Information Sciences最新文献_第5页

Safe reinforcement learning-based control using deep deterministic policy gradient algorithm and slime mould algorithm with experimental tower crane system validation 通过塔式起重机系统的实验验证，使用深度确定性策略梯度算法和粘模算法实现基于强化学习的安全控制

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-15 DOI: 10.1016/j.ins.2024.121640

Iuliu Alexandru Zamfirache , Radu-Emil Precup , Emil M. Petriu

This paper presents a novel optimal control approach resulting from the combination between the safe Reinforcement Learning (RL) framework represented by a Deep Deterministic Policy Gradient (DDPG) algorithm and a Slime Mould Algorithm (SMA) as a representative nature-inspired optimization algorithm. The main drawbacks of the traditional DDPG-based safe RL optimal control approach are the possible instability of the control system caused by randomly generated initial values of the controller parameters and the lack of state safety guarantees in the first iterations of the learning process due to (i) and (ii): (i) the safety constraints are considered only in the DDPG-based training process of the controller, which is usually implemented as a neural network (NN); (ii) the initial values of the weights and the biases of the NN-based controller are initialized with randomly generated values. The proposed approach mitigates these drawbacks by initializing the parameters of the NN-based controller using SMA. The fitness function of the SMA-based initialization process is designed to incorporate state safety constraints into the search process, resulting in an initial NN-based controller with embedded state safety constraints. The proposed approach is compared to the classical one using real-time experimental results and performance indices popular for optimal reference tracking control problems and based on a state safety score.

本文介绍了一种新颖的优化控制方法，它是由以深度确定性策略梯度（DDPG）算法为代表的安全强化学习（RL）框架和以粘液模算法（SMA）为代表的自然启发优化算法相结合而产生的。基于 DDPG 的传统安全 RL 优化控制方法的主要缺点是，由于(i)和(ii)的原因，随机生成的控制器参数初始值可能导致控制系统不稳定，并且在学习过程的第一次迭代中缺乏状态安全保证：(i) 安全约束仅在基于 DDPG 的控制器训练过程中得到考虑，而控制器通常以神经网络 (NN) 的形式实现；(ii) 基于 NN 的控制器的权重和偏置初始值为随机生成值。所提出的方法通过使用 SMA 对基于 NN 的控制器参数进行初始化，缓解了这些缺点。基于 SMA 的初始化过程的适配函数旨在将状态安全约束纳入搜索过程，从而产生一个具有嵌入式状态安全约束的基于 NN 的初始控制器。利用实时实验结果和最优参考跟踪控制问题常用的性能指标，并基于状态安全评分，对所提出的方法与传统方法进行了比较。

{"title":"Safe reinforcement learning-based control using deep deterministic policy gradient algorithm and slime mould algorithm with experimental tower crane system validation","authors":"Iuliu Alexandru Zamfirache , Radu-Emil Precup , Emil M. Petriu","doi":"10.1016/j.ins.2024.121640","DOIUrl":"10.1016/j.ins.2024.121640","url":null,"abstract":"<div><div>This paper presents a novel optimal control approach resulting from the combination between the safe Reinforcement Learning (RL) framework represented by a Deep Deterministic Policy Gradient (DDPG) algorithm and a Slime Mould Algorithm (SMA) as a representative nature-inspired optimization algorithm. The main drawbacks of the traditional DDPG-based safe RL optimal control approach are the possible instability of the control system caused by randomly generated initial values of the controller parameters and the lack of state safety guarantees in the first iterations of the learning process due to (i) and (ii): (i) the safety constraints are considered only in the DDPG-based training process of the controller, which is usually implemented as a neural network (NN); (ii) the initial values of the weights and the biases of the NN-based controller are initialized with randomly generated values. The proposed approach mitigates these drawbacks by initializing the parameters of the NN-based controller using SMA. The fitness function of the SMA-based initialization process is designed to incorporate state safety constraints into the search process, resulting in an initial NN-based controller with embedded state safety constraints. The proposed approach is compared to the classical one using real-time experimental results and performance indices popular for optimal reference tracking control problems and based on a state safety score.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121640"},"PeriodicalIF":8.1,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Statistical feature likelihood evidential reasoning rule for equipment health state assessment considering asynchronous unequal interval data 考虑异步不等间隔数据的设备健康状态评估统计特征似然证据推理规则

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-15 DOI: 10.1016/j.ins.2024.121650

Chaoli Zhang , Zhijie Zhou , Jiayu Luo , Jie Wang

There are high-dimensional correlation variables and uncertainty asynchronous unequal interval data during the equipment test process, making it difficult to establish a health assessment model directly. Therefore, a statistical feature likelihood evidential reasoning rule for equipment health assessment is proposed, which achieves the alignment of the asynchronous unequal interval data, the decorrelation of the high-dimensional correlation variables, and the reduction of the assessment results uncertainty. Specifically, the reconstruction-based data stage division method is developed to determine the feature transformation reference value. Then, the independent evidence is constructed from the principal component features based on likelihood function normalization. Finally, the evidence activated by the feature samples is fused based on the evidential reasoning rule to assess the health state of the equipment. A numerical simulation case is conducted to demonstrate the implementation procedure. The advantage of the proposed method is verified by the case studies of the aircraft engine and the inertial measurement unit.

