Pub Date : 2024-11-17DOI: 10.1016/j.ins.2024.121657
Linshan Li , Puhantong Rong , Meizhu Li
A novel set type, termed Random Permutation Set (RPS), has recently been introduced to account for permutations of sets. Serving as an extension of evidence theory, the concern about whether it might yield counterintuitive outcomes when confronted with high conflict akin to evidence theory arises as a pertinent issue in practical engineering applications. In this paper, we initially explore the outcomes of direct fusion amidst varying levels of extreme conflict. Following this, we innovatively proposed a fusion method based on RPS distance and entropy metrics. This method utilizes the distances between RPS for weighting and determines the final RPS subset used for weighting through the entropy of the RPS. Through the presentation of several examples and specific experiments, we demonstrate its efficacy in handling extreme conflict scenarios and enhancing the quality of fusion outcomes.
{"title":"Combining Permutation Mass Functions based on distance and entropy of Random Permutation Set","authors":"Linshan Li , Puhantong Rong , Meizhu Li","doi":"10.1016/j.ins.2024.121657","DOIUrl":"10.1016/j.ins.2024.121657","url":null,"abstract":"<div><div>A novel set type, termed Random Permutation Set (RPS), has recently been introduced to account for permutations of sets. Serving as an extension of evidence theory, the concern about whether it might yield counterintuitive outcomes when confronted with high conflict akin to evidence theory arises as a pertinent issue in practical engineering applications. In this paper, we initially explore the outcomes of direct fusion amidst varying levels of extreme conflict. Following this, we innovatively proposed a fusion method based on RPS distance and entropy metrics. This method utilizes the distances between RPS for weighting and determines the final RPS subset used for weighting through the entropy of the RPS. Through the presentation of several examples and specific experiments, we demonstrate its efficacy in handling extreme conflict scenarios and enhancing the quality of fusion outcomes.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121657"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704070","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121652
Gayeon Park , Hyeongjun Yang , Kyuhwan Yeom , Myeongheon Jeon , Yunjeong Ko , Byungkook Oh , Kyong-Ho Lee
Recommender systems aim to accurately capture user preferences based on interacted items. Conventional recommender systems mainly rely on the singular-type behavior of users, which may limit their ability to handle practical scenarios (e.g., E-commerce). In contrast, multi-type behavior recommendation (MBR) exploits auxiliary types of behaviors (e.g., view, cart), as well as the target behavior (e.g., buy), and has proven to be an effective way to identify user preferences from various perspectives. Existing MBR methods assume that all auxiliary behaviors of a user have a positive relevance with the target behavior. However, users may not interact with items using all available behaviors, but the degree of relatedness is not explicitly taken into account. To address the issue, we propose a Knowledge-constrained Interest-aware Framework with Behavior Pattern Identification (KIPI). The proposed model identifies user-specific behavior patterns by introducing pair-wise dependency modeling to explicitly reflect the fine-grained relatedness between behavior pairs. Additionally, we enhance item representations by leveraging both instance-view knowledge graph (KG) and ontology-view KG, which provides broader concept information of items. Moreover, we design a concept-constrained Bayesian Personalized Ranking loss to reflect a user's general interest. Extensive studies on the real-world datasets demonstrate that our model outperforms state-of-the-art baselines.
