Applied Soft Computing最新文献

{"title":"Pythagorean cubic fuzzy multiple attributes group decision method for sustainable supply chain management","authors":"Fei Wang","doi":"10.1016/j.asoc.2025.112802","DOIUrl":"10.1016/j.asoc.2025.112802","url":null,"abstract":"<div><div>A Pythagorean cubic fuzzy set (PCFS) is composed of Pythagorean fuzzy values and interval details. Unlike interval Pythagorean fuzzy sets, PCFS contains more data and can be valuable in complex multi-attribute group decision making (MAGDM). However, as a novel fuzzy set, certain essential principles of PCFS, such as the scoring function's implausibility and the absence of operations, require improvement. To address these concerns, we have refined the PCFS scoring function and introduced a new PCFS operation. Additionally, we have developed a PCFS reliability measure to account for uncertain expert opinions and attribute weights in MAGDM. Furthermore, overcoming the challenge of collecting PCFS evaluation data presents an obstacle. In the context of content distribution, the Heronian-mean (HM) operator tackles attribute association. While most existing Pythagorean-cubic fuzzy aggregation operators have an algebraic nature, we leverage the HM operator to establish a variety of Pythagorean cubic fuzzy aggregation operators. These operators showcase properties such as equivalence, monotonicity, boundedness, and commutative invariance. Finally, grounded in the Pythagorean cubic fuzzy HM aggregation operator, we introduce a MAGDM approach for sustainable supply chain management (SSCM). We conduct a practicality and superiority comparison with the existing Pythagorean cubic fuzzy aggregation operator. The primary contribution of this article is to enrich the research on aggregation operators of PCFS and expand their social applications in the realm of SSCM.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"172 ","pages":"Article 112802"},"PeriodicalIF":7.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387132","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":"Application of personalized individual semantics in MAGDM with preference information","authors":"Hongbin Liu ,&nbsp;Zhuoyu Xu","doi":"10.1016/j.asoc.2025.112822","DOIUrl":"10.1016/j.asoc.2025.112822","url":null,"abstract":"<div><div>Subjective and objective evaluations are often utilized simultaneously in Multi-Attribute Group Decision Making (MAGDM) problems. Decision makers’ different understanding of linguistic terms, i.e., personalized individual semantics, may influence decision making results. In this study, we propose a novel MAGDM model to deal with these problems based on two types of preference information: an objective multi-attribute linguistic decision matrix and subjective alternative rankings. In the first stage, we introduce a consistency-driven model to obtain the personalized interval numerical scales associated with each linguistic term and attribute weights. In the second stage, we introduce dynamic personalized individual semantics to maximize consensus by minimizing the discrepancy between individual opinions and collective opinion. The optimal alternative is then determined based on overall scores of the alternatives. We finally apply the proposed model in the selection of new energy vehicles, and conduct simulation experiments and comparative analysis. The results show that considering personalized individual semantics and weights of the decision makers brings much benefit for consensus reaching process in group decision making. A high group consensus level can be reached in this model, and the computational complexity of this model is acceptable.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112822"},"PeriodicalIF":7.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378388","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":"Deep neural network-based intelligent health monitoring system for oil and gas pipelines","authors":"Mohamed Almahakeri ,&nbsp;Ahmad Jobran Al-Mahasneh ,&nbsp;Mohammed Abu Mallouh ,&nbsp;Basel Jouda","doi":"10.1016/j.asoc.2025.112827","DOIUrl":"10.1016/j.asoc.2025.112827","url":null,"abstract":"<div><div>Oil and gas pipelines are critical infrastructures that require continuous monitoring to ensure public safety and prevent economic losses. This paper addresses the challenges associated with pipeline failures by proposing a Deep Neural Network (DNN)-based Structural Health Monitoring (SHM) system for real-time monitoring of oil and gas pipelines. The system utilizes installed transducers and ultrasound guided waves to collect data about the structural health without the need for pipeline shutdown. The DNN-based SHM system predicts three crucial crack parameters: crack location, width, and depth. The performance of the proposed system is compared with five commonly used Machine Learning (ML) approaches. The results demonstrate that the DNN-based SHM system outperforms the other ML-based systems, achieving 18 % less prediction error than the most accurate of the other ML approaches. Moreover, the average prediction accuracy with the proposed DNN approach for crack location, width, and depth were 97 %, 93 % and 96 %, respectively. The findings highlight the potential of DNNs for accurate and efficient pipeline health monitoring, contributing to improved decision-making and safe pipeline operations.