{"title":"Zilean: A modularized framework for large-scale temporal concept drift type classification","authors":"Zhao Deng , QuanXi Feng , Bin Lin , Gary G. Yen","doi":"10.1016/j.ins.2025.122134","DOIUrl":"10.1016/j.ins.2025.122134","url":null,"abstract":"<div><div>In the analysis of time series data, particularly in real-world applications, concept drift classification is crucial for enabling models to adapt in a differentiated manner to future data. To address the challenge of identifying diverse types of drift, we propose Zilean, a novel framework that integrates feature-based and predictor-based techniques while accounting for drift residues and fragmentation during repeated drift detection. The framework incorporates the pre-trained BERT-Base language model into its classifier design, leveraging deep learning for automatic drift classification and eliminating the need for judgment curve analysis. To evaluate its performance, experiments were conducted on a variety of real-world and synthetic datasets, each exhibiting different types of concept drift. The results show that on real-world datasets, our framework achieves a classification accuracy of 91.03%, outperforming XGBoost by 7.94% and surpassing TCN-CNN by 4.28%. Additionally, experiments exploring a frozen parameter strategy and the use of a more lightweight language model, DistilBERT, further enhance accuracy to 96.93% and 97.17%, respectively. These findings underscore the framework's effectiveness in large-scale temporal concept drift classification.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122134"},"PeriodicalIF":8.1,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739395","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}
Gökhan Göksel, Ahmet Aydın, Zeynep Batmaz, Cihan Kaleli
{"title":"A novel missing value imputation for multi-criteria recommender systems","authors":"Gökhan Göksel, Ahmet Aydın, Zeynep Batmaz, Cihan Kaleli","doi":"10.1016/j.ins.2025.122139","DOIUrl":"10.1016/j.ins.2025.122139","url":null,"abstract":"<div><div>As the internet continues to expand, users increasingly rely on digital platforms for activities such as movie streaming and travel planning, leading to an overwhelming amount of information. This information overload complicates the process of making efficient and informed decisions. To address this challenge, personalized recommender systems, particularly multi-criteria collaborative filtering (MCCF) models, have been developed to tailor recommendations based on detailed user evaluations across various sub-criteria. However, as the number of criteria in MCCF systems increases, the issue of data sparsity becomes more prominent, with more criteria resulting in more missing evaluations. In this study, we introduce an innovative application of the Bidirectional Encoder Representations from Transformers (BERT) model—well-known for its advances in natural language processing—to impute missing values within MCCF systems. By leveraging contextual insights from user reviews, we hypothesize that BERT can enhance the imputation process, thereby improving coverage and recommendation accuracy in MCCF models. Our experimental results indicate that BERT-based imputation significantly reduces data sparsity and enhances the accuracy and coverage of recommendations. This study underscores BERT's potential in processing linguistic data and highlights its utility in multi-criteria recommender systems. Integrating BERT with MCCF offers a promising advancement in addressing the inherent challenges of personalized recommendation systems.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122139"},"PeriodicalIF":8.1,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739391","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}
Bohua Li , Ming Chen , Lining Xing , Yingguo Chen , Yingwu Chen
{"title":"Optimizing time-dependent multi-agile Earth observation satellite scheduling problem using deep Q-learning and ensemble heuristics","authors":"Bohua Li , Ming Chen , Lining Xing , Yingguo Chen , Yingwu Chen","doi":"10.1016/j.ins.2025.122140","DOIUrl":"10.1016/j.ins.2025.122140","url":null,"abstract":"<div><div>The Multi-Agile Earth Observation Satellite Scheduling Problem (MAEOSSP) aims to maximize the total observation profits of a multi-satellite system while satisfying temporal and resource constraints. This problem has gained prominence owing to the increasing complexity of task scheduling scenarios and challenges in satellite management and control. MAEOSSP typically consists of two decision-making stages: task allocation and single-satellite scheduling. However, its NP-hard characteristic renders traditional methods susceptible to problem instance variations and computationally intensive. To address these issues, we propose the TAM-ECH, which integrates a Task Allocation Model (TAM) and an Ensemble Construction Heuristic (ECH) to solve MAEOSSP. TAM utilizes a Deep Q-learning Network (DQN) to efficiently allocate tasks to each satellite, while ECH employs ensemble heuristics for fast and stable single-satellite scheduling. Experimental results demonstrate that TAM-ECH outperforms state-of-the-art algorithms in both optimization speed and quality. On average, it achieves a profit rate 6% higher than GRILS and 30% higher than A-ALNS, with reduced solving time. Further experiments validate TAM's efficiency in task allocation and ECH's ability to provide stable, high-quality foundational assistance. Therefore, TAM-ECH provides an efficient solution to MAEOSSP, demonstrating its potential for application in upcoming large constellations and new management modes.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122140"},"PeriodicalIF":8.1,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739394","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}
