Pub Date : 2025-02-19DOI: 10.1016/j.ins.2025.121993
Junhong Zhao , Yunliu Li , Ting Liu , Peng Liu , Junwei Sun
This paper investigates the cluster output synchronization of coupled fractional-order uncertain neural networks. By utilizing Lyapunov's theorem and effective inequalities applicable to fractional-order systems, sufficient criteria are established to achieve the cluster output synchronization of coupled fractional-order uncertain neural networks for two different communication topologies, namely strongly connected topology and topology with a spanning tree. Unlike previous works that have focused on the output synchronization of neural networks within the confines of integer order systems or strongly connected topologies, this paper extends the exploration to the output synchronization of coupled fractional-order uncertain neural networks with a spanning tree. Additionally, the conclusions of this paper include the complete synchronization of both fractional-order and integer-order neural networks as special cases. Numerical examples are shown to substantiate the obtained results.
{"title":"Cluster output synchronization analysis of coupled fractional-order uncertain neural networks","authors":"Junhong Zhao , Yunliu Li , Ting Liu , Peng Liu , Junwei Sun","doi":"10.1016/j.ins.2025.121993","DOIUrl":"10.1016/j.ins.2025.121993","url":null,"abstract":"<div><div>This paper investigates the cluster output synchronization of coupled fractional-order uncertain neural networks. By utilizing Lyapunov's theorem and effective inequalities applicable to fractional-order systems, sufficient criteria are established to achieve the cluster output synchronization of coupled fractional-order uncertain neural networks for two different communication topologies, namely strongly connected topology and topology with a spanning tree. Unlike previous works that have focused on the output synchronization of neural networks within the confines of integer order systems or strongly connected topologies, this paper extends the exploration to the output synchronization of coupled fractional-order uncertain neural networks with a spanning tree. Additionally, the conclusions of this paper include the complete synchronization of both fractional-order and integer-order neural networks as special cases. Numerical examples are shown to substantiate the obtained results.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121993"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444224","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 : 2025-02-18DOI: 10.1016/j.ins.2025.121986
Jinrong Sheng, Jiaruo Yu, Ziqiang Li, Ao Li, Yongxin Ge
Weakly-supervised temporal action localization (WTAL) identifies and localizes actions in untrimmed videos with only video-level labels. Most methods prioritize discriminative snippets, often neglecting of hard action snippets while focusing on class-specific background. Although recent methods have tackled this issue through temporal modeling, they overlook the local temporal structure of actions. To model such temporal structure effectively, we propose a novel self-supervised temporal adaptive learning (STAL) framework, which is composed of two core parts, i.e. self-supervised temporal learning (STL) network and the adaptive learning unit (ALU). Specifically, STL constructs a self-supervised task by performing an erasure and reconstruction process. This pseudo-label-based method relies on a classification task to perceive continuous temporal information for action localization task. To avoid the disturbance of un-confident pseudo labels during self-supervised learning process, two adaptive learning strategies of ALU are designed from two perspectives. In detail, a task-adaptive learning strategy is used to train the proposed tasks to the best for more reliable pseudo labels. Meanwhile, a score-adaptive learning strategy is designed to balance class activation and attention scores. Experiments on two classical datasets, namely, THUMOS14 and ActivityNet datasets, verify the effectiveness of our method.
