Advanced Engineering Informatics最新文献

{"title":"A novel hierarchical attention-guided refinement method with EEG assistance for enhancing target speech in a multi-speaker competing environment","authors":"Zehui Feng ,&nbsp;Yangge Yang ,&nbsp;Chenqi Zhang ,&nbsp;Junxuan Li ,&nbsp;Ting Han","doi":"10.1016/j.aei.2025.103363","DOIUrl":"10.1016/j.aei.2025.103363","url":null,"abstract":"<div><div>Enhancing target speech in noisy, multi-speaker environments is a critical challenge, particularly in engineering contexts, such as construction sites, factories, and transportation systems, where multi-source competing speech scenarios are common and the need for efficient speech enhancement is critical to ensuring safety and operational effectiveness. The latest research is prone to recovering auditory attention with brain activity assistance. However, existing methods emerged with the challenges of multimodal feature extraction bottleneck, and fusion bottleneck. To address these challenges, this paper proposes a hierarchical attention-guided refinement network for enhancing EEG-assisted speech (HierEEG). HierEEG is an end-to-end explainable time-domain model comprising three core modules: a Multi-Scale Feature Modulation Refinement (MFMR) module, a Hierarchical Attention Fusion (HAF) network, and a Lightweight Speech Decoder. The first module learns the different granularities of feature representations and facilitates the interaction between short-term and long-term features through a feature modulator, obtaining multi-scale refined speech embeddings and EEG features. Then, the second module hierarchically guides the model’s attention focusing on high-level semantic features, outputting the generation of clean speech mask embeddings. Finally, a lightweight speech decoder is used to reconstruct the clean speech sample. Our comprehensive experiments on comparison, ablation, subject-dependent, subject-independent, transfer-learning, engineering, and calculation-cost experiments show that our proposed framework, HierEEG, outperforms state-of-the-art methods on mainstream Cocktail Party Datasets, especially achieving relative improvements of 0.21 dB and 0.15 in SI-SDR and PESQ. The proposed HierEEG validates the robustness in engineer simulated experiment, over 10 dB accuracy even with the various noises, artifacts, and poor contact. Furthermore, HierEEG makes great transfer performance for personalized user-specific adjustments, with simply 12 min of fine-tuning samples. HierEEG’s efficient processing and low computational cost, with under 70 % inference utilization on the Jeston Nano embedding device, enhances the potential applications in multi-speaker competing environments. Finally, the brain region experiment demonstrates the explainability of HierEEG, which ensures that the decisions made by the HierEEG can be understood in the context of the brain’s functional organization.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103363"},"PeriodicalIF":8.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Collaborative human-computer fault diagnosis via calibrated confidence estimation","authors":"Haidong Shao ,&nbsp;Yiming Xiao ,&nbsp;Jiewu Leng ,&nbsp;Xiaoli Zhao ,&nbsp;Bin Liu","doi":"10.1016/j.aei.2025.103349","DOIUrl":"10.1016/j.aei.2025.103349","url":null,"abstract":"<div><div>Most intelligent fault diagnostic studies focus solely on improving accuracy, which implies that decisions are made exclusively by a model. This lacks consideration, both from a safety and ethical perspective. Human-computer collaboration leverages the strengths of both parties to provide more informed and reliable decisions, requiring confidence as a key support. However, deep models typically suffer from miscalibration, i.e., the softmax probability does not represent the true likelihood that the predicted label is correct, motivating many calibration methods, among which confidence penalty (CP) receives attention as a simple method. CP’s performance is highly sensitive to a trade-off parameter and relies on cross-validation tests. However, although the parameter value chosen in this way has better overall performance, it does not outperform the other values in every confidence bin. The way CP penalizes the confidence of all samples with equal strength also makes it difficult to calibrate the confidence of some samples. For this reason, this paper proposes adaptive CP, which can adaptively assign a parameter value to each bin. Furthermore, a novel paradigm of collaborative human–computer fault diagnosis based on the method is established. The experimental results elucidate our motivations for designing the method and demonstrate its superiority.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103349"},"PeriodicalIF":8.