Information Sciences最新文献

英文中文

Ensuring privacy and correlation awareness in multi-dimensional service quality prediction and recommendation for IoT

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

Information Sciences

Pub Date : 2025-02-25 DOI: 10.1016/j.ins.2025.122017

Weiyi Zhong , Wei Fang , Yifan Zhao , Sifeng Wang , Chao Yan , Rong Jiang , Maqbool Khan , Xuan Yang , Wajid Rafique

Edge computing, with its advantages in terms of lightweight data transmission between users and cloud platforms, has become a promising solution for alleviating the heavy burden of timely data processing in many IoT scenarios, such as smart commerce and smart healthcare. However, several challenges arise when fusing multi-source IoT data recorded by different edge servers. First of all, data repetition within each edge server can greatly reduce the efficiency of various edge-based smart applications. Besides, IoT data fusion associated with multiple distributed edge servers can compromise user privacy. In addition, the multi-dimensional and interrelated nature of IoT data complicates precise data mining and analysis. To tackle these issues, a novel edge data fusion method (named TLTM) for cross-platform service recommendation is brought forth, which considers data dimensions, data correlation, and data privacy simultaneously. Finally, to validate the effectiveness and efficiency of the TLTM method, we have designed extensive experiments on the popular WS-DREAM dataset. The reported experimental results show that our TLTM method is superior to other related methods in terms of popular performance metrics including MAE, RMSE, Precision, Recall, F1-Score, and Time cost.

{"title":"Ensuring privacy and correlation awareness in multi-dimensional service quality prediction and recommendation for IoT","authors":"Weiyi Zhong , Wei Fang , Yifan Zhao , Sifeng Wang , Chao Yan , Rong Jiang , Maqbool Khan , Xuan Yang , Wajid Rafique","doi":"10.1016/j.ins.2025.122017","DOIUrl":"10.1016/j.ins.2025.122017","url":null,"abstract":"<div><div>Edge computing, with its advantages in terms of lightweight data transmission between users and cloud platforms, has become a promising solution for alleviating the heavy burden of timely data processing in many IoT scenarios, such as smart commerce and smart healthcare. However, several challenges arise when fusing multi-source IoT data recorded by different edge servers. First of all, data repetition within each edge server can greatly reduce the efficiency of various edge-based smart applications. Besides, IoT data fusion associated with multiple distributed edge servers can compromise user privacy. In addition, the multi-dimensional and interrelated nature of IoT data complicates precise data mining and analysis. To tackle these issues, a novel edge data fusion method (named <em>TLTM</em>) for cross-platform service recommendation is brought forth, which considers data dimensions, data correlation, and data privacy simultaneously. Finally, to validate the effectiveness and efficiency of the <em>TLTM</em> method, we have designed extensive experiments on the popular WS-DREAM dataset. The reported experimental results show that our <em>TLTM</em> method is superior to other related methods in terms of popular performance metrics including MAE, RMSE, Precision, Recall, F1-Score, and Time cost.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 122017"},"PeriodicalIF":8.1,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GRANA: Graph convolutional network based network representation learning method for attributed network alignment

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

Information Sciences

Pub Date : 2025-02-25 DOI: 10.1016/j.ins.2025.122014

Yao Li , He Cai , Huilin Liu

Social network alignment, which aims at identifying the correspondences of the same users across networks, is the very first step of information process from multiple social networks. Previous efforts on this task are either more inclined to preserve structural consistency or attribute consistency. Therefore, they only achieve good performance on specific alignment tasks or obtain compromised results on all kinds of alignment tasks. To achieve good generalization, in this paper, we propose a novel multi-task learning method to solve different social network alignment tasks, which is named GRANA (Graph convolutional network-based network Representation learning framework for Attributed Network Alignment). Specifically, a new two-layer cross-network convolutional neural network dubbed Cross-GCN is proposed as shared layers of GRANA. And the intra-network and inter-network attribute and structural information are learned respectively with diverse objective functions in the task specific layer of GRANA. To enhance the alignment performance and accelerate the learning process, a weight learning method with a novel weight initialization process is applied. Experimental results on six kinds of datasets show that GRANA outperforms seven state-of-the-art methods by at least 0.002-0.697 in terms of precision@15 value. The ablation studies further support the effectiveness of proposed Cross-GCN and weight initialization process.