{"title":"Knowledge-constrained interest-aware multi-behavior recommendation with behavior pattern identification","authors":"Gayeon Park , Hyeongjun Yang , Kyuhwan Yeom , Myeongheon Jeon , Yunjeong Ko , Byungkook Oh , Kyong-Ho Lee","doi":"10.1016/j.ins.2024.121652","DOIUrl":"10.1016/j.ins.2024.121652","url":null,"abstract":"<div><div>Recommender systems aim to accurately capture user preferences based on interacted items. Conventional recommender systems mainly rely on the singular-type behavior of users, which may limit their ability to handle practical scenarios (e.g., E-commerce). In contrast, multi-type behavior recommendation (MBR) exploits auxiliary types of behaviors (e.g., view, cart), as well as the target behavior (e.g., buy), and has proven to be an effective way to identify user preferences from various perspectives. Existing MBR methods assume that all auxiliary behaviors of a user have a positive relevance with the target behavior. However, users may not interact with items using all available behaviors, but the degree of relatedness is not explicitly taken into account. To address the issue, we propose a <strong>K</strong>nowledge-constrained <strong>I</strong>nterest-aware Framework with Behavior <strong>P</strong>attern <strong>I</strong>dentification (KIPI). The proposed model identifies user-specific behavior patterns by introducing pair-wise dependency modeling to explicitly reflect the fine-grained relatedness between behavior pairs. Additionally, we enhance item representations by leveraging both instance-view knowledge graph (KG) and ontology-view KG, which provides broader concept information of items. Moreover, we design a concept-constrained Bayesian Personalized Ranking loss to reflect a user's general interest. Extensive studies on the real-world datasets demonstrate that our model outperforms state-of-the-art baselines.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121652"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142703997","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121662
Haiquan Zhao , Yuan Gao
This paper presents an innovative the minimum error entropy with fiducial points (MEEF)-based spline adaptive filtering (S-AF) algorithm, called SAF-MEEF algorithm, which outperforms the conventional SAF algorithms that use the mean square error (MSE) criterion in reducing non-Gaussian interference. To overcome the limitation of the fixed step-size, a variable step-size strategy is also developed, resulting in the SAF-VMEEF algorithm, which improves the convergence speed and steady-state error performance. Furthermore, the computational complexity and convergence analysis of the SAF-MEEF are discussed. Nonlinear system identification simulations test the performance of the presented algorithms. Furthermore, this article accomplishes the application of nonlinear active noise control (ANC). Their effectiveness and robustness against non-Gaussian noise are demonstrated in different experimental scenarios, including α-stable noise, real-world functional magnetic resonance imaging (fMRI) noise, and real-life server room (SR) noise.
本文提出了一种创新的基于靶点（MEEF）的最小误差熵样条自适应滤波（S-AF）算法，称为 SAF-MEEF 算法，它在减少非高斯干扰方面优于使用均方误差（MSE）准则的传统 SAF 算法。为了克服固定步长的限制，还开发了一种可变步长策略，形成了 SAF-VMEEF 算法，该算法提高了收敛速度和稳态误差性能。此外，还讨论了 SAF-MEEF 算法的计算复杂性和收敛性分析。非线性系统辨识仿真检验了所提出算法的性能。此外，本文还完成了非线性主动噪声控制（ANC）的应用。在不同的实验场景中，包括α稳定噪声、真实世界的功能磁共振成像（fMRI）噪声和现实生活中的服务器机房（SR）噪声，都证明了它们对非高斯噪声的有效性和鲁棒性。
{"title":"MEEF criterion-based spline adaptive filtering algorithm and its application","authors":"Haiquan Zhao , Yuan Gao","doi":"10.1016/j.ins.2024.121662","DOIUrl":"10.1016/j.ins.2024.121662","url":null,"abstract":"<div><div>This paper presents an innovative the minimum error entropy with fiducial points (MEEF)-based spline adaptive filtering (S-AF) algorithm, called SAF-MEEF algorithm, which outperforms the conventional SAF algorithms that use the mean square error (MSE) criterion in reducing non-Gaussian interference. To overcome the limitation of the fixed step-size, a variable step-size strategy is also developed, resulting in the SAF-VMEEF algorithm, which improves the convergence speed and steady-state error performance. Furthermore, the computational complexity and convergence analysis of the SAF-MEEF are discussed. Nonlinear system identification simulations test the performance of the presented algorithms. Furthermore, this article accomplishes the application of nonlinear active noise control (ANC). Their effectiveness and robustness against non-Gaussian noise are demonstrated in different experimental scenarios, including α-stable noise, real-world functional magnetic resonance imaging (fMRI) noise, and real-life server room (SR) noise.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121662"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704078","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121658
Mozhgan Rezaie Manavand , Mohammad Hosien Salarifar , Mohammad Ghavami , Mehran Taghipour-Gorjikolaie
Understanding drivers’ emotions is crucial for safety and comfort in autonomous vehicles. While Facial Expression Recognition (FER) systems perform well in controlled environments, struggle in real driving situations. To address this challenge, an Interlaced Local Attention Block within a Convolutional Neural Network (ILAB-CNN) model has been proposed to analyze drivers’ emotions. In real-world scenarios, not all facial regions contribute equally to expressing emotions; specific areas or combinations are key. Inspired by the attention mechanism, an ILAB and a Modified Squeeze-and-Excitation (MSE) block has been proposed to learn more discriminative features. The MSE block applies a self-attention mechanism on the channels, effectively identifying key features by incorporating global information and discarding irrelevant features. ILAB employs the MSE and encoder-decoder structures for region-channel specific attention in one branch and combines it with the obtained feature map of the MSE from the other branch. The proposed approach successfully captures essential information from facial expressions while utilizing a reduced number of parameters, leading to significantly improved recognition accuracy and recognition time for real-time applications. Evaluated on diverse datasets, our method shows 75.3 % recognition rate on FER-2013, 85.06 % on RAF-DB, and 98.8 % on KMU-FED, demonstrating its potential to advance FER technology.
