Complex & Intelligent Systems最新文献_第4页

Incremental data modeling based on neural ordinary differential equations

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-02-17 DOI: 10.1007/s40747-025-01793-0

Zhang Chen, Hanlin Bian, Wei Zhu

{"title":"Incremental data modeling based on neural ordinary differential equations","authors":"Zhang Chen, Hanlin Bian, Wei Zhu","doi":"10.1007/s40747-025-01793-0","DOIUrl":"https://doi.org/10.1007/s40747-025-01793-0","url":null,"abstract":"With the development of data acquisition technology, a large amount of time-series data can be collected. However, handling too much data often leads to a waste of social resources. It becomes significant to determine the minimum data size required for training. In this paper, a framework for neural ordinary differential equations based on incremental learning is discussed, which can enhance learning ability and determine the minimum data size required in data modeling compared to neural ordinary differential equations. This framework continuously updates the neural ordinary differential equations with newly added data while avoiding the addition of extra parameters. Once the preset accuracy is reached, the minimum data size needed for training can be determined. Furthermore, the minimum data size required for five classic models under various sampling rates is discussed. By incorporating new data, it enhances accuracy instead of increasing the depth and width of the neural network. The close integration of data generation and training can significantly reduce the total time required. Theoretical analysis confirms convergence, while numerical results demonstrate that the framework offers superior predictive ability and reduced computation time compared to traditional neural differential equations.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Swin-Diff: a single defocus image deblurring network based on diffusion model

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-02-17 DOI: 10.1007/s40747-025-01789-w

Hanyan Liang, Shuyao Chai, Xixuan Zhao, Jiangming Kan

{"title":"Swin-Diff: a single defocus image deblurring network based on diffusion model","authors":"Hanyan Liang, Shuyao Chai, Xixuan Zhao, Jiangming Kan","doi":"10.1007/s40747-025-01789-w","DOIUrl":"https://doi.org/10.1007/s40747-025-01789-w","url":null,"abstract":"Single Image Defocus Deblurring (SIDD) remains challenging due to spatially varying blur kernels, particularly in processing high-resolution images where traditional methods often struggle with artifact generation, detail preservation, and computational efficiency. This paper presents Swin-Diff, a novel architecture integrating diffusion models with Transformer-based networks for robust defocus deblurring. Our approach employs a two-stage training strategy where a diffusion model generates prior information in a compact latent space, which is then hierarchically fused with intermediate features to guide the regression model. The architecture incorporates a dual-dimensional self-attention mechanism operating across channel and spatial domains, enhancing long-range modeling capabilities while maintaining linear computational complexity. Extensive experiments on three public datasets (DPDD, RealDOF, and RTF) demonstrate Swin-Diff’s superior performance, achieving average improvements of 1.37% in PSNR, 3.6% in SSIM, 2.3% in MAE, and 25.2% in LPIPS metrics compared to state-of-the-art methods. Our results validate the effectiveness of combining diffusion models with hierarchical attention mechanisms for high-quality defocus blur removal.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"15 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Sequence-to-point learning based on spatio-temporal attention fusion network for non-intrusive load monitoring

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-02-17 DOI: 10.1007/s40747-025-01803-1

Shiqing Zhang, Youyao Fu, Xiaoming Zhao, Jiangxiong Fang, Yadong Liu, Xiaoli Wang, Baochang Zhang, Jun Yu

引用次数: 0

HFA-Net: hierarchical feature aggregation network for micro-expression recognition

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-02-12 DOI: 10.1007/s40747-025-01804-0