{"title":"GRANA: Graph convolutional network based network representation learning method for attributed network alignment","authors":"Yao Li , He Cai , Huilin Liu","doi":"10.1016/j.ins.2025.122014","DOIUrl":"10.1016/j.ins.2025.122014","url":null,"abstract":"<div><div>Social network alignment, which aims at identifying the correspondences of the same users across networks, is the very first step of information process from multiple social networks. Previous efforts on this task are either more inclined to preserve structural consistency or attribute consistency. Therefore, they only achieve good performance on specific alignment tasks or obtain compromised results on all kinds of alignment tasks. To achieve good generalization, in this paper, we propose a novel multi-task learning method to solve different social network alignment tasks, which is named GRANA (Graph convolutional network-based network Representation learning framework for Attributed Network Alignment). Specifically, a new two-layer cross-network convolutional neural network dubbed Cross-GCN is proposed as shared layers of GRANA. And the intra-network and inter-network attribute and structural information are learned respectively with diverse objective functions in the task specific layer of GRANA. To enhance the alignment performance and accelerate the learning process, a weight learning method with a novel weight initialization process is applied. Experimental results on six kinds of datasets show that GRANA outperforms seven state-of-the-art methods by at least 0.002-0.697 in terms of precision@15 value. The ablation studies further support the effectiveness of proposed Cross-GCN and weight initialization process.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 122014"},"PeriodicalIF":8.1,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

EVA: Key values eclosion with space anchor used in hand pose estimation and shape reconstruction

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

Information Sciences

Pub Date : 2025-02-24 DOI: 10.1016/j.ins.2025.122003

Xuefeng Li , Xiangbo Lin

3D hand pose estimation and shape reconstruction from single RGB image face challenges of self-occlusion, object occlusion, and depth ambiguity. Previous methods tried efforts to detect relevant information from images directly. Differently, this paper considers the task as a union of detection and generation. A novel framework called Key Value Eclosion is proposed. It utilizes powerful Diffusion generation strategies to gradually generate and refine occluded joints, vertices, and depth, using visible 2D joint locations as clues. To make the latent codes more comprehensive for hand shape reconstruction, 2D image features are transformed into 3D space using the proposed Space Anchor based feature inverse projection strategy. Integrating the Space Anchor based feature inverse projection into the Key Values Eclosion framework, a complete hand pose estimation and shape reconstruction model called EVA is constructed. The EVA model demonstrates excellent accuracy on both aligned and unaligned metrics using the HO-3D and DexYCB datasets. Especially, the improvement on Mean Error and Trans&Scale metrics are about 30%~50%, compared to state-of-the-art methods.

{"title":"EVA: Key values eclosion with space anchor used in hand pose estimation and shape reconstruction","authors":"Xuefeng Li , Xiangbo Lin","doi":"10.1016/j.ins.2025.122003","DOIUrl":"10.1016/j.ins.2025.122003","url":null,"abstract":"<div><div>3D hand pose estimation and shape reconstruction from single RGB image face challenges of self-occlusion, object occlusion, and depth ambiguity. Previous methods tried efforts to detect relevant information from images directly. Differently, this paper considers the task as a union of detection and generation. A novel framework called Key Value Eclosion is proposed. It utilizes powerful Diffusion generation strategies to gradually generate and refine occluded joints, vertices, and depth, using visible 2D joint locations as clues. To make the latent codes more comprehensive for hand shape reconstruction, 2D image features are transformed into 3D space using the proposed Space Anchor based feature inverse projection strategy. Integrating the Space Anchor based feature inverse projection into the Key Values Eclosion framework, a complete hand pose estimation and shape reconstruction model called EVA is constructed. The EVA model demonstrates excellent accuracy on both aligned and unaligned metrics using the HO-3D and DexYCB datasets. Especially, the improvement on Mean Error and Trans&Scale metrics are about 30%~50%, compared to state-of-the-art methods.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 122003"},"PeriodicalIF":8.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CDTDNet: A neural network for capturing deep temporal dependencies in time series