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112827"},"PeriodicalIF":7.2,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378386","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":"Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world","authors":"Chengyin Hu ,&nbsp;Weiwen Shi ,&nbsp;Wen Yao ,&nbsp;Tingsong Jiang ,&nbsp;Ling Tian ,&nbsp;Wen Li","doi":"10.1016/j.asoc.2025.112818","DOIUrl":"10.1016/j.asoc.2025.112818","url":null,"abstract":"<div><div>Visible-infrared cross-modal object detectors, leveraging both visible and infrared imaging technologies, play a pivotal role in vision-based systems. However, they necessitate thorough security scrutiny due to the risks posed by physical adversarial attacks, which employ tailored physical inputs to deceive vision-based models, posing significant peril to the integrity of vision-based systems. While previous research has predominantly focused on the security of visible and infrared detectors individually, real-world scenarios often necessitate the use of visible-infrared cross-modal detectors with heightened reliability. However, there is a notable dearth of comprehensive security evaluations for these hybrid systems. Despite some efforts to explore attacks on cross-modal detectors, developing a robust and practical strategy remains a significant challenge. This study introduces TOUAP, a novel two-stage adversarial patch technique designed specifically for real-world, black-box visible-infrared detectors. TOUAP initiates with octagonal-shape optimization to create infrared adversarial samples, leveraging this to disrupt infrared detection. Subsequently, it generates visible patches resembling color QR codes while preserving the geometry of the infrared patch for precise cropping, thereby undermining the visible detector. The extensive experimental validation in both digital and physical domains emphatically underscores the superior effectiveness and robustness of TOUAP, outperforming conventional baseline methods convincingly.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112818"},"PeriodicalIF":7.2,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348764","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":"Small aerial object detection through GAN-integrated feature pyramid networks","authors":"Usman Ahmad ,&nbsp;Jing Liang ,&nbsp;Tianlei Ma ,&nbsp;Kunjie Yu ,&nbsp;Faisal Mehmood ,&nbsp;Farhad Banoori","doi":"10.1016/j.asoc.2025.112834","DOIUrl":"10.1016/j.asoc.2025.112834","url":null,"abstract":"<div><div>Small Aerial Object Detection (SAOD) is a pivotal research domain in computer vision, with significant applications in environmental regulation, intelligent surveillance, and autonomous vehicles. However, SAOD remains challenging due to low resolution, background noise, and variable object sizes. In this study, we propose a novel Feature Pyramid Generative Adversarial Network (FPGAN) to address these issues. FPGAN enhances feature extraction across multiple scales, improving precision, recall, and accuracy in detecting small aerial objects of diverse sizes. Furthermore, we integrate an Edge Sharpening Network (ESN) using the U-Net architecture to mitigate noise and distortions generated during adversarial learning, resulting in the FPGAN+ESN model. Extensive experiments on three SAOD datasets, namely DOTA, COWC, and OGST, demonstrate that our model outperforms state-of-the-art methods, showcasing remarkable improvements in detection accuracy. The proposed FPGAN+ESN approach enhances the resolution of small aerial objects and improves edge quality, leading to more robust and efficient SAOD. Our findings underscore the potential of the FPGAN+ESN model for tackling the complexities associated with SAOD tasks.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112834"},"PeriodicalIF":7.2,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394751","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":"Enhancing prediction accuracy for high-dimensional small-sample-size microarray data cancer by combining chebyshev interpolation with new dual-net GAN","authors":"Liang-Sian Lin ,&nbsp;Yao-San Lin ,&nbsp;Der-Chiang Li ,&nbsp;Susan C. Hu ,&nbsp;Chih-I Huang","doi":"10.1016/j.asoc.2025.112826","DOIUrl":"10.1016/j.asoc.2025.112826","url":null,"abstract":"<div><div>Cancer is a complex and multi-cellular interaction disease in the human immune system with compelling morbidity and mortality in patients. To improve cancer patient survival rate, medical professionals and clinicians commonly formulate prudent and effective cancer treatment plans by using the assistance of human microarray data. Studies reveal that gene expression profiling from microarray data has been frequently used to identify gene mutations in human cancers. But practically, this