Applied Soft Computing最新文献_第3页

Development of fuzzy rule-based models in the presence of the big data environment 大数据环境下基于模糊规则的模型开发

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-04 DOI: 10.1016/j.asoc.2025.113869

Yinghua Shen , Dan Zhao , Yan Li , Xingchen Hu , Yuan Chen , Bingsheng Liu

{"title":"Development of fuzzy rule-based models in the presence of the big data environment","authors":"Yinghua Shen , Dan Zhao , Yan Li , Xingchen Hu , Yuan Chen , Bingsheng Liu","doi":"10.1016/j.asoc.2025.113869","DOIUrl":"10.1016/j.asoc.2025.113869","url":null,"abstract":"<div><div>In this study, we propose a series of methods to build fuzzy rule-based models (FRBMs) in the presence of the big data environment such that the formed predictive models are more accurate, efficient, and robust. We follow two major steps to realize this target. In the first step, we build numeric FRBMs with the big data set such that the formed predictive models are more accurate and efficient. Specifically, based on the divide-and-conquer strategy, the big data set is divided into subsets through either the hyperplane division-based method or the <em>K</em>-Means clustering-based method; then either a global-based strategy or a local-based strategy is used to build numeric FRBMs. As a result, four Options are generated to develop numeric FRBMs. In the second step, we build the granular FRBMs based on the four Options developing the numeric FRBMs. Specifically, given a certain Option, based on the Principle of Justifiable Granularity (PJG), we granulate both condition parts and conclusion parts of the rules, forming the granular FRBMs; then the predictive models are further evaluated based on the PJG and optimized based on the Particle Swarm Optimization (PSO) algorithm to enhance the robustness. Finally, experimental studies on both synthetic datasets and publicly available datasets are conducted to prove the effectiveness of the proposed methods.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113869"},"PeriodicalIF":6.6,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating regional green industry competitiveness in China: A CoSOGR-MABAC-sort framework 中国区域绿色产业竞争力评价：基于cosogr - mabac的框架

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-03 DOI: 10.1016/j.asoc.2025.113831

Jiafu Su , Baojian Xu , Lvcheng Li , Yijun Chen , Hongyu Liu , Na Zhang

{"title":"Evaluating regional green industry competitiveness in China: A CoSOGR-MABAC-sort framework","authors":"Jiafu Su , Baojian Xu , Lvcheng Li , Yijun Chen , Hongyu Liu , Na Zhang","doi":"10.1016/j.asoc.2025.113831","DOIUrl":"10.1016/j.asoc.2025.113831","url":null,"abstract":"<div><div>With the rise of concepts such as the green economy and sustainable development, the development of green industry has become increasingly urgent. Regional green industry competitiveness, as a key indicator reflecting the development status and competitive advantages of regional green industry, has not yet received sufficient attention and research. To fill this research gap, this paper proposes an evaluation framework, CoSOGR-MABAC-Sort (Combined Subjective-Objective, Grey Relational analysis-Multi-Attributive Border Approximation area Comparison-Sort), to assess the green industry competitiveness in 31 regions of China. In the proposed framework, the MABAC-Sort method is a novel multi-criteria decision sorting method with six classification rules. Compared to other MCDS methods, this method does not require predefined profile boundaries and can provide more detailed classification results. Furthermore, we propose an optimal model<strong>,</strong> called CoSOGR, to determine the weights of each indicator. Finally, by collecting subjective and objective data, we use the proposed framework to assess the green industry competitiveness in the 31 provinces of China. The main findings are as follows: 1) The CoSOGR demonstrates the highest consistency (99.33 %) in regions ranking compared to existing weight methods (CRITIC, EWM, ROCOSD, and MEREC). 2) The CoSOGR addresses the weight determination issues that ROCOSD (a mixed-integer linear programming model) cannot resolve. 3) The CoSOGR-MABAC-Sort method exhibit strong robustness and stability. 4) The green industry competitiveness in each region shows a positive correlation with the sustainable development of that region.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113831"},"PeriodicalIF":6.6,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145003722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An interpretable dual-output multivariate wind speed interval prediction scheme using hyper-heuristic optimization algorithm and deep neural networks 基于超启发式优化算法和深度神经网络的可解释双输出多变量风速区间预测方案

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-03 DOI: 10.1016/j.asoc.2025.113829

Mengzheng Lv , Jianzhou Wang , Shuai Wang , Yang Zhao , Jialu Gao , Yuansheng Qian

