Engineering Applications of Artificial Intelligence最新文献_第5页

A fuzzy multi-criteria decision-making approach for public projects–bidders matching under heterogeneous information 异构信息下招标人匹配的模糊多准则决策方法

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112833

Faizan Ahemad , Mukesh Kumar Mehlawat , Pankaj Gupta , Shilpi Verma , Dragan Pamucar

{"title":"A fuzzy multi-criteria decision-making approach for public projects–bidders matching under heterogeneous information","authors":"Faizan Ahemad , Mukesh Kumar Mehlawat , Pankaj Gupta , Shilpi Verma , Dragan Pamucar","doi":"10.1016/j.engappai.2025.112833","DOIUrl":"10.1016/j.engappai.2025.112833","url":null,"abstract":"<div><div>This study presents an intelligent decision-support framework for addressing the Projects–Bidders Matching (PBM) problem in public procurement, designed to handle heterogeneous and uncertain information. The approach employs fuzzy set theory, through triangular fuzzy numbers, intuitionistic fuzzy sets, and linguistic evaluations, to capture vagueness, hesitancy, and imprecision in expert judgments. To determine the relative importance of criteria from project and bidder perspectives, we employ a hybrid weighting mechanism that combines deviation from a reference point with entropy-based measures to derive data-driven weights. By combining fuzzy modeling, objective weighting, and behavioral decision theory within an artificial intelligence framework, the model enhances explainability and supports data-driven decision-making under uncertainty. From an engineering perspective, the framework is applied to optimize bidder assignments in real-world Indian public procurement scenarios. A multi-objective optimization model is formulated to (i) maximize cumulative prospect values that jointly reflect individual preferences and socially influenced preferences for both bidders and projects, (ii) minimize the absolute deviation between these cumulative prospect values, ensuring fairness, transparency, and alignment and (iii) satisfy a stability constraint to ensure that no bidder–project pair has an incentive to deviate from the assigned matching. The framework’s effectiveness is demonstrated through a practical case study, and its robustness is validated through extensive sensitivity and variation analyses.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112833"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Missing microseismic data imputation in tunnel monitoring using a transformer model with an integrated Gaussian mixture model 综合高斯混合模型变压器模型在隧道监测中缺失微震数据的输入

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112771

Zhihao Kuang , Shaojun Li , Shili Qiu , Yong Huang , Shuaipeng Chang

{"title":"Missing microseismic data imputation in tunnel monitoring using a transformer model with an integrated Gaussian mixture model","authors":"Zhihao Kuang , Shaojun Li , Shili Qiu , Yong Huang , Shuaipeng Chang","doi":"10.1016/j.engappai.2025.112771","DOIUrl":"10.1016/j.engappai.2025.112771","url":null,"abstract":"<div><div>Microseismic (MS) monitoring is essential for early warning and evaluation of structural safety in tunnel engineering. However, data loss due to environmental interference often compromises the reliability of such systems. To address this challenge, a data imputation model that integrates the Gaussian Mixture Model (GMM) with a transformer-based neural network, referred to as the GMM–Transformer model, was developed. Its performance was evaluated using real-world MS monitoring data from a deep-buried tunnel project in southwestern China. The proposed method achieves high accuracy in reconstructing missing data, with the imputed results closely matching observed values across multiple characteristic parameters. By leveraging the probabilistic nature of the Gaussian mixture distribution and Monte Carlo Dropout, the model can also quantify predictive uncertainty, yielding narrow confidence intervals that reinforce its reliability. The influence of missing data duration on the imputation quality was examined. The results imply that a missing window of approximately 3.5 h yields optimal results. A comparison between direct and indirect imputation strategies indicates that the direct approach significantly reduces reconstruction errors, from 25.73 % to 13.37 %. Additionally, benchmark comparisons with models such as random forest and long short-term memory networks show that the proposed model offers superior accuracy in recovering spatial characteristic critical to MS analysis. Overall, the GMM–Transformer model provides an effective, robust solution for dealing with data loss in MS monitoring. This work provides a forward-looking methodology and theoretical foundation for advancing artificial intelligence–based MS monitoring technologies in complex tunnel environments.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112771"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Time series anomaly detection based on time–frequency domain with masking strategy and contrastive learning 基于掩蔽策略和对比学习的时频域时间序列异常检测

