide brief and relevant summaries. Furthermore, the hermit crab shell exchange algorithm is integrated to optimize hyperparameters for improved performance. The experimental results indicate that this proposed approach performs better than existing approaches with a recall-oriented understudy for gisting evaluation-1 score of 48.11 on the Multimodal Medical Question Summarization (MMQS) dataset. This approach significantly enhances the identification and summarization of medical disorders, demonstrating the potential to enhance healthcare communication and decision-making.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104348"},"PeriodicalIF":6.9,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144858241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive confidence-driven learning and cross-modal hard sample mining for unsupervised visible-infrared person re-identification 无监督可见红外人再识别的自适应信心驱动学习和跨模态硬样本挖掘

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-15 DOI: 10.1016/j.ipm.2025.104346

Yifeng Zhang , Canlong Zhang , Haifei Ma , Zhixin Li , Zhiwen Wang , Chunrong Wei

{"title":"Adaptive confidence-driven learning and cross-modal hard sample mining for unsupervised visible-infrared person re-identification","authors":"Yifeng Zhang , Canlong Zhang , Haifei Ma , Zhixin Li , Zhiwen Wang , Chunrong Wei","doi":"10.1016/j.ipm.2025.104346","DOIUrl":"10.1016/j.ipm.2025.104346","url":null,"abstract":"<div><div>This research addresses the critical challenges in Cross-modal Visible-Infrared Person Re-ID (VI-ReID), including significant modal differences, lack of cross-modal correspondence, and pseudo-label noise accumulation. To mitigate these issues, we propose an innovative framework integrating an adaptive multidimensional enhanced clustering method and a confidence-driven dynamic label correction mechanism. Specifically, we design a dynamic clustering framework leveraging neighborhood consistency and intra-class distribution entropy to autonomously model data distributions. A confidence-driven dynamic label correction mechanism is introduced, employing multi-prototype similarity probability models to filter pseudo-label noise effectively. Moreover, a cross-modal feature alignment strategy based on optimal transport theory addresses many-to-many feature matching between visible and infrared modalities. Additionally, a Hard Sample Aware Contrastive Learning (HCL) strategy is implemented to enhance feature learning in complex data distributions through dynamic feature storage. Extensive experiments conducted on SYSU-MM01 and RegDB datasets, comprising 29,533 and 4120 image pairs, respectively, demonstrate the framework’s effectiveness. The proposed method achieves a 3.9% mAP improvement on average compared to state-of-the-art methods, highlighting its advantages in cross-modal feature alignment and pseudo-label optimization.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104346"},"PeriodicalIF":6.9,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144841886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Is generative AI reshaping academic practices worldwide? A survey of adoption, benefits, and concerns 生成式人工智能正在重塑全球的学术实践吗？对采用、利益和关注点的调查

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-15 DOI: 10.1016/j.ipm.2025.104350

Ehsan Mohammadi , Mike Thelwall , Yizhou Cai , Taylor Collier , Iman Tahamtan , Azar Eftekhar

{"title":"Is generative AI reshaping academic practices worldwide? A survey of adoption, benefits, and concerns","authors":"Ehsan Mohammadi , Mike Thelwall , Yizhou Cai , Taylor Collier , Iman Tahamtan , Azar Eftekhar","doi":"10.1016/j.ipm.2025.104350","DOIUrl":"10.1016/j.ipm.2025.104350","url":null,"abstract":"<div><div>Although generative AI is transforming academic research and education, little is known about the role, gender, international, and disciplinary variations in uptake and use. This 20-country survey of publishing academics shows the widespread awareness and adoption of generative AI tools in academia, but with substantial international and disciplinary differences, and some role and gender differences. In particular, females were 10 % less likely to use Gen AI frequently (daily or weekly) for research, which may exacerbate gender inequalities. Perhaps surprisingly, the highest adoption rates occurred in some non-Western nations, possibly because of a greater need for translation services. The highest awareness is in the social sciences, perhaps because of the greater need for text analysis. Across all groups, these tools were mainly used for academic writing rather than data analysis and support for critical thinking. Despite this, personalized instruction and problem-solving are among generative AI's most generally claimed benefits. However, participants in all groups were skeptical about the creativity, accuracy, and consistency of AI-generated content in academic contexts. The most significant concerns about using generative AI in academia were inaccuracy, plagiarism, discouraging critical thinking, a lack of transparency and explainability, intellectual property rights violations, and data privacy risks. For policymakers, the findings point to fields and countries that may need action to prevent falling behind, as well as the ongoing need to investigate and monitor the impacts of generative AI on research practices.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104350"},"PeriodicalIF":6.9,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144841887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Empowering Arabic diacritic restoration models with robustness, generalization, and minimal diacritization 赋予阿拉伯语变音符恢复模型鲁棒性，泛化和最小的变音符化

