Pub Date : 2024-11-28DOI: 10.1016/j.ins.2024.121707
Inayat Ullah , Muhammad Akram , Tofigh Allahviranloo
Multi-polar fuzzy sets are crucial for capturing and representing diverse opinions or conflicting criteria in decision-making processes with greater flexibility and precision. While, Z-numbers are important for effectively modeling uncertainty by incorporating both the reliability of information and its degree of fuzziness, enhancing decision-making in uncertain environments. To date, no model in the literature exhibits the properties of multi-polar fuzzy sets and Z-numbers. In this article, we introduce a new concept of multi-polar fuzzy Z-number and Hamacher operations for multi-polar fuzzy Z-numbers. Based on the Hamacher operations, we propose aggregation operators for multi-polar fuzzy Z-numbers, namely, multi-polar fuzzy Z-number Hamacher weighted averaging operator, multi-polar fuzzy Z-number Hamacher ordered weighted averaging operator, multi-polar fuzzy Z-number Hamacher weighted geometric operator and multi-polar fuzzy Z-number Hamacher ordered weighted geometric operator. Additionally, we develop a decision-making model based on the proposed Hamacher aggregation operators. Further, we apply the proposed technique to a couple of case studies to check the validity and authenticity of the proposed methodology. Finally, we compare the outcomes of the study with several existing techniques to assess the accuracy of the proposed model.
{"title":"Multi-criteria decision making with Hamacher aggregation operators based on multi-polar fuzzy Z-numbers","authors":"Inayat Ullah , Muhammad Akram , Tofigh Allahviranloo","doi":"10.1016/j.ins.2024.121707","DOIUrl":"10.1016/j.ins.2024.121707","url":null,"abstract":"<div><div>Multi-polar fuzzy sets are crucial for capturing and representing diverse opinions or conflicting criteria in decision-making processes with greater flexibility and precision. While, <em>Z</em>-numbers are important for effectively modeling uncertainty by incorporating both the reliability of information and its degree of fuzziness, enhancing decision-making in uncertain environments. To date, no model in the literature exhibits the properties of multi-polar fuzzy sets and <em>Z</em>-numbers. In this article, we introduce a new concept of multi-polar fuzzy <em>Z</em>-number and Hamacher operations for multi-polar fuzzy <em>Z</em>-numbers. Based on the Hamacher operations, we propose aggregation operators for multi-polar fuzzy <em>Z</em>-numbers, namely, multi-polar fuzzy <em>Z</em>-number Hamacher weighted averaging operator, multi-polar fuzzy <em>Z</em>-number Hamacher ordered weighted averaging operator, multi-polar fuzzy <em>Z</em>-number Hamacher weighted geometric operator and multi-polar fuzzy <em>Z</em>-number Hamacher ordered weighted geometric operator. Additionally, we develop a decision-making model based on the proposed Hamacher aggregation operators. Further, we apply the proposed technique to a couple of case studies to check the validity and authenticity of the proposed methodology. Finally, we compare the outcomes of the study with several existing techniques to assess the accuracy of the proposed model.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"694 ","pages":"Article 121707"},"PeriodicalIF":8.1,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747227","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}
Pub Date : 2024-11-28DOI: 10.1016/j.ins.2024.121693
Lingxiao Wu, Hao Chen, Zhouwang Yang
In the field of global optimization, finding the global optimum for complex problems remains a significant challenge. Traditional optimization methods often struggle to escape local minima and achieve global solutions, particularly when the initial solutions are far from the global optimum. This study addresses these challenges by introducing a novel algorithm called neural network transformation based global optimization. Our approach transforms original decision variables into higher-dimensional neural network parameters and constructs an empirical loss function using multiple sample points. By employing stochastic gradient descent for training, our approach effectively navigates the optimization landscape, escaping local minima and reaching low-loss solutions with high probability, even from distant starting points. We also propose a hybrid optimization method that combines the strength of metaheuristic strategies. The experimental results show that our hybrid method surpasses traditional global optimization algorithms, achieving an average 5% improvement in the success rate across benchmark functions. In practical applications, such as the B-spline curve approximation, our method reduces the fitting error by at least 10% compared with conventional approaches, delivering more accurate results. This study contributes a new gradient-based algorithm to the global optimization field, particularly effective for complex real-world problems where the initial points are far from the global minima.