{"title":"An interpretable dual-output multivariate wind speed interval prediction scheme using hyper-heuristic optimization algorithm and deep neural networks","authors":"Mengzheng Lv , Jianzhou Wang , Shuai Wang , Yang Zhao , Jialu Gao , Yuansheng Qian","doi":"10.1016/j.asoc.2025.113829","DOIUrl":"10.1016/j.asoc.2025.113829","url":null,"abstract":"<div><div>Uncertainty analysis of wind speed forecasting using the Lower Upper Bound Estimation (LUBE) represents an advanced interval prediction method that does not require assumptions about data distribution. Previous studies, however, have exclusively focused on univariate prediction models, neglecting the information from other variables, and have not fully exploited the prediction errors in their loss function during training. To address these issues, an interpretable dual-output multivariate wind speed interval prediction scheme (IMWSIPS) that utilizes a hyper-heuristic optimization algorithm and a deep neural network is proposed, along with a novel loss function for training. The system initially takes multiple inputs such as historical wind speed and other influencing factors including wind direction, density, temperature, and pressure into a deep neural network. The actual wind speeds are then scaled up and down by factors of 1 + θ<sub>1</sub> (0 <θ<sub>1</sub><1) and 1 + θ<sub>2</sub> (-1 <θ<sub>2</sub><0), respectively, to produce two outputs from the network. On this basis, an optimization problem to minimize interval width under a given coverage probability is formulated and solved using the developed hyper-heuristic algorithm, yielding optimal values for θ<sub>1</sub> and θ<sub>2</sub> and the prediction intervals for sub-models. Subsequently, the advantages of five deep neural network models are leveraged to construct an ensemble model, with weights optimized by the hyper-heuristic algorithm to derive the final prediction intervals. Ultimately, the system's interpretability is analyzed at both variable and sub-model levels. Experimental and discussion results demonstrate that the introduction of IMWSIPS not only signifies enhancements in forecasting performance but also implies improvements in wind energy utilization efficiency and reductions in operational costs for power systems.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"185 ","pages":"Article 113829"},"PeriodicalIF":6.6,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic-linguistic fusion for brain tumor classification: A cross-modal attention framework with clinical interpretability 动态语言融合用于脑肿瘤分类：具有临床可解释性的跨模态注意框架

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-03 DOI: 10.1016/j.asoc.2025.113839

Jiancong Fan , Fangyuan Chen , Yang Li , Jiehan Zhou

{"title":"Dynamic-linguistic fusion for brain tumor classification: A cross-modal attention framework with clinical interpretability","authors":"Jiancong Fan , Fangyuan Chen , Yang Li , Jiehan Zhou","doi":"10.1016/j.asoc.2025.113839","DOIUrl":"10.1016/j.asoc.2025.113839","url":null,"abstract":"<div><div>Accurate classification of brain tumors is a key challenge in medical image analysis, and existing methods mainly rely on static MRI images, which are difficult to capture the dynamic evolutionary features of tumors. In addition, the lack of descriptive clinical text and efficient multimodal feature fusion limits the classification accuracy and generalization. To overcome these limitations, this paper proposes a new dynamic language fusion (DLF) framework. The framework (1) utilizes ResNet18 in conjunction with LSTM for time series modeling to capture the temporal evolution of tumor morphology, (2) uses BioGPT and BERT for clinical text processing for semantic understanding, and (3) applies an interpretable cross-modal attentional mechanism for feature fusion to optimize dynamic perception and semantic alignment. Experiments on 10,287 images (from four publicly available datasets) show that the proposed framework achieves an overall accuracy of 98.96 %, a precision of 99.58 %, and an AUC higher than 0.998 for all categories on the test set, which is significantly better than the existing SOTA models, and especially exhibits stronger robustness and discriminative ability in boundary ambiguity and feature overlap samples. This study validates the synergistic effect of temporal modeling and semantic understanding in brain tumor diagnosis, providing clinicians with interpretable classification outputs to assist in decision-making for complex cases, while establishing a scalable framework for medical AI systems based on large language models.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113839"},"PeriodicalIF":6.6,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning-based kiwifruit flower recognition method to facilitate automated pollination 基于深度学习的猕猴桃花朵识别方法，便于自动授粉

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-03 DOI: 10.1016/j.asoc.2025.113855