is an expensive and time-consuming technique when working with high-dimensional microarray cancer datasets. As a result, more recently, deep learning techniques in the field of artificial intelligence (AI) have become a widely effective and worthy technique to implement for cancer diagnosis and prognosis predictions in clinical applications. However, under high-dimensional but small-sample-size (HDSSS), statistically less sufficient patient sample cases, classic deep learning and machine learning models often fail to provide reliable prediction results in cancer diagnosis and prognosis. To tackle these tasks, this study focus effort on developing an AI approach termed Cheby-Dual-GAN virtual sample generation (VSG) technique, which combines Chebyshev interpolation with a novel dual-net GAN (Generative Adversarial Networks) generator, to generate high-dimensional artificial samples resembling the original data. We fed Chebyshev points and their membership function (MF) into the dual-net generator to generate highly representative virtual samples while avoiding mode collapse in GAN. Six microarray cancer datasets were used to demonstrate efficacy of the proposed method. Based on these microarray cancer datasets, we compared the Cheby-Dual-GAN method with two state-of-the-art VSG techniques. With different small training sample sizes, the proposed method can achieve significantly superior prediction accuracy in two predictive models compared to the two VSG techniques in terms of Accuracy (ACC), F-measure, mean absolute error (MAE), and mean absolute percentage error (MAPE) indicators. As a theoretical validation, the paired t-test is employed to determine whether the suggested method has statistically significant differences from the other methods. The results of paired t-test demonstrate that the proposed Cheby-Dual-GAN method enjoys significant improvement effects in terms of ACC, F-measure, MAE, MAPE indicators. According to our experimental results, the proposed method successfully outperforms other VSG methods for HDSSS microarray cancer datasets.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112826"},"PeriodicalIF":7.2,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372908","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":"Integrated generation adversarial and semi-supervised network for Corpus Callosum and Cavum Septum Pellucidum Complex segmentation in fetal brain ultrasound via progressive training","authors":"Qifeng Wang ,&nbsp;Dan Zhao ,&nbsp;Hao Ma ,&nbsp;Xiangjun Yang ,&nbsp;Bin Liu","doi":"10.1016/j.asoc.2025.112767","DOIUrl":"10.1016/j.asoc.2025.112767","url":null,"abstract":"<div><div>In prenatal diagnostics, measuring the Corpus Callosum (CC) is crucial for assessing fetal brain development, with the Cavum Septum Pellucidum (CSP) also playing a key role due to its close association with the CC. Our study addresses the challenge of distinguishing these interconnected structures by segmenting the Corpus Callosum and Cavum Septum Pellucidum Complex (CCSP) as a unified entity in mid-sagittal fetal brain ultrasound images. This approach ensures accurate biological measurements that reflect their combined significance in brain development. To improve segmentation accuracy and reduce errors inherent in manual methods, we propose the Fetal Brian Ultrasound Semi-supervised Generative Adversarial Segmentation Network (FB-SGASNet) tailored for few-shot datasets. FB-SGASNet enhances clinical applicability through: (i) an integrated framework combining the Target Segmentation Module (TSM) and Data Expansion Module (DEM) with a semi-supervised learning strategy; (ii) a progressive training strategy promoting parameter sharing between TSM and DEM; (iii) the introduction of Feature Fusion Attention Module (FFAM) and Dual-Stream Feature Attention Module (DSFAM) to improve key anatomical feature recognition; and (iv) the use of a specialized Fetal Brain CCSP dataset (FB-CCSP) with 200 annotated images for network training and validation. FB-SGASNet provides a practical solution for CCSP segmentation in few-shot datasets, enhancing the efficiency and accuracy of fetal brain ultrasound analysis, reducing reliance on specialized expertise, and enabling more timely prenatal evaluations.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112767"},"PeriodicalIF":7.2,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372801","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":"Space-distributed machine learning based on climate lag effect: Dynamic prediction of tuberculosis","authors":"Shuo Wang ,&nbsp;Ziheng Li ,&nbsp;Tianzuo Zhang ,&nbsp;Mengqing Li ,&nbsp;Liyao Wang ,&nbsp;Jinglan Hong","doi":"10.1016/j.asoc.2025.112840","DOIUrl":"10.1016/j.asoc.2025.112840","url":null,"abstract":"<div><div>An in-depth grasp of the complex relationship between climate and disease is crucial for fostering the development of public health security. However, certain limitations, such as overlooking spatial heterogeneity and lag effects, persist when revealing this complex relationship. With tuberculosis (TB) as