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

Information Sciences

Pub Date : 2025-02-20 DOI: 10.1016/j.ins.2025.121995

Congbing He , Zhenhong Jia , Jie Hu , Fei Shi , Xiaohui Huang

The current research in time series forecasting is still deficient in extracting the time dependencies in depth. For this reason, a novel deep learning framework is proposed in this paper to extract deep temporal dependencies from time series data, and effectively feature-fuse temporal dependencies with other time series features. The Cell State Capture Recurrent Unit is used as a novel recurrent neural network together with Temporal Convolutional Network to capture the deep temporal dependencies of the data. Historical statistical information is constructed to introduce linear correlation variables for the model. Novel temporal attention coordinates the importance of time series time steps. Coupled attention improves the decoder's ability to interpret the encoded information. Finally, the AutoEncoder is employed as a prediction calibrator to improve the accuracy and robustness of the network. Comparisons with baseline methods and state-of-the-art strategies on datasets from four different domains confirm the effectiveness as well as the robustness of the proposed predictive network. In addition, the Cell State Capture Recurrent Unit can be considered a benchmark for time series forecasting instead of being limited to the Long and Short-Term Memory or Gated Recurrent Unit.

{"title":"CDTDNet: A neural network for capturing deep temporal dependencies in time series","authors":"Congbing He , Zhenhong Jia , Jie Hu , Fei Shi , Xiaohui Huang","doi":"10.1016/j.ins.2025.121995","DOIUrl":"10.1016/j.ins.2025.121995","url":null,"abstract":"<div><div>The current research in time series forecasting is still deficient in extracting the time dependencies in depth. For this reason, a novel deep learning framework is proposed in this paper to extract deep temporal dependencies from time series data, and effectively feature-fuse temporal dependencies with other time series features. The Cell State Capture Recurrent Unit is used as a novel recurrent neural network together with Temporal Convolutional Network to capture the deep temporal dependencies of the data. Historical statistical information is constructed to introduce linear correlation variables for the model. Novel temporal attention coordinates the importance of time series time steps. Coupled attention improves the decoder's ability to interpret the encoded information. Finally, the AutoEncoder is employed as a prediction calibrator to improve the accuracy and robustness of the network. Comparisons with baseline methods and state-of-the-art strategies on datasets from four different domains confirm the effectiveness as well as the robustness of the proposed predictive network. In addition, the Cell State Capture Recurrent Unit can be considered a benchmark for time series forecasting instead of being limited to the Long and Short-Term Memory or Gated Recurrent Unit.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121995"},"PeriodicalIF":8.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143473968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Practical searchable encryption scheme against response identity attacks

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

Information Sciences

Pub Date : 2025-02-20 DOI: 10.1016/j.ins.2025.121975

Shengming Li , Xuan Jing , Yunling Wang , Xin Xu , Zichen Zhang , Jianfeng Wang

Searchable symmetric encryption (SSE) enables efficient keyword-based search over encrypted data while revealing nothing about data and query beyond some pre-defined leakage, such as access pattern and search pattern. A new class of leakage-abuse attacks, called response identity attacks, can exploit access patterns to recover the queried keywords. Although some progress has been made to resist on response identity attacks, it is challenging to design a practical SSE scheme that resists on response identity attacks while protecting the security of data and queries (i.e., end-to-end SSE). To this end, we first present a novel dynamic SSE scheme supporting toward privacy based on the modified Path-ORAM, where the server cannot identify update patterns. We then design a dynamic end-to-end SSE scheme defending response identity attacks under two non-colluding servers model, which splits each encrypted document into the main document and extra blocks, and stores them separately using different obfuscation strategies. The proposed scheme can prevent adversaries from identifying which document in prior knowledge contains the searched keyword while hiding the data content and queries. Experimental results show that our proposed scheme is superior to the state-of-the-art scheme.