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-20 DOI: 10.1016/j.engappai.2025.112775

Zhengkai Wang , Hui Liu , Longjing Kuang , Xueliang Zhang , Xiude Chen , Junzhao Du

{"title":"Time series anomaly detection based on time–frequency domain with masking strategy and contrastive learning","authors":"Zhengkai Wang , Hui Liu , Longjing Kuang , Xueliang Zhang , Xiude Chen , Junzhao Du","doi":"10.1016/j.engappai.2025.112775","DOIUrl":"10.1016/j.engappai.2025.112775","url":null,"abstract":"<div><div>Anomalies in time series often indicate underlying issues or system failures. Timely detection is critical to avoid severe consequences like system crashes and traffic accidents. Although some high-performing time series anomaly detection models already exist, several challenges remain: (1) Training Bias: Unsupervised anomaly detection models are typically trained on clean normal data. If the training data contains noise or potential anomalies, it can cause the model parameters to deviate from the ideal state during optimization, hindering accurate anomaly detection. (2) Distribution Shift: Time series exhibit periodicity and trends, and the training and testing data may have different distribution patterns. This may cause the model to incorrectly classify normal data as anomalies during testing. Therefore, we propose an anomaly detection network called TFCLNet, which utilizes a time–frequency domain masking strategy combined with contrastive learning. Since the frequency domain reveals potential periodicity and frequency variations, a dual-branch structure is adopted to simultaneously process time-domain and frequency-domain features. Additionally, we employ targeted masking strategies in both domains to reduce the impact of noise and address training bias, thereby learning the core data patterns of time series. Furthermore, unlike traditional contrastive learning strategies based on raw features, we minimize the distribution differences between the reconstructed time–frequency domain features through a contrastive objective function, mitigating the negative impact of distribution shifts in the original data on detection performance. Finally, adversarial training is incorporated to prevent overfitting. Experimental results on five real-world datasets demonstrate that TFCLNet outperforms all baseline models and achieves state-of-the-art performance.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"112775"},"PeriodicalIF":8.0,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A welding sequence optimization method of multilayer thin-walled structures via combined architecture of convolutional long short-term memory-UNet and non-dominated sorting genetic algorithm II 基于卷积长短期记忆- unet和非支配排序遗传算法的多层薄壁结构焊接顺序优化方法

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-20 DOI: 10.1016/j.engappai.2025.112810

Danning Fan , Cheng Luo , Yansong Zhang

{"title":"A welding sequence optimization method of multilayer thin-walled structures via combined architecture of convolutional long short-term memory-UNet and non-dominated sorting genetic algorithm II","authors":"Danning Fan , Cheng Luo , Yansong Zhang","doi":"10.1016/j.engappai.2025.112810","DOIUrl":"10.1016/j.engappai.2025.112810","url":null,"abstract":"<div><div>Numerous welding seams in multilayer thin-walled structures of ship blocks could include thousands of welding sequences and lead to various structural deformations, significantly undermining the manufacturing quality. Welding sequence optimization based on numerical finite element (FE) simulations needs repeated model modification and calculation, facing challenges of time-consuming cost. Thus, this paper proposed a novel welding sequence optimization method based on a combined architecture of convolutional long short-term memory-UNet (ConvLSTM-UNet) and non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ), reducing welding deformation of multilayer thin-walled structures of ship blocks. The ConvLSTM network was used to extract the spatiotemporal characteristics of welding seams, and then welding deformation was rapidly predicted by the UNet network. NSGA-II was employed to automatically generate thousands of welding sequences, which would be input to the ConvLSTM-UNet network for fitness calculation. The multi-objective function consisted of distortion unevenness of each layer and the maximum flatness was applied for fitness evaluation and regeneration of new welding sequences. The optimized welding sequence could reduce the maximum deformation of the multilayer thin-walled structure of ship blocks up to 40.8 %.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"112810"},"PeriodicalIF":8.0,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-target search with incomplete information based on partial global path planning with Signal Caching And Rebound Exploration 基于局部全局路径规划的不完全信息多目标搜索