设备测试过程中存在高维相关变量和不确定性异步不等间隔数据，难以直接建立健康评估模型。因此，提出了一种用于设备健康评估的统计特征似然举证推理规则，实现了异步不等间隔数据的对齐、高维相关变量的去相关以及评估结果不确定性的降低。具体来说，该方法采用基于重构的数据阶段划分方法来确定特征变换参考值。然后，基于似然函数归一化，从主成分特征中构建独立证据。最后，根据证据推理规则融合由特征样本激活的证据，以评估设备的健康状态。我们通过一个数值模拟案例来演示实施过程。通过对飞机发动机和惯性测量单元的案例研究，验证了所提方法的优势。

{"title":"Statistical feature likelihood evidential reasoning rule for equipment health state assessment considering asynchronous unequal interval data","authors":"Chaoli Zhang , Zhijie Zhou , Jiayu Luo , Jie Wang","doi":"10.1016/j.ins.2024.121650","DOIUrl":"10.1016/j.ins.2024.121650","url":null,"abstract":"<div><div>There are high-dimensional correlation variables and uncertainty asynchronous unequal interval data during the equipment test process, making it difficult to establish a health assessment model directly. Therefore, a statistical feature likelihood evidential reasoning rule for equipment health assessment is proposed, which achieves the alignment of the asynchronous unequal interval data, the decorrelation of the high-dimensional correlation variables, and the reduction of the assessment results uncertainty. Specifically, the reconstruction-based data stage division method is developed to determine the feature transformation reference value. Then, the independent evidence is constructed from the principal component features based on likelihood function normalization. Finally, the evidence activated by the feature samples is fused based on the evidential reasoning rule to assess the health state of the equipment. A numerical simulation case is conducted to demonstrate the implementation procedure. The advantage of the proposed method is verified by the case studies of the aircraft engine and the inertial measurement unit.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121650"},"PeriodicalIF":8.1,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704068","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

Privacy-preserving and communication-efficient stochastic alternating direction method of multipliers for federated learning 用于联合学习的隐私保护和通信效率高的随机交替方向乘法

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-14 DOI: 10.1016/j.ins.2024.121641

Yi Zhang , Yunfan Lu , Fengxia Liu , Cheng Li , Zixian Gong , Zhe Hu , Qun Xu

Federated learning constitutes a paradigm in distributed machine learning, wherein model training unfolds through the exchange of intermediary results between a central server and federated clients. Given its decentralized nature, conventional machine learning algorithms find limited applicability in the context of federated learning models. Hence, the alternating direction method of multipliers (ADMM), tailored for distributed optimization, is leveraged for this purpose. However, despite the considerable promise of the ADMM algorithm in federated learning, it faces challenges related to computational efficiency, communication efficiency, and data security. In response to these challenges, this study proposes the privacy-preserving and communication-efficient stochastic ADMM (PPCESADMM) algorithm that enhances the computational efficiency through the stochastic optimization method, reduces communication costs through sparse communication method, and ensures the security of federated clients' data via the homomorphic encryption method. Theoretical analyses confirm the convergence of the PPCESADMM algorithm under mild conditions and establish its convergence rate as

O (1 / \sqrt{T})

. Experiments illustrate the superior performance of our algorithm in communication cost compared to ADMM and CEADMM algorithms, achieving reductions of 65.10% and 44.32%, respectively. Furthermore, our method surpasses classical federated learning algorithms such as FedAvg, FedAvgM, and SCAFFOLD in terms of algorithmic convergence, achieving superior convergence precision within predefined training epochs. Finally, our algorithm converges to the same results as those obtained without using homomorphic encryption, albeit at the cost of increased computation time.

