Information Sciences最新文献_第10页

Multiple event detection via bi-graph attention network with syntactic and semantic features 具有句法和语义特征的双图注意网络多事件检测

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-27 DOI: 10.1016/j.ins.2025.122593

Yi Zhang, Xin Ye, Chen Qian, Lei Zhang

{"title":"Multiple event detection via bi-graph attention network with syntactic and semantic features","authors":"Yi Zhang, Xin Ye, Chen Qian, Lei Zhang","doi":"10.1016/j.ins.2025.122593","DOIUrl":"10.1016/j.ins.2025.122593","url":null,"abstract":"<div><div>The complicated inter-dependency among events poses a significant challenge to modeling event correlations in multiple event detection. While graph-based methods outperform sequence-based methods in capturing global features, two limitations may arise. First, redundant syntactic structures and ignored inter-event connections influence explicit relationship modeling. Second, the context-independent nature of syntactic features limits the semantic correlation modeling between events. To alleviate these challenges, we propose Bi-Graph Attention Network for Event Detection (BiGAT-ED), integrating syntactic and semantic features through a multi-perspective graph architecture. Specifically, we propose the Edge-Enhanced Graph Attention Network (EE-GAT) to incorporate syntactic dependency information into the attention mechanism, reducing the impact of redundant connections. We further construct the Event Relation Graph (ERG) to model inter-event connections and encode it with the Node-Aware Graph Attention Network (NA-GAT), which leverages event label knowledge within its attention mechanism for enhanced semantic correlation modeling. Finally, BiGAT-ED integrates event correlations from EE-GAT and NA-GAT through an attention fusion mechanism, improving performance for multiple event identification. Experimental results on cross-domain datasets demonstrate that BiGAT-ED consistently surpasses existing competitive models and leading LLMs.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122593"},"PeriodicalIF":6.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144907512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

A distinct classification of attention mechanisms in video understanding 视频理解中注意机制的不同分类

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-26 DOI: 10.1016/j.ins.2025.122609

Shilin Chen , Xingwang Wang , Yafeng Sun , Kun Yang , Xiaohui Wei

引用次数: 0

A novel approach to antinoise multi-granularity classification through graph-based feature selection 一种基于图的多粒度分类抗噪方法

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-26 DOI: 10.1016/j.ins.2025.122632

Xiaoyan Zhang, Xuan Shen, Weicheng Zhao

{"title":"A novel approach to antinoise multi-granularity classification through graph-based feature selection","authors":"Xiaoyan Zhang, Xuan Shen, Weicheng Zhao","doi":"10.1016/j.ins.2025.122632","DOIUrl":"10.1016/j.ins.2025.122632","url":null,"abstract":"<div><div>This study proposes a novel anti-noise multi-granularity classification method that incorporates graph-based feature selection to effectively reduce computational complexity while enhancing classification accuracy and robustness. Traditional multi-granularity fuzzy rough set (MFRS) models are often highly sensitive to noisy samples, which hinders the acquisition of reliable knowledge. To address this issue, we design a heuristic feature selection algorithm within the framework of the weighted multi-granulation neighborhood-constrained fuzzy rough set (WMNcFRS) model. The algorithm first utilizes graph theory to evaluate inter-feature correlation and redundancy, enabling efficient partitioning of multi-granularity spaces. It then introduces a granularity-weighted strategy that ranks and prioritizes granularities based on approximation precision, thereby improving approximation capability. Finally, the feature selection strategy is formulated using the fuzzy dependency measure defined in the WMNcFRS model, which effectively suppresses noise interference, reduces the computational costs, and enhances the model's generalization ability. Extensive experiments on fifteen publicly available datasets demonstrate that, compared to six state-of-the-art algorithms, the proposed method exhibits superior robustness and classification performance, validating its effectiveness in practical applications.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122632"},"PeriodicalIF":6.8,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Event-based stochastic Lyapunov-type theorem and its application to leader-following multi-agent systems 基于事件的随机lyapunov型定理及其在领导-跟随多智能体系统中的应用

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-26 DOI: 10.1016/j.ins.2025.122622

Zunjie Yu , Weihai Zhang , Qingpeng Meng , Chao Guo

引用次数: 0

The Frequency-Domain Corrected Attention Operator for solving PDEs 求解偏微分方程的频域校正注意算子

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-25 DOI: 10.1016/j.ins.2025.122611