{"title":"General decay projection synchronization of proportional delay memristive competitive neural networks with uncertain parameters for image encryption","authors":"Yaru Wang , Liqun Zhou","doi":"10.1016/j.ins.2025.122136","DOIUrl":"10.1016/j.ins.2025.122136","url":null,"abstract":"<div><div>This research delves into the general decay projection synchronization (GDPS) in memristive competitive neural networks (MCNNs) incorporating proportional delays and uncertain parameters. There are two main aspects to consider: one is to add switch controllers to both long-term memory (LTM) and short-term memory (STM), and the other is that given that MCNNs are coupled systems, we only add the controller to STM. Then, by formulating appropriate Lyapunov functional and using inequality methods, algebraic synchronization criteria for implementing GDPS behavior are derived, all of which rely on proportional delayed factors. To validate the effectiveness of our proposed methods, we conduct two numerical examples and apply one of them to image encryption.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122136"},"PeriodicalIF":8.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739393","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}
{"title":"Distributed neurodynamic optimization for optimal multicluster resource allocation with cardinality constraints","authors":"Meng Lin , Zicong Xia , Shuting Sun , Yang Liu","doi":"10.1016/j.ins.2025.122138","DOIUrl":"10.1016/j.ins.2025.122138","url":null,"abstract":"<div><div>In this paper, a distributed neurodynamic optimization method is developed for a class of multicluster resource allocation models with 0-1 integer constraints and cardinality constraints. In the optimization model, the objective function is the sum of multiple clusters of convex local objective functions with 0-1 integer constraints that lead to nonconvexity; additionally, the resource allocation model is subject to globally coupled resource allocation constraints and bound constraints, and the cardinality constraints are introduced to limit the total number of resource-allocated points in each cluster. To address challenges caused by the nonconvexity and hybrid constraints, a distributed neurodynamic optimization method based on an augmented Lagrangian function is developed, and it is proven to converge to a local minimum. The validity of the main results is demonstrated via two examples involving a power system.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122138"},"PeriodicalIF":8.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739396","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}
{"title":"Polytomous knowledge structures constructed by L-fuzzy approximation operators","authors":"Bochi Xu , Jinjin Li , Fugui Shi","doi":"10.1016/j.ins.2025.122137","DOIUrl":"10.1016/j.ins.2025.122137","url":null,"abstract":"<div><div>Rough set theory is more concerned with the character of the upper and lower approximations of a particular set than with the overall structure. Knowledge space theory can provide another new perspective on rough sets. In this paper, we establish a theoretical linkage between polytomous knowledge structures and <em>L</em>-fuzzy approximation operators. We generate polytomous knowledge structures constructed by <em>L</em>-fuzzy approximation operators and give the corresponding properties, and find that a polytomous knowledge space (polytomous closure space, respectively) and can be completely characterized by an upper (lower, respectively) <em>L</em>-fuzzy approximation. In particular, we discuss the dichotomous knowledge structure by the means of fuzzy approximation operators, which corresponds to the method of fuzzy skill maps. Finally, by <em>L</em>-fuzzy relation constructing two particular dichotomous knowledge structures, which are called backward-graded and forward-graded, is also discussed. This study proposes a framework to analyze <em>L</em>-fuzzy rough sets through knowledge space theory, bridging these mathematical disciplines.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122137"},"PeriodicalIF":8.1,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739392","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}
{"title":"Knowledge-aware differential equation discovery with automated background knowledge extraction","authors":"Elizaveta Ivanchik, Alexander Hvatov","doi":"10.1016/j.ins.2025.122131","DOIUrl":"10.1016/j.ins.2025.122131","url":null,"abstract":"<div><div>In differential equation discovery algorithms, a priori expert knowledge is mainly used to constrain the form of the expected equation, making it impossible for the algorithm to truly discover equations. As a result, most differential equation discovery algorithms try to recover the coefficients for a known fixed form of the equation. In this paper, we, using the initial guess obtained automatically, modify the structure space instead of imposing rigid constraints so that specific terms appear more likely within the cross-over and mutation operators. In this way, we mimic expertly chosen terms while preserving the possibility of obtaining any form of differential equation. The paper shows that the extraction and use of knowledge allow it to outperform the SINDy algorithm in terms of search stability and robustness. Synthetic examples are given for Burgers, wave, and Korteweg–de Vries equations.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122131"},"PeriodicalIF":8.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724336","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}