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-13 DOI: 10.1016/j.ipm.2025.104345

Ruba Kharsa , Ashraf Elnagar , Sane Yagi

{"title":"Empowering Arabic diacritic restoration models with robustness, generalization, and minimal diacritization","authors":"Ruba Kharsa , Ashraf Elnagar , Sane Yagi","doi":"10.1016/j.ipm.2025.104345","DOIUrl":"10.1016/j.ipm.2025.104345","url":null,"abstract":"<div><div>Arabic diacritization is essential for ensuring accurate pronunciation, clarity, and disambiguation of texts. It is a vital task in Arabic natural language processing. Despite substantial progress in the field, existing models struggle to generalize across the diverse forms of Arabic and perform poorly in noisy, error-prone environments. These limitations may be tied to problems in training data and, more critically, to insufficient contextual understanding. To address these gaps, we present SukounBERT.v2, a BERT-based Arabic diacritization system that is built using a multi-phase approach. We refine the Arabic Diacritization (AD) dataset by correcting spelling mistakes, introducing a line-splitting mechanism, and by injecting various forms of noise into the dataset, such as spelling errors, transliterated non-Arabic words, and nonsense tokens. Furthermore, we develop a context-aware training dataset that incorporates explicit diacritic markings and the diacritic naming of classical grammar treatises. Our work also introduces the Sukoun Corpus, a large-scale, diverse dataset comprising over 5.2 million lines and 71 million tokens that were sourced from Classical Arabic texts, Modern Standard Arabic writings, dictionaries, poetry, and purpose-built contextual sentences. Complementing this is a token-level mapping dictionary that enables minimal diacritization without sacrificing accuracy. This is a previously unreported feature in Arabic diacritization research. Trained on this enriched dataset, SukounBERT.v2 delivers state-of-the-art performance with over 55% relative reduction in Diacritic Error Rate (DER) and Word Error Rate (WER) compared to leading models. These results underscore the impact of context-aware and noise-resilient modeling in advancing the field of Arabic text processing.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104345"},"PeriodicalIF":6.9,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144831391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

EASeg: Environmental adaptation for weakly-supervised autonomous driving semantic segmentation 弱监督自动驾驶语义分割的环境适应

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-13 DOI: 10.1016/j.ipm.2025.104349

Yongqiang Li , Chuanping Hu , Kai Ren , Hao Xi , Jinhao Fan

{"title":"EASeg: Environmental adaptation for weakly-supervised autonomous driving semantic segmentation","authors":"Yongqiang Li , Chuanping Hu , Kai Ren , Hao Xi , Jinhao Fan","doi":"10.1016/j.ipm.2025.104349","DOIUrl":"10.1016/j.ipm.2025.104349","url":null,"abstract":"<div><div>Weakly supervised semantic segmentation (WSSS) offers a promising solution to reduce annotation costs in autonomous driving perception systems. However, existing methods struggle with the complex environmental conditions inherent to real-world driving scenarios, including adverse weather, variable lighting, and challenging visibility conditions. To address these limitations, we introduce EASeg, a novel framework that enhances segmentation robustness across diverse environmental conditions while requiring only image-level supervision. Our approach introduces three key innovations: (1) a multi-scale feature module that captures objects at varying scales followed by a boundary-aware enhancement component for precise delineation; (2) a dual-stream environmental adaptation mechanism that separately models global weather patterns and local illumination variations; and (3) a reliability-guided feature integration strategy that dynamically combines backbone features with foundation models based on their estimated reliability. Extensive experiments demonstrate that EASeg outperforms previous best methods, increasing mIoU by 24.5% on Cityscapes, 27.5% on CamVid, and 22.5% on WildDash2. Ablation studies confirm that our work represents a significant advancement toward practical, all-weather autonomous driving systems that enhance safety through improved segmentation of small objects and precise boundary delineation, while minimizing annotation requirements.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104349"},"PeriodicalIF":6.9,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144831389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Three-way decisions with text data and its application in market regulation 基于文本数据的三方决策及其在市场监管中的应用

