Applied Soft Computing最新文献

{"title":"Feature selection via Class-specific Approximate Markov Blanket and Rough Set-based Mapping","authors":"Jie Zhao ,&nbsp;Junchao Chen ,&nbsp;JiaXin Wu ,&nbsp;Ling Tan ,&nbsp;Pei Liang ,&nbsp;Eric W.K. See-To","doi":"10.1016/j.asoc.2025.113154","DOIUrl":"10.1016/j.asoc.2025.113154","url":null,"abstract":"<div><div>Markov Blanket (MB) is a currently popular approach to feature selection that helps to effectively select correlated features and eliminate redundant features. However, existing MB-based approaches involve complex computations and extensive search. Therefore, we propose a novel concept, Class-specific Approximate Markov Blanket (CSAMB), to solve the above two problems from a class-specific perspective. This concept involves the transformation of decision attributes and features in the specific class using a proposed Rough Set-based Mapping (RSM) method, facilitating the selection results with high classification correlation and low inter-redundancy. The RSM not only preserves the positive, negative and boundary regions of a specific class with respect to a given feature, but also accurately quantifies the relationship between features within that class. Notably, we explore the approximate upper and lower bounds of grouping of correlation features via CSAMB. We then design a CSAMB-based algorithm, and extend it to two variants: CSAMB-min and CSAMB-max using the approximate upper and lower bounds, which demonstrates the performance range of our algorithm. Experiments shows that our algorithms outperform state-of-the-art algorithms regarding accuracy and efficiency, especially for large-scale and high-dimensional datasets.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113154"},"PeriodicalIF":7.2,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874096","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":"Block-Level Index Mixing and Classification Enhancement Attention for occluded person re-identification","authors":"Lun Zhang,&nbsp;Shuli Cheng ,&nbsp;Liejun Wang","doi":"10.1016/j.asoc.2025.113127","DOIUrl":"10.1016/j.asoc.2025.113127","url":null,"abstract":"<div><div>In the field of occluded person re-identification (Re-ID), a major challenge lies in effectively recognizing partially occluded pedestrian images. Existing methods leveraging occlusion simulation and local feature segmentation often struggle with real-world complexity and inadvertently introduce noise from non-target regions. To address these limitations, this paper proposes the Block-level Index Mixing and Classification Enhancement Attention (BMCE) framework, which integrates data augmentation and classification enhancement strategies. For data augmentation, the Block-level Index Mixing (BLIM) module partitions images with different labels into several blocks. By sharing an index list and controlling the proportion of sampled blocks, the module simulates diverse occluded images. Additionally, adaptive weight mixing of labels enhances the discriminative ability of the simulated images. For classification enhancement, the Classification Enhancement Attention (CEA) module leverages multi-granularity features to enhance classification weights and mitigates the influence of non-target regions through an attention mechanism, improving performance in occlusion scenarios. Experimental results demonstrate that BMCE achieves competitive performance on occlusion, partial, and holistic Re-ID datasets. Notably, it attains 74.1% Rank-1 accuracy and 64.7% mAP on the Occluded-Duke dataset. Source code is available at <span><span>https://github.com/aohan-del/BMCE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113127"},"PeriodicalIF":7.2,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868641","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 variable window multi-interval rescheduling optimization algorithm for dynamic flexible job shop problem","authors":"Zeyin Guo ,&nbsp;Lixin Wei ,&nbsp;Xin Li ,&nbsp;Shengxiang Yang ,&nbsp;Jinlu Zhang","doi":"10.1016/j.asoc.2025.113157","DOIUrl":"10.1016/j.asoc.2025.113157","url":null,"abstract":"<div><div>The dynamic flexible workshop scheduling problem (DFJSP) requires the generation of new scheduling plans after being subjected to dynamic disturbances. Due to the reconfigurability of chromosomal gene, scheduling schemes have a large search space, which poses challenges for solving scheduling schemes. Therefore, a variable window multi-interval optimization (VWMI) rescheduling algorithm is proposed to solve the DFJSP. A nonlinear adaptive crossover probability and mutation probability function is proposed to address the issue of combinatorial optimization easily getting stuck in local optima. Based on the mapping relationship between individual space and objective space, a spatial joint selection method is proposed to select diverse individuals. Compared with other algorithms in dynamic workshop test cases, the rescheduling strategy achieved 7 optimal performance values in 15 test cases, with a maximum time efficiency improvement of 30.2%. In addition, the VWMI achieved 11 good performances in test cases, outperforming other optimization methods.