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incorporating machine learning in shot peening and laser peening: A review and beyond","authors":"Rui Qin ,&nbsp;Zhifen Zhang ,&nbsp;James Marcus Griffin ,&nbsp;Jing Huang ,&nbsp;Guangrui Wen ,&nbsp;Weifeng He ,&nbsp;Xuefeng Chen","doi":"10.1016/j.aei.2025.103350","DOIUrl":"10.1016/j.aei.2025.103350","url":null,"abstract":"<div><div>While shot peening and laser peening are effective in improving the mechanical properties of material surfaces, their process optimization and quality assessment in advanced manufacturing still present significant challenges. Traditional optimization and evaluation methods rely on simplistic regression and hypothetical models, which tend to lead to unreliable results. In the macro-era context of intelligent manufacturing, the progressive machine learning has already had a profound impact in this field. This paper systematically reviews the machine learning methods that have been used in recent years for process optimization and quality assessment in shot peening and laser peening. These algorithms have played a crucial role in predicting surface quality characteristics, optimizing key process parameters, and achieving significant performance improvements. The primary objective of this paper is to summarize the core ideas of these works and offer a structured critique of their effectiveness. In addition, this paper critically discusses some of the emerging challenges associated with machine learning-driven quality assessment in surface peening. By analyzing these challenges and future directions in detail, researchers and engineers alike will gain important insights into the continuous optimization and quality control of the surface peening process.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103350"},"PeriodicalIF":8.0,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143825580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep concept identification for generative design","authors":"Ryo Tsumoto,&nbsp;Kentaro Yaji,&nbsp;Yutaka Nomaguchi,&nbsp;Kikuo Fujita","doi":"10.1016/j.aei.2025.103354","DOIUrl":"10.1016/j.aei.2025.103354","url":null,"abstract":"<div><div>Generative design techniques have become sophisticated methods for generating diverse alternatives by incorporating topology optimization with artificial intelligence techniques. As their diversity increases, the cognitive burden on designers in selecting the most appropriate alternatives also increases. The concept identification approach, which finds various categories of entities, is expected to be effective for systematically interpreting their diversity. However, conventional concept identification approaches cannot provide meaningful categories when their geometric properties face high-dimensionality. To address this challenge, this study proposes a new concept identification framework for generative design using deep learning (DL) techniques. One of the key abilities of DL is the automatic learning of effective representations of a specific task. This study first outlines the key points of concept identification based on the general design theory, then proposes a basic framework that consists of generating diverse alternatives using a generative design technique, clustering the alternatives into several categories using a DL technique, and arranging these categories into design concepts using a classification model. This study demonstrates its fundamental capabilities by implementing variational deep embedding, a generative and clustering model based on the DL paradigm, and logistic regression as a classification model. Its implementation is applied to a simplified design problem of a two-dimensional bridge structure as a case study. The proposed deep concept identification framework can systematically identify meaningful categories of diverse alternatives, while it still requires designer cognition in several steps because of the gap between the data-driven approach and the nature of concept identification.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103354"},"PeriodicalIF":8.0,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143825578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BIM-based automated analysis of dynamic hazards for proactive safety measures during the earthwork construction stage using CCTV data","authors":"Almo Senja Kulinan ,&nbsp;Yuntae Jeon ,&nbsp;Pa Pa Win Aung ,&nbsp;Minsoo Park ,&nbsp;Gichun Cha ,&nbsp;Seunghee Park","doi":"10.1016/j.aei.2025.103296","DOIUrl":"10.1016/j.aei.2025.103296","url":null,"abstract":"<div><div>Current safety management during the earthwork construction stage often fail to anticipate the dynamic nature of construction sites, leading to frequent accidents due to a lack of proactive measures. To address these challenges, this paper presents a system to prevent dynamic hazards on construction sites by identifying proximity hazard zones caused by heavy equipment activity, as well as areas where workers are exposed to these hazards, within a BIM framework. This system uses a computer vision-based CCTV approach for continuous monitoring to obtain important information within the site. The obtained information is then processed and integrated into a BIM model to visualize the hazard zones according to the risk estimation results. A case study highlights the system’s ability to generate up-to-date hazard maps within the BIM model, along with integrated hazard analysis results. The proposed system provides valuable insights for safety managers regarding dynamic hazard zones to improve site planning and reduce the likelihood of accidents.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103296"},"PeriodicalIF":8.