联合学习是分布式机器学习的一种范式，它通过中央服务器与联合客户端之间交换中间结果来展开模型训练。鉴于其分散性，传统的机器学习算法在联合学习模型中的适用性有限。因此，为分布式优化量身定制的乘法交替方向法（ADMM）被用于此目的。然而，尽管 ADMM 算法在联合学习中大有可为，但它在计算效率、通信效率和数据安全方面仍面临挑战。针对这些挑战，本研究提出了隐私保护和通信效率随机 ADMM 算法（PPCESADMM），该算法通过随机优化方法提高计算效率，通过稀疏通信方法降低通信成本，并通过同态加密方法确保联盟客户数据的安全性。理论分析证实了 PPCESADMM 算法在温和条件下的收敛性，并确定其收敛速率为 O(1/T)。实验表明，与 ADMM 算法和 CEADMM 算法相比，我们的算法在通信成本方面表现出色，分别降低了 65.10% 和 44.32%。此外，在算法收敛性方面，我们的方法超越了 FedAvg、FedAvgM 和 SCAFFOLD 等经典联合学习算法，在预定义的训练历时内实现了卓越的收敛精度。最后，我们的算法收敛到了与不使用同态加密时相同的结果，尽管代价是计算时间的增加。

{"title":"Privacy-preserving and communication-efficient stochastic alternating direction method of multipliers for federated learning","authors":"Yi Zhang , Yunfan Lu , Fengxia Liu , Cheng Li , Zixian Gong , Zhe Hu , Qun Xu","doi":"10.1016/j.ins.2024.121641","DOIUrl":"10.1016/j.ins.2024.121641","url":null,"abstract":"<div><div>Federated learning constitutes a paradigm in distributed machine learning, wherein model training unfolds through the exchange of intermediary results between a central server and federated clients. Given its decentralized nature, conventional machine learning algorithms find limited applicability in the context of federated learning models. Hence, the alternating direction method of multipliers (ADMM), tailored for distributed optimization, is leveraged for this purpose. However, despite the considerable promise of the ADMM algorithm in federated learning, it faces challenges related to computational efficiency, communication efficiency, and data security. In response to these challenges, this study proposes the privacy-preserving and communication-efficient stochastic ADMM (PPCESADMM) algorithm that enhances the computational efficiency through the stochastic optimization method, reduces communication costs through sparse communication method, and ensures the security of federated clients' data via the homomorphic encryption method. Theoretical analyses confirm the convergence of the PPCESADMM algorithm under mild conditions and establish its convergence rate as <span><math><mi>O</mi><mo>(</mo><mn>1</mn><mo>/</mo><msqrt><mrow><mi>T</mi></mrow></msqrt><mo>)</mo></math></span>. Experiments illustrate the superior performance of our algorithm in communication cost compared to ADMM and CEADMM algorithms, achieving reductions of 65.10% and 44.32%, respectively. Furthermore, our method surpasses classical federated learning algorithms such as FedAvg, FedAvgM, and SCAFFOLD in terms of algorithmic convergence, achieving superior convergence precision within predefined training epochs. Finally, our algorithm converges to the same results as those obtained without using homomorphic encryption, albeit at the cost of increased computation time.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"691 ","pages":"Article 121641"},"PeriodicalIF":8.1,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658126","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

Aggregation or separation? Adaptive embedding message passing for knowledge graph completion 聚合还是分离？知识图谱完成的自适应嵌入信息传递

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-13 DOI: 10.1016/j.ins.2024.121639

Zhifei Li , Lifan Chen , Yue Jian , Han Wang , Yue Zhao , Miao Zhang , Kui Xiao , Yan Zhang , Honglian Deng , Xiaoju Hou

Knowledge graph completion intends to infer information within knowledge graphs, thereby bolstering the functionality of knowledge-driven applications. Recently, there has been a significant increase in the utilization of graph convolutional networks (GCNs) for knowledge graph completion. These GCN-based models primarily focus on aggregating information from neighboring entities and relations. Nonetheless, a fundamental question arises: is it beneficial to consider all neighbor information, and should some neighbor features be separated? We tackle this issue and present an adaptive graph convolutional network (AdaGCN) for knowledge graph completion, which can adaptively aggregate or separate neighbor information for knowledge embedding learning. Specifically, AdaGCN utilizes the adaptive message-passing mechanism to determine the importance of each relation, allocating weights to neighbor entity embeddings. This adaptive approach facilitates the propagation of valuable information while effectively separating less relevant or unnecessary details. Experimental results demonstrate that AdaGCN can efficiently acquire the embeddings of various triplets within knowledge graphs, and it achieves competitive performance compared to SOTA models on six datasets for the tasks of knowledge graph completion.