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113157"},"PeriodicalIF":7.2,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864863","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":"Tomato Leaf Disease recognition based on Fine-Grained Interpretable Knowledge Distillation model for smart agricultural","authors":"Daxiang Li ,&nbsp;Cuiyun Hua ,&nbsp;Ying Liu","doi":"10.1016/j.asoc.2025.113195","DOIUrl":"10.1016/j.asoc.2025.113195","url":null,"abstract":"<div><div>In large-scale smart agricultural plantations, in order to utilize computer vision technology for automatic recognition of Tomato Leaf Diseases (TLD) and improve the intelligence level of Smart Agricultural Internet of Things (SAIoT), this paper designs a novel Fine-Grained Interpretable Knowledge Distillation (FGIKD) model. Firstly, based on Deformable Dilated Convolution (DDC) and Simplified Self-Attention (SSA) mechanism, a new Deformable Multi-Scale Perception (DMSP) spatial attention module is designed to integrate the irregular local perception ability of DDC with the global modeling ability of self-attention, thereby enhancing the low-level visual feature extraction capability of the model. Secondly, based on Cross-Layer Feature Fusion (CLFF) and Graph Self-Supervised Learning (GSSL), a new Fine-Grained (FG) feature extraction module is designed to alleviate the problem of \"high intra-class variance and low inter-class variance\" in TLD images. Thirdly, DMSP and FG distillation functions are designed to transfer the knowledges from teacher network to student network, enabling it to achieve performance close to the teacher network with a small number of parameters. Finally, combining class activation maps with regional confidence weighting technique, a new CNN model post-hoc explanation scheme is designed in the form of \"saliency map\". In the comparison experiments of standard dataset validation and real-world application testing, the knowledge-distilled student network achieves 98.13 % and 97.56 % TLD recognition accuracies, while the number of model parameters is only 2.921MB, which can meet the requirements of SAIoT terminal model deployment.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113195"},"PeriodicalIF":7.2,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874094","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":"Optimizing performance evaluation of green supply chain management practices with linguistic q-rung orthopair fuzzy information","authors":"Shahid Hussain Gurmani ,&nbsp;Harish Garg ,&nbsp;Huayou Chen ,&nbsp;Zhifu Tao ,&nbsp;Zhao Zhang","doi":"10.1016/j.asoc.2025.113194","DOIUrl":"10.1016/j.asoc.2025.113194","url":null,"abstract":"<div><div>Green supply chain management (GSCM) and environmentally conscious manufacturing have emerged as critical strategies for companies to enhance operational efficiency, reduce environmental impact, and improve profitability and market competitiveness. To address the inherent fuzziness and uncertainty in selecting optimal GSCM practices, this paper proposes a novel decision framework by integrating Criteria Importance Through Intercriteria Correlation (CRITIC) and Evaluation based on Distance from Average Solution (EDAS) methods under the linguistic q-rung orthopair fuzzy (Lq-ROF) environment. To support this integration, we define Hamacher operations for Lq-ROF numbers and develop two Hamacher aggregation operators. Then, the Lq-ROF-CRITIC-EDAS approach is designed to solve multi-criteria group decision-making problems by using these proposed aggregation operators. Moreover, the relative weights of the evaluation criteria for GSCM practices were determined using the Lq-ROF-CRITIC model. A real-world decision problem of evaluating the performance of GSCM practices is solved to verify our suggested approach. In addition, the sensitivity analysis is also carried out by changing the parameter’s value to check the consistency of the ranking order. Finally, the proposed model is compared with existing approaches to demonstrate its strength. The sensitivity and comparative analyses reveal that the suggested technique offers greater feasibility, reliability, and precision in ranking alternatives, outperforming traditional methods in handling uncertainty and aligning with real-world GSCM requirements.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113194"},"PeriodicalIF":7.