{"title":"Driver’s facial expression recognition by using deep local and global features","authors":"Mozhgan Rezaie Manavand , Mohammad Hosien Salarifar , Mohammad Ghavami , Mehran Taghipour-Gorjikolaie","doi":"10.1016/j.ins.2024.121658","DOIUrl":"10.1016/j.ins.2024.121658","url":null,"abstract":"<div><div>Understanding drivers’ emotions is crucial for safety and comfort in autonomous vehicles. While Facial Expression Recognition (FER) systems perform well in controlled environments, struggle in real driving situations. To address this challenge, an Interlaced Local Attention Block within a Convolutional Neural Network (ILAB-CNN) model has been proposed to analyze drivers’ emotions. In real-world scenarios, not all facial regions contribute equally to expressing emotions; specific areas or combinations are key. Inspired by the attention mechanism, an ILAB and a Modified Squeeze-and-Excitation (MSE) block has been proposed to learn more discriminative features. The MSE block applies a self-attention mechanism on the channels, effectively identifying key features by incorporating global information and discarding irrelevant features. ILAB employs the MSE and encoder-decoder structures for region-channel specific attention in one branch and combines it with the obtained feature map of the MSE from the other branch. The proposed approach successfully captures essential information from facial expressions while utilizing a reduced number of parameters, leading to significantly improved recognition accuracy and recognition time for real-time applications. Evaluated on diverse datasets, our method shows 75.3 % recognition rate on FER-2013, 85.06 % on RAF-DB, and 98.8 % on KMU-FED, demonstrating its potential to advance FER technology.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121658"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704164","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121667
Yanyan Ye , Lei Ouyang , Zhixia Ding , Yao Zhao
This paper investigates the consensus problem of fractional-order complex networks via intermittent sampled position control. A delay-induced consensus protocol with intermittent sampled position for the fractional-order system is proposed, where only the current and delayed sampled positions are used. Meanwhile, the controllers operate only for a period of time in each sampling interval, which decrease the working time and update rates of controllers. Successively, by discussing four situations involving delay, sampling period, and communication width, necessary and sufficient consensus criteria are presented. It is interesting to find the delay has a positive impact on consensus of fractional-order complex networks, since consensus cannot be achieved without delay under the proposed protocol. Finally, simulation examples are presented to illustrate the theoretical analysis.