{"title":"Self-supervised temporal adaptive learning for weakly-supervised temporal action localization","authors":"Jinrong Sheng, Jiaruo Yu, Ziqiang Li, Ao Li, Yongxin Ge","doi":"10.1016/j.ins.2025.121986","DOIUrl":"10.1016/j.ins.2025.121986","url":null,"abstract":"<div><div>Weakly-supervised temporal action localization (WTAL) identifies and localizes actions in untrimmed videos with only video-level labels. Most methods prioritize discriminative snippets, often neglecting of hard action snippets while focusing on class-specific background. Although recent methods have tackled this issue through temporal modeling, they overlook the local temporal structure of actions. To model such temporal structure effectively, we propose a novel self-supervised temporal adaptive learning (STAL) framework, which is composed of two core parts, i.e. self-supervised temporal learning (STL) network and the adaptive learning unit (ALU). Specifically, STL constructs a self-supervised task by performing an erasure and reconstruction process. This pseudo-label-based method relies on a classification task to perceive continuous temporal information for action localization task. To avoid the disturbance of un-confident pseudo labels during self-supervised learning process, two adaptive learning strategies of ALU are designed from two perspectives. In detail, a task-adaptive learning strategy is used to train the proposed tasks to the best for more reliable pseudo labels. Meanwhile, a score-adaptive learning strategy is designed to balance class activation and attention scores. Experiments on two classical datasets, namely, THUMOS14 and ActivityNet datasets, verify the effectiveness of our method.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121986"},"PeriodicalIF":8.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437279","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 : 2025-02-18DOI: 10.1016/j.ins.2025.121988
Hector Zenil , Luan Carlos de Sena Monteiro Ozelim
In communication systems, the circumstances and capabilities of senders and receivers cannot be known/assumed beforehand so as to design optimal semantic transference strategies. Regardless of the recipient (plants, insects, or even life forms unknown on Earth), the spatio-temporal scale of a message could be inappropriate and may never be decoded due to incompatibilities at both ends. We devise a new method to encode messages that is agnostic vis-a-vis space and time scales. We propose the use of fractal functions as self-executable carriers for sending messages, given their properties of structural self-similarity and scale invariance. We call this ‘fractal messaging’. Starting from a spatial embedding, we introduce a framework for a space-time scale-free messaging approach. In creating a space and time agnostic framework for message transmission, encoding a message that could be decoded at several spatio-temporal scales is the objective. Our core idea is to encode a binary message as waves along infinitely many frequencies (in power-like distributions) and amplitudes, transmit such a message, and then decode and reproduce it. To do so, the components/cycles of the Weierstrass function, a known fractal, are used as carriers of the message. Each component will have its amplitude modulated to embed the binary stream, allowing for a space-time agnostic approach to messaging.
{"title":"Fractal spatio-temporal scale-free messaging: Amplitude modulation of self-executable carriers given by the Weierstrass function's components","authors":"Hector Zenil , Luan Carlos de Sena Monteiro Ozelim","doi":"10.1016/j.ins.2025.121988","DOIUrl":"10.1016/j.ins.2025.121988","url":null,"abstract":"<div><div>In communication systems, the circumstances and capabilities of senders and receivers cannot be known/assumed beforehand so as to design optimal semantic transference strategies. Regardless of the recipient (plants, insects, or even life forms unknown on Earth), the spatio-temporal scale of a message could be inappropriate and may never be decoded due to incompatibilities at both ends. We devise a new method to encode messages that is agnostic vis-a-vis space and time scales. We propose the use of fractal functions as self-executable carriers for sending messages, given their properties of structural self-similarity and scale invariance. We call this ‘fractal messaging’. Starting from a spatial embedding, we introduce a framework for a space-time scale-free messaging approach. In creating a space and time agnostic framework for message transmission, encoding a message that could be decoded at several spatio-temporal scales is the objective. Our core idea is to encode a binary message as waves along infinitely many frequencies (in power-like distributions) and amplitudes, transmit such a message, and then decode and reproduce it. To do so, the components/cycles of the Weierstrass function, a known fractal, are used as carriers of the message. Each component will have its amplitude modulated to embed the binary stream, allowing for a space-time agnostic approach to messaging.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121988"},"PeriodicalIF":8.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479517","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 : 2025-02-17DOI: 10.1016/j.ins.2025.121977
Mamadou Ben Hamidou Cissoko , Vincent Castelain , Nicolas Lachiche
In personalized predictive medicine, accurately modeling a patient's illness and care processes is essential, given their inherent long-term temporal dependencies. However, Electronic Health Records (EHRs) often contain episodic and irregularly timed data, resulting from patients' sporadic hospital admissions, leading to unique patterns for each hospital stay. Consequently, constructing a personalized predictive model requires careful consideration of these factors to accurately capture the patient's health journey and assist in clinical decision-making.