{"title":"A stable framework-based modeling of the complex dynamical system using a double context layered with self-weighted output feedback loop Elman recurrent neural network","authors":"Rajesh Kumar","doi":"10.1016/j.ins.2025.122132","DOIUrl":"10.1016/j.ins.2025.122132","url":null,"abstract":"<div><div>In this paper, a modified structure of the classical Elman recurrent neural network (ERNN) named Double context layered with output self-weighted feedback loop Elman recurrent neural network (DCLOSWFLERNN) is proposed. It consists of two additional components (as compared to the ERNN model): one extra context layer and an adjustable weighted feedback loop in the output layer. This has resulted in the model's ability to approximate the underlying unknown mathematical relationship relating to the input-output data (obtained from any complex dynamical plant). The second emphasis of this paper pertains to the stability component, wherein the Lyapunov stability is utilized to develop a stable Back-propagation (BP) based weight update rule. Lastly, an adjustable learning rate is also suggested, which contributes to improving the learning algorithm's overall performance. The simulation results reveal that the proposed model has given better modeling accuracy as compared to the other considered neural models. This can be observed from the values obtained of the error-based indicators such as Root Mean Square Error (RMSE) and Mean Average Error (MSE). The values of RMSE and MAE obtained from the proposed model during the modeling procedure are 0.0028 and 0.0035 which are the least among the obtained with other neural models.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122132"},"PeriodicalIF":8.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705465","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}
Xiaoyang Liu , Minghao Hui , Lu Fan , Wenwu Yu , Jinde Cao
{"title":"Adaptive fuzzy funnel control of nonlinear multi-agent systems via dual-channel event-triggered strategy","authors":"Xiaoyang Liu , Minghao Hui , Lu Fan , Wenwu Yu , Jinde Cao","doi":"10.1016/j.ins.2025.122129","DOIUrl":"10.1016/j.ins.2025.122129","url":null,"abstract":"<div><div>This paper focuses on the constraint control problem of nonlinear multi-agent systems (MASs). An adjustable funnel control is proposed by designing a new transformation variable, which ensures the consensus errors converge within the funnel. By utilizing adaptive fuzzy logic systems, the unknown dynamics of agents are approximated. A novel dual-channel event-triggered strategy is designed by employing the concept of two channels, to save the communication resources and controller resources at the same time. Meanwhile, the Zeno behavior is avoided as well. Two simulation results demonstrate the effectiveness of the proposed control approach.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122129"},"PeriodicalIF":8.1,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705466","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}
{"title":"Semantic enhanced bi-syntactic graph convolutional network for aspect-based sentiment analysis","authors":"Junyang Xiao , Yun Xue , Fenghuan Li","doi":"10.1016/j.ins.2025.122130","DOIUrl":"10.1016/j.ins.2025.122130","url":null,"abstract":"<div><div>Previous work on fine-grained sentiment analysis focuses on establishing the semantic correlations between words by means of attention mechanisms. More recently, effects of syntax-based models, applying graph convolution operation over dependency trees, are highlighted due to their superiority. However, these methods still have deficiencies. For one thing, little aspect-specific information is considered during semantic modeling of contextual words, which introduces irrelevant noise toward the aspect. For another, current syntax-based approaches either ignore the syntactic constituent knowledge, or fail to maintain the syntactic information from the reconstructed constituent tree. As such, no relation among words, phrases and clauses is built. In this work, a Semantic Enhanced Bi-Syntax Graph Convolutional Network (SEBS-GCN) is proposed to enhance semantics of context to the aspect, and capture the sentiment relevance among words, phrases and clauses. Specifically, we devise an aspect-aware gated mechanism to obtain the aspect-aware feature, based on the semantic correlations between the specific aspect and its contexts. Furthermore, the syntax information of the constituent tree is sufficiently exploited to analyze the hierarchical structure and the logical relation among words, phrases and clauses, based on which to capture the sentiment clues of the aspect.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"712 ","pages":"Article 122130"},"PeriodicalIF":8.1,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143705463","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}