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-20 DOI: 10.1016/j.engappai.2025.112799

Zimin Xu , Jinyan Huang , Jianlei Zhang

{"title":"Multi-target search with incomplete information based on partial global path planning with Signal Caching And Rebound Exploration","authors":"Zimin Xu , Jinyan Huang , Jianlei Zhang","doi":"10.1016/j.engappai.2025.112799","DOIUrl":"10.1016/j.engappai.2025.112799","url":null,"abstract":"<div><div>To address challenges such as global information loss, sparse target distribution, and environmental complexity, this paper proposes an efficient single-agent search strategy based on Signal Caching And Rebound Exploration (SCARE). The strategy enhances multi-target search efficiency by integrating a target signal information caching mechanism, a constrained motion pattern, and a path planning approach that synergizes local perception with global guidance. In signal-absent scenarios, the method employs the constrained walking space and confidence evaluation mechanism to redirect the robot and improve search coverage. Conversely, when signal conditions are available, a target-oriented strategy enhances target localization accuracy and efficiency. Extensive simulations, including ablation studies and comparative experiments, demonstrate the robustness and effectiveness of the proposed method. SCARE significantly outperforms baseline algorithms in diverse scenarios, achieving nearly 100% success rate with 4 targets in a 50 × 50 map containing 22% obstacles. Additional experiments validate the scalability to increasing target counts and obstacle densities, as well as its resilience against signal interference through enhanced caching mechanisms. These results highlight the method’s strong potential for deployment in complex and partially observable environments.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"112799"},"PeriodicalIF":8.0,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Anatomically accurate cardiac segmentation using Dense Associative Networks 利用密集关联网络进行解剖学上准确的心脏分割

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-20 DOI: 10.1016/j.engappai.2025.112742

Zahid Ullah, Jihie Kim

{"title":"Anatomically accurate cardiac segmentation using Dense Associative Networks","authors":"Zahid Ullah, Jihie Kim","doi":"10.1016/j.engappai.2025.112742","DOIUrl":"10.1016/j.engappai.2025.112742","url":null,"abstract":"<div><div>Deep learning-based cardiac segmentation has seen significant advancements over the years. Many studies have tackled the challenge of anatomically incorrect segmentation predictions by introducing auxiliary modules. These modules either post-process segmentation outputs or enforce consistency between specific points to ensure anatomical correctness. However, such approaches often increase network complexity, require separate training for these modules, and may lack robustness in scenarios with poor visibility. To address these limitations, we propose a novel transformer-based architecture that leverages dense associative networks to learn and retain specific patterns inherent to cardiac inputs. Unlike traditional methods, our approach restricts the network to memorize a limited set of patterns. During forward propagation, a weighted sum of these patterns is used to enforce anatomical correctness in the output. Since these patterns are input-independent, the model demonstrates enhanced robustness, even in cases with poor visibility. The proposed pipeline was evaluated on two publicly available datasets, i.e., Cardiac Acquisitions for Multi-structure Ultrasound Segmentation and CardiacNet. Experimental results indicate that our model consistently outperforms baseline approaches across all evaluation metrics, highlighting its effectiveness and robustness in cardiac segmentation tasks. Code is available at: <span><span>https://github.com/Zahid672/cardio-segmentation</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"112742"},"PeriodicalIF":8.0,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Textual backdoor attacks and a novel defense method for context-aware Arabic biomedical questions classifiers 上下文感知阿拉伯生物医学问题分类器的文本后门攻击和一种新的防御方法

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-18 DOI: 10.1016/j.engappai.2025.112583