Ma Qinglong , Hu Xuebin , Zhao Peizhi , Cao Xichen , Wang Sen , Song Tao

{"title":"The Frequency-Domain Corrected Attention Operator for solving PDEs","authors":"Ma Qinglong , Hu Xuebin , Zhao Peizhi , Cao Xichen , Wang Sen , Song Tao","doi":"10.1016/j.ins.2025.122611","DOIUrl":"10.1016/j.ins.2025.122611","url":null,"abstract":"<div><div>Two classical Neural Operators are widely used for solving PDEs. One approach utilizes spectral transformations for learning in the spectral domain, while the other employs attention mechanisms for learning in the physical space. Neural Operators based on spectral transformations excel at solving PDEs with smooth solutions but struggle to capture local details, particularly when the solution exhibits sharp variations. Neural Operators based on attention mechanisms exhibit greater adaptability to complex physical phenomena but lack global constraints, resulting in weaker generalization capabilities. In this paper, we propose the Frequency-Domain Corrected Attention Operator (FDCAO), which combines the advantages of both classical Neural Operators. Specifically, the method uses filters to introduce global constraints and enhance the high-frequency response. Then, it enhances the linear attention mechanism through dot-product to further amplify local physical phenomena, thereby better learning rapidly changing complex physical phenomena. Extensive benchmark experiments demonstrate that FDCAO performs excellently across various partial differential equation solving scenarios, effectively learning operator mappings.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122611"},"PeriodicalIF":6.8,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Detecting the jumps from the data: Elastic anomaly detection algorithms and parameter estimation of uncertain differential equations with jumps 从数据中检测跳跃：弹性异常检测算法和不确定微分方程的参数估计

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-25 DOI: 10.1016/j.ins.2025.122614

Jiajia Wang, Jue Lu, Lianlian Zhou, Anshui Li

{"title":"Detecting the jumps from the data: Elastic anomaly detection algorithms and parameter estimation of uncertain differential equations with jumps","authors":"Jiajia Wang, Jue Lu, Lianlian Zhou, Anshui Li","doi":"10.1016/j.ins.2025.122614","DOIUrl":"10.1016/j.ins.2025.122614","url":null,"abstract":"<div><div>In financial and actuarial modeling, alongside diverse other applied domains, stochastic differential equation models incorporating jump components, used to characterize the dynamics of financial variables, have witnessed a marked rise in prominence in recent years. The jump component serves to capture event-driven uncertainties, including corporate defaults, operational failures, or insured events.</div><div>However, to detect the jump component is a very vital but challenging issue. Uncertain differential equations are used widely to model many complicated phenomena in financial market, physics, engineering, and so on. One of key research issues in this area is to estimate the parameters of the corresponding equations based on observations from their solutions.</div><div>One parameter estimation framework for uncertain differential equations with jumps, combining numerical algorithms and moment methods, is proposed in this paper. To be more precise, one anomaly detection algorithm is designed to preprocess the data first; then the process of parameter estimation is implemented by the method of moments. To illustrate our method, some numerical examples are given. Additionally, empirical studies of quarterly government consumption expenditure data for Australia as well as Microsoft's stock prices are also presented. With a throughly comparative study with other jump detection methods as well as a study with its stochastic counterparts for real data, our model outperforms all others. We conclude this paper with some possible directions and remarks.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122614"},"PeriodicalIF":6.8,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

A multi-scale attention Siamese point cloud network for 3D similarity matching of firing pin impressions 一种多尺度关注连体点云网络，用于火针印痕的三维相似性匹配

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-22 DOI: 10.1016/j.ins.2025.122619

Binrong Yang , Linyu Huang , Yong Guo

{"title":"A multi-scale attention Siamese point cloud network for 3D similarity matching of firing pin impressions","authors":"Binrong Yang , Linyu Huang , Yong Guo","doi":"10.1016/j.ins.2025.122619","DOIUrl":"10.1016/j.ins.2025.122619","url":null,"abstract":"<div><div>The similarity matching of firing pin impressions on cartridge cases plays a critical role in forensic firearm identification. Traditional comparison methods, whether manual or geometry-based, often struggle to capture the subtle local variations and global structural patterns present in high-precision 3D impression data, leading to limited robustness and accuracy. In this paper, we propose a novel deep learning framework based on a Multi-Scale Attention Siamese Point Cloud Network to address these challenges. The proposed model integrates a PointMLP-based Siamese architecture with a multi-scale attention mechanism to jointly extract local geometric details and global contextual information from 3D point cloud representations of firing pin impressions. This design enables the network to effectively capture fine-grained differences between highly similar impressions, improving similarity discrimination capability. The framework is evaluated on a self-constructed dataset of 3D firing pin impressions, acquired through high-precision laser scanning from actual firearm discharges. The experimental results demonstrate that the proposed method outperforms traditional and existing learning-based approaches, achieving similarity matching accuracies of 98.91% on the training set and 99.30% on the test set. The approach offers a transferable solution for 3D similarity learning tasks, with potential applications in other 3D object comparison and forensic scenarios.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122619"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

State estimation of stochastic temporal Boolean control networks 随机时序布尔控制网络的状态估计

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-22 DOI: 10.1016/j.ins.2025.122620