{"title":"Delay-induced consensus of fractional-order complex networks via intermittent sampled position control","authors":"Yanyan Ye , Lei Ouyang , Zhixia Ding , Yao Zhao","doi":"10.1016/j.ins.2024.121667","DOIUrl":"10.1016/j.ins.2024.121667","url":null,"abstract":"<div><div>This paper investigates the consensus problem of fractional-order complex networks via intermittent sampled position control. A delay-induced consensus protocol with intermittent sampled position for the fractional-order system is proposed, where only the current and delayed sampled positions are used. Meanwhile, the controllers operate only for a period of time in each sampling interval, which decrease the working time and update rates of controllers. Successively, by discussing four situations involving delay, sampling period, and communication width, necessary and sufficient consensus criteria are presented. It is interesting to find the delay has a positive impact on consensus of fractional-order complex networks, since consensus cannot be achieved without delay under the proposed protocol. Finally, simulation examples are presented to illustrate the theoretical analysis.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121667"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704059","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121653
Bo Liu , Fan Cao , Shilei Zhao , Yanshan Xiao
Transfer learning can leverage knowledge from source tasks to improve learning on a target task, even when training samples are limited. However, most previous transfer learning approaches focus on a single view of the data and assume no uncertainty in the training samples. To address these limitations, we propose a novel method called boosting one-class transfer learning for multi-view uncertain data (UMTO-SVMs), which handles one-class classification in multi-view data with uncertain information. Our method transfers knowledge containing uncertainty from multiple source tasks to the target task and constrains complementary information across different views to improve consistency. By combining basic classifiers using the Adaboost algorithm, we build a robust classifier. We also design an iterative framework to optimize the method and prove the convergence of the algorithm. Experimental results on three benchmark datasets show that UMTO-SVMs outperform previous one-class classification methods.
{"title":"Boosting one-class transfer learning for multiple view uncertain data","authors":"Bo Liu , Fan Cao , Shilei Zhao , Yanshan Xiao","doi":"10.1016/j.ins.2024.121653","DOIUrl":"10.1016/j.ins.2024.121653","url":null,"abstract":"<div><div>Transfer learning can leverage knowledge from source tasks to improve learning on a target task, even when training samples are limited. However, most previous transfer learning approaches focus on a single view of the data and assume no uncertainty in the training samples. To address these limitations, we propose a novel method called boosting one-class transfer learning for multi-view uncertain data (UMTO-SVMs), which handles one-class classification in multi-view data with uncertain information. Our method transfers knowledge containing uncertainty from multiple source tasks to the target task and constrains complementary information across different views to improve consistency. By combining basic classifiers using the Adaboost algorithm, we build a robust classifier. We also design an iterative framework to optimize the method and prove the convergence of the algorithm. Experimental results on three benchmark datasets show that UMTO-SVMs outperform previous one-class classification methods.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121653"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704069","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121668
Ruizhi Zhou , Lingfeng Niu , Dachuan Xu
Deep neural networks (DNNs) have shown great success in machine learning tasks and widely used in many fields. However, the substantial computational and storage requirements inherent to DNNs are usually high, which poses challenges for deploying deep learning models on resource-limited devices and hindering further applications. To address this issue, the lightweight nature of neural networks has garnered significant attention, and quantization has become one of the most popular approaches to compress DNNs. In this paper, we introduce a sparse loss-aware ternarization (SLT) model for training ternary neural networks, which encodes the floating-point parameters into . Specifically, we abstract the ternarization process as an optimization problem with discrete constraints, and then modify it by applying sparse regularization to identify insignificant weights. To deal with the challenges brought by the discreteness of the model, we decouple discrete constraints from the objective function and design a new algorithm based on the Alternating Direction Method of Multipliers (ADMM). Extensive experiments are conducted on public datasets with popular network architectures. Comparisons with several state-of-the-art baselines demonstrate that SLT always attains comparable accuracy while having better compression performance.