Ismail Ait Talghalit , Hamza Alami , Said Ouatik El Alaoui

{"title":"Textual backdoor attacks and a novel defense method for context-aware Arabic biomedical questions classifiers","authors":"Ismail Ait Talghalit , Hamza Alami , Said Ouatik El Alaoui","doi":"10.1016/j.engappai.2025.112583","DOIUrl":"10.1016/j.engappai.2025.112583","url":null,"abstract":"<div><div>Despite the growing reliance on deep learning models in the Arabic biomedical domain, their susceptibility to backdoor attacks, where adversaries inject subtle textual triggers to manipulate outcomes, remains critically underexplored. In this paper, we propose two main contributions: (1) a backdoor attack method against various pre-trained transformer models used for Arabic biomedical questions classification; (2) a novel defense mechanism to prevent textual backdoor attacks. The basic idea of our backdoor attack is to inject triggers into original questions, which manipulate models negatively, by applying three insertion strategies, namely contextual, pre-insertion, and post-insertion. Our defense method leverages Bidirectional Encoder Representations from Transformers (BERT) as a Masked Language Model to remove tokens with a low probability of being the masked token in the Arabic biomedical question. To assess the impact of our backdoor attacks and defense method, we conduct various experiments using the Medical Arabic Questions and Answers (Q&A) dataset. Our backdoor attack achieved an attack success rate of 95.13%, 94.13%, 89.64%, and 88.89% on fine-tuned Arabic biomedical classifiers based on an Arabic-adapted version of the Efficiently Learning an Encoder that Classifies Token Replacements Accurately model (AraELECTRA), an Arabic BERT (AraBERT), a Long Short Term Memory (LSTM), and an Arabic-adapted text-to-text transformer (AraT5) models, respectively. Furthermore, our defense method reduces the attack success rate by 56.57% and 71.86% in the case of AraBERT and LSTM classifiers.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112583"},"PeriodicalIF":8.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A structure-aware routing based anomaly detection for industrial multi-sensor time series 基于结构感知路由的工业多传感器时间序列异常检测

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-18 DOI: 10.1016/j.engappai.2025.112765

Qixuan Zhao , Jingling Yuan , Peiliang Zhang , Xin Zhang , Jianquan Liu , Lin Li

{"title":"A structure-aware routing based anomaly detection for industrial multi-sensor time series","authors":"Qixuan Zhao , Jingling Yuan , Peiliang Zhang , Xin Zhang , Jianquan Liu , Lin Li","doi":"10.1016/j.engappai.2025.112765","DOIUrl":"10.1016/j.engappai.2025.112765","url":null,"abstract":"<div><div>Anomaly detection in multi-sensor time series (MTS) is a critical technology for ensuring the stable operation of modern industrial systems. Current mainstream methods identify anomalies by learning the structural consistency of normal data. As a result, natural structural breaks, a typical random non-stationary phenomenon in multi-sensor systems, are frequently misclassified as anomalies by these methods. To address this issue, we propose a Structure-Aware Routing (SaR) based Mixture-of-Experts (MoE) framework (SMoE) for anomaly detection. SMoE eliminates interference from structural breaks by assigning sensor series to specialized experts through SaR. First, the proposed SaR consists of Spatial Routing and Temporal Routing, which capture structural breaks at two levels: global breaks between sensors and local window-level breaks within individual sensors. Second, the SMoE-based anomaly detection framework can be applied to various sensor time series backbone networks, including large-scale models, significantly enhancing anomaly detection accuracy in MTS. Extensive experiments conducted on eight datasets across five industrial domains demonstrate that SMoE achieves an F1 score improvement ranging from 1% to 9% across four distinct backbone networks for anomaly detection. SMoE achieves an F1 score improvement of up to 8.4% compared to ten advanced baselines.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112765"},"PeriodicalIF":8.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale target detection of metal surface defects in additive manufacturing based on reinforcement learning 基于强化学习的增材制造金属表面缺陷多尺度目标检测

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-18 DOI: 10.1016/j.engappai.2025.112754