Long Short-Term Memory (LSTM) is an effective model for handling sequential data, such as EHRs, but it encounters two major limitations when applied to EHRs: it is unable to interpret the prediction results and it ignores the irregular time intervals between consecutive events. To tackle these limitations, we present a novel deep dynamic memory neural network called Adaptive Multi-Way Interpretable Time-Aware LSTM for irregularly collected sequential data “AMITA”. The primary objective of AMITA is to leverage medical records, memorize illness trajectories and care processes, estimate current illness states, and predict future risks, thereby providing a high level of precision and predictive power.
To enhance its capabilities, AMITA extends the standard LSTM model in two key ways. Firstly, it incorporates frequency measurement and the most recent observation to enhance personalized predictive modeling of patient illnesses, enabling a more accurate understanding of the patient's condition. Secondly, it parameterizes the cell state to handle irregular timing effectively, utilizing both elapsed times and a frequency-based decay factor, which considers both measurement frequency and contextual information. Furthermore, the model capitalizes on both to comprehend the impact of interventions on the course of illness on the cell state, facilitating the memorization of illness courses and improving its ability to capture the temporal dynamics of healthcare data, accommodating variations and irregularities in event and observation timing.
The effectiveness of our proposed model is validated through empirical experiments conducted on two real-world clinical datasets. The results demonstrate the superiority of AMITA over current state-of-the-art models and other robust baselines, showcasing its potential in advancing personalized predictive medicine by offering a more accurate and comprehensive approach to modeling patient health trajectories.
{"title":"Predicting and interpreting healthcare trajectories from irregularly collected sequential patient data using AMITA","authors":"Mamadou Ben Hamidou Cissoko , Vincent Castelain , Nicolas Lachiche","doi":"10.1016/j.ins.2025.121977","DOIUrl":"10.1016/j.ins.2025.121977","url":null,"abstract":"<div><div>In personalized predictive medicine, accurately modeling a patient's illness and care processes is essential, given their inherent long-term temporal dependencies. However, Electronic Health Records (EHRs) often contain episodic and irregularly timed data, resulting from patients' sporadic hospital admissions, leading to unique patterns for each hospital stay. Consequently, constructing a personalized predictive model requires careful consideration of these factors to accurately capture the patient's health journey and assist in clinical decision-making.</div><div>Long Short-Term Memory (LSTM) is an effective model for handling sequential data, such as EHRs, but it encounters two major limitations when applied to EHRs: it is unable to interpret the prediction results and it ignores the irregular time intervals between consecutive events. To tackle these limitations, we present a novel deep dynamic memory neural network called Adaptive Multi-Way Interpretable Time-Aware LSTM for irregularly collected sequential data “AMITA”. The primary objective of AMITA is to leverage medical records, memorize illness trajectories and care processes, estimate current illness states, and predict future risks, thereby providing a high level of precision and predictive power.</div><div>To enhance its capabilities, AMITA extends the standard LSTM model in two key ways. Firstly, it incorporates frequency measurement and the most recent observation to enhance personalized predictive modeling of patient illnesses, enabling a more accurate understanding of the patient's condition. Secondly, it parameterizes the cell state to handle irregular timing effectively, utilizing both elapsed times and a frequency-based decay factor, which considers both measurement frequency and contextual information. Furthermore, the model capitalizes on both to comprehend the impact of interventions on the course of illness on the cell state, facilitating the memorization of illness courses and improving its ability to capture the temporal dynamics of healthcare data, accommodating variations and irregularities in event and observation timing.</div><div>The effectiveness of our proposed model is validated through empirical experiments conducted on two real-world clinical datasets. The results demonstrate the superiority of AMITA over current state-of-the-art models and other robust baselines, showcasing its potential in advancing personalized predictive medicine by offering a more accurate and comprehensive approach to modeling patient health trajectories.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121977"},"PeriodicalIF":8.1,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428158","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 : 2025-02-17DOI: 10.1016/j.ins.2025.121969
Jiazhen Liang , Wai Li , Qingshan Zhong , Jun Huang , Dazhi Jiang , Erik Cambria