知识图谱补全旨在推断知识图谱中的信息，从而增强知识驱动型应用的功能。最近，利用图卷积网络（GCN）完成知识图谱的情况显著增加。这些基于 GCN 的模型主要侧重于聚合相邻实体和关系的信息。然而，一个基本问题随之而来：考虑所有相邻信息是否有益，是否应该分离某些相邻特征？针对这一问题，我们提出了一种用于知识图谱补全的自适应图卷积网络（AdaGCN），它可以自适应地聚合或分离邻居信息，从而实现知识嵌入学习。具体来说，AdaGCN 利用自适应信息传递机制来确定每种关系的重要性，并为相邻实体嵌入分配权重。这种自适应方法有利于传播有价值的信息，同时有效分离相关性较低或不必要的细节。实验结果表明，AdaGCN 可以高效地获取知识图谱中各种三元组的嵌入信息，并且在六个数据集的知识图谱补全任务中取得了与 SOTA 模型相比具有竞争力的性能。

{"title":"Aggregation or separation? Adaptive embedding message passing for knowledge graph completion","authors":"Zhifei Li , Lifan Chen , Yue Jian , Han Wang , Yue Zhao , Miao Zhang , Kui Xiao , Yan Zhang , Honglian Deng , Xiaoju Hou","doi":"10.1016/j.ins.2024.121639","DOIUrl":"10.1016/j.ins.2024.121639","url":null,"abstract":"<div><div>Knowledge graph completion intends to infer information within knowledge graphs, thereby bolstering the functionality of knowledge-driven applications. Recently, there has been a significant increase in the utilization of graph convolutional networks (GCNs) for knowledge graph completion. These GCN-based models primarily focus on aggregating information from neighboring entities and relations. Nonetheless, a fundamental question arises: is it beneficial to consider all neighbor information, and should some neighbor features be separated? We tackle this issue and present an adaptive graph convolutional network (AdaGCN) for knowledge graph completion, which can adaptively aggregate or separate neighbor information for knowledge embedding learning. Specifically, AdaGCN utilizes the adaptive message-passing mechanism to determine the importance of each relation, allocating weights to neighbor entity embeddings. This adaptive approach facilitates the propagation of valuable information while effectively separating less relevant or unnecessary details. Experimental results demonstrate that AdaGCN can efficiently acquire the embeddings of various triplets within knowledge graphs, and it achieves competitive performance compared to SOTA models on six datasets for the tasks of knowledge graph completion.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"691 ","pages":"Article 121639"},"PeriodicalIF":8.1,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658123","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

Integrating hybrid deep learning and path allocation for real-time inbound passenger flow prediction and anomaly detection in urban rail transit 将混合深度学习与路径分配相结合，用于城市轨道交通的实时进站客流预测和异常检测

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-12 DOI: 10.1016/j.ins.2024.121621

Huiran Liu , Zheng Wang , Zhiming Fang

This paper study the problem of real-time prediction of inbound passenger flow and the detection and alerting of abnormal passenger flows in urban rail transit (URT) networks. We propose a fused framework that combines a hybrid deep learning model and an evaluation strategy. Specifically, the learning model incorporates Graph Convolutional Networks (GCN), Gated Recurrent Units (GRU), and attention mechanisms to effectively capture spatial and temporal correlations in passenger flow data. The evaluation strategy utilizes a depth-first search algorithm to determine the optimal travel paths for each individual passenger. And based on the paths, we develop a real-time method for estimating the origin–destination (OD) matrix that utilizes both long-term and short-term historical destination trend vectors to reduce dimensions while improving predictive accuracy. Through extensive testing using data from the Shanghai rail transit system, we demonstrate that this fused framework achieves high prediction accuracy for inbound passenger flow at various stations while efficiently identifying and warning sudden large-scale events involving significant increases in passenger flow volume. This research contributes towards improving overall passenger experience as well as operational resilience within urban rail systems when dealing with large-scale influxes of passengers.

本文研究了城市轨道交通（URT）网络中进站客流的实时预测以及异常客流的检测和警报问题。我们提出了一种混合深度学习模型与评估策略相结合的融合框架。具体来说，该学习模型结合了图卷积网络（GCN）、门控递归单元（GRU）和注意力机制，以有效捕捉客流数据中的空间和时间相关性。评估策略采用深度优先搜索算法，以确定每个乘客的最佳旅行路径。根据这些路径，我们开发了一种实时估算出发地-目的地（OD）矩阵的方法，利用长期和短期的历史目的地趋势向量来减少维数，同时提高预测精度。通过使用上海轨道交通系统的数据进行广泛测试，我们证明了这一融合框架对不同车站的进站客流实现了较高的预测精度，同时还能有效识别和预警涉及客流量大幅增加的大规模突发事件。这项研究有助于改善整体乘客体验，并提高城市轨道交通系统在应对大规模客流时的运营应变能力。

