Liyan Zhang , Yifan Li , Xinghui Hao , Qinyu Zhang , Aimin Yang , Jingfeng Guo , Lei Zhang
{"title":"Hypergraph representation learning based on fuzzy attention network","authors":"Liyan Zhang , Yifan Li , Xinghui Hao , Qinyu Zhang , Aimin Yang , Jingfeng Guo , Lei Zhang","doi":"10.1016/j.asoc.2025.113602","DOIUrl":"10.1016/j.asoc.2025.113602","url":null,"abstract":"<div><div>Since different nodes in hypergraph have different contributions to hyperedge learning, it is a hot topic in the field of graph representation learning to introduce attention mechanism into hypergraph neural network to represent the importance of different nodes or hyperedges. However, the existing hypergraph attention network methods are mostly based on the assumption that node attributes and topology are perfectly given. In practice, node links and attributes are usually fuzzy concepts, which will lead to the uncertainty of feature learning and then affect the effectiveness of node representation. Based on this, inspired by the attention mechanism and fuzzy logic, this paper proposes a new fuzzy attention hypergraph neural network (HFATN), which is used to quantify the contribution ability of different vertices and hyperedges to better learn the vector representation of nodes in the hypergraph. HFATN consists of two modules: fuzzy attention vertex convolution and fuzzy attention hyperedge convolution. In the process of node convolution and hyperedge convolution, the attention mechanism based on hyperedge and node uncertainty characteristics is introduced respectively. By fuzzing the node set and hyperedge set on the hypergraph, the membership degree of nodes and hyperedges is calculated, which is used to extract effective features to deal with the uncertainty in the hypergraph data. Finally, we conduct experiments on three benchmark datasets for hypergraph node classification. The results show that compared with the latest TDHGNN model, the classification accuracy of FHATN on the three datasets is improved by 2.28 %, 8.99 % and 1.85 % respectively.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113602"},"PeriodicalIF":6.6,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723362","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}
Haibo Zhang , Xu Wang , Pan Dang , Chaohui Ma , Shuai Liu , Zhuang Xiong , Cheng Liu
{"title":"UL-Phys:Ultra-lightweight remote physiological measurement in facial videos based on unsupervised learning","authors":"Haibo Zhang , Xu Wang , Pan Dang , Chaohui Ma , Shuai Liu , Zhuang Xiong , Cheng Liu","doi":"10.1016/j.asoc.2025.113593","DOIUrl":"10.1016/j.asoc.2025.113593","url":null,"abstract":"<div><div>Remote photoplethysmography (rPPG) enables non-contact monitoring of vital signs using facial videos, but current supervised learning methods often rely on complex architectures and large annotated datasets, limiting their practicality in real-time and resource-constrained scenarios. This paper addresses these limitations by proposing UL-Phys, an ultra-lightweight self-supervised framework for rPPG signal estimation. From a research standpoint, we reformulate the rPPG task as a linear self-supervised reconstruction problem, introducing a novel frequency-constrained objective to extract inherent periodic information without requiring ground truth labels. The framework integrates a lightweight 3D spatiotemporal encoder-decoder network, and a neuroscience-inspired hybrid attention module to enhance pulsatile signal regions while suppressing noise. Experimental evaluations on PURE and UBFC-rPPG datasets demonstrate that UL-Phys achieves superior performance compared to existing supervised and self-supervised baselines, while significantly reducing model complexity and inference latency. Our method also shows strong generalization across datasets, highlighting the value of embedding physiological priors into lightweight, self-supervised architectures. These findings offer a promising direction for scalable and deployable rPPG systems in real-world settings.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113593"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144665518","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}
Junhao Huang , Bing Xue , Yanan Sun , Mengjie Zhang , Gary G. Yen
{"title":"Efficient perturbation-aware distinguishing score for zero-shot neural architecture search","authors":"Junhao Huang , Bing Xue , Yanan Sun , Mengjie Zhang , Gary G. Yen","doi":"10.1016/j.asoc.2025.113447","DOIUrl":"10.1016/j.asoc.2025.113447","url":null,"abstract":"<div><div>Zero-cost proxies are under the spotlight of neural architecture search (NAS) lately, thanks to their low computational cost in predicting architecture performance in a training-free manner. The NASWOT score is one of the representative proxies that measures the architecture’s ability to distinguish inputs at the activation layers. However, obtaining such a score still requires considerable calculations on a large kernel matrix about input similarity. Moreover, the NASWOT score is relatively coarse-grained and provides a rough estimation of the architecture’s ability to distinguish general inputs. In this paper, to further reduce the computational complexity, we first propose a simplified NASWOT scoring term by relaxing its original matrix-based calculation into a vector-based one. More importantly, we develop a fine-grained perturbation-aware term to measure how well the architecture can distinguish between inputs and their perturbed counterparts. We propose a layer-wise score multiplication approach to combine these two scoring terms, deriving a new proxy, named efficient perturbation-aware distinguishing score (ePADS). Experiments on various NAS spaces and datasets show that ePADS consistently outperforms other zero-cost proxies in terms of both predictive reliability and efficiency. Particularly, ePADS achieves the highest ranking correlation among the advanced competitors (e.g., Kendall’s coefficient of 0.620 on NAS-Bench-201 with ImageNet-16-120 and 0.485 on NDS-ENAS), and ePADS-based random architecture search spends only 0.018 GPU days on DARTS-CIFAR to find networks with an average error rate of 2.64%.