Emotion recognition in conversation (ERC) is essential for enhancing human-computer interaction and improving intelligent systems' emotional intelligence. Despite advancements, ERC still struggles to capture the complexity and nuances of emotions in dialogues. Traditional approaches rely on context modeling to improve text representations but often fail to fully capture emotions' continuous and intricate nature. While contrastive learning has emerged as a promising technique to enhance the discriminative power of text features, many methods still rely on discrete emotion labels, limiting their ability to model emotions' inherent continuity and relational structure. To address these challenges, we introduce the Chain of Triplex Contrastive Learning (CoTCL) framework, which progressively refines utterance representations, strengthens emotional distinctions, and incorporates contextual information from dialogues. CoTCL employs instance contrastive learning using dropout-based positive samples to improve the richness and separation of utterance features. Additionally, it introduces the Pleasure-Arousal-Dominance (PAD) space as a continuous representation framework, embedding utterances in a way that reduces confusion between similar emotions. This allows for more nuanced, relation-aware emotion modeling. Furthermore, CoTCL enhances contextual understanding by constructing an utterance graph, where nodes represent utterances and edges denote relationships. By integrating external knowledge from the COMET model and applying graph-based contrastive learning with edge perturbation and node masking, CoTCL improves contextual transmission, making the model more robust and adaptable to real-world dialogues. Experimental results demonstrate that CoTCL achieves state-of-the-art performance across multiple ERC benchmarks, highlighting the importance of continuous emotion modeling and context integration. By refining text representation, introducing a continuous emotion space, and leveraging external knowledge, CoTCL provides a strong foundation for advancing ERC research and improving real-world dialogue systems.
{"title":"Learning chain for clause awareness: Triplex-contrastive learning for emotion recognition in conversations","authors":"Jiazhen Liang , Wai Li , Qingshan Zhong , Jun Huang , Dazhi Jiang , Erik Cambria","doi":"10.1016/j.ins.2025.121969","DOIUrl":"10.1016/j.ins.2025.121969","url":null,"abstract":"<div><div>Emotion recognition in conversation (ERC) is essential for enhancing human-computer interaction and improving intelligent systems' emotional intelligence. Despite advancements, ERC still struggles to capture the complexity and nuances of emotions in dialogues. Traditional approaches rely on context modeling to improve text representations but often fail to fully capture emotions' continuous and intricate nature. While contrastive learning has emerged as a promising technique to enhance the discriminative power of text features, many methods still rely on discrete emotion labels, limiting their ability to model emotions' inherent continuity and relational structure. To address these challenges, we introduce the Chain of Triplex Contrastive Learning (CoTCL) framework, which progressively refines utterance representations, strengthens emotional distinctions, and incorporates contextual information from dialogues. CoTCL employs instance contrastive learning using dropout-based positive samples to improve the richness and separation of utterance features. Additionally, it introduces the Pleasure-Arousal-Dominance (PAD) space as a continuous representation framework, embedding utterances in a way that reduces confusion between similar emotions. This allows for more nuanced, relation-aware emotion modeling. Furthermore, CoTCL enhances contextual understanding by constructing an utterance graph, where nodes represent utterances and edges denote relationships. By integrating external knowledge from the COMET model and applying graph-based contrastive learning with edge perturbation and node masking, CoTCL improves contextual transmission, making the model more robust and adaptable to real-world dialogues. Experimental results demonstrate that CoTCL achieves state-of-the-art performance across multiple ERC benchmarks, highlighting the importance of continuous emotion modeling and context integration. By refining text representation, introducing a continuous emotion space, and leveraging external knowledge, CoTCL provides a strong foundation for advancing ERC research and improving real-world dialogue systems.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121969"},"PeriodicalIF":8.1,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454852","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 : 2025-02-17DOI: 10.1016/j.ins.2025.121985
Yuhang Hu , Yuelin Qu , Wei Li , Ying Huang
Constraint multiobjective algorithms are the most widely applied direction in intelligent optimization, with excellent research value. Currently, most multiobjective multi-constraints algorithms are designed based on the relationship between feasible and infeasible solutions, but they ignore the complex associations between constraints. At the same time, the most significant difficulty in constraint problems lies in the irregularity of constrained Pareto front (CPF) and the lack of a powerful strategy for exploration. The paper proposes a Pareto front searching based on reinforcement learning (PFRL) for multi-constraints multiobjective optimization problems. The algorithm employs reinforcement learning to guide the evolution process through interaction with the environment and adaptively learns the shape and characteristics of CPF to cover the structure of CPF effectively. The environment and CPF information gained by reinforcement learning are utilized for CPF translation and extension to deal with various irregular feasible regions. In addition, the paper also designs a constraint priority evaluation mechanism based on the correlation distance (CD) metric to process constraint relationships. It allows the algorithm to effectively cross over Pareto front (PF) of a single constraint that is unrelated to CPF, improving algorithm efficiency. The introduced algorithm implemented the above strategy using only one population. The effectiveness of the introduced algorithm was verified and compared with nine state-of-the-art algorithms and four real-world constrained multiobjective optimization problems (CMOPs). Experimental results show that the algorithm provides a low-resource and efficient method for solving CMOPs.