Xiaopeng Li , Jinzhi Du , Xiaoyu Chen , Fuxi Shi , Shuqin Li

{"title":"Deep learning-based kiwifruit flower recognition method to facilitate automated pollination","authors":"Xiaopeng Li , Jinzhi Du , Xiaoyu Chen , Fuxi Shi , Shuqin Li","doi":"10.1016/j.asoc.2025.113855","DOIUrl":"10.1016/j.asoc.2025.113855","url":null,"abstract":"<div><div>Accurate flowering-stage recognition is vital for intelligent orchard management, automated pollination, and yield forecasting. However, in complex natural scenes, existing models struggle to balance detection accuracy with inference speed. To bridge this gap, we propose the Kiwifruit Recognition Network (KiwiRecNet), a lightweight yet high-performance framework tailored to kiwifruit blossoms in the wild. KiwiRecNet first employs the Kiwifruit Generative Adversarial Network for Low-light Improvement (KiwiGAN-LI) to enhance under-exposed images. We then design a novel backbone, the Multi-Scale Shuffle Block (MSBlock), which combines structural re-parameterisation with channel–spatial shuffling to shrink the network footprint. Next, we propose the Partial-Mixing Vision Transformer (PMVIT), a convolution-Transformer hybrid that captures fine-grained features and remains robust to occlusion. Finally, we devise a Bidirectional Cross-Scale Fusion module (Bi-CSF) to enrich multiscale perception. Evaluated on the NWAFU Kiwifruit_F dataset, KiwiRecNet achieves 94.07 % mAP at 82.67 FPS with only 0.93 million parameters, outperforming existing lightweight detectors while approaching heavyweight baselines at a fraction of their cost. Consistent gains across multiple flower datasets confirm its generalisation ability. These results demonstrate an effective route to high-accuracy, real-time flowering-phase recognition on resource-constrained devices, paving the way for scalable agricultural automation.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113855"},"PeriodicalIF":6.6,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A lightweight network enhanced by attention-guided cross-scale interaction for underwater object detection 基于注意力引导的跨尺度相互作用增强的水下目标检测轻量级网络

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-02 DOI: 10.1016/j.asoc.2025.113811

Dehua Zhang, Changcheng Yu, Zhen Li, Chunbin Qin, Ruixue Xia

{"title":"A lightweight network enhanced by attention-guided cross-scale interaction for underwater object detection","authors":"Dehua Zhang, Changcheng Yu, Zhen Li, Chunbin Qin, Ruixue Xia","doi":"10.1016/j.asoc.2025.113811","DOIUrl":"10.1016/j.asoc.2025.113811","url":null,"abstract":"<div><div>To address the image quality degradation caused by multipath effects and scattering in underwater environments, we propose a lightweight neural network architecture, PRCII-Net, optimized for small target detection under complex underwater conditions. First, a Progressive Re-parameterized Attention-based Intra-scale Feature Interaction module (PR-AIFI) is proposed, which improves the network performance while reducing the difficulty of training and maintaining training stability. Second, a feature pyramid network named as the Cross-scale Information Interaction Feature Pyramid Network (CII-FPN) is proposed, including the two main fusion structures. The CII-FPN not only fully utilizes shallow and deep information, but also enhances the network’s spatial representation and the interaction between deep feature layers, thereby boosting the detection capability for small targets. Meanwhile, to reduce the model’s size and resource consumption, 1x1 convolutions are introduced into the backbone network for efficient channel compression and cross-channel feature fusion, significantly lowering computational complexity. Experiments on the Detecting Underwater Objects (DUO) and Real-time Underwater Object Detection (RUOD) datasets demonstrate that PRCII-Net outperforms existing real-time neural network models in mAP and F1 scores while maintaining efficient inference on resource-constrained devices.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113811"},"PeriodicalIF":6.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145003718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Path planning for flexible needle puncture based on multi-objective particle swarm optimization 基于多目标粒子群优化的柔性穿刺路径规划

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-02 DOI: 10.1016/j.asoc.2025.113838

Ting Yang , Beibei Liu , Ru Sun , Bi Chen , Guijuan Ji

引用次数: 0

Identifying suicidal ideations from social media posts using deep learning and explainable AI-driven approach 使用深度学习和可解释的人工智能驱动方法从社交媒体帖子中识别自杀想法

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-02 DOI: 10.1016/j.asoc.2025.113813

Md. Sabab Zulfiker , Nasrin Kabir , Al Amin Biswas , Md. Mashih Ibn Yasin Adan , Mohammad Shorif Uddin