{"title":"Integrating hybrid deep learning and path allocation for real-time inbound passenger flow prediction and anomaly detection in urban rail transit","authors":"Huiran Liu , Zheng Wang , Zhiming Fang","doi":"10.1016/j.ins.2024.121621","DOIUrl":"10.1016/j.ins.2024.121621","url":null,"abstract":"<div><div>This paper study the problem of real-time prediction of inbound passenger flow and the detection and alerting of abnormal passenger flows in urban rail transit (URT) networks. We propose a fused framework that combines a hybrid deep learning model and an evaluation strategy. Specifically, the learning model incorporates Graph Convolutional Networks (GCN), Gated Recurrent Units (GRU), and attention mechanisms to effectively capture spatial and temporal correlations in passenger flow data. The evaluation strategy utilizes a depth-first search algorithm to determine the optimal travel paths for each individual passenger. And based on the paths, we develop a real-time method for estimating the origin–destination (OD) matrix that utilizes both long-term and short-term historical destination trend vectors to reduce dimensions while improving predictive accuracy. Through extensive testing using data from the Shanghai rail transit system, we demonstrate that this fused framework achieves high prediction accuracy for inbound passenger flow at various stations while efficiently identifying and warning sudden large-scale events involving significant increases in passenger flow volume. This research contributes towards improving overall passenger experience as well as operational resilience within urban rail systems when dealing with large-scale influxes of passengers.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121621"},"PeriodicalIF":8.1,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704066","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

Dynamic quantization of event-triggered adaptive sliding mode control for networked control systems under false data injection attack 虚假数据注入攻击下网络控制系统事件触发自适应滑模控制的动态量化

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-12 DOI: 10.1016/j.ins.2024.121626

Xinggui Zhao, Bo Meng, Zhen Wang

The dynamic quantization of event-triggered (ET) adaptive sliding mode control (SM, SMC) for networked control systems (NCS) under false data injection attack (FDIA) is considered in this article. To begin with, to reduce the network transmission burden, dynamic quantizers are used to quantize the states and the input on the channels from the plant to the ET mechanism and from the controller to the plant, respectively. Secondly, the dynamic ET mechanism employs quantized state error, and the existence of the minimum inter-event time demonstrates that the system does not experience the Zeno phenomenon. Thirdly, this paper uses the adaptive parameter to estimate the unknown upper bound of the attack mode. In addition, the range of values for the adaptive gain of the SMC is derived by combining with the Lyapunov stability theory. On the last, the comparative simulation results of different methods for numerical examples are given to verify the superiority of the method proposed in this paper.

本文研究了在虚假数据注入攻击（FDIA）下网络控制系统（NCS）的事件触发（ET）自适应滑模控制（SM，SMC）的动态量化问题。首先，为了减少网络传输负担，本文使用动态量化器分别量化从工厂到 ET 机制以及从控制器到工厂的通道上的状态和输入。其次，动态 ET 机制采用量化状态误差，最小事件间时间的存在表明系统不会出现芝诺现象。第三，本文利用自适应参数估计攻击模式的未知上限。此外，本文还结合李雅普诺夫稳定性理论，得出了 SMC 自适应增益的取值范围。最后，本文给出了不同方法的数值实例仿真结果对比，以验证本文所提方法的优越性。

引用次数: 0

LSketch: A label-enabled graph stream sketch toward time-sensitive queries LSketch：支持标签的图流草图，用于时间敏感型查询

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-09 DOI: 10.1016/j.ins.2024.121624

Yiling Zeng , Chuanfeng Jian , Chunyao Song , Tingjian Ge , Yuhan Li , Yuqing Zhou

Heterogeneous graph streams represent data interactions in real-world applications and are characterized by dynamic and heterogeneous properties including varying node labels, edge labels and edge weights. The mining of graph streams is critical in fields such as network security, social network analysis, and traffic control. However, the sheer volume and high dynamics of graph streams pose significant challenges for efficient storage and accurate query analysis. To address these challenges, we propose LSketch, a novel sketch technique designed for heterogeneous graph streams. Unlike traditional methods, LSketch effectively preserves the diverse label information inherent in these streams, enhancing the expressive ability of sketches. Furthermore, as graph streams evolve over time, some edges may become outdated and lose their relevance. LSketch incorporates a sliding window model that eliminates expired edges, ensuring that the analysis remains focused on the most current and relevant data automatically. LSketch operates with sub-linear storage space and supports both structure-based and time-sensitive queries with high accuracy. We perform extensive experiments over four real datasets, demonstrating that LSketch outperforms state-of-the-art methods in terms of query accuracy and time efficiency.