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113447"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144663627","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}
{"title":"Cooperative co-evolutionary search for meta multigraph and graph neural architecture on heterogeneous information networks","authors":"Yang Liu , Xiangyi Teng , Jing Liu","doi":"10.1016/j.asoc.2025.113541","DOIUrl":"10.1016/j.asoc.2025.113541","url":null,"abstract":"<div><div>To model the rich semantic information on heterogeneous information networks (HINs), heterogeneous graph neural architecture search (HGNAS) has become a research hotspot, as it offers a promising automatic search technique for heterogeneous graph neural networks (HGNNs). However, there is no method that can simultaneously solve the meta multigraph and neural architecture search, which are the two core problems of HGNAS. In addition, existing HGNAS methods can only search for the meta graph or determine the number of edge types by setting a threshold hyperparameter, which has limited expression or is difficult to determine and significantly affects performance. In this paper, a cooperative co-evolutionary meta multigraph and graph neural architecture search method (called CCMG) on HINs is proposed. Specifically, CCMG first represents the meta multigraph and neural architecture by discrete encodings, and the number of network layers is variable. Second, whether an encoding of the architecture is meaningful or not is affected by the value of the encoding taken at the corresponding meta multigraph position and their search space sizes are not imbalanced. To cope with these situations, they are cooperatively and collaboratively optimized in the form of subproblems, facilitating group collaboration and information sharing. Finally, the effectiveness and superiority of the CCMG are verified on six datasets for node classification and recommendation tasks. Over the comparison HGNAS method, CCMG improves its performance on the two tasks by an average of 2.29% and 1.21%, respectively.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113541"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654214","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}
{"title":"Dual-branch fusion network with mutual learning for 12-lead electrocardiogram signal classification","authors":"Ke Ma , Tao Zhang , Hengyuan Zhang , Wu Huang","doi":"10.1016/j.asoc.2025.113638","DOIUrl":"10.1016/j.asoc.2025.113638","url":null,"abstract":"<div><div>At present, the vast majority of methods use 12-lead electrocardiograms as a two-dimensional array as network input, and use deep neural networks to extract inter-lead correlation features. However, extracting intra-lead differential features is particularly important, as not every lead’s feature carries equal significance for classification. In this paper, we propose a dual-branch fusion network with 12-lead separation and combination, integrating the idea of mutual learning. The dual-branch network extracts differentiated and correlated features respectively and fuse them for classification. Each branch network is not only supervised by the ground truth but also referenced the learning experience of another branch network to further improve its classification ability. To address data imbalance, we introduced a category weighted binary focal loss to increase the attention of the network to the samples with few classes. We validated the proposed method on two publicly available multi-label datasets. Compared to the baseline model, our model has significantly improved in performance, demonstrating strong competitiveness and validating the effectiveness of our method. The experimental results show that our proposed method surpasses existing methods and achieves state-of-the-art performance. The method enables lightweight deployment on wearable devices, such as 12-lead ECG garments and smartwatches, facilitating real-time arrhythmia monitoring.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113638"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685480","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}