{"title":"A neural network transformation based global optimization algorithm","authors":"Lingxiao Wu, Hao Chen, Zhouwang Yang","doi":"10.1016/j.ins.2024.121693","DOIUrl":"10.1016/j.ins.2024.121693","url":null,"abstract":"<div><div>In the field of global optimization, finding the global optimum for complex problems remains a significant challenge. Traditional optimization methods often struggle to escape local minima and achieve global solutions, particularly when the initial solutions are far from the global optimum. This study addresses these challenges by introducing a novel algorithm called neural network transformation based global optimization. Our approach transforms original decision variables into higher-dimensional neural network parameters and constructs an empirical loss function using multiple sample points. By employing stochastic gradient descent for training, our approach effectively navigates the optimization landscape, escaping local minima and reaching low-loss solutions with high probability, even from distant starting points. We also propose a hybrid optimization method that combines the strength of metaheuristic strategies. The experimental results show that our hybrid method surpasses traditional global optimization algorithms, achieving an average 5% improvement in the success rate across benchmark functions. In practical applications, such as the B-spline curve approximation, our method reduces the fitting error by at least 10% compared with conventional approaches, delivering more accurate results. This study contributes a new gradient-based algorithm to the global optimization field, particularly effective for complex real-world problems where the initial points are far from the global minima.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"694 ","pages":"Article 121693"},"PeriodicalIF":8.1,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747226","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}
At present, (quasi-)overlap functions have been extended to various universes of discourse and become a hot research topic. Meanwhile, the investigation of extended aggregation operations for normal convex fuzzy truth values has also attracted much attention. This paper mainly studies the representation of quasi-overlap functions for normal convex fuzzy truth values based on generalized extended overlap functions, which is the fundamental problem in the whole study of overlap functions for normal convex fuzzy truth values. Firstly, we present the definitions of (restrictive-)quasi-overlap functions and lattice-ordered-(restrictive-)quasi-overlap functions for normal convex fuzzy truth values and generalized extended overlap functions, respectively. Secondly, we present the (equivalent) characterizations for the closure properties of generalized extended overlap functions for various fuzzy truth values. Thirdly, we characterize the basic properties of generalized extended overlap functions for normal convex fuzzy truth values. Finally, by an equivalent characterization with a prerequisite, we successfully represent quasi-overlap functions for normal convex fuzzy truth values based on generalized extended overlap functions. Notably, we can quickly obtain (restrictive-)quasi-overlap functions for normal convex fuzzy truth values using the left-continuous quasi-overlap functions on interval . Moreover, regarding the relationships between four types of quasi-overlap functions for normal convex fuzzy truth values, the details implication relations are that lattice-ordered-(restrictive-)quasi-overlap functions are strictly stronger than (restrictive-)quasi-overlap functions for normal convex fuzzy truth values even if all of them are constructed by generalized extended overlap functions.
{"title":"Representation of quasi-overlap functions for normal convex fuzzy truth values based on generalized extended overlap functions","authors":"Yiding Wang , Junsheng Qiao , Wei Zhang , Humberto Bustince","doi":"10.1016/j.ins.2024.121710","DOIUrl":"10.1016/j.ins.2024.121710","url":null,"abstract":"<div><div>At present, (quasi-)overlap functions have been extended to various universes of discourse and become a hot research topic. Meanwhile, the investigation of extended aggregation operations for normal convex fuzzy truth values has also attracted much attention. This paper mainly studies the representation of quasi-overlap functions for normal convex fuzzy truth values based on generalized extended overlap functions, which is the fundamental problem in the whole study of overlap functions for normal convex fuzzy truth values. Firstly, we present the definitions of (restrictive-)quasi-overlap functions and lattice-ordered-(restrictive-)quasi-overlap functions for normal convex fuzzy truth values and generalized extended overlap functions, respectively. Secondly, we present the (equivalent) characterizations for the closure properties of generalized extended overlap functions for various fuzzy truth values. Thirdly, we characterize the basic properties of generalized extended overlap functions for normal convex fuzzy truth values. Finally, by an equivalent characterization with a prerequisite, we successfully represent quasi-overlap functions for normal convex fuzzy truth values based on generalized extended overlap functions. Notably, we can quickly obtain (restrictive-)quasi-overlap functions for normal convex fuzzy truth values using the left-continuous quasi-overlap functions on interval <span><math><mo>[</mo><mn>0</mn><mo>,</mo><mn>1</mn><mo>]</mo></math></span>. Moreover, regarding the relationships between four types of quasi-overlap functions for normal convex fuzzy truth values, the details implication relations are that lattice-ordered-(restrictive-)quasi-overlap functions are strictly stronger than (restrictive-)quasi-overlap functions for normal convex fuzzy truth values even if all of them are constructed by generalized extended overlap functions.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"694 ","pages":"Article 121710"},"PeriodicalIF":8.1,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747225","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}