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lithium-ion batteries remaining useful life prediction via Fourier-mixed window attention enhanced Informer with decomposition and adaptive error correction strategy","authors":"Fang Cheng ,&nbsp;Hui Liu ,&nbsp;Xinwei Lv","doi":"10.1016/j.aei.2025.103292","DOIUrl":"10.1016/j.aei.2025.103292","url":null,"abstract":"<div><div>Remaining useful life (RUL) prediction for lithium-ion batteries is crucial for safe and reliable operation in energy storage systems (ESS). However, the complex characteristics of capacity degradation make accurate and stable RUL prediction a critical problem. In response, this paper proposes a novel framework called FFWinformerAGA, which merges Fourier Decomposition Method (FDM), Fourier-mixed Window Attention-enhanced Informer (FWinformer), and adaptive error correction strategy via Gated Recurrent Unit-Attention Mechanism (AGA). The FDM initially decomposes original sequence into detail and trend components, effectively reducing the nonlinearity. Utilizing two distinct streams, the FWinformer then specially integrates local and global information in both time and frequency domains of the detail component, significantly enhancing the capture of abrupt changes and long-term dependencies under limited samples. Additionally, the AGA is incorporated to mine predictive relationships in the residual series. Experiments and analysis on four real-world datasets yielded the following conclusions: each component within the FFWinformerAGA is demonstrated to be necessity and superior, leading to enhanced results. The model outperforms state-of-the-art models, with improvements in Root Mean Square Error ranging from 30.39% to 85.30%, while maintaining reasonable performance times. Furthermore, the robustness of FFWinformerAGA is demonstrated by training it with fewer degradation samples and incorporating three different types of noise as additional inputs. Findings of this study hold potential application value in prognostics and health management of ESS.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103292"},"PeriodicalIF":8.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of agricultural sustainability in agro-climatic regions of India: A single-valued neutrosophic distance measure-based hybrid ranking framework","authors":"Arunodaya Raj Mishra ,&nbsp;Pratibha Rani ,&nbsp;Erfan Babaee Tirkolaee ,&nbsp;Adel Fahad Alrasheedi ,&nbsp;Ahmad M. Alshamrani","doi":"10.1016/j.aei.2025.103323","DOIUrl":"10.1016/j.aei.2025.103323","url":null,"abstract":"&lt;div&gt;&lt;div&gt;With the significant dependency on climate patterns and water availability, the agriculture sector is highly prone to fluctuating climate conditions. However, the assessment of agricultural sustainability in agro-climatic regions is a multifaceted and uncertain decision-making problem due to the involvement of multiple sustainability aspects concerning environmental, economic, and social dimensions. To this aim, this work proposes a hybrid ranking framework in the context of single-valued neutrosophic sets, which combines the modified relative closeness coefficient-based approach, the pivot pairwise relative criteria importance assessment tool, and the weighted integrated sum product method with single-valued neutrosophic information. This framework first presents a formula to obtain the significance of decision experts’ opinions using the truth membership, indeterminacy membership, and falsity membership degrees of a single-valued neutrosophic set. Next, the decision experts’ opinions are unified to determine the aggregated single-valued neutrosophic decision matrix, wherein each of its elements denotes the single-valued neutrosophic performance rating of an alternative with respect to considered evaluation indicators. Further, the weights of indicators are determined by combining the objective and subjective weighting models through the relative closeness coefficient-based approach and the pivot pairwise relative criteria importance assessment model, respectively. To find the relative closeness coefficient of indicators, a novel single-valued neutrosophic distance measure is proposed, which evades the deficiencies of existing distance measures. Finally, a hybrid weighted integrated sum product method is presented to rank the alternatives. To demonstrate the relevance and exhibit the efficacy of the introduced framework, it is applied to a case study of agricultural sustainability assessment in 10 considered agro-climatic regions of India. For this purpose, some indicators related to the triple bottom line of sustainability have been recognized from the literature review for the selection of a sustainable agro-climate region in India. The outcomes demonstrate that the “Trans-Gangetic Plain” region has the maximum preference, while the “Western Dry Region” has the least preference among the other agro-climatic regions. Irrigation intensity, crop diversification, receiving remittance as well as membership in the agricultural credit society are influencing indicators responsible for agricultural sustainability in the “Trans-Gangetic Plain” region compared with the “Western Dry Region”. Lastly, sensitivity and comparative discussions are shown to test the stability and strength of the proposed ranking model under the setting of single-valued neutrosophic sets. The proposed multi-criteria evaluation method provides insights for policymakers in evaluating and selecting economically, socially, and environmentally sustainable agro-climatic reg","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103323"},"PeriodicalIF":8.