Meng Zhang, Wenzhong Yang, Liejun Wang, Zhonghua Wu, Danny Chen

{"title":"HFA-Net: hierarchical feature aggregation network for micro-expression recognition","authors":"Meng Zhang, Wenzhong Yang, Liejun Wang, Zhonghua Wu, Danny Chen","doi":"10.1007/s40747-025-01804-0","DOIUrl":"https://doi.org/10.1007/s40747-025-01804-0","url":null,"abstract":"Micro-expressions (MEs) are unconscious and involuntary reactions that genuinely reflect an individual’s inner emotional state, making them valuable in the fields of emotion analysis and behavior recognition. MEs are characterized by subtle changes within specific facial action units, and effective feature learning and fusion tailored to these characteristics still require in-depth research. To address this challenge, this paper proposes a novel hierarchical feature aggregation network (HFA-Net). In the local branch, the multi-scale attention (MSA) block is proposed to capture subtle facial changes and local information. The global branch introduces the retentive meet transformers (RMT) block to establish dependencies between holistic facial features and structural information. Considering that single-scale features are insufficient to fully capture the subtleties of MEs, a multi-level feature aggregation (MLFA) module is proposed to extract and fuse features from different levels across the two branches, preserving more comprehensive feature information. To enhance the representation of key features, an adaptive attention feature fusion (AAFF) module is designed to focus on the most useful and relevant feature channels. Extensive experiments conducted on the SMIC, CASME II, and SAMM benchmark databases demonstrate that the proposed HFA-Net outperforms current state-of-the-art methods. Additionally, ablation studies confirm the superior discriminative capability of HFA-Net when learning feature representations from limited ME samples. Our code is publicly available at https://github.com/tairuwu/HFA-Net.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"18 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143393219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Manet: motion-aware network for video action recognition Manet：用于视频动作识别的运动感知网络

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-02-06 DOI: 10.1007/s40747-024-01774-9

Xiaoyang Li, Wenzhu Yang, Kanglin Wang, Tiebiao Wang, Chen Zhang

{"title":"Manet: motion-aware network for video action recognition","authors":"Xiaoyang Li, Wenzhu Yang, Kanglin Wang, Tiebiao Wang, Chen Zhang","doi":"10.1007/s40747-024-01774-9","DOIUrl":"https://doi.org/10.1007/s40747-024-01774-9","url":null,"abstract":"Video action recognition is a fundamental task in video understanding. Actions in videos may vary at different speeds or scales, and it is difficult to cope with a wide variety of actions by relying on a single spatio-temporal scale to extract features. To address this problem, we propose a Motion-Aware Network (MANet), which includes three key modules: (1) Local Motion Encoding Module (LMEM) for capturing local motion features, (2) Spatio-Temporal Excitation Module (STEM) for extracting multi-granular motion information, and (3) Multiple Temporal Aggregation Module (MTAM) for modeling multi-scale temporal information. The MANet, equipped with these modules, can capture multi-granularity spatio-temporal cues. We conducted extensive experiments on five mainstream datasets, Something-Something V1 & V2, Jester, Diving48, and UCF-101, to validate the effectiveness of MANet. The MANet achieves competitive performance on Something-Something V1 (52.5%), Something-Something V2 (63.6%), Jester (95.9%), Diving48 (81.8%) and UCF-101 (86.2%). In addition, we visualize the feature representation of the MANet using Grad-CAM to validate its effectiveness.\u0000","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"8 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A low-carbon scheduling method based on improved ant colony algorithm for underground electric transportation vehicles

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-30 DOI: 10.1007/s40747-024-01775-8

Yizhe Zhang, Yinan Guo, Yao Huang, Shirong Ge

{"title":"A low-carbon scheduling method based on improved ant colony algorithm for underground electric transportation vehicles","authors":"Yizhe Zhang, Yinan Guo, Yao Huang, Shirong Ge","doi":"10.1007/s40747-024-01775-8","DOIUrl":"https://doi.org/10.1007/s40747-024-01775-8","url":null,"abstract":"Improved scheduling of underground transportation vehicles in coal mines can significantly enhance work efficiency and contribute to safer production. However, the specific working conditions and limitations of electric vehicles pose significant challenges to effective vehicle scheduling. To address this issue, a constrained single-objective optimization model is developed to minimize transportation costs for low-carbon scheduling of underground electric transportation vehicles (ETVs). The model incorporates constraints related to load capacity, cruising range, and safety regulations. A specific energy consumption model for ETVs is formulated, considering factors such as road conditions, load, and driving state. To solve this problem, an improved ant colony optimization algorithm integrated with Q-learning (ACO-QL) is proposed. Specifically, ant colony optimization explores the global solution space and identifies promising regions, while the split strategy effectively distributes demand across multiple vehicles. Q-learning enhances local search by selecting the most appropriate operator, preventing premature convergence to local optima. Experimental results on four real-world instances demonstrate the superior performance of ACO-QL compared to state-of-the-art algorithms.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"62 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143056604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A survey of security threats in federated learning

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-29 DOI: 10.1007/s40747-024-01664-0

Yunhao Feng, Yanming Guo, Yinjian Hou, Yulun Wu, Mingrui Lao, Tianyuan Yu, Gang Liu

引用次数: 0

Vehicle positioning systems in tunnel environments: a review

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-29 DOI: 10.1007/s40747-024-01744-1