{"title":"Sparse loss-aware ternarization for neural networks","authors":"Ruizhi Zhou , Lingfeng Niu , Dachuan Xu","doi":"10.1016/j.ins.2024.121668","DOIUrl":"10.1016/j.ins.2024.121668","url":null,"abstract":"<div><div>Deep neural networks (DNNs) have shown great success in machine learning tasks and widely used in many fields. However, the substantial computational and storage requirements inherent to DNNs are usually high, which poses challenges for deploying deep learning models on resource-limited devices and hindering further applications. To address this issue, the lightweight nature of neural networks has garnered significant attention, and quantization has become one of the most popular approaches to compress DNNs. In this paper, we introduce a sparse loss-aware ternarization (SLT) model for training ternary neural networks, which encodes the floating-point parameters into <span><math><mo>{</mo><mo>−</mo><mn>1</mn><mo>,</mo><mn>0</mn><mo>,</mo><mn>1</mn><mo>}</mo></math></span>. Specifically, we abstract the ternarization process as an optimization problem with discrete constraints, and then modify it by applying sparse regularization to identify insignificant weights. To deal with the challenges brought by the discreteness of the model, we decouple discrete constraints from the objective function and design a new algorithm based on the Alternating Direction Method of Multipliers (ADMM). Extensive experiments are conducted on public datasets with popular network architectures. Comparisons with several state-of-the-art baselines demonstrate that SLT always attains comparable accuracy while having better compression performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"693 ","pages":"Article 121668"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706188","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121659
Fan Zhang , Min Wang , Wenchang Zhang , Hua Wang
The performance of time-series forecasting, which is crucial for predicting future values from historical data, improves with an accurate representation of time-series data. An accurate representation aids in adopting effective strategies to address future uncertainties and reduce the risks associated with planning and decision-making. However, most studies in long-term time-series forecasting integrate features across all time steps, complicating the representation of relationships among cyclical patterns in a series. This paper introduces the Temporal Hierarchical Aggregation Tree Structure Network (THATSN), which is a model that focuses on dynamic modeling over time. We transform time-series data into sequences with multiple cyclical patterns and model the interrelationships among these features to generate a hierarchical tree structure. We design a tree-structured long short-term memory network that functions as a gated adaptive aggregator to process the features of learned child nodes. This aggregator, which can train parameters, adaptively selects child node information benefiting the parent node. This method enhances information usage within the tree and captures cyclical information dynamically. Experiments validate the effectiveness of THATSN, demonstrating its capacity to express cyclical relationships in time-series data. The model exhibits state-of-the-art forecasting performance across several datasets, achieving an overall 15% improvement in MSE, thereby establishing its robustness in long-term forecasting.
{"title":"THATSN: Temporal hierarchical aggregation tree structure network for long-term time-series forecasting","authors":"Fan Zhang , Min Wang , Wenchang Zhang , Hua Wang","doi":"10.1016/j.ins.2024.121659","DOIUrl":"10.1016/j.ins.2024.121659","url":null,"abstract":"<div><div>The performance of time-series forecasting, which is crucial for predicting future values from historical data, improves with an accurate representation of time-series data. An accurate representation aids in adopting effective strategies to address future uncertainties and reduce the risks associated with planning and decision-making. However, most studies in long-term time-series forecasting integrate features across all time steps, complicating the representation of relationships among cyclical patterns in a series. This paper introduces the Temporal Hierarchical Aggregation Tree Structure Network (THATSN), which is a model that focuses on dynamic modeling over time. We transform time-series data into sequences with multiple cyclical patterns and model the interrelationships among these features to generate a hierarchical tree structure. We design a tree-structured long short-term memory network that functions as a gated adaptive aggregator to process the features of learned child nodes. This aggregator, which can train parameters, adaptively selects child node information benefiting the parent node. This method enhances information usage within the tree and captures cyclical information dynamically. Experiments validate the effectiveness of THATSN, demonstrating its capacity to express cyclical relationships in time-series data. The model exhibits state-of-the-art forecasting performance across several datasets, achieving an overall 15% improvement in MSE, thereby establishing its robustness in long-term forecasting.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121659"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704067","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 : 2024-11-17DOI: 10.1016/j.ins.2024.121648
Wenguan Luo , Xiaobing Yu , Gary G. Yen , Yifan Wei
Effectively managing convergence, diversity, and feasibility constitutes a fundamental trinity of tasks in optimizing constrained multiobjective optimization problems (CMOPs). Nevertheless, contemporary constrained multiobjective evolutionary algorithms (CMOEAs) frequently encounter challenges in reconciling these imperatives simultaneously. Drawing inspiration from overwhelming success in artificial intelligence, we propose a deep reinforcement learning-guided coevolutionary algorithm (DRLCEA) to tackle this predicament. DRLCEA employs two populations to optimize the original and unconstrained versions of the CMOP, respectively and then fosters cooperation between them according to the guidance of DRL. The established DRL employs two evaluation metrics to appraise population convergence, diversity, and feasibility, thus remarkably proficient in reflecting and steering the coevolution. Therefore, the proposed DRLCEA could effectively locate the feasible regions and approximate the constrained Pareto front. We assess the proposed algorithm on 32 benchmark CMOPs and one real-world UAV emergency track planning (UETP) application. Experimental results undoubtedly demonstrate the superiority and robustness of the proposed DRLCEA.