{"title":"A Pareto Front searching algorithm based on reinforcement learning for constrained multiobjective optimization","authors":"Yuhang Hu , Yuelin Qu , Wei Li , Ying Huang","doi":"10.1016/j.ins.2025.121985","DOIUrl":"10.1016/j.ins.2025.121985","url":null,"abstract":"<div><div>Constraint multiobjective algorithms are the most widely applied direction in intelligent optimization, with excellent research value. Currently, most multiobjective multi-constraints algorithms are designed based on the relationship between feasible and infeasible solutions, but they ignore the complex associations between constraints. At the same time, the most significant difficulty in constraint problems lies in the irregularity of constrained Pareto front (CPF) and the lack of a powerful strategy for exploration. The paper proposes a Pareto front searching based on reinforcement learning (PFRL) for multi-constraints multiobjective optimization problems. The algorithm employs reinforcement learning to guide the evolution process through interaction with the environment and adaptively learns the shape and characteristics of CPF to cover the structure of CPF effectively. The environment and CPF information gained by reinforcement learning are utilized for CPF translation and extension to deal with various irregular feasible regions. In addition, the paper also designs a constraint priority evaluation mechanism based on the correlation distance (CD) metric to process constraint relationships. It allows the algorithm to effectively cross over Pareto front (PF) of a single constraint that is unrelated to CPF, improving algorithm efficiency. The introduced algorithm implemented the above strategy using only one population. The effectiveness of the introduced algorithm was verified and compared with nine state-of-the-art algorithms and four real-world constrained multiobjective optimization problems (CMOPs). Experimental results show that the algorithm provides a low-resource and efficient method for solving CMOPs.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121985"},"PeriodicalIF":8.1,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437278","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}
In this paper, a data-driven fault-tolerant control (FTC) method is proposed to solve the consensus problem of constrained multiagent systems (MASs) with denial-of-service attacks. First, a resilient distributed observer is introduced to extract the leader's state in real-time for each follower, even in the presence of attacks. A nonlinear mapping is employed to transform the original system with state constraints into an equivalent constraint-free system, ensuring that the original system's states remain within prescribed limits. Then, an adaptive dynamic programming (ADP)-based FTC scheme is designed for the system to mitigate the effects of actuator faults, enabling the nominal system to balance cost and performance. The ADP algorithm is implemented using an actor-critic structure to solve the Hamilton-Jacobi-Bellman equation based on system data collected via the least-squares method. In this framework, the designed controller is data-driven rather than reliant on precise system information, which broadens the controller's applicability to systems with unknown dynamics. Finally, the effectiveness of the established controller is validated through two examples.