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-13 DOI: 10.1016/j.ipm.2025.104307

Tengbiao Li , Junsheng Qiao , Guomin Chao

{"title":"Three-way decisions with text data and its application in market regulation","authors":"Tengbiao Li , Junsheng Qiao , Guomin Chao","doi":"10.1016/j.ipm.2025.104307","DOIUrl":"10.1016/j.ipm.2025.104307","url":null,"abstract":"<div><div>In the era of artificial intelligence, text classification of comment letters (CLs) data can help the stock exchanges predict the CLs’ response statuses and enhance market regulatory efficiency. In this paper, a novel three-way classifier based on word embedding and aggregation function (AF), called WE-AF-TWC, is proposed for multi-label classification using textual information from annual CLs of Chinese quoted companies. Firstly, we introduce the classical Word2Vec to extract mathematical values from the potential information in each text. Subsequently, we develop a novel AF with idempotent property as a mathematical tool to stably fuse multiple word vectors and generate a fuzzy relation matrix, and we discuss several properties of it. Lastly, we introduce a parameterized construction form to construct the three-way decision space, which formally simulate human decision logic, and further improve classification performance by training the optimal decision region. Particularly, the performance of WE-AF-TWC is validated on a manually curated Chinese market regulation CL response dataset, called CNletters, containing 5,727 records, as well as on three commonly used public datasets. The experimental results show that WE-AF-TWC not only demonstrates accuracy and robustness in the CL text classification task, but also exhibits superior performance in multi-scenario applications. Specifically, on CNletters, the weighted-precision of WE-AF-TWC is 82.76%, which is better than several most advanced classifiers. On SciCite, compared with three advanced classifiers, the weighted-precision obtained by WE-AF-TWC shows an improvement of 6.60%, 0.50% and 1.80%, respectively. Similarly, on AGNews and PubMed 200k RCT, the corresponding improvement is 1.95%, 1.02%, 0.03% and 8.93%, 0.34%, 1.56%, respectively.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104307"},"PeriodicalIF":6.9,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MI3S: A multimodal large language model assisted quality assessment framework for AI-generated talking heads MI3S：一个多模态大语言模型辅助人工智能生成谈话头的质量评估框架

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-12 DOI: 10.1016/j.ipm.2025.104321

Yingjie Zhou, Zicheng Zhang, Sijing Wu, Jun Jia, Yanwei Jiang, Wei Sun, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai

{"title":"MI3S: A multimodal large language model assisted quality assessment framework for AI-generated talking heads","authors":"Yingjie Zhou, Zicheng Zhang, Sijing Wu, Jun Jia, Yanwei Jiang, Wei Sun, Xiaohong Liu, Xiongkuo Min, Guangtao Zhai","doi":"10.1016/j.ipm.2025.104321","DOIUrl":"10.1016/j.ipm.2025.104321","url":null,"abstract":"<div><div>Although current speech-driven technologies enable the rapid generation of AI-generated talking heads (AGTHs), human supervision remains necessary to ensure the quality of the output. However, manual evaluation becomes increasingly impractical for large-scale AGTH production due to its time-consuming and labor-intensive nature. To overcome this limitation, we propose a novel objective quality assessment framework, MI3S, which employs a <strong>M</strong>ultimodal Large Language Model (MLLM) to evaluate AGTHs across four key dimensions: <strong>I</strong>mage quality, <strong>I</strong>mage aesthetics, <strong>I</strong>dentity consistency, and <strong>S</strong>ound-lip synchronization. <strong>To capture temporal dynamics more effectively,</strong> we introduce a variable-length video memory filter (VVMF), inspired by principles of human visual cognition. The MI3S framework supports both zero-shot inference and supervised learning paradigms. On the THQA dataset comprising 800 AGTHs, MI3S achieves a prediction-human perceptual correlation coefficient of 0.7946, which exceeds that of existing quality assessment methods by 3.4%, thereby offering an efficient, robust, and objective solution for evaluating AGTH quality.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104321"},"PeriodicalIF":6.9,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pattern dynamics analysis of higher-order network epidemic-like information propagation model 高阶网络类流行信息传播模型的模式动力学分析