{"title":"Practical searchable encryption scheme against response identity attacks","authors":"Shengming Li , Xuan Jing , Yunling Wang , Xin Xu , Zichen Zhang , Jianfeng Wang","doi":"10.1016/j.ins.2025.121975","DOIUrl":"10.1016/j.ins.2025.121975","url":null,"abstract":"<div><div>Searchable symmetric encryption (SSE) enables efficient keyword-based search over encrypted data while revealing nothing about data and query beyond some pre-defined leakage, such as access pattern and search pattern. A new class of leakage-abuse attacks, called response identity attacks, can exploit access patterns to recover the queried keywords. Although some progress has been made to resist on response identity attacks, it is challenging to design a practical SSE scheme that resists on response identity attacks while protecting the security of data and queries (i.e., end-to-end SSE). To this end, we first present a novel dynamic SSE scheme supporting toward privacy based on the modified Path-ORAM, where the server cannot identify update patterns. We then design a dynamic end-to-end SSE scheme defending response identity attacks under two non-colluding servers model, which splits each encrypted document into the main document and extra blocks, and stores them separately using different obfuscation strategies. The proposed scheme can prevent adversaries from identifying which document in prior knowledge contains the searched keyword while hiding the data content and queries. Experimental results show that our proposed scheme is superior to the state-of-the-art scheme.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121975"},"PeriodicalIF":8.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Polynomial-time verification of pattern diagnosability for timed discrete event systems

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

Information Sciences

Pub Date : 2025-02-20 DOI: 10.1016/j.ins.2025.121997

Ye Liang , Dimitri Lefebvre , Zhiwu Li

This work focuses on the verification of diagnosability of timed patterns in discrete event systems by using a specific class of timed automata. A timed pattern refers to a set of behaviors which are defined by a sequence of events taking place in a given order and within specific time intervals. A silent closure is derived from a tick recognizer by removing all silent events, which provides benefits for the systems encompassing numerous silent events. For the diagnosability test, a timed pair composition structure is created by combining a normal silent closure with an accepted silent closure, both of which are obtained from the silent closure with respect to normal and faulty behaviors, respectively. The constructed timed pair composition can track normal and faulty behaviors simultaneously. By analyzing the timed pair composition regarding the presence of indeterminate cycles, we formulate a necessary and sufficient condition for the diagnosability verification of timed patterns, affirming that a system is diagnosable if and only if there is no indeterminate cycle in the timed pair composition. The proposed method is shown to be of polynomial time complexity at most.

{"title":"Polynomial-time verification of pattern diagnosability for timed discrete event systems","authors":"Ye Liang , Dimitri Lefebvre , Zhiwu Li","doi":"10.1016/j.ins.2025.121997","DOIUrl":"10.1016/j.ins.2025.121997","url":null,"abstract":"<div><div>This work focuses on the verification of diagnosability of timed patterns in discrete event systems by using a specific class of timed automata. A timed pattern refers to a set of behaviors which are defined by a sequence of events taking place in a given order and within specific time intervals. A silent closure is derived from a tick recognizer by removing all silent events, which provides benefits for the systems encompassing numerous silent events. For the diagnosability test, a timed pair composition structure is created by combining a normal silent closure with an accepted silent closure, both of which are obtained from the silent closure with respect to normal and faulty behaviors, respectively. The constructed timed pair composition can track normal and faulty behaviors simultaneously. By analyzing the timed pair composition regarding the presence of indeterminate cycles, we formulate a necessary and sufficient condition for the diagnosability verification of timed patterns, affirming that a system is diagnosable if and only if there is no indeterminate cycle in the timed pair composition. The proposed method is shown to be of polynomial time complexity at most.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121997"},"PeriodicalIF":8.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143473966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synchronization of quaternion-valued multi-layer coupled networks: An adaptive activation-time-based event-triggered scheme