Pub Date : 2024-11-28DOI: 10.1016/j.ins.2024.121711
A. Argente-Garrido , C. Zuheros , M.V. Luzón , F. Herrera
Trustworthy Artificial Intelligence solutions are essential in today's data-driven applications, prioritizing principles such as robustness, safety, transparency, explainability, and privacy among others. This has led to the emergence of Federated Learning as a solution for privacy and distributed machine learning. While decision trees, as self-explanatory models, are ideal for collaborative model training across multiple devices in resource-constrained environments such as federated learning environments for injecting interpretability in these models. Decision tree structure makes the aggregation in a federated learning environment not trivial. They require techniques that can merge their decision paths without introducing bias or overfitting while keeping the aggregated decision trees robust and generalizable. In this paper, we propose an Interpretable Client Decision Tree Aggregation process for Federated Learning scenarios that keeps the interpretability and the precision of the base decision trees used for the aggregation. This model is based on aggregating multiple decision paths of the decision trees and can be used on different decision tree types, such as ID3, CART and C4.5. We carry out the experiments within four datasets, and the analysis shows that the tree built with the model improves the local models without federated learning, and outperforms the state-of-the-art.
{"title":"An interpretable client decision tree aggregation process for federated learning","authors":"A. Argente-Garrido , C. Zuheros , M.V. Luzón , F. Herrera","doi":"10.1016/j.ins.2024.121711","DOIUrl":"10.1016/j.ins.2024.121711","url":null,"abstract":"<div><div>Trustworthy Artificial Intelligence solutions are essential in today's data-driven applications, prioritizing principles such as robustness, safety, transparency, explainability, and privacy among others. This has led to the emergence of Federated Learning as a solution for privacy and distributed machine learning. While decision trees, as self-explanatory models, are ideal for collaborative model training across multiple devices in resource-constrained environments such as federated learning environments for injecting interpretability in these models. Decision tree structure makes the aggregation in a federated learning environment not trivial. They require techniques that can merge their decision paths without introducing bias or overfitting while keeping the aggregated decision trees robust and generalizable. In this paper, we propose an Interpretable Client Decision Tree Aggregation process for Federated Learning scenarios that keeps the interpretability and the precision of the base decision trees used for the aggregation. This model is based on aggregating multiple decision paths of the decision trees and can be used on different decision tree types, such as ID3, CART and C4.5. We carry out the experiments within four datasets, and the analysis shows that the tree built with the model improves the local models without federated learning, and outperforms the state-of-the-art.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"694 ","pages":"Article 121711"},"PeriodicalIF":8.1,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747223","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}
Pub Date : 2024-11-26DOI: 10.1016/j.ins.2024.121714
Gang Hu , Feiyang Huang , Bin Shu , Guo Wei
Path planning is a critical part of unmanned aerial vehicle (UAV) achieving mission objectives, and the complexity of this problem is further increased when used for a group of UAVs. In addition, introducing curves based on different polynomials can design a smooth path for UAV that is continuous and meets safety constraints. Considering the above challenges, this paper proposes a multi-algorithm hybrid ant colony optimizer (ACO) named MAHACO, which is used for a 3D smooth path planning model of a group of UAVs based on the Said-Ball curve (SBC, for short). Firstly, by using the basic principles of other intelligent algorithms, ACO is extended to the continuous domain and three strategies are designed. Subsequently, the adaptive foraging strategy optimizes the ability of ACO to balance the exploration and exploitation phases and enhances its exploration ability in the search space. In addition, the multi-stage stochastic strategy expands the exploration range of ACO in the search space by enriching the selection of random vectors. Finally, the aggregation-mutation strategy improves the behavioral diversity and dynamics of ACO. To test the overall performance of MAHACO, it is compared with some state-of-the-art or improved metaheuristic algorithms on the highest dimensional CEC2020 and CEC2022 test sets, respectively. From the experimental results, the proposed MAHACO exhibits stronger performance advantages on 17 of the 22 functions. Then, the collision avoidance constraint and the communication constraint are introduced into the basic 3D path planning model of single UAV, and the model is extended to the application of a group of UAVs. This paper establishes a 3D smooth path planning model of a group of UAVs by taking the control points of SBC as the optimization variable of intelligent algorithms. Compared with other algorithms that rank high in the overall performance on the benchmark sets, MAHACO demonstrates its better practicability through basic and smooth path planning models, respectively.