{"title":"A multi-bipolar fuzzy graph and its centrality measure based decision making system for healthcare waste treatment method selection","authors":"Deva Nithyanandham, Felix Augustin","doi":"10.1016/j.asoc.2025.113564","DOIUrl":"10.1016/j.asoc.2025.113564","url":null,"abstract":"<div><div>Fuzzy graphs help to handle various real-life uncertain problems and fuzzy preference relations have widely been utilized to deal with various decision-making problems. In reality, the multi-dimensional and counter investigations of a problem always provide an efficient outcome. However, these conventional approaches often lack consideration of counter-views and multi-dimensional perspectives in problem-solving. Therefore, the present study defines the notion of multi-bipolar fuzzy preference relation to fuse the multi-dimensional and bipolar views in handling uncertain relations in real-time problems. The notion of multi-bipolar fuzzy preference relation graph is explored to effectively study the pairwise importance in terms of multi-bipolar fuzzy relations between the multi-bipolar fuzzy sets. Additionally, the concepts of degree, in-degree and out-degree centrality measures are explored within the multi-bipolar fuzzy graph context. On the other hand, these concepts are fused to design a multi-criteria decision-making technique, where the preference relation graph helps to analyze the pairwise importance among the criteria and in-degree centrality aids to consider the importance of a criteria from other criteria. Furthermore, this fusion is implemented to address the healthcare waste treatment selection problem, where steam sterilization and chemical disinfection resulted in first and last rank, respectively. For this problem, five alternatives and their ten essential criteria are considered from the view of technical, social, environmental and economic aspects. To demonstrate the superiority and validity of the proposed technique, a comparative study is performed with existing techniques. Finally, the stability of the results is analyzed through a sensitivity performance.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113564"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680389","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}
Linjie Wu , Tianhao Zhao , Xingjuan Cai , Zhihua Cui , Jinjun Chen
{"title":"Dynamic multi-objective optimization for uncertain order insertion green shop production scheduling","authors":"Linjie Wu , Tianhao Zhao , Xingjuan Cai , Zhihua Cui , Jinjun Chen","doi":"10.1016/j.asoc.2025.113573","DOIUrl":"10.1016/j.asoc.2025.113573","url":null,"abstract":"<div><div>Efficient production scheduling of forgings is critical to manufacturing. However, production orders in manufacturing can change dynamically, making it challenging to quickly track changes between orders and ensure productivity and environmentally friendly production in the shop. This paper presents a dynamic multi-objective green shop production scheduling optimization problem that addresses uncertain order insertion, considering the objectives of total completion time, energy consumption, and carbon emission. When a new batch of orders arrives, changes in the dimensionality of decision variables for production scheduling lead to environmental alterations. By integrating the workpiece completion rates of orders from historical environments with the workpiece quantities of orders in the new environment, the scheduling plan is dynamically adjusted and promptly responded to. Therefore, we design a discrete matrix-based dynamic multi-objective optimization algorithm (DM-DMOEA), which can measure the similarity of the orders before and after the dynamic changes, and reconstruct a high-quality scheduling solution under the new environment, which solves the problem of variable dimensionality changes due to the dynamic environment. Finally, experiments were conducted in a real case of a flange manufacturing company, and the results proved the validity of the proposed model and the superior performance of the algorithm.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113573"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694370","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}
{"title":"A dual-dynamic population multi-objective evolutionary algorithm for large-scale crude oil scheduling optimization","authors":"Xianyu Hou , Renchu He , Wei Du","doi":"10.1016/j.asoc.2025.113570","DOIUrl":"10.1016/j.asoc.2025.113570","url":null,"abstract":"<div><div>As refinery production scales and equipment complexity increase, refineries are setting stricter requirements for crude oil scheduling. Consequently, large-scale multi-objective crude oil scheduling problems (LSMCOSPs) involve a vast quantity of binary variables, nonlinear restrictions, and many multiple optimization objectives, making it challenging for conventional algorithms to efficiently explore the solution space and often resulting in suboptimal outcomes. This paper addresses this challenge by constructing a discrete-time mixed-integer nonlinear programming (MINLP) model for offshore refinery crude oil scheduling, covering stages such as unloading, transportation, processing in crude distillation units (CDUs), and intermediate product inventory management. Based on this model, we propose a dual-dynamic population co-evolutionary algorithm (denoted by DDPCEA) to solve the problem. The experiment consists of three scheduling cases, involving multiple crude oil types, storage tanks, and processing equipment, with a total of thousands of binary variables and dozens of nonlinear constraints. During the algorithm’s execution, the initially fixed mutation factor, crossover factor, and nonlinear learning factor dynamically evolve with the number of iterations. Additionally, a repair strategy is introduced to further optimize local continuous variables, moving infeasible solutions toward the feasible region. Experimental results demonstrate that, compared to commonly used multi-objective algorithms for LSMCOSPs, the proposed DDPCEA significantly improves both the number of changeovers and runtime efficiency, while also achieving superior performance in terms of HV and IGD metrics.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113570"},"PeriodicalIF":7.2,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680390","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}