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855477","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 top-weighted classification method with expert ability characterization for failure mode and effect analysis","authors":"Sihai Zhao ,&nbsp;Siqi Wu ,&nbsp;Haiming Liang ,&nbsp;Hengjie Zhang","doi":"10.1016/j.asoc.2025.113168","DOIUrl":"10.1016/j.asoc.2025.113168","url":null,"abstract":"<div><div>Failure mode and effect analysis (FMEA) is a useful tool to assess the potential risks of a system and provide necessary correction suggestions. This study proposes a top-weighted classification method with expert ability characterization for FMEA to deal with two crucial issues: few studies have attempted to characterize the ability of FMEA experts to provide accurate assessments in the risk assessment process, and the realistic feature that different risk categories have different importance was not considered. First, we develop a synergy theory-based weight iterative algorithm, by which the ability of experts is characterized and specific weight information is automatically generated at the element level of their assessment matrices. Then, we suggest a novel top-weighted distance measure that considers the importance of different risk categories, based on which the consensus-based top-weighted classification method (CTWCM) is proposed. After that, a simulation comparison experiment is designed to examine the performance of the CTWCM against the ABC analysis and ELECTRE-TRI methods. The numerical results show that the CTWCM outperforms the other two methods on all three key classification indices. In addition, a theoretical comparison is further presented to demonstrate our novelty and significance. Finally, the proposed method is illustrated through a SARS-CoV-2 management case.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113168"},"PeriodicalIF":7.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864997","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":"Graphics processing unit-enabled path planning based on global evolutionary dynamic programming and local genetic algorithm optimization","authors":"Junlin Ou,&nbsp;Ge Song,&nbsp;Yi Wang","doi":"10.1016/j.asoc.2025.113167","DOIUrl":"10.1016/j.asoc.2025.113167","url":null,"abstract":"<div><div>This paper presents a novel path planning method for real-time robotic path planning in a dynamic environment involving moving obstacles. It combines on a holistic platform a global approach to rapidly generate initial paths of prominent diversity and a heuristic approach to enable local path refinement for enhanced computational efficiency, exploration, and robustness. The global approach innovates a formulation that treats a path planning problem with a visibility graph as a Markov decision process and decomposes the process into many subproblems. A new evolutionary dynamic programming approach (EDP) is proposed to solve these subproblems in an iterative manner using graphics processing unit (GPU) computing to allow backpropagation of state values from goal to start points. The EDP generates multiple feasible initial paths with salient state values, each initializing an independent genetic algorithm (GA) optimization on waypoints only near the mobile robot, and all GAs are run in parallel on GPU, further improving exploration and convergence speed. The strategy to fully utilize CPU/GPU resources for various components in the pipeline is also established. The proposed algorithms are then implemented on an edge computing device (Jetson AGX Xavier) onboard a mobile robot (TurtleBot 3 Waffle Pi). Optimal paths can be continuously generated at the rate of 0.1 seconds/path, enabling successful obstacle avoidance and robot navigation through dynamic environments and, hence, verifying the real-time capabilities and accuracy of the present method. Compared to other benchmarks, the present method greatly enhances path planning robustness, computing speed, and path quality.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113167"},"PeriodicalIF":7.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854811","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":"Dynamically allocated interval-based generative linguistic steganography with roulette wheel","authors":"Yihao Wang ,&nbsp;Ruiqi Song,&nbsp;Lingxiao Li ,&nbsp;Ru Zhang,&nbsp;Jianyi Liu","doi":"10.1016/j.asoc.2025.113101","DOIUrl":"10.1016/j.asoc.2025.113101","url":null,"abstract":"<div><div>Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool, allocating the one coding to all tokens, which results in identical selection likelihoods. This approach leads to the selection of low-CP tokens, degrading the quality of stegos and making them more detectable. This paper proposes a scheme based on the interval allocated, called DAIRstega. DAIRstega first uses a portion of the read secret to build the roulette area. Then, this scheme uses the idea of the roulette wheel and takes the CPs of tokens as the main basis for allocating the roulette area (i.e., the interval length). Thus, tokens with larger CPs are allocated more area. The secret will have an increased likelihood of selecting a token with a higher CP. During allocation, we design some allocation functions and three constraints to optimize the process. Additionally, DAIRstega supports prompt-based controllable generation of stegos. Rich experiments show that the proposed embedding way and DAIRstega perform better than the existing ways and baselines, which shows strong perceptual, statistical, and semantic concealment, as well as anti-steganalysis ability. It can also generate high-quality longer stegos, addressing the deficiencies in this task. DAIRstega is confirmed to have potential as a secure watermarking, offering insights for its development. Our codes and data are available at: <span><span>https://github.com/WangYH-BUPT/DAIRstega</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113101"},"PeriodicalIF":7.