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

Information Sciences

Pub Date : 2025-02-20 DOI: 10.1016/j.ins.2025.121999

Yue Ren , Haijun Jiang , Cheng Hu , Lianyang Hu , Jiarong Li

This paper develops an adaptive activation-time-based event-triggered scheme (ETS) to investigate the synchronization of quaternion-valued multi-layer coupled networks (QVMLCNs). Firstly, the QVMLCN models with linear coupling and nonlinear coupling are established, respectively. Subsequently, a new adaptive activation-time-based ETS that can only be activated after some particular moments is presented to address the synchronization issue of the considered two types of QVMLCNs. It is worth emphasizing that the principal advantage of the proposed adaptive activation-time-based ETS is that Zeno behavior can be naturally excluded and a positive minimum interevent time can be strictly ensured, which is more resource-conserving than existing adaptive ETSs. Lastly, the usefulness of the theoretical results is verified by some numerical simulations.

引用次数: 0

The grouping weighted averaging operator via three-way conflict analysis

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

Information Sciences

Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121990

Xiaonan Li , Rong Liang , Huangjian Yi

Aggregation operators play an important role in problems related to information fusion. There are various aggregation operators, and selecting appropriate ones for a specific problem remains a challenging task. For the evaluation problem in three-way conflict analysis, this paper attempts to propose a new type of aggregation operator: the grouping weighted averaging (GWA) operator. GWA operators not only consider the implicit information in data, but also do not require strong prior knowledge of data to be aggregated. First, we divide the data into groups, which correspond to coalitions in three-way conflict analysis. Second, weights of groups are generated according to their properties. Third, the final result is obtained via two aggregations: within and between groups. Besides, we also provide multiple GWA operators based on various partitions and weight allocation methods, and study their theoretical properties. Especially, as an application to conflict analysis, we propose an index of stability based on the GWA operator to compare coalition systems.

引用次数: 0

Preserving knowledge from the source domain for cross-domain person re-identification

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

Information Sciences

Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121994

Yifeng Gou , Ziqiang Li , Junyin Zhang , Yongxin Ge

Although recent cross-domain person re-identification approaches have obtained great progress, they still suffer from two core issues. The first one is the insufficient useful knowledge transfer, which means the beneficial knowledge learned from the source domain is not utilized fully due to the fine-tuning process of the two-stage training especially. The second problem is the inappropriate transfer of the source domain knowledge. Concretely, this knowledge is not distinguished before being transferred, leading to the domain-specific knowledge is detrimental to the target domain performance. To circumvent them, we design a novel collaborative learning method named Preserving Knowledge from the Source Domain (PKSD) from both instance and pixel levels, composed of Ranking-guided Instance Selection (RIS) and Projection based Gradient Selection (PGS). Firstly, the collaborative learning manner could safeguard sufficient knowledge transfer from the source domain. Additionally, RIS tries to select reliable and informative samples from the source domain dataset for training to provide sufficient domain-shared knowledge at the instance level. Subsequently, PGS fine-tunes the feature maps of the selected samples according to the gradient modifying at the pixel level of feature maps to suppress remaining domain-specific knowledge from the source domain. Experiments show that PKSD outperforms existing state-of-the-art methods.

{"title":"Preserving knowledge from the source domain for cross-domain person re-identification","authors":"Yifeng Gou , Ziqiang Li , Junyin Zhang , Yongxin Ge","doi":"10.1016/j.ins.2025.121994","DOIUrl":"10.1016/j.ins.2025.121994","url":null,"abstract":"<div><div>Although recent cross-domain person re-identification approaches have obtained great progress, they still suffer from two core issues. The first one is the insufficient useful knowledge transfer, which means the beneficial knowledge learned from the source domain is not utilized fully due to the fine-tuning process of the two-stage training especially. The second problem is the inappropriate transfer of the source domain knowledge. Concretely, this knowledge is not distinguished before being transferred, leading to the domain-specific knowledge is detrimental to the target domain performance. To circumvent them, we design a novel collaborative learning method named Preserving Knowledge from the Source Domain (PKSD) from both instance and pixel levels, composed of Ranking-guided Instance Selection (RIS) and Projection based Gradient Selection (PGS). Firstly, the collaborative learning manner could safeguard sufficient knowledge transfer from the source domain. Additionally, RIS tries to select reliable and informative samples from the source domain dataset for training to provide sufficient domain-shared knowledge at the instance level. Subsequently, PGS fine-tunes the feature maps of the selected samples according to the gradient modifying at the pixel level of feature maps to suppress remaining domain-specific knowledge from the source domain. Experiments show that PKSD outperforms existing state-of-the-art methods.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121994"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Joint discriminant projection with cosine weighted dynamic graph regularization for feature extraction