Suying Jiang, Qiufeng Xu, Wei Wang, Peng Peng, Jiachun Li

{"title":"Vehicle positioning systems in tunnel environments: a review","authors":"Suying Jiang, Qiufeng Xu, Wei Wang, Peng Peng, Jiachun Li","doi":"10.1007/s40747-024-01744-1","DOIUrl":"https://doi.org/10.1007/s40747-024-01744-1","url":null,"abstract":"Real-time, accurate, and robust positioning system plays a crucial role in many vehicular applications for automatic driving system and Vehicular Ad-hoc Network (VANET). In the tunnel, the positioning accuracy of Global Navigation Satellite System (GNSS) decreases due to blocked satellite signals. In order to estimate the exact location of vehicles in tunnel environments, many positioning systems have been presented. However, there is a lack of effort in systematically comparing, organizing and analyzing these existing positioning systems, and identifying the strengths and weaknesses of different technologies and applicable scenarios. Therefore, this paper undertakes a thorough investigation into current vehicle localization technologies and methods for tunnel scenarios. The analysis starts with discussing various application scenarios for vehicle positioning system. Then, various vehicle positioning technologies are investigated, the advantages and drawbacks of each technology are illustrated. Thereafter, we discuss some widely used positioning methods in terms of range-based localization method, range-free localization method, multi-sensor fusion localization method, and cooperative positioning (CP) method. Finally, we discuss some challenges faced in vehicle positioning for tunnel environments, and propose some potential research topics for future research work.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"45 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143055098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Barriers and enhance strategies for green supply chain management using continuous linear diophantine neural networks

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-29 DOI: 10.1007/s40747-024-01623-9

Shougi S. Abosuliman, Saleem Abdullah, Nawab Ali

{"title":"Barriers and enhance strategies for green supply chain management using continuous linear diophantine neural networks","authors":"Shougi S. Abosuliman, Saleem Abdullah, Nawab Ali","doi":"10.1007/s40747-024-01623-9","DOIUrl":"https://doi.org/10.1007/s40747-024-01623-9","url":null,"abstract":"Artificial neural networks, a major element of machine learning, focus additional attention on the decision-making process. We extended the idea of artificial neural networks to continuous linear Diophantine fuzzy neural networks. A few operational concepts for continuous linear Diophantine fuzzy sets are further developed, and they are subsequently made simpler to apply to more than two such sets. Also, a real multi-criteria decision-making problem has been formulated. The environment plays a very important role in our daily lives. We cause different types of pollution in our environment, and it has a bad impact on our lives. Air pollution is one of the various forms of pollution that is thought to affect the entire globe. Millions of people die due to air pollution, and industries are the main contributors to air pollution. To overcome air pollution, green supply chain management plays a vital role, but green supply chain management faces some barriers as well. According to the proposed model, ({mathfrak{R}}_{1}) is the best alternative and green supply chain management faces financial problems more than other barriers and also provides strategies to overcome financial barriers. In addition, a comparative analysis develops to illustrate the reliability and feasibility of the suggested technique in relation to current techniques.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"52 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143055103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

XTNSR: Xception-based transformer network for single image super resolution

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-25 DOI: 10.1007/s40747-024-01760-1

Jagrati Talreja, Supavadee Aramvith, Takao Onoye

{"title":"XTNSR: Xception-based transformer network for single image super resolution","authors":"Jagrati Talreja, Supavadee Aramvith, Takao Onoye","doi":"10.1007/s40747-024-01760-1","DOIUrl":"https://doi.org/10.1007/s40747-024-01760-1","url":null,"abstract":"Single image super resolution has significantly advanced by utilizing transformers-based deep learning algorithms. However, challenges still need to be addressed in handling grid-like image patches with higher computational demands and addressing issues like over-smoothing in visual patches. This paper presents a Deep Learning model for single-image super-resolution. In this paper, we present the XTNSR model, a novel multi-path network architecture that combines Local feature window transformers (LWFT) with Xception blocks for single-image super-resolution. The model processes grid-like image patches effectively and reduces computational complexity by integrating a Patch Embedding layer. Whereas the Xception blocks use depth-wise separable convolutions for hierarchical feature extraction, the LWFT blocks capture long-range dependencies and fine-grained qualities. A multi-layer feature fusion block with skip connections, part of this hybrid architecture, guarantees efficient local and global feature fusion. The experimental results show better performance in Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual quality than the state-of-the-art techniques. By optimizing parameters, the suggested architecture also lowers computational complexity. Overall, the architecture presents a promising approach for advancing image super-resolution capabilities.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"35 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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