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864862","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":"Development and optimization of geopolymer concrete with compressive strength prediction using particle swarm-optimized extreme gradient boosting","authors":"Shimol Philip,&nbsp;Nidhi Marakkath","doi":"10.1016/j.asoc.2025.113149","DOIUrl":"10.1016/j.asoc.2025.113149","url":null,"abstract":"<div><div>This study presents an experimental investigation of the workability and strength behavior of eco-friendly binary geopolymer concrete (GPC) containing ground granulated blast furnace slag (GGBS) and sugarcane bagasse ash (SBA). Initially, this study optimizes binder content (GGBS) in GGBS-based GPC by utilizing the Taguchi method by examining various variables, including alkaline activator-to-binder ratio (AAS/B), sodium hydroxide molarity (M), sodium silicate-to-sodium hydroxide ratio (SS/SH). After optimizing the binder (GGBS) content, SBA is incorporated to formulate a binary GPC by partially replacing GGBS with SBA at substitution levels of 0 %, 5 %, 10 %, 15 %, and 20 %. The effects of varying the AAS/B, M, and SS/SH ratios at different SBA additions on the workability and compressive strength of binary GPC were analyzed. Split and flexural strength were tested on optimized binary GPC samples with varying SBA replacement levels. Moreover, machine learning prediction models using the XGBoost and hyperparameter-optimized XGBoost using particle swarm optimization (PSO) were developed to predict the 28th day compressive strength of binary GPC. Finally, the cost efficiency of binary GPC at different SBA replacement levels was determined. The experimental findings demonstrate that an AAS/B ratio of 0.6, an SS/SH ratio of 2.5, and a sodium hydroxide molarity of 12 M provide an optimal balance between workability and compressive strength. Furthermore, the binary GPC incorporating GGBS and SBA demonstrated compressive strengths ranging from 57 to 79 MPa after curing for 28 days at ambient temperature. This study suggests that 15 % SBA was the optimal replacement level in GGBS-based GPC without significantly compromising its mechanical properties. The prediction outcomes demonstrate that the PSO-XGBoost model is highly effective in predicting binary GPC compressive strength, with an R² value of 0.97. According to the SHAP (Shapley Additive exPlanations) study, the compressive strength of binary GPC was substantially impacted by the quantities of GGBS and SBA.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113149"},"PeriodicalIF":7.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868640","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":"Meta-ensemble learning with adaptive sampling for imbalanced medical Raman spectroscopy data","authors":"Yishan Guo ,&nbsp;Chenjie Chang ,&nbsp;Cheng Chen ,&nbsp;Jiahao Li ,&nbsp;Jun Yu ,&nbsp;Xue Wu ,&nbsp;Yuxuan Guo ,&nbsp;Shunzhe Mao ,&nbsp;Wei Bi ,&nbsp;Chen Chen ,&nbsp;Xiaoyi Lv","doi":"10.1016/j.asoc.2025.113142","DOIUrl":"10.1016/j.asoc.2025.113142","url":null,"abstract":"<div><div>Raman spectroscopy combined with artificial intelligence algorithms for disease diagnosis has been widely used in the medical field with great potential. However, since the low prevalence of certain diseases makes it difficult to obtain disease samples, the problem of medical Raman spectroscopy data imbalance occurs in disease diagnosis, where the model tends to predict samples in most classes and has a lower diagnostic accuracy for the disease class, which may delay the patient’s treatment or lead to an increased risk of misdiagnosis. In this study, we propose the MAEL model, which utilizes meta-learning ideas to automatically learn a sampling strategy from the data and adaptively resample the query set iteratively, to tackle the problem of unbalance in medical Raman spectroscopy data. We apply the model for the first time to unbalanced medical Raman spectral data to improve the unbalanced data distribution of the spectral data, and use integration learning to integrate all sampling results during model training to improve model performance. We used three metrics, AUC-PRC, G-mean, and F1-score values, to evaluate the performance of the model and compared it with six traditional data balancing methods. The experimental results show that the MAEL model achieves significant improvements on various medical Raman spectroscopy datasets, with maximum improvements of 0.364, 0.563, and 0.587 for the AUC-PRC, G-mean, and F1-score values, respectively. This study provides an effective way to solve the data imbalance problem in medical spectroscopy and has potential applications.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113142"},"PeriodicalIF":7.2,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864998","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}