异构图流代表了真实世界应用中的数据交互，具有动态和异构特性，包括节点标签、边标签和边权重的变化。图流的挖掘在网络安全、社交网络分析和交通控制等领域至关重要。然而，图流的庞大数量和高动态性给高效存储和准确查询分析带来了巨大挑战。为了应对这些挑战，我们提出了 LSketch，一种专为异构图流设计的新型草图技术。与传统方法不同，LSketch 有效地保留了这些图流中固有的各种标签信息，增强了草图的表达能力。此外，随着图流的不断演化，一些边可能会过时并失去相关性。LSketch 采用了一种滑动窗口模型，可以消除过期的边缘，确保自动将分析重点放在最新的相关数据上。LSketch 使用亚线性存储空间运行，支持基于结构的高精度查询和时间敏感型查询。我们在四个真实数据集上进行了大量实验，证明 LSketch 在查询准确性和时间效率方面都优于最先进的方法。

{"title":"LSketch: A label-enabled graph stream sketch toward time-sensitive queries","authors":"Yiling Zeng , Chuanfeng Jian , Chunyao Song , Tingjian Ge , Yuhan Li , Yuqing Zhou","doi":"10.1016/j.ins.2024.121624","DOIUrl":"10.1016/j.ins.2024.121624","url":null,"abstract":"<div><div>Heterogeneous graph streams represent data interactions in real-world applications and are characterized by dynamic and heterogeneous properties including varying node labels, edge labels and edge weights. The mining of graph streams is critical in fields such as network security, social network analysis, and traffic control. However, the sheer volume and high dynamics of graph streams pose significant challenges for efficient storage and accurate query analysis. To address these challenges, we propose LSketch, a novel sketch technique designed for heterogeneous graph streams. Unlike traditional methods, LSketch effectively preserves the diverse label information inherent in these streams, enhancing the expressive ability of sketches. Furthermore, as graph streams evolve over time, some edges may become outdated and lose their relevance. LSketch incorporates a sliding window model that eliminates expired edges, ensuring that the analysis remains focused on the most current and relevant data automatically. LSketch operates with sub-linear storage space and supports both structure-based and time-sensitive queries with high accuracy. We perform extensive experiments over four real datasets, demonstrating that LSketch outperforms state-of-the-art methods in terms of query accuracy and time efficiency.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"691 ","pages":"Article 121624"},"PeriodicalIF":8.1,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658024","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

Modeling information propagation for target user groups in online social networks based on guidance and incentive strategies 基于引导和激励策略的在线社交网络目标用户群信息传播建模

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-08 DOI: 10.1016/j.ins.2024.121628

Lei Meng , Guiqiong Xu , Chen Dong , Shoujin Wang

The rapid development of online social networks has greatly facilitated the dissemination and sharing of information. Effectively guiding the propagation of information to specific target groups is a significant and challenging research issue, which can be formulated as the target propagation problem. Most existing studies, however, focus on traditional information propagation methods, treating all users in the network as target audiences, which results in low efficiency and high costs. To address this issue, we propose a novel information propagation model that incorporates adaptive guidance and incentive strategies, called the

S I I_{i n} R_{g u}

model, to simulate the target spreading process in online social networks. Our model is designed to enhance both global communication capabilities and information transmission efficiency by introducing a mutual influence score that quantifies the interaction between target and non-target users. Based on this, the

S I I_{i n} R_{g u}

model adaptively guides and incentivizes non-target users to disseminate information specifically to target user groups. We conducted several groups of experiments on nine real-world social networks, assessing scenarios with both single and multiple target groups. Experimental results demonstrate that the

S I I_{i n} R_{g u}

model outperforms existing methods in terms of target influence range and the effectiveness of information spreading, thereby offering valuable insights for practical applications.

在线社交网络的快速发展极大地促进了信息的传播和共享。如何有效引导信息向特定目标群体传播是一个重要而富有挑战性的研究课题，可将其表述为目标传播问题。然而，现有的大多数研究都集中在传统的信息传播方法上，将网络中的所有用户都视为目标受众，导致效率低、成本高。为解决这一问题，我们提出了一种融合了自适应引导和激励策略的新型信息传播模型，称为 SIIinRgu 模型，用于模拟在线社交网络中的目标传播过程。我们的模型旨在通过引入相互影响分值来量化目标用户和非目标用户之间的互动，从而提高全局传播能力和信息传播效率。在此基础上，SIIinRgu 模型自适应地引导和激励非目标用户专门向目标用户群传播信息。我们在九个真实世界的社交网络上进行了多组实验，评估了单一目标群体和多个目标群体的情景。实验结果表明，SIIinRgu 模型在目标影响范围和信息传播效果方面优于现有方法，从而为实际应用提供了有价值的见解。