Lina Wang , Amol Yerudkar , Yang Liu , Jianquan Lu , Jinde Cao

{"title":"State estimation of stochastic temporal Boolean control networks","authors":"Lina Wang , Amol Yerudkar , Yang Liu , Jianquan Lu , Jinde Cao","doi":"10.1016/j.ins.2025.122620","DOIUrl":"10.1016/j.ins.2025.122620","url":null,"abstract":"<div><div>In this paper, the state estimation problem for stochastic temporal Boolean control networks (STBCNs) is investigated. The STBCNs evolve according to a temporal Boolean model affected by process noise, while the measurements are corrupted by observation noise. Based on the available input and output sequences, optimal state and state sequence estimation methods that minimize the mean-square error are developed. First, leveraging the semi-tensor product (STP) of matrices, the state-space representation of STBCNs is formulated. A Boolean Bayesian filtering method is then proposed, and two recursive matrix-based procedures are designed to compute the conditional probability distributions of the system states and state sequences in vector form, respectively. Furthermore, by employing the STP framework, these probability distributions are transformed into Boolean-valued expectations for each node. In addition, for a fixed observation window, a forward–backward estimation technique is introduced to obtain the state probability distribution vector at each time instant, which is also transformed into Boolean-valued expectations for each node. Based on these expectations, the optimal state and state sequence estimates that minimize the mean-square error are derived. Finally, the effectiveness of the proposed approach is demonstrated using the Escherichia coli Boolean model.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122620"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

AutoVMR: An autonomous event generation and localization approach for video moment retrieval AutoVMR：一种用于视频时刻检索的自主事件生成和定位方法

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-22 DOI: 10.1016/j.ins.2025.122615

Shu Luo , Qiwei Ma , Jiawei Wang , Da Cao , Shaofei Lu

{"title":"AutoVMR: An autonomous event generation and localization approach for video moment retrieval","authors":"Shu Luo , Qiwei Ma , Jiawei Wang , Da Cao , Shaofei Lu","doi":"10.1016/j.ins.2025.122615","DOIUrl":"10.1016/j.ins.2025.122615","url":null,"abstract":"<div><div>Video Moment Retrieval (VMR) aims to identify a semantically relevant segment within a video based on a descriptive language query, specifying the segment's boundaries through start and end timestamps. Despite recent advancements, various VMR frameworks still rely heavily on extensive manual annotations, which are resource-intensive and not scalable for large-scale video databases. Besides, although large language model has been applied to VMR, it still suffers from sophisticated prompt design and multi-turn question answering, which is far from being automated. To address these issues, we propose AutoVMR, a novel multimodal large language model framework that employs an autonomous event generation and localization approach for VMR. AutoVMR utilizes an autoregressive architecture, accepting video input and a fixed prompt template, to generate event descriptions of video segments along with their corresponding start and end times. We also introduce a reward model based on Intersection over Union (IoU), trained using reinforcement learning from human feedback. This model is integrated into the Proximal Policy Optimization (PPO) training strategy and includes a query-time boundary generation mechanism to improve AutoVMR's performance. The reward model's modeling approach effectively filters out noise in the VMR dataset, enabling the PPO method to better comprehend video content and generate more accurate temporal localizations. Moreover, the integration of the autoregressive process with PPO training allows the model to be trained on unannotated video data, leading to improved performance in a semi-supervised setting. Experimental results demonstrate that AutoVMR outperforms traditional VMR methods and the latest multimodal large language models, achieving state-of-the-art performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122615"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

A rational incentive mechanism driven group consensus optimization model by trust attenuation propagation with optimal path under social network 一个理性激励机制驱动的社会网络下具有最优路径的信任衰减传播群体共识优化模型

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-08-22 DOI: 10.1016/j.ins.2025.122616

Huimin Qi , Yumei Xing , Gaofeng Yu , Sha Wang , Jian Wu

{"title":"A rational incentive mechanism driven group consensus optimization model by trust attenuation propagation with optimal path under social network","authors":"Huimin Qi , Yumei Xing , Gaofeng Yu , Sha Wang , Jian Wu","doi":"10.1016/j.ins.2025.122616","DOIUrl":"10.1016/j.ins.2025.122616","url":null,"abstract":"<div><div>Traditional consensus feedback mechanisms often rely on established models, assuming that trust is transmitted without loss among decision makers and that consensus is achieved solely based on this ideal process. However, they fail to consider trust attenuation due to path differences during propagation and the varying tolerance of decision makers towards opinion adjustments. To address this issue, this paper proposes a group consensus optimization model driven by a rational incentive mechanism, integrating trust attenuation propagation with optimal trust path selection. First, an inverse dynamic programming model with trust amplitude is developed to explore the optimal propagation path of trust relationships between decision makers. Second, a distributed linguistic trust propagation operator considering trust attenuation (impacts of path length and decision makers' positions in the trust chain) is constructed to analyze the dynamic changes of trust relationships during propagation. Furthermore, a dynamic incentive feedback model based on rational adjustment is established, followed by a minimum adjustment optimization model driven by the rational incentive mechanism. The key innovation of the model lies in: enhancing decision makers' willingness to adjust opinions proactively through incentives (avoiding resistance from forced adjustment) and constraining rational adjustment within a maximum tolerance range (mitigating divergence caused by trust transmission risks). Finally, a case study of builder selection for industrial park construction illustrates the effectiveness and superiority of the proposed method.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"721 ","pages":"Article 122616"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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