{"title":"Deep reinforcement learning-guided coevolutionary algorithm for constrained multiobjective optimization","authors":"Wenguan Luo , Xiaobing Yu , Gary G. Yen , Yifan Wei","doi":"10.1016/j.ins.2024.121648","DOIUrl":"10.1016/j.ins.2024.121648","url":null,"abstract":"<div><div>Effectively managing convergence, diversity, and feasibility constitutes a fundamental trinity of tasks in optimizing constrained multiobjective optimization problems (CMOPs). Nevertheless, contemporary constrained multiobjective evolutionary algorithms (CMOEAs) frequently encounter challenges in reconciling these imperatives simultaneously. Drawing inspiration from overwhelming success in artificial intelligence, we propose a deep reinforcement learning-guided coevolutionary algorithm (DRLCEA) to tackle this predicament. DRLCEA employs two populations to optimize the original and unconstrained versions of the CMOP, respectively and then fosters cooperation between them according to the guidance of DRL. The established DRL employs two evaluation metrics to appraise population convergence, diversity, and feasibility, thus remarkably proficient in reflecting and steering the coevolution. Therefore, the proposed DRLCEA could effectively locate the feasible regions and approximate the constrained Pareto front. We assess the proposed algorithm on 32 benchmark CMOPs and one real-world UAV emergency track planning (UETP) application. Experimental results undoubtedly demonstrate the superiority and robustness of the proposed DRLCEA.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121648"},"PeriodicalIF":8.1,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142703999","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 : 2024-11-16DOI: 10.1016/j.ins.2024.121651
Yuxuan Lu, Jujie Wang, Qian Li
Precise carbon price prediction is crucial for informing climate policies, maintaining carbon markets, and driving global green transformation. Currently, decomposition integration methods are extensively employed for carbon price forecasting. However, most studies focus on predicting single values, neglecting the inherent volatility and uncertainty of interval-valued data. To address this gap, this study introduces an advanced interval-valued decomposition integration model that incorporates data preprocessing, improved multi-scale feature selection, and data-driven prediction technique. Initially, data preprocessing transforms the maximum and minimum carbon prices into central and radius sequences, capturing greater volatility information while eliminating noise and managing outliers. Subsequently, improved variational mode decomposition is utilized to optimally decompose and reconstruct the center and radius series, which enables a deeper exploration of the features of interval-valued data. A tailored data-driven prediction method is then employed to analyze sub-sequences with distinct characteristics separately, significantly reducing prediction errors. To assess the reliability and stability of the proposed model, a comprehensive comparative experiment is conducted, with results providing strong evidence supporting its effectiveness.
{"title":"An interval-valued carbon price prediction model based on improved multi-scale feature selection and optimal multi-kernel support vector regression","authors":"Yuxuan Lu, Jujie Wang, Qian Li","doi":"10.1016/j.ins.2024.121651","DOIUrl":"10.1016/j.ins.2024.121651","url":null,"abstract":"<div><div>Precise carbon price prediction is crucial for informing climate policies, maintaining carbon markets, and driving global green transformation. Currently, decomposition integration methods are extensively employed for carbon price forecasting. However, most studies focus on predicting single values, neglecting the inherent volatility and uncertainty of interval-valued data. To address this gap, this study introduces an advanced interval-valued decomposition integration model that incorporates data preprocessing, improved multi-scale feature selection, and data-driven prediction technique. Initially, data preprocessing transforms the maximum and minimum carbon prices into central and radius sequences, capturing greater volatility information while eliminating noise and managing outliers. Subsequently, improved variational mode decomposition is utilized to optimally decompose and reconstruct the center and radius series, which enables a deeper exploration of the features of interval-valued data. A tailored data-driven prediction method is then employed to analyze sub-sequences with distinct characteristics separately, significantly reducing prediction errors. To assess the reliability and stability of the proposed model, a comprehensive comparative experiment is conducted, with results providing strong evidence supporting its effectiveness.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"692 ","pages":"Article 121651"},"PeriodicalIF":8.1,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142703995","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