Bing Xue , Xin Gao , Heping Lu , Baofeng Li , Feng Zhai , Meng Xu , Taizhi Wang , Jiawen Lu
{"title":"A dual-reconstruction self-rectification framework with momentum memory-augmented network for multivariate time series anomaly detection","authors":"Bing Xue , Xin Gao , Heping Lu , Baofeng Li , Feng Zhai , Meng Xu , Taizhi Wang , Jiawen Lu","doi":"10.1016/j.asoc.2025.113558","DOIUrl":"10.1016/j.asoc.2025.113558","url":null,"abstract":"<div><div>The discrepancy between the actual contaminated data and the normality assumption poses a serious challenge to existing methods that rely on clean training data. For methods that consider contamination, the mainstream model-level methods with memory-augmented structures struggle with biased similarity measures and fail to utilize historical information, leading to inaccurate reconstruction of latent variables. Most training-level methods may confuse contaminated data with hard-to-learn normal data, affecting the model’s ability to learn normal patterns. Moreover, there is a lack of using adjustment loss to effectively constrain model-level methods to learn normal data while suppressing contaminated data, which limits the further improvement of anomaly detection performance. This paper proposes a <strong>D</strong>ual-Reconstruction Self-<strong>R</strong>ectification framework with <strong>Mo</strong>mentum <strong>Me</strong>mory-augmented network based on Transformer (<strong>DRMoMe</strong>) for multivariate time series anomaly detection. At the model level, a momentum memory module based on Transformer is proposed, which employs the momentum-updated framework to align the representation space and designs the multihead-attention mechanism with the similarity-based update strategy to ensure the accuracy and diversity of the memory vectors. At the training level, this paper designs a self-rectification framework, which uses the difference between dual-reconstruction paths as the loss adjustment weights to adjust the model’s learning dynamically. Additionally, the method uses the characteristic of the memory module to amplify the weight difference between the contaminated and normal data, effectively integrating the model-level and training-level approach to help the model focus on learning the normal pattern. The DRMoMe outperforms 21 state-of-the-art baselines in experiments conducted on five benchmark datasets from different domains.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113558"},"PeriodicalIF":7.2,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654166","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}
Ahmad M. Alshamrani , Edmundas Kazimieras Zavadskas , Pratibha Rani , Jurgita Antucheviciene , Adel Fahad Alrasheedi
{"title":"Evaluation and prioritization of software packages for remote education assistance using picture fuzzy comprehensive distance-based ranking approach","authors":"Ahmad M. Alshamrani , Edmundas Kazimieras Zavadskas , Pratibha Rani , Jurgita Antucheviciene , Adel Fahad Alrasheedi","doi":"10.1016/j.asoc.2025.113606","DOIUrl":"10.1016/j.asoc.2025.113606","url":null,"abstract":"<div><div>Growing competition for online education has motivated the need for software packages assessment. Selecting the most suitable software package depends on several criteria, therefore, the decision-making approaches can be more appropriate to deal with such types of problems. To this aim, this work introduces a picture fuzzy information-based ranking approach for evaluating and prioritizing the software packages by means of several criteria. This approach firstly derives the weights of invited decision-making experts using the picture fuzzy distance measure-based procedure. To this aim, novel distance measure is proposed for describing the difference between picture fuzzy sets with its usefulness in comparison with the prior developed distance measures. To aggregate the opinions of decision-making experts about the performance of each software with respect to considered criteria, the picture fuzzy weighted averaging operator is utilized and created the aggregated decision matrix. Next, the criteria weights are calculated with the amalgamation of objective and subjective weights through picture fuzzy standard deviation model and picture fuzzy ranking comparison model, respectively. Finally, a picture fuzzy extension of comprehensive distance-based ranking model is presented to solve the multi-criteria software packages evaluation problem, which validates its rationality and feasibility. The acquired results prove that the software package “Google Workspace for Education Plus” is the most suitable choice due to its lowest comprehensive degree among the others. The stability and robustness of the outcomes are further verified through sensitivity and comparative analyses.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113606"},"PeriodicalIF":7.2,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671096","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}