{"title":"Modeling information propagation for target user groups in online social networks based on guidance and incentive strategies","authors":"Lei Meng , Guiqiong Xu , Chen Dong , Shoujin Wang","doi":"10.1016/j.ins.2024.121628","DOIUrl":"10.1016/j.ins.2024.121628","url":null,"abstract":"<div><div>The rapid development of online social networks has greatly facilitated the dissemination and sharing of information. Effectively guiding the propagation of information to specific target groups is a significant and challenging research issue, which can be formulated as the <em>target propagation</em> problem. Most existing studies, however, focus on traditional information propagation methods, treating all users in the network as target audiences, which results in low efficiency and high costs. To address this issue, we propose a novel information propagation model that incorporates adaptive guidance and incentive strategies, called the <span><math><mi>S</mi><mi>I</mi><msub><mrow><mi>I</mi></mrow><mrow><mi>i</mi><mi>n</mi></mrow></msub><msub><mrow><mi>R</mi></mrow><mrow><mi>g</mi><mi>u</mi></mrow></msub></math></span> model, to simulate the target spreading process in online social networks. Our model is designed to enhance both global communication capabilities and information transmission efficiency by introducing a mutual influence score that quantifies the interaction between target and non-target users. Based on this, the <span><math><mi>S</mi><mi>I</mi><msub><mrow><mi>I</mi></mrow><mrow><mi>i</mi><mi>n</mi></mrow></msub><msub><mrow><mi>R</mi></mrow><mrow><mi>g</mi><mi>u</mi></mrow></msub></math></span> model adaptively guides and incentivizes non-target users to disseminate information specifically to target user groups. We conducted several groups of experiments on nine real-world social networks, assessing scenarios with both single and multiple target groups. Experimental results demonstrate that the <span><math><mi>S</mi><mi>I</mi><msub><mrow><mi>I</mi></mrow><mrow><mi>i</mi><mi>n</mi></mrow></msub><msub><mrow><mi>R</mi></mrow><mrow><mi>g</mi><mi>u</mi></mrow></msub></math></span> model outperforms existing methods in terms of target influence range and the effectiveness of information spreading, thereby offering valuable insights for practical applications.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"691 ","pages":"Article 121628"},"PeriodicalIF":8.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658133","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

Antagonistic-information-dependent integral-type event-trigger scheme for bipartite synchronization of cooperative-competitive neural networks and its application 用于合作竞争神经网络两端同步的拮抗-信息依赖积分型事件触发方案及其应用

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-08 DOI: 10.1016/j.ins.2024.121617

Xindong Si , Yingjie Fan , Zhen Wang

This paper focuses on the bipartite synchronization problem for cooperative-competitive neural networks (CCNNs) by using an antagonistic-information-dependent integral-type event-trigger scheme. Here, the designed antagonistic-information implies that both the cooperation and competition interactions of CCNNs are utilized to design trigger scheme. First, the signed digraph theory, in the presence of structurally balanced topology, is used to describe the antagonistic interactions among neuron nodes. On this basis, such a trigger scheme consisting of antagonistic-information and integral term is proposed to relax communication burden, which can remember the evolution information of CCNNs dynamic process. Meanwhile, the discontinuity of event-triggered scheme can avoid the occurrence of Zeno behavior directly without complicated mathematical analysis. Then, an important lemma is derived to facilitate bipartite synchronization problem. By constructing appropriate Lyapunov function, two novel bipartite synchronization criteria are developed by utilizing the hybrid Lyapunov theories, new lemma, and inequality techniques. At last, an application and an effective example are presented to illustrate the validity and advantage of the proposed method.

本文通过使用依赖于拮抗信息的积分型事件触发方案，重点研究了合作竞争神经网络（CCNN）的两端同步问题。在这里，所设计的拮抗信息意味着利用 CCNN 的合作与竞争相互作用来设计触发方案。首先，在拓扑结构平衡的情况下，使用签名数字图理论来描述神经元节点之间的拮抗相互作用。在此基础上，提出了由拮抗信息和积分项组成的触发方案，以减轻通信负担，从而记住 CCNN 动态过程的演化信息。同时，事件触发方案的不连续性可以直接避免芝诺行为的发生，而无需复杂的数学分析。然后，推导出了一个重要的两端同步问题。通过构建适当的 Lyapunov 函数，利用混合 Lyapunov 理论、新的 Lemma 和不等式技术，提出了两个新的双端同步准则。最后，介绍了一个应用和有效实例，以说明所提方法的有效性和优势。