a case, a pioneering space-distributed machine learning (SDML) framework is introduced to enhance TB prediction accuracy and unveil its complex relationship with climatic factors. Results demonstrate the nonlinear, intricate relationship between TB and climate variables, emphasizing the significant lag effect of climate variables on TB. Model comparisons demonstrate that SDML has a significant improvement in prediction, particularly in lag effect identification. The determination coefficient average of SDML (0.786) surpasses that of traditional machine learning (ML, 0.719). Utilizing an interpretable ML method to identify the impact of climate variables on TB, this study reveals evident spatial heterogeneity in the response of TB to climate. The spatial heterogeneity of the effects of extreme climate on TB suggests regionalized prevention and control strategies for diverse regions. This study provides a novel perspective on comprehending the intricate relationship between TB and climate, showcasing the feasibility of artificial intelligence-assisted scientific discovery.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112840"},"PeriodicalIF":7.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143316946","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":"Deep non-local point cloud denoising network","authors":"Huankun Sheng ,&nbsp;Ying Li","doi":"10.1016/j.asoc.2025.112835","DOIUrl":"10.1016/j.asoc.2025.112835","url":null,"abstract":"<div><div>As an efficient representation of objects, the 3D point cloud is increasingly prevalent in various application fields. However, raw point clouds captured from scanning devices often contain noise, which significantly impairs the performance of downstream tasks such as surface reconstruction and object recognition. Consequently, point cloud denoising has emerged as a crucial task in geometry modeling and processing. Although deep learning has proven effective in this domain, existing learning-based methods predominantly focus on local information and tend to neglect the non-local features inherent in 3D point clouds. In this paper, we propose a deep non-local point cloud denoising network, DnPCD-Net, to address this issue. DnPCD-Net consists of three key components: 1) a feature extraction module that extracts local features for each point; 2) a densely-connected Transformer module that captures long-range dependencies across the input point set and feature channels; and 3) a feature fusion module that adaptively combines local and non-local features. Extensive experiments on both synthetic and real-scanned datasets demonstrate that DnPCD-Net achieves superior denoising performance, with statistically significant improvements in Chamfer Distance and Earth Mover’s Distance, as well as better visual quality, confirming its effectiveness and robustness in practical applications.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"171 ","pages":"Article 112835"},"PeriodicalIF":7.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143316944","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 fuzzy Kano model proposal for sustainable product design: Mobile application feature analysis","authors":"Necip Fazıl Karakurt ,&nbsp;Selcuk Cebi","doi":"10.1016/j.asoc.2025.112824","DOIUrl":"10.1016/j.asoc.2025.112824","url":null,"abstract":"<div><div>Companies aim to maximize profits by effectively designing mobile applications to promote their services in a competitive market. However, identifying the design features that significantly impact mobile applications is challenging due to their subjective nature. Traditional Kano approaches face limitations, such as information loss caused by considering only the most frequent values. To address these limitations, this study proposes a novel fuzzy Kano approach to better manage the subjectivity in human judgments and the uncertainty in user preferences. This approach uncovers hidden preference levels, accounts for uncertainties, resolves dual classification issues, compares membership degrees, and emphasizes subtle details that may otherwise be overlooked. The fuzzy Kano approach was applied to survey data from 100 participants, covering 33 mobile application features. By classifying these features, the fuzzy Kano model examined their influence on user satisfaction and quality perception. The results demonstrated the feasibility and effectiveness of the proposed method, identifying key features—such as Product Details, Order Management and Returns, and Product Opinions and Reviews—that, if absent, could lead to customer dissatisfaction. Additionally, the findings revealed significant differences between the fuzzy and traditional Kano models and highlighted variations in mobile application characteristics across different demographic groups, providing valuable insights for mobile application design.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"172 ","pages":"Article 112824"},"PeriodicalIF":7.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437256","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}