{"title":"MAHACO: Multi-algorithm hybrid ant colony optimizer for 3D path planning of a group of UAVs","authors":"Gang Hu , Feiyang Huang , Bin Shu , Guo Wei","doi":"10.1016/j.ins.2024.121714","DOIUrl":"10.1016/j.ins.2024.121714","url":null,"abstract":"<div><div>Path planning is a critical part of unmanned aerial vehicle (UAV) achieving mission objectives, and the complexity of this problem is further increased when used for a group of UAVs. In addition, introducing curves based on different polynomials can design a smooth path for UAV that is continuous and meets safety constraints. Considering the above challenges, this paper proposes a multi-algorithm hybrid ant colony optimizer (ACO) named MAHACO, which is used for a 3D smooth path planning model of a group of UAVs based on the Said-Ball curve (SBC, for short). Firstly, by using the basic principles of other intelligent algorithms, ACO is extended to the continuous domain and three strategies are designed. Subsequently, the adaptive foraging strategy optimizes the ability of ACO to balance the exploration and exploitation phases and enhances its exploration ability in the search space. In addition, the multi-stage stochastic strategy expands the exploration range of ACO in the search space by enriching the selection of random vectors. Finally, the aggregation-mutation strategy improves the behavioral diversity and dynamics of ACO. To test the overall performance of MAHACO, it is compared with some state-of-the-art or improved metaheuristic algorithms on the highest dimensional CEC2020 and CEC2022 test sets, respectively. From the experimental results, the proposed MAHACO exhibits stronger performance advantages on 17 of the 22 functions. Then, the collision avoidance constraint and the communication constraint are introduced into the basic 3D path planning model of single UAV, and the model is extended to the application of a group of UAVs. This paper establishes a 3D smooth path planning model of a group of UAVs by taking the control points of SBC as the optimization variable of intelligent algorithms. Compared with other algorithms that rank high in the overall performance on the benchmark sets, MAHACO demonstrates its better practicability through basic and smooth path planning models, respectively.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"694 ","pages":"Article 121714"},"PeriodicalIF":8.1,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747224","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}
Interval-valued time series (ITSs) multi-step forecasting research is still in its infancy. Two cruces here lie in counterintuitive or conservative nature of semantic descriptors for ITSs, and disregard for multiplicity of causalities resulting from uncertainty in causalities between data or between trends within a set of interval-valued data. In this paper, we put forth a type of joint interval-trend fuzzy information granules, which takes non-loss of within-interval information as the main design criterion. A modified fuzzy information granulation method carries originality in portraying intuitive and accurate interval-trends, directly linked with inherent relational constraints such as lower bound data should not be greater than upper bound data. Furthermore, we formulate a legible format of multi-factor fuzzy IF-THEN rules, which exhibits interesting interpretations to causalities between interval-trends at a higher level of multiplicity. The forecasting process is fuzzy rules-based, resulting in wise results by calculating rule firing weights. Thus, we develop a well construct of accuracy and interpretability for multi-step forecasting of ITSs, manifested in: (a) reducing cumulative errors by operating at the granular level, and (b) perceiving interval-trends in an intelligible manner and emphasizing multiple causalities via transparent fuzzy logic inference. Experimental results convincingly confirm the validity of the model.