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-11 DOI: 10.1016/j.ipm.2025.104340

Yicen Zhou, Linhe Zhu

{"title":"Pattern dynamics analysis of higher-order network epidemic-like information propagation model","authors":"Yicen Zhou, Linhe Zhu","doi":"10.1016/j.ipm.2025.104340","DOIUrl":"10.1016/j.ipm.2025.104340","url":null,"abstract":"<div><div>This paper constructs a reaction–diffusion <span><math><mrow><mi>S</mi><mi>I</mi></mrow></math></span> (Susceptible-Infected) rumor propagation model based on spatio-temporal factors. This model incorporates higher-order interactions into the reaction terms in order to reflect the complexity of rumor propagation in reality. It has become more realistic and applicable in the complexity of spatiotemporal patterns. In the beginning, we do not consider the diffusion effect and then calculate the equilibrium points of the model with higher-order. The necessary conditions are analyzed for Turing bifurcation to occur. However, the necessary conditions of the Turing bifurcation can only explain the instability of the spatio-temporal propagation of rumors, and cannot accurately predict the spatial distribution pattern of information. Therefore, we have further derived the amplitude equations to predict the evolution of different pattern formations. Finally, we have presented some numerical simulations in different propagation network environments to investigate the influence of various parameters on the distribution density of susceptible populations. Moreover, we use two algorithms to fit the actual data with the model for rumor propagation and conclude that the second method has a better fitting effect.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104340"},"PeriodicalIF":6.9,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144809372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CSCAD: Modeling cross-scale sequence correlations for multivariate time series anomaly detection 多变量时间序列异常检测的跨尺度序列相关性建模

IF 6.9 1区管理学

Information Processing & Management Pub Date : 2025-08-11 DOI: 10.1016/j.ipm.2025.104315

Hanfeng Lee , Zhixia Zeng , Zhipeng Qiu , Weifu Zhu , Ruliang Xiao

{"title":"CSCAD: Modeling cross-scale sequence correlations for multivariate time series anomaly detection","authors":"Hanfeng Lee , Zhixia Zeng , Zhipeng Qiu , Weifu Zhu , Ruliang Xiao","doi":"10.1016/j.ipm.2025.104315","DOIUrl":"10.1016/j.ipm.2025.104315","url":null,"abstract":"<div><div>Current anomaly detection methods struggle to adequately model the complex attribute correlations in multivariate time series and often overlook the heteroskedasticity within the series, resulting in the misidentification of low-amplitude noise and false alarms. This paper proposes Modeling Cross-Scale Sequence Correlations for Multivariate Time Series Anomaly Detection (CSCAD), a novel unsupervised anomaly detection method that models attribute correlations across time scales by constructing cross-scale splicing representations and multiscale interactive convolution. Additionally, the weights across time scales are adaptively adjusted to suppress noise interference and enhance the heterogeneous correlation representation by combining sequence heteroskedasticity with the attention mechanism. Inspired by Kolmogorov–Arnold networks (KANs), adaptive activation functions are introduced to enhance the model’s ability to capture complex temporal patterns. Detection experiments based on reconstruction error demonstrate that CSCAD improves the F1 score by 1.1% and recall by 2.14% compared to 19 baseline methods across five real datasets, validating its effectiveness in anomaly detection tasks.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104315"},"PeriodicalIF":6.9,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0