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive collision avoidance strategy for USVs in perception-limited environments using dynamic priority guidance","authors":"Shihong Yin,&nbsp;Zhengrong Xiang","doi":"10.1016/j.aei.2025.103355","DOIUrl":"10.1016/j.aei.2025.103355","url":null,"abstract":"<div><div>This paper proposes a dynamic adaptive priority guidance (DAPG) strategy for unmanned surface vehicles (USVs) to improve collision avoidance in dynamic maritime environments, particularly in unpredictable moving obstacles. Traditional local navigation methods often depend on fixed parameters within their cost functions, limiting adaptability. In contrast, the DAPG strategy integrates the strengths of multi-agent reinforcement learning (MARL) and multi-source information fusion strategy (MIFS). At a high level, the MARL-based algorithm dynamically adjusts fusion weights using neural networks, enabling the system to adapt flexibly to changing environments. At the low level, the MIFS algorithm processes these prioritized observations to generate the optimal navigation commands, ensuring safe and efficient navigation for each USV. The network is trained in a simulated dynamic environment using the parameter-sharing soft actor-critic (PSSAC) algorithm, enhanced with prioritized experience replay (PER) to accelerate learning. Experimental results show that the PSSAC-PER-MIFS algorithm significantly outperforms traditional reinforcement learning methods in convergence speed, reward stability, and navigation efficiency. Moreover, the DAPG strategy ensures compliance with COLREGs (International Regulations for Preventing Collisions at Sea), facilitating smooth and cooperative navigation in multi-USV scenarios. The source code is available at <span><span>https://github.com/Shihong-Yin/PSSAC-PER-MIFS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103355"},"PeriodicalIF":8.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In-trainNet: A Two-Step Data-Driven Framework for Enhancing Railway In-Train Forces Monitoring","authors":"Sheng Zhang,&nbsp;Wenyi Yan","doi":"10.1016/j.aei.2025.103352","DOIUrl":"10.1016/j.aei.2025.103352","url":null,"abstract":"<div><div>Railway in-train forces are critical for ensuring safe and efficient train operations. However, real-time monitoring of these forces across multiple couplers in various trains remains challenge due to variations in train configurations and coupler locations. This paper proposes In-trainNet, a two-step data-driven framework that leverages automatic train operation system to enhance in-train forces monitoring. In the first step, a specially designed multi-task model is pre-trained to simultaneously estimate multiple in-train forces on multiple couplers for a specific train configuration. In the second step, a transfer learning scheme transfers and adapts the pre-trained model to different train configurations, significantly reducing the need for extensive training data and computational resources. Comparative experiments demonstrate the superior performance of the pre-trained model, which achieves higher accuracy and efficiency compared to single-task models. The integration of transfer learning further enhances the framework’s adaptability, enabling robust and accurate monitoring across diverse train configurations. The proposed approach offers a promising solution for real-time, in-situ monitoring of railway in-train forces, with potential applications in both research and industrial applications.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103352"},"PeriodicalIF":8.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of cognitive load and user experience in alternative interaction modes under different noise degrees","authors":"Xiaojiao Xie ,&nbsp;Yao Wang ,&nbsp;Yan Cui ,&nbsp;Suihuai Yu ,&nbsp;Dengkai Chen ,&nbsp;Jianjie Chu","doi":"10.1016/j.aei.2025.103328","DOIUrl":"10.1016/j.aei.2025.103328","url":null,"abstract":"<div><div>In the context of multimodal interaction, user-centered research on alternative interaction modes is crucial for their application in real-world scenarios. In intelligent cockpits of specialized vehicles and aircraft, broadband continuous noise is a common challenge. This study aims to investigate the cognitive load and user experience associated with alternative interaction modes when performing tasks under varying levels of broadband continuous noise. 24 participants completed a point-and-select task with four interaction modes: Touch-Based Interaction (TBI), Speech-Based Interaction (SBI) with Speech Recognition (SRT) and Wizard of Oz (WoZ), Gesture-Based Interaction (GBI), and Multimodal Interaction (MMI) at three noise levels (45dBA, 65dBA, 85dBA). Cognitive load was assessed through blinks, pupil diameters, and NASA-TLX scores, while task performance (completion time, error rate) and user experience (pragmatic quality (PQ), hedonic quality (HQ), and attractiveness) were recorded. Results showed that speech recognition errors in noisy environments increased cognitive load and decreased user experience for SBI-SRT and MMI-SRT. Regardless of noise degrees, SBI-WoZ exhibited the lowest cognitive load, followed by GBI and MMI-WoZ. TBI had the highest cognitive load. GBI required the most physical demand and effort. TBI and GBI showed better robustness in noise, achieving higher HQ and PQ, while HQ and PQ for SBI and MMI declined with noise. MMI provided a better user experience than SBI. SBI-SRT was seen as redundant at 85 dBA. These findings provide valuable insights for the practical application of alternative interaction modes in noisy environments.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103328"},"PeriodicalIF":8.0,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}