{"title":"Causalities-multiplicity oriented joint interval-trend fuzzy information granulation for interval-valued time series multi-step forecasting","authors":"Yuqing Tang , Fusheng Yu , Wenyi Zeng , Chenxi Ouyang , Yanan Jiang , Yuming Liu","doi":"10.1016/j.ins.2024.121717","DOIUrl":"10.1016/j.ins.2024.121717","url":null,"abstract":"<div><div>Interval-valued time series (ITSs) multi-step forecasting research is still in its infancy. Two cruces here lie in counterintuitive or conservative nature of semantic descriptors for ITSs, and disregard for multiplicity of causalities resulting from uncertainty in causalities between data or between trends within a set of interval-valued data. In this paper, we put forth a type of joint interval-trend fuzzy information granules, which takes non-loss of within-interval information as the main design criterion. A modified fuzzy information granulation method carries originality in portraying intuitive and accurate interval-trends, directly linked with inherent relational constraints such as lower bound data should not be greater than upper bound data. Furthermore, we formulate a legible format of multi-factor fuzzy IF-THEN rules, which exhibits interesting interpretations to causalities between interval-trends at a higher level of multiplicity. The forecasting process is fuzzy rules-based, resulting in wise results by calculating rule firing weights. Thus, we develop a well construct of accuracy and interpretability for multi-step forecasting of ITSs, manifested in: (a) reducing cumulative errors by operating at the granular level, and (b) perceiving interval-trends in an intelligible manner and emphasizing multiple causalities via transparent fuzzy logic inference. Experimental results convincingly confirm the validity of the model.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"694 ","pages":"Article 121717"},"PeriodicalIF":8.1,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747222","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}
Pub Date : 2024-11-22DOI: 10.1016/j.ins.2024.121685
Ying Yang , Qinghua Zhang , Fan Zhao , Yunlong Cheng , Qin Xie , Guoyin Wang
Optimal scale combination (OSC) selection plays a crucial role in multi-scale decision systems for data mining and knowledge discovery, and its aim is to select an appropriate subsystem for classification or decision-making while keeping a certain consistency criterion. Selecting the OSC with existing methods requires judging the consistency of all multi-scale attributes; however, judging consistency and selecting scales for unimportant multi-scale attributes increases the selection cost in vain. Moreover, the existing definitions of OSC are only applicable to rough set classifiers (RSCs), which makes the selected OSC perform poorly on other machine learning classifiers. To this end, the main objective of this paper is to investigate multi-scale attribute subset selection and OSC selection applicable to any classifier in generalized multi-scale decision systems. First, a novel consistency criterion based on the multi-scale attribute subset is proposed, which is called p-consistency criterion. Second, the relevance and redundancy among multi-scale attributes are measured based on the information entropy, and an algorithm for selecting the multi-scale attribute subset is given based on this. Third, an extended definition of OSC, called the accuracy OSC, is proposed, which can be widely applied to classification tasks using any classifier. On this basis, an OSC selection algorithm based on genetic algorithm is proposed. Finally, the results of many experiments show that the proposed method can significantly improve the classification accuracy and selection efficiency.
{"title":"Optimal scale combination selection based on genetic algorithm in generalized multi-scale decision systems for classification","authors":"Ying Yang , Qinghua Zhang , Fan Zhao , Yunlong Cheng , Qin Xie , Guoyin Wang","doi":"10.1016/j.ins.2024.121685","DOIUrl":"10.1016/j.ins.2024.121685","url":null,"abstract":"<div><div>Optimal scale combination (OSC) selection plays a crucial role in multi-scale decision systems for data mining and knowledge discovery, and its aim is to select an appropriate subsystem for classification or decision-making while keeping a certain consistency criterion. Selecting the OSC with existing methods requires judging the consistency of all multi-scale attributes; however, judging consistency and selecting scales for unimportant multi-scale attributes increases the selection cost in vain. Moreover, the existing definitions of OSC are only applicable to rough set classifiers (RSCs), which makes the selected OSC perform poorly on other machine learning classifiers. To this end, the main objective of this paper is to investigate multi-scale attribute subset selection and OSC selection applicable to any classifier in generalized multi-scale decision systems. First, a novel consistency criterion based on the multi-scale attribute subset is proposed, which is called <em>p</em>-consistency criterion. Second, the relevance and redundancy among multi-scale attributes are measured based on the information entropy, and an algorithm for selecting the multi-scale attribute subset is given based on this. Third, an extended definition of OSC, called the accuracy OSC, is proposed, which can be widely applied to classification tasks using any classifier. On this basis, an OSC selection algorithm based on genetic algorithm is proposed. Finally, the results of many experiments show that the proposed method can significantly improve the classification accuracy and selection efficiency.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"693 ","pages":"Article 121685"},"PeriodicalIF":8.1,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706187","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}
Pub Date : 2024-11-22DOI: 10.1016/j.ins.2024.121676
Mengjun Hu
Existing conflict analysis models, mostly based on Pawlak's framework, start with a situation table containing agent ratings toward issues. These ratings can take various formats with differing assumptions and are often implicitly assumed to be independent. However, in practice, an agent more often specifies the ratings through relative comparisons across issues. Furthermore, consistent interpretation of ratings is hard to achieve across different agents. A numeric rating of 0.7 might indicate very strong support when provided by a conservative agent but reflect only weak support when given by a radical agent. These challenges complicate both data collection and subsequent analysis. This paper proposes a preference-based conflict analysis model to address these limitations. The model begins with preference-based conflict situations, representing pairwise preferences over issues, and defines conflict degrees based on these preferences. It further establishes three-way agent relationships to capture conflict dynamics. The model integrates seamlessly with existing rating-based approaches, demonstrated through examples involving three-valued ratings and triangular-fuzzy-number ratings. A case study illustrates its practical applicability. By prioritizing preferences over direct ratings, the proposed approach ensures more intuitive and consistent data collection while enhancing the explainability and reliability of conflict analysis.