{"title":"Identifying suicidal ideations from social media posts using deep learning and explainable AI-driven approach","authors":"Md. Sabab Zulfiker , Nasrin Kabir , Al Amin Biswas , Md. Mashih Ibn Yasin Adan , Mohammad Shorif Uddin","doi":"10.1016/j.asoc.2025.113813","DOIUrl":"10.1016/j.asoc.2025.113813","url":null,"abstract":"<div><h3>Background</h3><div>At present, suicide has become one of the leading causes of unnatural deaths worldwide. Individuals having suicidal urges often express their self-harming ideas through social media posts. Early identification of such ideations is critical for timely intervention and prevention. Besides, continuous assessment of the texts containing suicidal thoughts can uncover the hidden triggers of suicidal urges. This study presents a comprehensive approach to analyze the user-generated textual contents on social media that reflect suicidal ideas.</div></div><div><h3>Methodology</h3><div>For identifying the underlying topics that express suicidal ideations, this study has employed the Latent Dirichlet Allocation (LDA) model. Semantic Network Analysis (SNA) is used to gain a deeper quantitative and qualitative insight into these texts. Besides, an exploratory investigation of different deep learning (DL) models has been performed to identify the posts speculating suicidal ideations. Furthermore, this study has integrated Explainable AI (XAI) techniques like Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) to enhance interpretability of the decisions taken by the DL models. Techniques like LDA and SNA offer a better understanding of the linguistic features of the suicidal posts, while the integration of the XAI techniques with the DL models elevates the transparency of their decisions.</div></div><div><h3>Contributions</h3><div>This study has developed an end-to-end web application, that can perform real-time classification of posts for suicidal ideation. Moreover, this application can provide insights into the rationale behind the taken decisions. This study aims to contribute to suicide prevention efforts through an innovative combination of computational techniques and AI-driven tools.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113813"},"PeriodicalIF":6.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An effective detection algorithm for small UAV based on lightweight You-Only-Look-Once (YOLOv4-L) approach 基于轻量级You-Only-Look-Once （YOLOv4-L）方法的小型无人机有效检测算法

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-02 DOI: 10.1016/j.asoc.2025.113841

Guoning Li , Jianghao Cheng , Yanyan Liu , Jin Li , Zengming Lv , Qiang Li

{"title":"An effective detection algorithm for small UAV based on lightweight You-Only-Look-Once (YOLOv4-L) approach","authors":"Guoning Li , Jianghao Cheng , Yanyan Liu , Jin Li , Zengming Lv , Qiang Li","doi":"10.1016/j.asoc.2025.113841","DOIUrl":"10.1016/j.asoc.2025.113841","url":null,"abstract":"<div><div>The control and monitoring of small Unmanned Aerial Vehicles (UAV) plays a crucial role in national defense and security. However, due to their compact size and high mobility, the detection of small UAV across diverse scenarios remains a significant challenge. To address this issue, this study proposes an improved detection algorithm tailored for small UAV. The model is initially trained on a virtual dataset, and the learned parameters are transferred to real-world data through a transfer learning framework. To optimize anchor box generation, clustering analysis is performed on bounding box dimensions, resulting in anchor boxes with appropriate scales and aspect ratios. Furthermore, the Ghost module is introduced to replace conventional convolutions in CSPDarknet53, enhancing feature extraction efficiency. An Efficient Channel Attention (ECA) mechanism is also incorporated to strengthen output feature representations and improve the capture of texture details critical for small target detection. Through experiments, the proposed algorithm can achieve the mAP0.5 of 82.2 %. Experimental results demonstrate the effectiveness of the proposed small UAV detection method.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113841"},"PeriodicalIF":6.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144989152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A state alignment-centric approach to federated system identification: The FedAlign framework 以状态对齐为中心的联邦系统识别方法：联邦框架

IF 6.6 1区计算机科学

Applied Soft Computing Pub Date : 2025-09-02 DOI: 10.1016/j.asoc.2025.113800

Ertuğrul Keçeci , Müjde Güzelkaya , Tufan Kumbasar

{"title":"A state alignment-centric approach to federated system identification: The FedAlign framework","authors":"Ertuğrul Keçeci , Müjde Güzelkaya , Tufan Kumbasar","doi":"10.1016/j.asoc.2025.113800","DOIUrl":"10.1016/j.asoc.2025.113800","url":null,"abstract":"<div><div>This paper presents FedAlign, a Federated Learning (FL) framework, designed for System Identification (SYSID) of linear State-Space Models (SSMs) by aligning state representations. Local workers can learn linear SSMs with equivalent representations but different parameter basins. We demonstrate that directly aggregating these local SSMs via FedAvg results in a global model with altered system dynamics. FedAlign overcomes this problem by employing similarity transformation matrices to align state representations of local SSMs, thereby establishing a common parameter basin that retains the dynamics of local SSMs. FedAlign computes similarity transformation matrices via two distinct approaches. In FedAlign-A, we represent the global SSM in controllable canonical form (CCF). We use control theory to analytically derive similarity transformation matrices that convert each local SSM into this form. Yet, establishing global SSM in CCF brings additional alignment challenges in multi-input multi-output SYSID, as CCF representation is not unique, unlike in single-input single-output SYSID. In FedAlign-O, we address the alignment challenges by reformulating the local parameter basin alignment problem as an optimization task. We set the parameter basin of a local worker as the common parameter basin and solve least square problems to obtain the transformation matrices needed to align the remaining local SSMs. The experiments conducted on synthetic and real-world datasets show that FedAlign outperforms FedAvg, converges faster, and provides improved global SSM stability thanks to local parameter basins’ alignment.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"184 ","pages":"Article 113800"},"PeriodicalIF":6.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0