{"title":"Antagonistic-information-dependent integral-type event-trigger scheme for bipartite synchronization of cooperative-competitive neural networks and its application","authors":"Xindong Si , Yingjie Fan , Zhen Wang","doi":"10.1016/j.ins.2024.121617","DOIUrl":"10.1016/j.ins.2024.121617","url":null,"abstract":"<div><div>This paper focuses on the bipartite synchronization problem for cooperative-competitive neural networks (CCNNs) by using an antagonistic-information-dependent integral-type event-trigger scheme. Here, the designed antagonistic-information implies that both the cooperation and competition interactions of CCNNs are utilized to design trigger scheme. First, the signed digraph theory, in the presence of structurally balanced topology, is used to describe the antagonistic interactions among neuron nodes. On this basis, such a trigger scheme consisting of antagonistic-information and integral term is proposed to relax communication burden, which can remember the evolution information of CCNNs dynamic process. Meanwhile, the discontinuity of event-triggered scheme can avoid the occurrence of Zeno behavior directly without complicated mathematical analysis. Then, an important lemma is derived to facilitate bipartite synchronization problem. By constructing appropriate Lyapunov function, two novel bipartite synchronization criteria are developed by utilizing the hybrid Lyapunov theories, new lemma, and inequality techniques. At last, an application and an effective example are presented to illustrate the validity and advantage of the proposed method.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"691 ","pages":"Article 121617"},"PeriodicalIF":8.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658187","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 context-enhanced neural network model for biomedical event trigger detection 用于生物医学事件触发检测的语境增强型神经网络模型

IF 8.1 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2024-11-08 DOI: 10.1016/j.ins.2024.121625

Zilin Wang , Yafeng Ren , Qiong Peng , Donghong Ji

As an important component of biomedical event extraction, biomedical event trigger detection has received extensive research attention in recent years. Most studies focus on designing various models or features according to the original text itself, but fail to leverage contextual information of the original text from external knowledge base such as Wikipedia, which is publicly available. To address the issue, we propose a context-enhanced neural network model that automatically integrates the related information from external knowledge base for biomedical event trigger detection. Specifically, the proposed model first extracts the related context of the original text from external knowledge base. Then the original text and its context are sequentially fed into the BERT embedding layer and Transformer convolution layer to learn high-level semantic representation. Finally, the probability of possible tags is calculated using the CRF layer. Experimental results on the MLEE dataset show our proposed model achieves 86.83% F1 score, outperforming the existing methods and context-enhanced baseline systems significantly. Experimental analysis also indicates the effectiveness of contextual information for trigger detection in biomedical domain.

作为生物医学事件提取的重要组成部分，生物医学事件触发检测近年来受到了广泛的研究关注。大多数研究都侧重于根据原文本身设计各种模型或特征，但却未能从维基百科等公开的外部知识库中充分利用原文的上下文信息。针对这一问题，我们提出了一种上下文增强神经网络模型，该模型可自动整合外部知识库中的相关信息，用于生物医学事件触发检测。具体来说，该模型首先从外部知识库中提取原文的相关上下文。然后，将原文及其上下文依次输入 BERT 嵌入层和 Transformer 卷积层，以学习高级语义表征。最后，使用 CRF 层计算可能标签的概率。在 MLEE 数据集上的实验结果表明，我们提出的模型获得了 86.83% 的 F1 分数，明显优于现有方法和上下文增强基线系统。实验分析还表明了上下文信息在生物医学领域触发检测中的有效性。

{"title":"A context-enhanced neural network model for biomedical event trigger detection","authors":"Zilin Wang , Yafeng Ren , Qiong Peng , Donghong Ji","doi":"10.1016/j.ins.2024.121625","DOIUrl":"10.1016/j.ins.2024.121625","url":null,"abstract":"<div><div>As an important component of biomedical event extraction, biomedical event trigger detection has received extensive research attention in recent years. Most studies focus on designing various models or features according to the original text itself, but fail to leverage contextual information of the original text from external knowledge base such as Wikipedia, which is publicly available. To address the issue, we propose a context-enhanced neural network model that automatically integrates the related information from external knowledge base for biomedical event trigger detection. Specifically, the proposed model first extracts the related context of the original text from external knowledge base. Then the original text and its context are sequentially fed into the BERT embedding layer and Transformer convolution layer to learn high-level semantic representation. Finally, the probability of possible tags is calculated using the CRF layer. Experimental results on the MLEE dataset show our proposed model achieves 86.83% F1 score, outperforming the existing methods and context-enhanced baseline systems significantly. Experimental analysis also indicates the effectiveness of contextual information for trigger detection in biomedical domain.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"691 ","pages":"Article 121625"},"PeriodicalIF":8.1,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142658035","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