{"title":"Data-driven fault-tolerant consensus control for constrained nonlinear multiagent systems via adaptive dynamic programming","authors":"Lulu Zhang , Huaguang Zhang , Tianbiao Wang , Xiaohui Yue","doi":"10.1016/j.ins.2025.121976","DOIUrl":"10.1016/j.ins.2025.121976","url":null,"abstract":"<div><div>In this paper, a data-driven fault-tolerant control (FTC) method is proposed to solve the consensus problem of constrained multiagent systems (MASs) with denial-of-service attacks. First, a resilient distributed observer is introduced to extract the leader's state in real-time for each follower, even in the presence of attacks. A nonlinear mapping is employed to transform the original system with state constraints into an equivalent constraint-free system, ensuring that the original system's states remain within prescribed limits. Then, an adaptive dynamic programming (ADP)-based FTC scheme is designed for the system to mitigate the effects of actuator faults, enabling the nominal system to balance cost and performance. The ADP algorithm is implemented using an actor-critic structure to solve the Hamilton-Jacobi-Bellman equation based on system data collected via the least-squares method. In this framework, the designed controller is data-driven rather than reliant on precise system information, which broadens the controller's applicability to systems with unknown dynamics. Finally, the effectiveness of the established controller is validated through two examples.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121976"},"PeriodicalIF":8.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428694","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 : 2025-02-14DOI: 10.1016/j.ins.2025.121967
Yuchen Pan , Lu Xu , David L. Olson
This study tackles the critical issue of medical resource allocation, with a particular focus on China, where the overutilization of top-tier hospitals exacerbates healthcare shortages. Given the challenges of expanding medical resources, optimizing their utilization becomes essential. We introduce a novel physician recommendation approach that estimates physician abilities by analyzing both external features derived from physician-disease interactions and internal characteristics, such as hospital levels and physician titles. By integrating these dimensions, we offer a comprehensive assessment of physician capabilities, considering both the complexity of diseases and the physician’s competence. Experimental results demonstrate that our method outperforms both traditional and state-of-the-art models, significantly improving the efficient distribution of limited medical resources. The effectiveness of the physician rankings in optimizing resource allocation is validated through the use of the Kendall Rank Correlation Coefficient (KRCC). Our approach holds considerable promise in enhancing healthcare resource utilization and alleviating resource constraints.
{"title":"An intelligent medical recommendation model based on big data-driven estimation of physician ability","authors":"Yuchen Pan , Lu Xu , David L. Olson","doi":"10.1016/j.ins.2025.121967","DOIUrl":"10.1016/j.ins.2025.121967","url":null,"abstract":"<div><div>This study tackles the critical issue of medical resource allocation, with a particular focus on China, where the overutilization of top-tier hospitals exacerbates healthcare shortages. Given the challenges of expanding medical resources, optimizing their utilization becomes essential. We introduce a novel physician recommendation approach that estimates physician abilities by analyzing both external features derived from physician-disease interactions and internal characteristics, such as hospital levels and physician titles. By integrating these dimensions, we offer a comprehensive assessment of physician capabilities, considering both the complexity of diseases and the physician’s competence. Experimental results demonstrate that our method outperforms both traditional and state-of-the-art models, significantly improving the efficient distribution of limited medical resources. The effectiveness of the physician rankings in optimizing resource allocation is validated through the use of the Kendall Rank Correlation Coefficient (KRCC). Our approach holds considerable promise in enhancing healthcare resource utilization and alleviating resource constraints.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121967"},"PeriodicalIF":8.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428697","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 : 2025-02-13DOI: 10.1016/j.ins.2025.121971
Qianhui Ji , Yuyan Han , Yuting Wang , Dunwei Gong , Kaizhou Gao
The distributed cell manufacturing can leverage resources from different geographic locations to achieve more efficient production and services. In its production lines, jobs requiring setup conditions are grouped together. To improve the flexibility of the production process, each process consists of multiple processing stages with each stage containing one or more parallel machines, and at least one stage has two or more than two machines. This shop floor layout can balance the workload of the individual machines and expand production capacity. In addition, on-time delivery is a significant criterion for assessing the impact on the competitiveness and long-term development of an organization. In this context, we study the distributed hybrid flow shop group scheduling problem (DHFGSP) with the total weighted earliness and tardiness criterion. For the first time, we establish a mixed integer linear programming model of DHFGSP, and validate its accuracy through the Gurobi solver. Meanwhile, we design a Q-learning-driven genetic algorithm (QGA) to solve the above problem. Within QGA, we first propose an idle-time insertion method for the last stage to further minimize the operation objective. Then, we devise multiple neighborhood structures tailored to penalty groups and worst factories, integrating them into three variable neighborhood searches as mutation methods. Next, a Q-learning table is designed by incorporating two states and eight actions, each action representing a unique combination of crossover and mutation techniques. The modified design can make the population into an intelligent agent, autonomously selecting evolutionary actions. Through experimental results and analysis on 405 test instances, we validate the effectiveness of all proposed strategies and confirm that QGA outperforms other existing advanced algorithms in solving the DHFGSP.