{"title":"Three-way conflict analysis with preference-based conflict situations","authors":"Mengjun Hu","doi":"10.1016/j.ins.2024.121676","DOIUrl":"10.1016/j.ins.2024.121676","url":null,"abstract":"<div><div>Existing conflict analysis models, mostly based on Pawlak's framework, start with a situation table containing agent ratings toward issues. These ratings can take various formats with differing assumptions and are often implicitly assumed to be independent. However, in practice, an agent more often specifies the ratings through relative comparisons across issues. Furthermore, consistent interpretation of ratings is hard to achieve across different agents. A numeric rating of 0.7 might indicate very strong support when provided by a conservative agent but reflect only weak support when given by a radical agent. These challenges complicate both data collection and subsequent analysis. This paper proposes a preference-based conflict analysis model to address these limitations. The model begins with preference-based conflict situations, representing pairwise preferences over issues, and defines conflict degrees based on these preferences. It further establishes three-way agent relationships to capture conflict dynamics. The model integrates seamlessly with existing rating-based approaches, demonstrated through examples involving three-valued ratings and triangular-fuzzy-number ratings. A case study illustrates its practical applicability. By prioritizing preferences over direct ratings, the proposed approach ensures more intuitive and consistent data collection while enhancing the explainability and reliability of conflict analysis.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"693 ","pages":"Article 121676"},"PeriodicalIF":8.1,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706181","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}
Pub Date : 2024-11-22DOI: 10.1016/j.ins.2024.121674
Christian Perez Bernal, Miguel A. Salido, Carlos March Moya
The industrial sector plays a significant role in global energy consumption and greenhouse gas emissions. To reduce this environmental impact, it's crucial to implement energy-efficient manufacturing systems that utilize sustainable materials and optimize energy usage. This can lead to benefits such as reduced carbon footprints and cost savings.
In recent years, metaheuristic approaches have been focused on minimizing energy consumption within the Unrelated Parallel Machine Scheduling Problem (UPMSP). Traditional methods often overlook complex factors like release dates, due dates, and job setup times. This research introduces a novel algorithm that integrates reinforcement learning (RL) with a genetic algorithm (GA) to address this gap.
The proposed RLGA algorithm, rooted in the dynamic field of evolutionary reinforcement learning, breaks down policies into smaller components to isolate essential parameters for problem-solving. Through comprehensive analysis, hyperparameters that influence optimal results are identified, facilitating automated hyperparameter selection and optimization. The expert system takes into account problem characteristics such as machine or job saturation, job overlap, and the maximum values of target variables, allowing instances to be grouped into clusters. These clusters are solved using a genetic algorithm with varying combinations of mutation and crossover hyperparameters. The most suitable approach for each cluster is determined by analyzing the results, and this configuration of hyperparameters is applied iteratively to optimize the solution search.
The effectiveness of RLGA is evaluated across benchmark instances with different complexities, machine sets, jobs, and constraints. Comprehensive comparisons against existing methods highlight the superior performance and efficiency of RLGA in optimizing energy use and solution quality. Experimental results show that RLGA outperforms well-known solvers like CPO, CPLEX, OR-tools, and Gecode, making it a promising approach for optimizing energy-efficient manufacturing systems.