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

Information Sciences

Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121987

Weijia Tang , Hongmei Chen , Tengyu Yin , Zhong Yuan , Chuan Luo , Shi-Jinn Horng , Tianrui Li

Obtaining low-dimensional discriminative features for original-dimensional data through projection in machine learning is challenging. The problems facing discriminative projection are: The data contains noise and outliers, and the effectiveness of the projection will be negatively affected. Extracting discriminative features by combining linear discriminative projection with preserving the local geometric structure is complex. The excess edges in the graph regularity term introduce redundant information, negatively impacting discriminative feature extraction. To address the issues above, the Joint Discriminant Projection with Cosine-Weighted Dynamic Graph Regularization (JDPCDG) is devised for feature extraction. The JDPCDG model consists of three main contributions: (1) The

ξ_{1}

-norm and

ξ_{2}

-norm are designed to adapt to outlier samples and noise features, respectively. (2) The

S_{c o s}

similarity graph matrix constructed with cosine weights is designed to preserve the global structure information within the class and obtain the local structure information in combination with the LDA model. (3) A framework model is constructed by effectively integrating manifold learning, linear discriminant analysis, and reconstructed data. Comprehensive experiments on synthetic data and multiple real-world datasets consistently demonstrate their superior performance over other relevant feature extraction methods. Experiments are conducted on non-image and image data, comparing them with related methods. The experimental results verify the robustness and superiority of the proposed JDPCDG.

{"title":"Joint discriminant projection with cosine weighted dynamic graph regularization for feature extraction","authors":"Weijia Tang , Hongmei Chen , Tengyu Yin , Zhong Yuan , Chuan Luo , Shi-Jinn Horng , Tianrui Li","doi":"10.1016/j.ins.2025.121987","DOIUrl":"10.1016/j.ins.2025.121987","url":null,"abstract":"<div><div>Obtaining low-dimensional discriminative features for original-dimensional data through projection in machine learning is challenging. The problems facing discriminative projection are: The data contains noise and outliers, and the effectiveness of the projection will be negatively affected. Extracting discriminative features by combining linear discriminative projection with preserving the local geometric structure is complex. The excess edges in the graph regularity term introduce redundant information, negatively impacting discriminative feature extraction. To address the issues above, the Joint Discriminant Projection with Cosine-Weighted Dynamic Graph Regularization (JDPCDG) is devised for feature extraction. The JDPCDG model consists of three main contributions: (1) The <span><math><msub><mrow><mi>ξ</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>-norm and <span><math><msub><mrow><mi>ξ</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span>-norm are designed to adapt to outlier samples and noise features, respectively. (2) The <span><math><msub><mrow><mi>S</mi></mrow><mrow><mi>c</mi><mi>o</mi><mi>s</mi></mrow></msub></math></span> similarity graph matrix constructed with cosine weights is designed to preserve the global structure information within the class and obtain the local structure information in combination with the LDA model. (3) A framework model is constructed by effectively integrating manifold learning, linear discriminant analysis, and reconstructed data. Comprehensive experiments on synthetic data and multiple real-world datasets consistently demonstrate their superior performance over other relevant feature extraction methods. Experiments are conducted on non-image and image data, comparing them with related methods. The experimental results verify the robustness and superiority of the proposed JDPCDG.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121987"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Information Sciences

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