Yunteng Niu , Yilin Zheng , Shujing Shi , Zhuo Li , Zhigong Song

{"title":"Multi-scale target detection of metal surface defects in additive manufacturing based on reinforcement learning","authors":"Yunteng Niu , Yilin Zheng , Shujing Shi , Zhuo Li , Zhigong Song","doi":"10.1016/j.engappai.2025.112754","DOIUrl":"10.1016/j.engappai.2025.112754","url":null,"abstract":"<div><div>Additive manufacturing technology has found wide application in aerospace, automotive manufacturing, and other industries. This technology builds complex geometric structures and high-precision parts by adding materials layer by layer, significantly reducing material waste and shortening the production cycle. However, the detection and repair of surface defects remain key challenges impacting product quality in the additive manufacturing process. The ambiguity of surface defects, constraints of fixed-scale features, and challenges in feature extraction accuracy are key obstacles to effective defect detection in machine vision target detection systems. To address these challenges, this study enhances the conventional feature extraction network by incorporating a reinforcement learning-based optimization strategy. A machine vision framework named Reinforcement Learning Multi-Scale You Only Look Once (RLMS-YOLO) is proposed for the automated detection and classification of surface defects. A high-resolution camera captures the surface image of the workpiece and in combination with a reinforcement learning algorithm, extracts the most distinctive multi-scale feature maps to analyze surface texture and morphology, accurately classifying and locating surface defects. Experimental results demonstrate that this method effectively detects tiny defects, significantly improves the quality and production efficiency of additive manufacturing products, and provides crucial data support for subsequent process optimization. In the task of additive manufacturing defect detection, the model improves the mean average precision at an intersection over union threshold of 0.5 for detecting surface hole defects by 12.7 %. This result demonstrates the significant effectiveness of reinforcement learning in enhancing multi-scale feature extraction and improving defect detection accuracy in complex industrial environments.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112754"},"PeriodicalIF":8.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Non-convex regularized robust multimodal feature selection via self-representation learning for Alzheimer’s disease diagnosis 基于自表示学习的非凸正则鲁棒多模态特征选择用于阿尔茨海默病诊断

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-18 DOI: 10.1016/j.engappai.2025.112770

Xi Guo , Hongmei Chen , Biao Xiang , Zhong Yuan , Chuan Luo , Shi-Jinn Horng , Tianrui Li

{"title":"Non-convex regularized robust multimodal feature selection via self-representation learning for Alzheimer’s disease diagnosis","authors":"Xi Guo , Hongmei Chen , Biao Xiang , Zhong Yuan , Chuan Luo , Shi-Jinn Horng , Tianrui Li","doi":"10.1016/j.engappai.2025.112770","DOIUrl":"10.1016/j.engappai.2025.112770","url":null,"abstract":"<div><div>Multimodal neuroimaging data fusion has become a key research direction in Alzheimer’s Disease (AD) diagnosis. However, existing methods face challenges such as (1) Limited robustness against outliers and noise, which hampers effective feature selection; (2) Limitations of conventional convex approximation methods, such as the <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>2</mn><mo>,</mo><mn>1</mn></mrow></msub></math></span> norm, in approximating the ideal <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>2</mn><mo>,</mo><mn>0</mn></mrow></msub></math></span> norm, making it challenging to capture sparse structures accurately; (3) Inadequate modeling of feature correlations, leading to missed identification of synergistic feature groups. To address these issues, this study proposes a Non-Convex Regularized Robust Multimodal Feature Selection method via Self-Representation Learning for Alzheimer’s Disease diagnosis (NCRRFS). Specifically, self-representation learning is employed to model the error terms of anomalous samples, enabling the adaptive detection and correction of abnormal data, thereby enhancing the robustness of the model. Furthermore, an <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>2</mn><mo>,</mo><mi>γ</mi></mrow></msub></math></span> norm row sparsity constraint based on the Smoothly Clipped Absolute Deviation (SCAD) function is designed to more accurately approximate the <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>2</mn><mo>,</mo><mn>0</mn></mrow></msub></math></span> norm. Additionally, a graph-structured regularization based on Pearson correlation promotes the selection of synergistic feature groups. Extensive experimental results demonstrate the effectiveness and superiority of the proposed method in the Alzheimer’s disease classification task.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112770"},"PeriodicalIF":8.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0