{"title":"Optimizing energy efficiency in unrelated parallel machine scheduling problem through reinforcement learning","authors":"Christian Perez Bernal, Miguel A. Salido, Carlos March Moya","doi":"10.1016/j.ins.2024.121674","DOIUrl":"10.1016/j.ins.2024.121674","url":null,"abstract":"<div><div>The industrial sector plays a significant role in global energy consumption and greenhouse gas emissions. To reduce this environmental impact, it's crucial to implement energy-efficient manufacturing systems that utilize sustainable materials and optimize energy usage. This can lead to benefits such as reduced carbon footprints and cost savings.</div><div>In recent years, metaheuristic approaches have been focused on minimizing energy consumption within the Unrelated Parallel Machine Scheduling Problem (UPMSP). Traditional methods often overlook complex factors like release dates, due dates, and job setup times. This research introduces a novel algorithm that integrates reinforcement learning (RL) with a genetic algorithm (GA) to address this gap.</div><div>The proposed RLGA algorithm, rooted in the dynamic field of evolutionary reinforcement learning, breaks down policies into smaller components to isolate essential parameters for problem-solving. Through comprehensive analysis, hyperparameters that influence optimal results are identified, facilitating automated hyperparameter selection and optimization. The expert system takes into account problem characteristics such as machine or job saturation, job overlap, and the maximum values of target variables, allowing instances to be grouped into clusters. These clusters are solved using a genetic algorithm with varying combinations of mutation and crossover hyperparameters. The most suitable approach for each cluster is determined by analyzing the results, and this configuration of hyperparameters is applied iteratively to optimize the solution search.</div><div>The effectiveness of RLGA is evaluated across benchmark instances with different complexities, machine sets, jobs, and constraints. Comprehensive comparisons against existing methods highlight the superior performance and efficiency of RLGA in optimizing energy use and solution quality. Experimental results show that RLGA outperforms well-known solvers like CPO, CPLEX, OR-tools, and Gecode, making it a promising approach for optimizing energy-efficient manufacturing systems.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"693 ","pages":"Article 121674"},"PeriodicalIF":8.1,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706190","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}
Pub Date : 2024-11-21DOI: 10.1016/j.ins.2024.121675
Xiangyang Wang, Yanqi Xu, Panpan Niu
Sorted-based LBP variants have been validated as effective grayscale inverse image classification methods. However, most of these methods encode the order of sampling points at the same scale and thus suffer from two problems: 1) Ignoring inter-scale correlation leads to descriptors that are not resistant to real scene changes. 2) The inherent flaws of sorted encoding cause descriptors to discriminate complex texture structures, showing low discriminability. To address these problems, we design the new scale-structure model and region encoding to realize a more robust and discriminative representation called Local Radial Grouped Invariant Order Pattern (LRGIOP). LRGIOP can effectively distinguish texture details in real scenes while resisting various complex imaging conditions. Experiments on several image databases show that the LRGIOP descriptor achieves state-of-the-art classification results under linear or even nonlinear grayscale-inversion transformations.
{"title":"A robust image descriptor-local radial grouped invariant order pattern","authors":"Xiangyang Wang, Yanqi Xu, Panpan Niu","doi":"10.1016/j.ins.2024.121675","DOIUrl":"10.1016/j.ins.2024.121675","url":null,"abstract":"<div><div>Sorted-based LBP variants have been validated as effective grayscale inverse image classification methods. However, most of these methods encode the order of sampling points at the same scale and thus suffer from two problems: 1) Ignoring inter-scale correlation leads to descriptors that are not resistant to real scene changes. 2) The inherent flaws of sorted encoding cause descriptors to discriminate complex texture structures, showing low discriminability. To address these problems, we design the new scale-structure model and region encoding to realize a more robust and discriminative representation called Local Radial Grouped Invariant Order Pattern (LRGIOP). LRGIOP can effectively distinguish texture details in real scenes while resisting various complex imaging conditions. Experiments on several image databases show that the LRGIOP descriptor achieves state-of-the-art classification results under linear or even nonlinear grayscale-inversion transformations.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"693 ","pages":"Article 121675"},"PeriodicalIF":8.1,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706189","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号