{"title":"A Q-learning-driven genetic algorithm for the distributed hybrid flow shop group scheduling problem with delivery time windows","authors":"Qianhui Ji , Yuyan Han , Yuting Wang , Dunwei Gong , Kaizhou Gao","doi":"10.1016/j.ins.2025.121971","DOIUrl":"10.1016/j.ins.2025.121971","url":null,"abstract":"<div><div>The distributed cell manufacturing can leverage resources from different geographic locations to achieve more efficient production and services. In its production lines, jobs requiring setup conditions are grouped together. To improve the flexibility of the production process, each process consists of multiple processing stages with each stage containing one or more parallel machines, and at least one stage has two or more than two machines. This shop floor layout can balance the workload of the individual machines and expand production capacity. In addition, on-time delivery is a significant criterion for assessing the impact on the competitiveness and long-term development of an organization. In this context, we study the distributed hybrid flow shop group scheduling problem (DHFGSP) with the total weighted earliness and tardiness criterion. For the first time, we establish a mixed integer linear programming model of DHFGSP, and validate its accuracy through the Gurobi solver. Meanwhile, we design a Q-learning-driven genetic algorithm (QGA) to solve the above problem. Within QGA, we first propose an idle-time insertion method for the last stage to further minimize the operation objective. Then, we devise multiple neighborhood structures tailored to penalty groups and worst factories, integrating them into three variable neighborhood searches as mutation methods. Next, a Q-learning table is designed by incorporating two states and eight actions, each action representing a unique combination of crossover and mutation techniques. The modified design can make the population into an intelligent agent, autonomously selecting evolutionary actions. Through experimental results and analysis on 405 test instances, we validate the effectiveness of all proposed strategies and confirm that QGA outperforms other existing advanced algorithms in solving the DHFGSP.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121971"},"PeriodicalIF":8.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428696","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}
Recently, many interpretable clustering algorithms have been proposed, which focus on characterizing the clustering outcome in terms of explainable models such as trees and rules. However, existing solutions are mainly developed for handling standard vectorial data and how to obtain interpretable clustering results for complicated non-vector data such as sequences and graphs is still in the infant stage. In this paper, we present a significance-based interpretable clustering algorithm for discrete sequences, which has the following key features. Firstly, instead of using a third-party clustering method to obtain the initial clusters, we directly extract cluster-critical sequential patterns to describe potential clusters. Secondly, without needing to specify the number of clusters, we guide the growth of the decision tree through a hypothesis testing procedure. As a result, not only the final clustering result is explainable but also the tree construction process is statistically interpretable. Experimental results on real-world sequential data sets show that our algorithm achieves comparable performance to state-of-the-art methods in both cluster quality and interpretability.
{"title":"Significance-based interpretable sequence clustering","authors":"Zengyou He, Lianyu Hu, Jinfeng He, Junjie Dong, Mudi Jiang, Xinying Liu","doi":"10.1016/j.ins.2025.121972","DOIUrl":"10.1016/j.ins.2025.121972","url":null,"abstract":"<div><div>Recently, many interpretable clustering algorithms have been proposed, which focus on characterizing the clustering outcome in terms of explainable models such as trees and rules. However, existing solutions are mainly developed for handling standard vectorial data and how to obtain interpretable clustering results for complicated non-vector data such as sequences and graphs is still in the infant stage. In this paper, we present a significance-based interpretable clustering algorithm for discrete sequences, which has the following key features. Firstly, instead of using a third-party clustering method to obtain the initial clusters, we directly extract cluster-critical sequential patterns to describe potential clusters. Secondly, without needing to specify the number of clusters, we guide the growth of the decision tree through a hypothesis testing procedure. As a result, not only the final clustering result is explainable but also the tree construction process is statistically interpretable. Experimental results on real-world sequential data sets show that our algorithm achieves comparable performance to state-of-the-art methods in both cluster quality and interpretability.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"704 ","pages":"Article 121972"},"PeriodicalIF":8.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422757","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